org.opencv.imgproc.Imgproc
|
OpenCV 2.4.4 | |||||||
| PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||
| SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD | |||||||
java.lang.Object
public class Imgproc
| Constructor Summary | |
|---|---|
Imgproc()
|
|
| Method Summary | |
|---|---|
static void |
accumulate(Mat src,
Mat dst)
Adds an image to the accumulator. |
static void |
accumulate(Mat src,
Mat dst,
Mat mask)
Adds an image to the accumulator. |
static void |
accumulateProduct(Mat src1,
Mat src2,
Mat dst)
Adds the per-element product of two input images to the accumulator. |
static void |
accumulateProduct(Mat src1,
Mat src2,
Mat dst,
Mat mask)
Adds the per-element product of two input images to the accumulator. |
static void |
accumulateSquare(Mat src,
Mat dst)
Adds the square of a source image to the accumulator. |
static void |
accumulateSquare(Mat src,
Mat dst,
Mat mask)
Adds the square of a source image to the accumulator. |
static void |
accumulateWeighted(Mat src,
Mat dst,
double alpha)
Updates a running average. |
static void |
accumulateWeighted(Mat src,
Mat dst,
double alpha,
Mat mask)
Updates a running average. |
static void |
adaptiveThreshold(Mat src,
Mat dst,
double maxValue,
int adaptiveMethod,
int thresholdType,
int blockSize,
double C)
Applies an adaptive threshold to an array. |
static void |
approxPolyDP(MatOfPoint2f curve,
MatOfPoint2f approxCurve,
double epsilon,
boolean closed)
Approximates a polygonal curve(s) with the specified precision. |
static double |
arcLength(MatOfPoint2f curve,
boolean closed)
Calculates a contour perimeter or a curve length. |
static void |
bilateralFilter(Mat src,
Mat dst,
int d,
double sigmaColor,
double sigmaSpace)
Applies the bilateral filter to an image. |
static void |
bilateralFilter(Mat src,
Mat dst,
int d,
double sigmaColor,
double sigmaSpace,
int borderType)
Applies the bilateral filter to an image. |
static void |
blur(Mat src,
Mat dst,
Size ksize)
Blurs an image using the normalized box filter. |
static void |
blur(Mat src,
Mat dst,
Size ksize,
Point anchor)
Blurs an image using the normalized box filter. |
static void |
blur(Mat src,
Mat dst,
Size ksize,
Point anchor,
int borderType)
Blurs an image using the normalized box filter. |
static int |
borderInterpolate(int p,
int len,
int borderType)
Computes the source location of an extrapolated pixel. |
static Rect |
boundingRect(MatOfPoint points)
Calculates the up-right bounding rectangle of a point set. |
static void |
boxFilter(Mat src,
Mat dst,
int ddepth,
Size ksize)
Blurs an image using the box filter. |
static void |
boxFilter(Mat src,
Mat dst,
int ddepth,
Size ksize,
Point anchor,
boolean normalize)
Blurs an image using the box filter. |
static void |
boxFilter(Mat src,
Mat dst,
int ddepth,
Size ksize,
Point anchor,
boolean normalize,
int borderType)
Blurs an image using the box filter. |
static void |
calcBackProject(java.util.List<Mat> images,
MatOfInt channels,
Mat hist,
Mat dst,
MatOfFloat ranges,
double scale)
Calculates the back projection of a histogram. |
static void |
calcHist(java.util.List<Mat> images,
MatOfInt channels,
Mat mask,
Mat hist,
MatOfInt histSize,
MatOfFloat ranges)
Calculates a histogram of a set of arrays. |
static void |
calcHist(java.util.List<Mat> images,
MatOfInt channels,
Mat mask,
Mat hist,
MatOfInt histSize,
MatOfFloat ranges,
boolean accumulate)
Calculates a histogram of a set of arrays. |
static void |
Canny(Mat image,
Mat edges,
double threshold1,
double threshold2)
Finds edges in an image using the [Canny86] algorithm. |
static void |
Canny(Mat image,
Mat edges,
double threshold1,
double threshold2,
int apertureSize,
boolean L2gradient)
Finds edges in an image using the [Canny86] algorithm. |
static double |
compareHist(Mat H1,
Mat H2,
int method)
Compares two histograms. |
static double |
contourArea(Mat contour)
Calculates a contour area. |
static double |
contourArea(Mat contour,
boolean oriented)
Calculates a contour area. |
static void |
convertMaps(Mat map1,
Mat map2,
Mat dstmap1,
Mat dstmap2,
int dstmap1type)
Converts image transformation maps from one representation to another. |
static void |
convertMaps(Mat map1,
Mat map2,
Mat dstmap1,
Mat dstmap2,
int dstmap1type,
boolean nninterpolation)
Converts image transformation maps from one representation to another. |
static void |
convexHull(MatOfPoint points,
MatOfInt hull)
Finds the convex hull of a point set. |
static void |
convexHull(MatOfPoint points,
MatOfInt hull,
boolean clockwise)
Finds the convex hull of a point set. |
static void |
convexityDefects(MatOfPoint contour,
MatOfInt convexhull,
MatOfInt4 convexityDefects)
Finds the convexity defects of a contour. |
static void |
copyMakeBorder(Mat src,
Mat dst,
int top,
int bottom,
int left,
int right,
int borderType)
Forms a border around an image. |
static void |
copyMakeBorder(Mat src,
Mat dst,
int top,
int bottom,
int left,
int right,
int borderType,
Scalar value)
Forms a border around an image. |
static void |
cornerEigenValsAndVecs(Mat src,
Mat dst,
int blockSize,
int ksize)
Calculates eigenvalues and eigenvectors of image blocks for corner detection. |
static void |
cornerEigenValsAndVecs(Mat src,
Mat dst,
int blockSize,
int ksize,
int borderType)
Calculates eigenvalues and eigenvectors of image blocks for corner detection. |
static void |
cornerHarris(Mat src,
Mat dst,
int blockSize,
int ksize,
double k)
Harris edge detector. |
static void |
cornerHarris(Mat src,
Mat dst,
int blockSize,
int ksize,
double k,
int borderType)
Harris edge detector. |
static void |
cornerMinEigenVal(Mat src,
Mat dst,
int blockSize)
Calculates the minimal eigenvalue of gradient matrices for corner detection. |
static void |
cornerMinEigenVal(Mat src,
Mat dst,
int blockSize,
int ksize)
Calculates the minimal eigenvalue of gradient matrices for corner detection. |
static void |
cornerMinEigenVal(Mat src,
Mat dst,
int blockSize,
int ksize,
int borderType)
Calculates the minimal eigenvalue of gradient matrices for corner detection. |
static void |
cornerSubPix(Mat image,
MatOfPoint2f corners,
Size winSize,
Size zeroZone,
TermCriteria criteria)
Refines the corner locations. |
static void |
createHanningWindow(Mat dst,
Size winSize,
int type)
This function computes a Hanning window coefficients in two dimensions. |
static void |
cvtColor(Mat src,
Mat dst,
int code)
Converts an image from one color space to another. |
static void |
cvtColor(Mat src,
Mat dst,
int code,
int dstCn)
Converts an image from one color space to another. |
static void |
dilate(Mat src,
Mat dst,
Mat kernel)
Dilates an image by using a specific structuring element. |
static void |
dilate(Mat src,
Mat dst,
Mat kernel,
Point anchor,
int iterations)
Dilates an image by using a specific structuring element. |
static void |
dilate(Mat src,
Mat dst,
Mat kernel,
Point anchor,
int iterations,
int borderType,
Scalar borderValue)
Dilates an image by using a specific structuring element. |
static void |
distanceTransform(Mat src,
Mat dst,
int distanceType,
int maskSize)
Calculates the distance to the closest zero pixel for each pixel of the source image. |
static void |
distanceTransformWithLabels(Mat src,
Mat dst,
Mat labels,
int distanceType,
int maskSize)
Calculates the distance to the closest zero pixel for each pixel of the source image. |
static void |
distanceTransformWithLabels(Mat src,
Mat dst,
Mat labels,
int distanceType,
int maskSize,
int labelType)
Calculates the distance to the closest zero pixel for each pixel of the source image. |
static void |
drawContours(Mat image,
java.util.List<MatOfPoint> contours,
int contourIdx,
Scalar color)
Draws contours outlines or filled contours. |
static void |
drawContours(Mat image,
java.util.List<MatOfPoint> contours,
int contourIdx,
Scalar color,
int thickness)
Draws contours outlines or filled contours. |
static void |
drawContours(Mat image,
java.util.List<MatOfPoint> contours,
int contourIdx,
Scalar color,
int thickness,
int lineType,
Mat hierarchy,
int maxLevel,
Point offset)
Draws contours outlines or filled contours. |
static void |
equalizeHist(Mat src,
Mat dst)
Equalizes the histogram of a grayscale image. |
static void |
erode(Mat src,
Mat dst,
Mat kernel)
Erodes an image by using a specific structuring element. |
static void |
erode(Mat src,
Mat dst,
Mat kernel,
Point anchor,
int iterations)
Erodes an image by using a specific structuring element. |
static void |
erode(Mat src,
Mat dst,
Mat kernel,
Point anchor,
int iterations,
int borderType,
Scalar borderValue)
Erodes an image by using a specific structuring element. |
static void |
filter2D(Mat src,
Mat dst,
int ddepth,
Mat kernel)
Convolves an image with the kernel. |
static void |
filter2D(Mat src,
Mat dst,
int ddepth,
Mat kernel,
Point anchor,
double delta)
Convolves an image with the kernel. |
static void |
filter2D(Mat src,
Mat dst,
int ddepth,
Mat kernel,
Point anchor,
double delta,
int borderType)
Convolves an image with the kernel. |
static void |
findContours(Mat image,
java.util.List<MatOfPoint> contours,
Mat hierarchy,
int mode,
int method)
Finds contours in a binary image. |
static void |
findContours(Mat image,
java.util.List<MatOfPoint> contours,
Mat hierarchy,
int mode,
int method,
Point offset)
Finds contours in a binary image. |
static RotatedRect |
fitEllipse(MatOfPoint2f points)
Fits an ellipse around a set of 2D points. |
static void |
fitLine(Mat points,
Mat line,
int distType,
double param,
double reps,
double aeps)
Fits a line to a 2D or 3D point set. |
static int |
floodFill(Mat image,
Mat mask,
Point seedPoint,
Scalar newVal)
Fills a connected component with the given color. |
static int |
floodFill(Mat image,
Mat mask,
Point seedPoint,
Scalar newVal,
Rect rect,
Scalar loDiff,
Scalar upDiff,
int flags)
Fills a connected component with the given color. |
static void |
GaussianBlur(Mat src,
Mat dst,
Size ksize,
double sigmaX)
Blurs an image using a Gaussian filter. |
static void |
GaussianBlur(Mat src,
Mat dst,
Size ksize,
double sigmaX,
double sigmaY)
Blurs an image using a Gaussian filter. |
static void |
GaussianBlur(Mat src,
Mat dst,
Size ksize,
double sigmaX,
double sigmaY,
int borderType)
Blurs an image using a Gaussian filter. |
static Mat |
getAffineTransform(MatOfPoint2f src,
MatOfPoint2f dst)
Calculates an affine transform from three pairs of the corresponding points. |
static Mat |
getDefaultNewCameraMatrix(Mat cameraMatrix)
Returns the default new camera matrix. |
static Mat |
getDefaultNewCameraMatrix(Mat cameraMatrix,
Size imgsize,
boolean centerPrincipalPoint)
Returns the default new camera matrix. |
static void |
getDerivKernels(Mat kx,
Mat ky,
int dx,
int dy,
int ksize)
Returns filter coefficients for computing spatial image derivatives. |
static void |
getDerivKernels(Mat kx,
Mat ky,
int dx,
int dy,
int ksize,
boolean normalize,
int ktype)
Returns filter coefficients for computing spatial image derivatives. |
static Mat |
getGaborKernel(Size ksize,
double sigma,
double theta,
double lambd,
double gamma)
|
static Mat |
getGaborKernel(Size ksize,
double sigma,
double theta,
double lambd,
double gamma,
double psi,
int ktype)
|
static Mat |
getGaussianKernel(int ksize,
double sigma)
Returns Gaussian filter coefficients. |
static Mat |
getGaussianKernel(int ksize,
double sigma,
int ktype)
Returns Gaussian filter coefficients. |
static Mat |
getPerspectiveTransform(Mat src,
Mat dst)
Calculates a perspective transform from four pairs of the corresponding points. |
static void |
getRectSubPix(Mat image,
Size patchSize,
Point center,
Mat patch)
Retrieves a pixel rectangle from an image with sub-pixel accuracy. |
static void |
getRectSubPix(Mat image,
Size patchSize,
Point center,
Mat patch,
int patchType)
Retrieves a pixel rectangle from an image with sub-pixel accuracy. |
static Mat |
getRotationMatrix2D(Point center,
double angle,
double scale)
Calculates an affine matrix of 2D rotation. |
static Mat |
getStructuringElement(int shape,
Size ksize)
Returns a structuring element of the specified size and shape for morphological operations. |
static Mat |
getStructuringElement(int shape,
Size ksize,
Point anchor)
Returns a structuring element of the specified size and shape for morphological operations. |
static void |
goodFeaturesToTrack(Mat image,
MatOfPoint corners,
int maxCorners,
double qualityLevel,
double minDistance)
Determines strong corners on an image. |
static void |
goodFeaturesToTrack(Mat image,
MatOfPoint corners,
int maxCorners,
double qualityLevel,
double minDistance,
Mat mask,
int blockSize,
boolean useHarrisDetector,
double k)
Determines strong corners on an image. |
static void |
grabCut(Mat img,
Mat mask,
Rect rect,
Mat bgdModel,
Mat fgdModel,
int iterCount)
Runs the GrabCut algorithm. |
static void |
grabCut(Mat img,
Mat mask,
Rect rect,
Mat bgdModel,
Mat fgdModel,
int iterCount,
int mode)
Runs the GrabCut algorithm. |
static void |
HoughCircles(Mat image,
Mat circles,
int method,
double dp,
double minDist)
Finds circles in a grayscale image using the Hough transform. |
static void |
HoughCircles(Mat image,
Mat circles,
int method,
double dp,
double minDist,
double param1,
double param2,
int minRadius,
int maxRadius)
Finds circles in a grayscale image using the Hough transform. |
static void |
HoughLines(Mat image,
Mat lines,
double rho,
double theta,
int threshold)
Finds lines in a binary image using the standard Hough transform. |
static void |
HoughLines(Mat image,
Mat lines,
double rho,
double theta,
int threshold,
double srn,
double stn)
Finds lines in a binary image using the standard Hough transform. |
static void |
HoughLinesP(Mat image,
Mat lines,
double rho,
double theta,
int threshold)
Finds line segments in a binary image using the probabilistic Hough transform. |
static void |
HoughLinesP(Mat image,
Mat lines,
double rho,
double theta,
int threshold,
double minLineLength,
double maxLineGap)
Finds line segments in a binary image using the probabilistic Hough transform. |
static void |
HuMoments(Moments m,
Mat hu)
Calculates seven Hu invariants. |
static void |
initUndistortRectifyMap(Mat cameraMatrix,
Mat distCoeffs,
Mat R,
Mat newCameraMatrix,
Size size,
int m1type,
Mat map1,
Mat map2)
Computes the undistortion and rectification transformation map. |
static float |
initWideAngleProjMap(Mat cameraMatrix,
Mat distCoeffs,
Size imageSize,
int destImageWidth,
int m1type,
Mat map1,
Mat map2)
|
static float |
initWideAngleProjMap(Mat cameraMatrix,
Mat distCoeffs,
Size imageSize,
int destImageWidth,
int m1type,
Mat map1,
Mat map2,
int projType,
double alpha)
|
static void |
integral(Mat src,
Mat sum)
Calculates the integral of an image. |
static void |
integral(Mat src,
Mat sum,
int sdepth)
Calculates the integral of an image. |
static void |
integral2(Mat src,
Mat sum,
Mat sqsum)
Calculates the integral of an image. |
static void |
integral2(Mat src,
Mat sum,
Mat sqsum,
int sdepth)
Calculates the integral of an image. |
static void |
integral3(Mat src,
Mat sum,
Mat sqsum,
Mat tilted)
Calculates the integral of an image. |
static void |
integral3(Mat src,
Mat sum,
Mat sqsum,
Mat tilted,
int sdepth)
Calculates the integral of an image. |
static float |
intersectConvexConvex(Mat _p1,
Mat _p2,
Mat _p12)
|
static float |
intersectConvexConvex(Mat _p1,
Mat _p2,
Mat _p12,
boolean handleNested)
|
static void |
invertAffineTransform(Mat M,
Mat iM)
Inverts an affine transformation. |
static boolean |
isContourConvex(MatOfPoint contour)
Tests a contour convexity. |
static void |
Laplacian(Mat src,
Mat dst,
int ddepth)
Calculates the Laplacian of an image. |
static void |
Laplacian(Mat src,
Mat dst,
int ddepth,
int ksize,
double scale,
double delta)
Calculates the Laplacian of an image. |
static void |
Laplacian(Mat src,
Mat dst,
int ddepth,
int ksize,
double scale,
double delta,
int borderType)
Calculates the Laplacian of an image. |
static double |
matchShapes(Mat contour1,
Mat contour2,
int method,
double parameter)
Compares two shapes. |
static void |
matchTemplate(Mat image,
Mat templ,
Mat result,
int method)
Compares a template against overlapped image regions. |
static void |
medianBlur(Mat src,
Mat dst,
int ksize)
Blurs an image using the median filter. |
static RotatedRect |
minAreaRect(MatOfPoint2f points)
Finds a rotated rectangle of the minimum area enclosing the input 2D point set. |
static void |
minEnclosingCircle(MatOfPoint2f points,
Point center,
float[] radius)
Finds a circle of the minimum area enclosing a 2D point set. |
static Moments |
moments(Mat array)
Calculates all of the moments up to the third order of a polygon or rasterized shape. |
static Moments |
moments(Mat array,
boolean binaryImage)
Calculates all of the moments up to the third order of a polygon or rasterized shape. |
static void |
morphologyEx(Mat src,
Mat dst,
int op,
Mat kernel)
Performs advanced morphological transformations. |
static void |
morphologyEx(Mat src,
Mat dst,
int op,
Mat kernel,
Point anchor,
int iterations)
Performs advanced morphological transformations. |
static void |
morphologyEx(Mat src,
Mat dst,
int op,
Mat kernel,
Point anchor,
int iterations,
int borderType,
Scalar borderValue)
Performs advanced morphological transformations. |
static Point |
phaseCorrelate(Mat src1,
Mat src2)
The function is used to detect translational shifts that occur between two images. |
static Point |
phaseCorrelate(Mat src1,
Mat src2,
Mat window)
The function is used to detect translational shifts that occur between two images. |
static Point |
phaseCorrelateRes(Mat src1,
Mat src2,
Mat window)
|
static Point |
phaseCorrelateRes(Mat src1,
Mat src2,
Mat window,
double[] response)
|
static double |
pointPolygonTest(MatOfPoint2f contour,
Point pt,
boolean measureDist)
Performs a point-in-contour test. |
static void |
preCornerDetect(Mat src,
Mat dst,
int ksize)
Calculates a feature map for corner detection. |
static void |
preCornerDetect(Mat src,
Mat dst,
int ksize,
int borderType)
Calculates a feature map for corner detection. |
static double |
PSNR(Mat src1,
Mat src2)
|
static void |
pyrDown(Mat src,
Mat dst)
Blurs an image and downsamples it. |
static void |
pyrDown(Mat src,
Mat dst,
Size dstsize)
Blurs an image and downsamples it. |
static void |
pyrDown(Mat src,
Mat dst,
Size dstsize,
int borderType)
Blurs an image and downsamples it. |
static void |
pyrMeanShiftFiltering(Mat src,
Mat dst,
double sp,
double sr)
Performs initial step of meanshift segmentation of an image. |
static void |
pyrMeanShiftFiltering(Mat src,
Mat dst,
double sp,
double sr,
int maxLevel,
TermCriteria termcrit)
Performs initial step of meanshift segmentation of an image. |
static void |
pyrUp(Mat src,
Mat dst)
Upsamples an image and then blurs it. |
static void |
pyrUp(Mat src,
Mat dst,
Size dstsize)
Upsamples an image and then blurs it. |
static void |
pyrUp(Mat src,
Mat dst,
Size dstsize,
int borderType)
Upsamples an image and then blurs it. |
static void |
remap(Mat src,
Mat dst,
Mat map1,
Mat map2,
int interpolation)
Applies a generic geometrical transformation to an image. |
static void |
remap(Mat src,
Mat dst,
Mat map1,
Mat map2,
int interpolation,
int borderMode,
Scalar borderValue)
Applies a generic geometrical transformation to an image. |
static void |
resize(Mat src,
Mat dst,
Size dsize)
Resizes an image. |
static void |
resize(Mat src,
Mat dst,
Size dsize,
double fx,
double fy,
int interpolation)
Resizes an image. |
static void |
Scharr(Mat src,
Mat dst,
int ddepth,
int dx,
int dy)
Calculates the first x- or y- image derivative using Scharr operator. |
static void |
Scharr(Mat src,
Mat dst,
int ddepth,
int dx,
int dy,
double scale,
double delta)
Calculates the first x- or y- image derivative using Scharr operator. |
static void |
Scharr(Mat src,
Mat dst,
int ddepth,
int dx,
int dy,
double scale,
double delta,
int borderType)
Calculates the first x- or y- image derivative using Scharr operator. |
static void |
sepFilter2D(Mat src,
Mat dst,
int ddepth,
Mat kernelX,
Mat kernelY)
Applies a separable linear filter to an image. |
static void |
sepFilter2D(Mat src,
Mat dst,
int ddepth,
Mat kernelX,
Mat kernelY,
Point anchor,
double delta)
Applies a separable linear filter to an image. |
static void |
sepFilter2D(Mat src,
Mat dst,
int ddepth,
Mat kernelX,
Mat kernelY,
Point anchor,
double delta,
int borderType)
Applies a separable linear filter to an image. |
static void |
Sobel(Mat src,
Mat dst,
int ddepth,
int dx,
int dy)
Calculates the first, second, third, or mixed image derivatives using an extended Sobel operator. |
static void |
Sobel(Mat src,
Mat dst,
int ddepth,
int dx,
int dy,
int ksize,
double scale,
double delta)
Calculates the first, second, third, or mixed image derivatives using an extended Sobel operator. |
static void |
Sobel(Mat src,
Mat dst,
int ddepth,
int dx,
int dy,
int ksize,
double scale,
double delta,
int borderType)
Calculates the first, second, third, or mixed image derivatives using an extended Sobel operator. |
static double |
threshold(Mat src,
Mat dst,
double thresh,
double maxval,
int type)
Applies a fixed-level threshold to each array element. |
static void |
undistort(Mat src,
Mat dst,
Mat cameraMatrix,
Mat distCoeffs)
Transforms an image to compensate for lens distortion. |
static void |
undistort(Mat src,
Mat dst,
Mat cameraMatrix,
Mat distCoeffs,
Mat newCameraMatrix)
Transforms an image to compensate for lens distortion. |
static void |
undistortPoints(MatOfPoint2f src,
MatOfPoint2f dst,
Mat cameraMatrix,
Mat distCoeffs)
Computes the ideal point coordinates from the observed point coordinates. |
static void |
undistortPoints(MatOfPoint2f src,
MatOfPoint2f dst,
Mat cameraMatrix,
Mat distCoeffs,
Mat R,
Mat P)
Computes the ideal point coordinates from the observed point coordinates. |
static void |
warpAffine(Mat src,
Mat dst,
Mat M,
Size dsize)
Applies an affine transformation to an image. |
static void |
warpAffine(Mat src,
Mat dst,
Mat M,
Size dsize,
int flags)
Applies an affine transformation to an image. |
static void |
warpAffine(Mat src,
Mat dst,
Mat M,
Size dsize,
int flags,
int borderMode,
Scalar borderValue)
Applies an affine transformation to an image. |
static void |
warpPerspective(Mat src,
Mat dst,
Mat M,
Size dsize)
Applies a perspective transformation to an image. |
static void |
warpPerspective(Mat src,
Mat dst,
Mat M,
Size dsize,
int flags)
Applies a perspective transformation to an image. |
static void |
warpPerspective(Mat src,
Mat dst,
Mat M,
Size dsize,
int flags,
int borderMode,
Scalar borderValue)
Applies a perspective transformation to an image. |
static void |
watershed(Mat image,
Mat markers)
Performs a marker-based image segmentation using the watershed algorithm. |
| Methods inherited from class java.lang.Object |
|---|
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
| Field Detail |
|---|
public static final int ADAPTIVE_THRESH_GAUSSIAN_C
public static final int ADAPTIVE_THRESH_MEAN_C
public static final int BORDER_CONSTANT
public static final int BORDER_DEFAULT
public static final int BORDER_ISOLATED
public static final int BORDER_REFLECT
public static final int BORDER_REFLECT_101
public static final int BORDER_REFLECT101
public static final int BORDER_REPLICATE
public static final int BORDER_TRANSPARENT
public static final int BORDER_WRAP
public static final int CHAIN_APPROX_NONE
public static final int CHAIN_APPROX_SIMPLE
public static final int CHAIN_APPROX_TC89_KCOS
public static final int CHAIN_APPROX_TC89_L1
public static final int COLOR_BayerBG2BGR
public static final int COLOR_BayerBG2BGR_VNG
public static final int COLOR_BayerBG2GRAY
public static final int COLOR_BayerBG2RGB
public static final int COLOR_BayerBG2RGB_VNG
public static final int COLOR_BayerGB2BGR
public static final int COLOR_BayerGB2BGR_VNG
public static final int COLOR_BayerGB2GRAY
public static final int COLOR_BayerGB2RGB
public static final int COLOR_BayerGB2RGB_VNG
public static final int COLOR_BayerGR2BGR
public static final int COLOR_BayerGR2BGR_VNG
public static final int COLOR_BayerGR2GRAY
public static final int COLOR_BayerGR2RGB
public static final int COLOR_BayerGR2RGB_VNG
public static final int COLOR_BayerRG2BGR
public static final int COLOR_BayerRG2BGR_VNG
public static final int COLOR_BayerRG2GRAY
public static final int COLOR_BayerRG2RGB
public static final int COLOR_BayerRG2RGB_VNG
public static final int COLOR_BGR2BGR555
public static final int COLOR_BGR2BGR565
public static final int COLOR_BGR2BGRA
public static final int COLOR_BGR2GRAY
public static final int COLOR_BGR2HLS
public static final int COLOR_BGR2HLS_FULL
public static final int COLOR_BGR2HSV
public static final int COLOR_BGR2HSV_FULL
public static final int COLOR_BGR2Lab
public static final int COLOR_BGR2Luv
public static final int COLOR_BGR2RGB
public static final int COLOR_BGR2RGBA
public static final int COLOR_BGR2XYZ
public static final int COLOR_BGR2YCrCb
public static final int COLOR_BGR2YUV
public static final int COLOR_BGR5552BGR
public static final int COLOR_BGR5552BGRA
public static final int COLOR_BGR5552GRAY
public static final int COLOR_BGR5552RGB
public static final int COLOR_BGR5552RGBA
public static final int COLOR_BGR5652BGR
public static final int COLOR_BGR5652BGRA
public static final int COLOR_BGR5652GRAY
public static final int COLOR_BGR5652RGB
public static final int COLOR_BGR5652RGBA
public static final int COLOR_BGRA2BGR
public static final int COLOR_BGRA2BGR555
public static final int COLOR_BGRA2BGR565
public static final int COLOR_BGRA2GRAY
public static final int COLOR_BGRA2RGB
public static final int COLOR_BGRA2RGBA
public static final int COLOR_COLORCVT_MAX
public static final int COLOR_GRAY2BGR
public static final int COLOR_GRAY2BGR555
public static final int COLOR_GRAY2BGR565
public static final int COLOR_GRAY2BGRA
public static final int COLOR_GRAY2RGB
public static final int COLOR_GRAY2RGBA
public static final int COLOR_HLS2BGR
public static final int COLOR_HLS2BGR_FULL
public static final int COLOR_HLS2RGB
public static final int COLOR_HLS2RGB_FULL
public static final int COLOR_HSV2BGR
public static final int COLOR_HSV2BGR_FULL
public static final int COLOR_HSV2RGB
public static final int COLOR_HSV2RGB_FULL
public static final int COLOR_Lab2BGR
public static final int COLOR_Lab2LBGR
public static final int COLOR_Lab2LRGB
public static final int COLOR_Lab2RGB
public static final int COLOR_LBGR2Lab
public static final int COLOR_LBGR2Luv
public static final int COLOR_LRGB2Lab
public static final int COLOR_LRGB2Luv
public static final int COLOR_Luv2BGR
public static final int COLOR_Luv2LBGR
public static final int COLOR_Luv2LRGB
public static final int COLOR_Luv2RGB
public static final int COLOR_mRGBA2RGBA
public static final int COLOR_RGB2BGR
public static final int COLOR_RGB2BGR555
public static final int COLOR_RGB2BGR565
public static final int COLOR_RGB2BGRA
public static final int COLOR_RGB2GRAY
public static final int COLOR_RGB2HLS
public static final int COLOR_RGB2HLS_FULL
public static final int COLOR_RGB2HSV
public static final int COLOR_RGB2HSV_FULL
public static final int COLOR_RGB2Lab
public static final int COLOR_RGB2Luv
public static final int COLOR_RGB2RGBA
public static final int COLOR_RGB2XYZ
public static final int COLOR_RGB2YCrCb
public static final int COLOR_RGB2YUV
public static final int COLOR_RGBA2BGR
public static final int COLOR_RGBA2BGR555
public static final int COLOR_RGBA2BGR565
public static final int COLOR_RGBA2BGRA
public static final int COLOR_RGBA2GRAY
public static final int COLOR_RGBA2mRGBA
public static final int COLOR_RGBA2RGB
public static final int COLOR_XYZ2BGR
public static final int COLOR_XYZ2RGB
public static final int COLOR_YCrCb2BGR
public static final int COLOR_YCrCb2RGB
public static final int COLOR_YUV2BGR
public static final int COLOR_YUV2BGR_I420
public static final int COLOR_YUV2BGR_IYUV
public static final int COLOR_YUV2BGR_NV12
public static final int COLOR_YUV2BGR_NV21
public static final int COLOR_YUV2BGR_UYNV
public static final int COLOR_YUV2BGR_UYVY
public static final int COLOR_YUV2BGR_Y422
public static final int COLOR_YUV2BGR_YUNV
public static final int COLOR_YUV2BGR_YUY2
public static final int COLOR_YUV2BGR_YUYV
public static final int COLOR_YUV2BGR_YV12
public static final int COLOR_YUV2BGR_YVYU
public static final int COLOR_YUV2BGRA_I420
public static final int COLOR_YUV2BGRA_IYUV
public static final int COLOR_YUV2BGRA_NV12
public static final int COLOR_YUV2BGRA_NV21
public static final int COLOR_YUV2BGRA_UYNV
public static final int COLOR_YUV2BGRA_UYVY
public static final int COLOR_YUV2BGRA_Y422
public static final int COLOR_YUV2BGRA_YUNV
public static final int COLOR_YUV2BGRA_YUY2
public static final int COLOR_YUV2BGRA_YUYV
public static final int COLOR_YUV2BGRA_YV12
public static final int COLOR_YUV2BGRA_YVYU
public static final int COLOR_YUV2GRAY_420
public static final int COLOR_YUV2GRAY_I420
public static final int COLOR_YUV2GRAY_IYUV
public static final int COLOR_YUV2GRAY_NV12
public static final int COLOR_YUV2GRAY_NV21
public static final int COLOR_YUV2GRAY_UYNV
public static final int COLOR_YUV2GRAY_UYVY
public static final int COLOR_YUV2GRAY_Y422
public static final int COLOR_YUV2GRAY_YUNV
public static final int COLOR_YUV2GRAY_YUY2
public static final int COLOR_YUV2GRAY_YUYV
public static final int COLOR_YUV2GRAY_YV12
public static final int COLOR_YUV2GRAY_YVYU
public static final int COLOR_YUV2RGB
public static final int COLOR_YUV2RGB_I420
public static final int COLOR_YUV2RGB_IYUV
public static final int COLOR_YUV2RGB_NV12
public static final int COLOR_YUV2RGB_NV21
public static final int COLOR_YUV2RGB_UYNV
public static final int COLOR_YUV2RGB_UYVY
public static final int COLOR_YUV2RGB_Y422
public static final int COLOR_YUV2RGB_YUNV
public static final int COLOR_YUV2RGB_YUY2
public static final int COLOR_YUV2RGB_YUYV
public static final int COLOR_YUV2RGB_YV12
public static final int COLOR_YUV2RGB_YVYU
public static final int COLOR_YUV2RGBA_I420
public static final int COLOR_YUV2RGBA_IYUV
public static final int COLOR_YUV2RGBA_NV12
public static final int COLOR_YUV2RGBA_NV21
public static final int COLOR_YUV2RGBA_UYNV
public static final int COLOR_YUV2RGBA_UYVY
public static final int COLOR_YUV2RGBA_Y422
public static final int COLOR_YUV2RGBA_YUNV
public static final int COLOR_YUV2RGBA_YUY2
public static final int COLOR_YUV2RGBA_YUYV
public static final int COLOR_YUV2RGBA_YV12
public static final int COLOR_YUV2RGBA_YVYU
public static final int COLOR_YUV420p2BGR
public static final int COLOR_YUV420p2BGRA
public static final int COLOR_YUV420p2GRAY
public static final int COLOR_YUV420p2RGB
public static final int COLOR_YUV420p2RGBA
public static final int COLOR_YUV420sp2BGR
public static final int COLOR_YUV420sp2BGRA
public static final int COLOR_YUV420sp2GRAY
public static final int COLOR_YUV420sp2RGB
public static final int COLOR_YUV420sp2RGBA
public static final int CV_BILATERAL
public static final int CV_BLUR
public static final int CV_BLUR_NO_SCALE
public static final int CV_CANNY_L2_GRADIENT
public static final int CV_CHAIN_CODE
public static final int CV_CLOCKWISE
public static final int CV_COMP_BHATTACHARYYA
public static final int CV_COMP_CHISQR
public static final int CV_COMP_CORREL
public static final int CV_COMP_HELLINGER
public static final int CV_COMP_INTERSECT
public static final int CV_CONTOURS_MATCH_I1
public static final int CV_CONTOURS_MATCH_I2
public static final int CV_CONTOURS_MATCH_I3
public static final int CV_COUNTER_CLOCKWISE
public static final int CV_DIST_C
public static final int CV_DIST_FAIR
public static final int CV_DIST_HUBER
public static final int CV_DIST_L1
public static final int CV_DIST_L12
public static final int CV_DIST_L2
public static final int CV_DIST_LABEL_CCOMP
public static final int CV_DIST_LABEL_PIXEL
public static final int CV_DIST_MASK_3
public static final int CV_DIST_MASK_5
public static final int CV_DIST_MASK_PRECISE
public static final int CV_DIST_USER
public static final int CV_DIST_WELSCH
public static final int CV_GAUSSIAN
public static final int CV_GAUSSIAN_5x5
public static final int CV_HOUGH_GRADIENT
public static final int CV_HOUGH_MULTI_SCALE
public static final int CV_HOUGH_PROBABILISTIC
public static final int CV_HOUGH_STANDARD
public static final int CV_LINK_RUNS
public static final int CV_MAX_SOBEL_KSIZE
public static final int CV_MEDIAN
public static final int CV_mRGBA2RGBA
public static final int CV_POLY_APPROX_DP
public static final int CV_RGBA2mRGBA
public static final int CV_SCHARR
public static final int CV_SHAPE_CROSS
public static final int CV_SHAPE_CUSTOM
public static final int CV_SHAPE_ELLIPSE
public static final int CV_SHAPE_RECT
public static final int CV_WARP_FILL_OUTLIERS
public static final int CV_WARP_INVERSE_MAP
public static final int DIST_LABEL_CCOMP
public static final int DIST_LABEL_PIXEL
public static final int FLOODFILL_FIXED_RANGE
public static final int FLOODFILL_MASK_ONLY
public static final int GC_BGD
public static final int GC_EVAL
public static final int GC_FGD
public static final int GC_INIT_WITH_MASK
public static final int GC_INIT_WITH_RECT
public static final int GC_PR_BGD
public static final int GC_PR_FGD
public static final int GHT_POSITION
public static final int GHT_ROTATION
public static final int GHT_SCALE
public static final int INTER_AREA
public static final int INTER_BITS
public static final int INTER_BITS2
public static final int INTER_CUBIC
public static final int INTER_LANCZOS4
public static final int INTER_LINEAR
public static final int INTER_MAX
public static final int INTER_NEAREST
public static final int INTER_TAB_SIZE
public static final int INTER_TAB_SIZE2
public static final int KERNEL_ASYMMETRICAL
public static final int KERNEL_GENERAL
public static final int KERNEL_INTEGER
public static final int KERNEL_SMOOTH
public static final int KERNEL_SYMMETRICAL
public static final int MORPH_BLACKHAT
public static final int MORPH_CLOSE
public static final int MORPH_CROSS
public static final int MORPH_DILATE
public static final int MORPH_ELLIPSE
public static final int MORPH_ERODE
public static final int MORPH_GRADIENT
public static final int MORPH_OPEN
public static final int MORPH_RECT
public static final int MORPH_TOPHAT
public static final int PROJ_SPHERICAL_EQRECT
public static final int PROJ_SPHERICAL_ORTHO
public static final int RETR_CCOMP
public static final int RETR_EXTERNAL
public static final int RETR_FLOODFILL
public static final int RETR_LIST
public static final int RETR_TREE
public static final int THRESH_BINARY
public static final int THRESH_BINARY_INV
public static final int THRESH_MASK
public static final int THRESH_OTSU
public static final int THRESH_TOZERO
public static final int THRESH_TOZERO_INV
public static final int THRESH_TRUNC
public static final int TM_CCOEFF
public static final int TM_CCOEFF_NORMED
public static final int TM_CCORR
public static final int TM_CCORR_NORMED
public static final int TM_SQDIFF
public static final int TM_SQDIFF_NORMED
public static final int WARP_INVERSE_MAP
| Constructor Detail |
|---|
public Imgproc()
| Method Detail |
|---|
public static void accumulate(Mat src,
Mat dst)
Adds an image to the accumulator.
The function adds src or some of its elements to
dst :
dst(x,y) <- dst(x,y) + src(x,y) if mask(x,y) != 0
The function supports multi-channel images. Each channel is processed independently.
The functions accumulate* can be used, for example, to collect
statistics of a scene background viewed by a still camera and for the further
foreground-background segmentation.
src - Input image as 1- or 3-channel, 8-bit or 32-bit floating point.dst - Accumulator image with the same number of channels as input image,
32-bit or 64-bit floating-point.accumulateWeighted(org.opencv.core.Mat, org.opencv.core.Mat, double, org.opencv.core.Mat),
accumulateProduct(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
accumulateSquare(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void accumulate(Mat src,
Mat dst,
Mat mask)
Adds an image to the accumulator.
The function adds src or some of its elements to
dst :
dst(x,y) <- dst(x,y) + src(x,y) if mask(x,y) != 0
The function supports multi-channel images. Each channel is processed independently.
The functions accumulate* can be used, for example, to collect
statistics of a scene background viewed by a still camera and for the further
foreground-background segmentation.
src - Input image as 1- or 3-channel, 8-bit or 32-bit floating point.dst - Accumulator image with the same number of channels as input image,
32-bit or 64-bit floating-point.mask - Optional operation mask.accumulateWeighted(org.opencv.core.Mat, org.opencv.core.Mat, double, org.opencv.core.Mat),
accumulateProduct(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
accumulateSquare(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void accumulateProduct(Mat src1,
Mat src2,
Mat dst)
Adds the per-element product of two input images to the accumulator.
The function adds the product of two images or their selected regions to the
accumulator dst :
dst(x,y) <- dst(x,y) + src1(x,y) * src2(x,y) if mask(x,y) != 0
The function supports multi-channel images. Each channel is processed independently.
src1 - First input image, 1- or 3-channel, 8-bit or 32-bit floating
point.src2 - Second input image of the same type and the same size as
src1.dst - Accumulator with the same number of channels as input images,
32-bit or 64-bit floating-point.accumulate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
accumulateWeighted(org.opencv.core.Mat, org.opencv.core.Mat, double, org.opencv.core.Mat),
accumulateSquare(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void accumulateProduct(Mat src1,
Mat src2,
Mat dst,
Mat mask)
Adds the per-element product of two input images to the accumulator.
The function adds the product of two images or their selected regions to the
accumulator dst :
dst(x,y) <- dst(x,y) + src1(x,y) * src2(x,y) if mask(x,y) != 0
The function supports multi-channel images. Each channel is processed independently.
src1 - First input image, 1- or 3-channel, 8-bit or 32-bit floating
point.src2 - Second input image of the same type and the same size as
src1.dst - Accumulator with the same number of channels as input images,
32-bit or 64-bit floating-point.mask - Optional operation mask.accumulate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
accumulateWeighted(org.opencv.core.Mat, org.opencv.core.Mat, double, org.opencv.core.Mat),
accumulateSquare(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void accumulateSquare(Mat src,
Mat dst)
Adds the square of a source image to the accumulator.
The function adds the input image src or its selected region,
raised to a power of 2, to the accumulator dst :
dst(x,y) <- dst(x,y) + src(x,y)^2 if mask(x,y) != 0
The function supports multi-channel images. Each channel is processed independently.
src - Input image as 1- or 3-channel, 8-bit or 32-bit floating point.dst - Accumulator image with the same number of channels as input image,
32-bit or 64-bit floating-point.accumulateWeighted(org.opencv.core.Mat, org.opencv.core.Mat, double, org.opencv.core.Mat),
accumulateProduct(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
accumulateSquare(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void accumulateSquare(Mat src,
Mat dst,
Mat mask)
Adds the square of a source image to the accumulator.
The function adds the input image src or its selected region,
raised to a power of 2, to the accumulator dst :
dst(x,y) <- dst(x,y) + src(x,y)^2 if mask(x,y) != 0
The function supports multi-channel images. Each channel is processed independently.
src - Input image as 1- or 3-channel, 8-bit or 32-bit floating point.dst - Accumulator image with the same number of channels as input image,
32-bit or 64-bit floating-point.mask - Optional operation mask.accumulateWeighted(org.opencv.core.Mat, org.opencv.core.Mat, double, org.opencv.core.Mat),
accumulateProduct(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
accumulateSquare(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void accumulateWeighted(Mat src,
Mat dst,
double alpha)
Updates a running average.
The function calculates the weighted sum of the input image src
and the accumulator dst so that dst becomes a
running average of a frame sequence:
dst(x,y) <- (1- alpha) * dst(x,y) + alpha * src(x,y) if mask(x,y) != 0
That is, alpha regulates the update speed (how fast the
accumulator "forgets" about earlier images).
The function supports multi-channel images. Each channel is processed
independently.
src - Input image as 1- or 3-channel, 8-bit or 32-bit floating point.dst - Accumulator image with the same number of channels as input image,
32-bit or 64-bit floating-point.alpha - Weight of the input image.accumulate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
accumulateProduct(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
accumulateSquare(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void accumulateWeighted(Mat src,
Mat dst,
double alpha,
Mat mask)
Updates a running average.
The function calculates the weighted sum of the input image src
and the accumulator dst so that dst becomes a
running average of a frame sequence:
dst(x,y) <- (1- alpha) * dst(x,y) + alpha * src(x,y) if mask(x,y) != 0
That is, alpha regulates the update speed (how fast the
accumulator "forgets" about earlier images).
The function supports multi-channel images. Each channel is processed
independently.
src - Input image as 1- or 3-channel, 8-bit or 32-bit floating point.dst - Accumulator image with the same number of channels as input image,
32-bit or 64-bit floating-point.alpha - Weight of the input image.mask - Optional operation mask.accumulate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
accumulateProduct(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
accumulateSquare(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void adaptiveThreshold(Mat src,
Mat dst,
double maxValue,
int adaptiveMethod,
int thresholdType,
int blockSize,
double C)
Applies an adaptive threshold to an array.
The function transforms a grayscale image to a binary image according to the formulae:
dst(x,y) = maxValue if src(x,y) > T(x,y); 0 otherwise
dst(x,y) = 0 if src(x,y) > T(x,y); maxValue otherwise
where T(x,y) is a threshold calculated individually for each pixel.
ADAPTIVE_THRESH_MEAN_C, the threshold
value T(x,y) is a mean of the blockSize x blockSize
neighborhood of (x, y) minus C.
ADAPTIVE_THRESH_GAUSSIAN_C, the threshold
value T(x, y) is a weighted sum (cross-correlation with a Gaussian
window) of the blockSize x blockSize neighborhood of (x, y)
minus C. The default sigma (standard deviation) is used for the
specified blockSize. See "getGaussianKernel".
The function can process the image in-place.
src - Source 8-bit single-channel image.dst - Destination image of the same size and the same type as
src.maxValue - Non-zero value assigned to the pixels for which the condition
is satisfied. See the details below.adaptiveMethod - Adaptive thresholding algorithm to use,
ADAPTIVE_THRESH_MEAN_C or ADAPTIVE_THRESH_GAUSSIAN_C.
See the details below.thresholdType - Thresholding type that must be either THRESH_BINARY
or THRESH_BINARY_INV.blockSize - Size of a pixel neighborhood that is used to calculate a
threshold value for the pixel: 3, 5, 7, and so on.C - Constant subtracted from the mean or weighted mean (see the details
below). Normally, it is positive but may be zero or negative as well.threshold(org.opencv.core.Mat, org.opencv.core.Mat, double, double, int),
GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
blur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, int)
public static void approxPolyDP(MatOfPoint2f curve,
MatOfPoint2f approxCurve,
double epsilon,
boolean closed)
Approximates a polygonal curve(s) with the specified precision.
The functions approxPolyDP approximate a curve or a polygon with
another curve/polygon with less vertices so that the distance between them is
less or equal to the specified precision. It uses the Douglas-Peucker
algorithm http://en.wikipedia.org/wiki/Ramer-Douglas-Peucker_algorithm
See http://code.opencv.org/projects/opencv/repository/revisions/master/entry/samples/cpp/contours.cpp for the function usage model.
curve - Input vector of a 2D point stored in:
std.vector or Mat (C++ interface)
Nx2 numpy array (Python interface)
CvSeq or CvMat" (C interface)
approxCurve - Result of the approximation. The type should match the
type of the input curve. In case of C interface the approximated curve is
stored in the memory storage and pointer to it is returned.epsilon - Parameter specifying the approximation accuracy. This is the
maximum distance between the original curve and its approximation.closed - If true, the approximated curve is closed (its first and last
vertices are connected). Otherwise, it is not closed.
public static double arcLength(MatOfPoint2f curve,
boolean closed)
Calculates a contour perimeter or a curve length.
The function computes a curve length or a closed contour perimeter.
curve - Input vector of 2D points, stored in std.vector or
Mat.closed - Flag indicating whether the curve is closed or not.
public static void bilateralFilter(Mat src,
Mat dst,
int d,
double sigmaColor,
double sigmaSpace)
Applies the bilateral filter to an image.
The function applies bilateral filtering to the input image, as described in
http://www.dai.ed.ac.uk/CVonline/LOCAL_COPIES/MANDUCHI1/Bilateral_Filtering.html
bilateralFilter can reduce unwanted noise very well while
keeping edges fairly sharp. However, it is very slow compared to most
filters.
This filter does not work inplace.
src - Source 8-bit or floating-point, 1-channel or 3-channel image.dst - Destination image of the same size and type as src.d - Diameter of each pixel neighborhood that is used during filtering.
If it is non-positive, it is computed from sigmaSpace.sigmaColor - Filter sigma in the color space. A larger value of the
parameter means that farther colors within the pixel neighborhood (see
sigmaSpace) will be mixed together, resulting in larger areas of
semi-equal color.sigmaSpace - Filter sigma in the coordinate space. A larger value of the
parameter means that farther pixels will influence each other as long as
their colors are close enough (see sigmaColor). When
d>0, it specifies the neighborhood size regardless of
sigmaSpace. Otherwise, d is proportional to
sigmaSpace.
public static void bilateralFilter(Mat src,
Mat dst,
int d,
double sigmaColor,
double sigmaSpace,
int borderType)
Applies the bilateral filter to an image.
The function applies bilateral filtering to the input image, as described in
http://www.dai.ed.ac.uk/CVonline/LOCAL_COPIES/MANDUCHI1/Bilateral_Filtering.html
bilateralFilter can reduce unwanted noise very well while
keeping edges fairly sharp. However, it is very slow compared to most
filters.
This filter does not work inplace.
src - Source 8-bit or floating-point, 1-channel or 3-channel image.dst - Destination image of the same size and type as src.d - Diameter of each pixel neighborhood that is used during filtering.
If it is non-positive, it is computed from sigmaSpace.sigmaColor - Filter sigma in the color space. A larger value of the
parameter means that farther colors within the pixel neighborhood (see
sigmaSpace) will be mixed together, resulting in larger areas of
semi-equal color.sigmaSpace - Filter sigma in the coordinate space. A larger value of the
parameter means that farther pixels will influence each other as long as
their colors are close enough (see sigmaColor). When
d>0, it specifies the neighborhood size regardless of
sigmaSpace. Otherwise, d is proportional to
sigmaSpace.borderType - a borderType
public static void blur(Mat src,
Mat dst,
Size ksize)
Blurs an image using the normalized box filter.
The function smoothes an image using the kernel:
K = 1/(ksize.width*ksize.height) 1 1 1 *s 1 1 1 1 1 *s 1 1.................. 1 1 1 *s 1 1
The call blur(src, dst, ksize, anchor, borderType) is equivalent
to boxFilter(src, dst, src.type(), anchor, true, borderType).
src - input image; it can have any number of channels, which are
processed independently, but the depth should be CV_8U,
CV_16U, CV_16S, CV_32F or
CV_64F.dst - output image of the same size and type as src.ksize - blurring kernel size.boxFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Size, org.opencv.core.Point, boolean, int),
GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
bilateralFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, double, double, int),
medianBlur(org.opencv.core.Mat, org.opencv.core.Mat, int)
public static void blur(Mat src,
Mat dst,
Size ksize,
Point anchor)
Blurs an image using the normalized box filter.
The function smoothes an image using the kernel:
K = 1/(ksize.width*ksize.height) 1 1 1 *s 1 1 1 1 1 *s 1 1.................. 1 1 1 *s 1 1
The call blur(src, dst, ksize, anchor, borderType) is equivalent
to boxFilter(src, dst, src.type(), anchor, true, borderType).
src - input image; it can have any number of channels, which are
processed independently, but the depth should be CV_8U,
CV_16U, CV_16S, CV_32F or
CV_64F.dst - output image of the same size and type as src.ksize - blurring kernel size.anchor - anchor point; default value Point(-1,-1) means
that the anchor is at the kernel center.boxFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Size, org.opencv.core.Point, boolean, int),
GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
bilateralFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, double, double, int),
medianBlur(org.opencv.core.Mat, org.opencv.core.Mat, int)
public static void blur(Mat src,
Mat dst,
Size ksize,
Point anchor,
int borderType)
Blurs an image using the normalized box filter.
The function smoothes an image using the kernel:
K = 1/(ksize.width*ksize.height) 1 1 1 *s 1 1 1 1 1 *s 1 1.................. 1 1 1 *s 1 1
The call blur(src, dst, ksize, anchor, borderType) is equivalent
to boxFilter(src, dst, src.type(), anchor, true, borderType).
src - input image; it can have any number of channels, which are
processed independently, but the depth should be CV_8U,
CV_16U, CV_16S, CV_32F or
CV_64F.dst - output image of the same size and type as src.ksize - blurring kernel size.anchor - anchor point; default value Point(-1,-1) means
that the anchor is at the kernel center.borderType - border mode used to extrapolate pixels outside of the
image.boxFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Size, org.opencv.core.Point, boolean, int),
GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
bilateralFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, double, double, int),
medianBlur(org.opencv.core.Mat, org.opencv.core.Mat, int)
public static int borderInterpolate(int p,
int len,
int borderType)
Computes the source location of an extrapolated pixel.
The function computes and returns the coordinate of a donor pixel
corresponding to the specified extrapolated pixel when using the specified
extrapolation border mode. For example, if you use BORDER_WRAP
mode in the horizontal direction, BORDER_REFLECT_101 in the
vertical direction and want to compute value of the "virtual" pixel
Point(-5, 100) in a floating-point image img, it
looks like:
// C++ code:
float val = img.at
borderInterpolate(-5, img.cols, BORDER_WRAP));
Normally, the function is not called directly. It is used inside
"FilterEngine" and "copyMakeBorder" to compute tables for quick extrapolation.
p - 0-based coordinate of the extrapolated pixel along one of the axes,
likely <0 or >= len.len - Length of the array along the corresponding axis.borderType - Border type, one of the BORDER_*, except for
BORDER_TRANSPARENT and BORDER_ISOLATED. When
borderType==BORDER_CONSTANT, the function always returns -1,
regardless of p and len.copyMakeBorder(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, int, int, org.opencv.core.Scalar)public static Rect boundingRect(MatOfPoint points)
Calculates the up-right bounding rectangle of a point set.
The function calculates and returns the minimal up-right bounding rectangle for the specified point set.
points - Input 2D point set, stored in std.vector or
Mat.
public static void boxFilter(Mat src,
Mat dst,
int ddepth,
Size ksize)
Blurs an image using the box filter.
The function smoothes an image using the kernel:
K = alpha 1 1 1 *s 1 1 1 1 1 *s 1 1.................. 1 1 1 *s 1 1
where
alpha = 1/(ksize.width*ksize.height) when normalize=true; 1 otherwise
Unnormalized box filter is useful for computing various integral characteristics over each pixel neighborhood, such as covariance matrices of image derivatives (used in dense optical flow algorithms, and so on). If you need to compute pixel sums over variable-size windows, use "integral".
src - input image.dst - output image of the same size and type as src.ddepth - the output image depth (-1 to use src.depth()).ksize - blurring kernel size.GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
medianBlur(org.opencv.core.Mat, org.opencv.core.Mat, int),
integral(org.opencv.core.Mat, org.opencv.core.Mat, int),
bilateralFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, double, double, int),
blur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, int)
public static void boxFilter(Mat src,
Mat dst,
int ddepth,
Size ksize,
Point anchor,
boolean normalize)
Blurs an image using the box filter.
The function smoothes an image using the kernel:
K = alpha 1 1 1 *s 1 1 1 1 1 *s 1 1.................. 1 1 1 *s 1 1
where
alpha = 1/(ksize.width*ksize.height) when normalize=true; 1 otherwise
Unnormalized box filter is useful for computing various integral characteristics over each pixel neighborhood, such as covariance matrices of image derivatives (used in dense optical flow algorithms, and so on). If you need to compute pixel sums over variable-size windows, use "integral".
src - input image.dst - output image of the same size and type as src.ddepth - the output image depth (-1 to use src.depth()).ksize - blurring kernel size.anchor - anchor point; default value Point(-1,-1) means
that the anchor is at the kernel center.normalize - flag, specifying whether the kernel is normalized by its
area or not.GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
medianBlur(org.opencv.core.Mat, org.opencv.core.Mat, int),
integral(org.opencv.core.Mat, org.opencv.core.Mat, int),
bilateralFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, double, double, int),
blur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, int)
public static void boxFilter(Mat src,
Mat dst,
int ddepth,
Size ksize,
Point anchor,
boolean normalize,
int borderType)
Blurs an image using the box filter.
The function smoothes an image using the kernel:
K = alpha 1 1 1 *s 1 1 1 1 1 *s 1 1.................. 1 1 1 *s 1 1
where
alpha = 1/(ksize.width*ksize.height) when normalize=true; 1 otherwise
Unnormalized box filter is useful for computing various integral characteristics over each pixel neighborhood, such as covariance matrices of image derivatives (used in dense optical flow algorithms, and so on). If you need to compute pixel sums over variable-size windows, use "integral".
src - input image.dst - output image of the same size and type as src.ddepth - the output image depth (-1 to use src.depth()).ksize - blurring kernel size.anchor - anchor point; default value Point(-1,-1) means
that the anchor is at the kernel center.normalize - flag, specifying whether the kernel is normalized by its
area or not.borderType - border mode used to extrapolate pixels outside of the
image.GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
medianBlur(org.opencv.core.Mat, org.opencv.core.Mat, int),
integral(org.opencv.core.Mat, org.opencv.core.Mat, int),
bilateralFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, double, double, int),
blur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, int)
public static void calcBackProject(java.util.List<Mat> images,
MatOfInt channels,
Mat hist,
Mat dst,
MatOfFloat ranges,
double scale)
Calculates the back projection of a histogram.
The functions calcBackProject calculate the back project of the
histogram. That is, similarly to calcHist, at each location
(x, y) the function collects the values from the selected
channels in the input images and finds the corresponding histogram bin. But
instead of incrementing it, the function reads the bin value, scales it by
scale, and stores in backProject(x,y). In terms of
statistics, the function computes probability of each element value in
respect with the empirical probability distribution represented by the
histogram. See how, for example, you can find and track a bright-colored
object in a scene:
This is an approximate algorithm of the "CamShift" color object tracker.
images - Source arrays. They all should have the same depth,
CV_8U or CV_32F, and the same size. Each of them
can have an arbitrary number of channels.channels - The list of channels used to compute the back projection. The
number of channels must match the histogram dimensionality. The first array
channels are numerated from 0 to images[0].channels()-1, the
second array channels are counted from images[0].channels() to
images[0].channels() + images[1].channels()-1, and so on.hist - Input histogram that can be dense or sparse.dst - a dstranges - Array of arrays of the histogram bin boundaries in each
dimension. See "calcHist".scale - Optional scale factor for the output back projection.calcHist(java.util.List, org.opencv.core.MatOfInt, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.MatOfInt, org.opencv.core.MatOfFloat, boolean)
public static void calcHist(java.util.List<Mat> images,
MatOfInt channels,
Mat mask,
Mat hist,
MatOfInt histSize,
MatOfFloat ranges)
Calculates a histogram of a set of arrays.
The functions calcHist calculate the histogram of one or more
arrays. The elements of a tuple used to increment a histogram bin are taken
from the correspondinginput arrays at the same location. The sample below
shows how to compute a 2D Hue-Saturation histogram for a color image.
// C++ code:
#include
#include
using namespace cv;
int main(int argc, char argv)
Mat src, hsv;
if(argc != 2 || !(src=imread(argv[1], 1)).data)
return -1;
cvtColor(src, hsv, CV_BGR2HSV);
// Quantize the hue to 30 levels
// and the saturation to 32 levels
int hbins = 30, sbins = 32;
int histSize[] = {hbins, sbins};
// hue varies from 0 to 179, see cvtColor
float hranges[] = { 0, 180 };
// saturation varies from 0 (black-gray-white) to
// 255 (pure spectrum color)
float sranges[] = { 0, 256 };
const float* ranges[] = { hranges, sranges };
MatND hist;
// we compute the histogram from the 0-th and 1-st channels
int channels[] = {0, 1};
calcHist(&hsv, 1, channels, Mat(), // do not use mask
hist, 2, histSize, ranges,
true, // the histogram is uniform
false);
double maxVal=0;
minMaxLoc(hist, 0, &maxVal, 0, 0);
int scale = 10;
Mat histImg = Mat.zeros(sbins*scale, hbins*10, CV_8UC3);
for(int h = 0; h < hbins; h++)
for(int s = 0; s < sbins; s++)
float binVal = hist.at
int intensity = cvRound(binVal*255/maxVal);
rectangle(histImg, Point(h*scale, s*scale),
Point((h+1)*scale - 1, (s+1)*scale - 1),
Scalar.all(intensity),
CV_FILLED);
namedWindow("Source", 1);
imshow("Source", src);
namedWindow("H-S Histogram", 1);
imshow("H-S Histogram", histImg);
waitKey();
images - Source arrays. They all should have the same depth,
CV_8U or CV_32F, and the same size. Each of them
can have an arbitrary number of channels.channels - List of the dims channels used to compute the
histogram. The first array channels are numerated from 0 to images[0].channels()-1,
the second array channels are counted from images[0].channels()
to images[0].channels() + images[1].channels()-1, and so on.mask - Optional mask. If the matrix is not empty, it must be an 8-bit
array of the same size as images[i]. The non-zero mask elements
mark the array elements counted in the histogram.hist - Output histogram, which is a dense or sparse dims
-dimensional array.histSize - Array of histogram sizes in each dimension.ranges - Array of the dims arrays of the histogram bin
boundaries in each dimension. When the histogram is uniform (uniform
=true), then for each dimension i it is enough to specify the
lower (inclusive) boundary L_0 of the 0-th histogram bin and the
upper (exclusive) boundary U_(histSize[i]-1) for the last histogram
bin histSize[i]-1. That is, in case of a uniform histogram each
of ranges[i] is an array of 2 elements. When the histogram is
not uniform (uniform=false), then each of ranges[i]
contains histSize[i]+1 elements: L_0, U_0=L_1, U_1=L_2,...,
U_(histSize[i]-2)=L_(histSize[i]-1), U_(histSize[i]-1). The array
elements, that are not between L_0 and U_(histSize[i]-1),
are not counted in the histogram.
public static void calcHist(java.util.List<Mat> images,
MatOfInt channels,
Mat mask,
Mat hist,
MatOfInt histSize,
MatOfFloat ranges,
boolean accumulate)
Calculates a histogram of a set of arrays.
The functions calcHist calculate the histogram of one or more
arrays. The elements of a tuple used to increment a histogram bin are taken
from the correspondinginput arrays at the same location. The sample below
shows how to compute a 2D Hue-Saturation histogram for a color image.
// C++ code:
#include
#include
using namespace cv;
int main(int argc, char argv)
Mat src, hsv;
if(argc != 2 || !(src=imread(argv[1], 1)).data)
return -1;
cvtColor(src, hsv, CV_BGR2HSV);
// Quantize the hue to 30 levels
// and the saturation to 32 levels
int hbins = 30, sbins = 32;
int histSize[] = {hbins, sbins};
// hue varies from 0 to 179, see cvtColor
float hranges[] = { 0, 180 };
// saturation varies from 0 (black-gray-white) to
// 255 (pure spectrum color)
float sranges[] = { 0, 256 };
const float* ranges[] = { hranges, sranges };
MatND hist;
// we compute the histogram from the 0-th and 1-st channels
int channels[] = {0, 1};
calcHist(&hsv, 1, channels, Mat(), // do not use mask
hist, 2, histSize, ranges,
true, // the histogram is uniform
false);
double maxVal=0;
minMaxLoc(hist, 0, &maxVal, 0, 0);
int scale = 10;
Mat histImg = Mat.zeros(sbins*scale, hbins*10, CV_8UC3);
for(int h = 0; h < hbins; h++)
for(int s = 0; s < sbins; s++)
float binVal = hist.at
int intensity = cvRound(binVal*255/maxVal);
rectangle(histImg, Point(h*scale, s*scale),
Point((h+1)*scale - 1, (s+1)*scale - 1),
Scalar.all(intensity),
CV_FILLED);
namedWindow("Source", 1);
imshow("Source", src);
namedWindow("H-S Histogram", 1);
imshow("H-S Histogram", histImg);
waitKey();
images - Source arrays. They all should have the same depth,
CV_8U or CV_32F, and the same size. Each of them
can have an arbitrary number of channels.channels - List of the dims channels used to compute the
histogram. The first array channels are numerated from 0 to images[0].channels()-1,
the second array channels are counted from images[0].channels()
to images[0].channels() + images[1].channels()-1, and so on.mask - Optional mask. If the matrix is not empty, it must be an 8-bit
array of the same size as images[i]. The non-zero mask elements
mark the array elements counted in the histogram.hist - Output histogram, which is a dense or sparse dims
-dimensional array.histSize - Array of histogram sizes in each dimension.ranges - Array of the dims arrays of the histogram bin
boundaries in each dimension. When the histogram is uniform (uniform
=true), then for each dimension i it is enough to specify the
lower (inclusive) boundary L_0 of the 0-th histogram bin and the
upper (exclusive) boundary U_(histSize[i]-1) for the last histogram
bin histSize[i]-1. That is, in case of a uniform histogram each
of ranges[i] is an array of 2 elements. When the histogram is
not uniform (uniform=false), then each of ranges[i]
contains histSize[i]+1 elements: L_0, U_0=L_1, U_1=L_2,...,
U_(histSize[i]-2)=L_(histSize[i]-1), U_(histSize[i]-1). The array
elements, that are not between L_0 and U_(histSize[i]-1),
are not counted in the histogram.accumulate - Accumulation flag. If it is set, the histogram is not
cleared in the beginning when it is allocated. This feature enables you to
compute a single histogram from several sets of arrays, or to update the
histogram in time.
public static void Canny(Mat image,
Mat edges,
double threshold1,
double threshold2)
Finds edges in an image using the [Canny86] algorithm.
The function finds edges in the input image image and marks them
in the output map edges using the Canny algorithm. The smallest
value between threshold1 and threshold2 is used for
edge linking. The largest value is used to find initial segments of strong
edges. See http://en.wikipedia.org/wiki/Canny_edge_detector
image - single-channel 8-bit input image.edges - output edge map; it has the same size and type as
image.threshold1 - first threshold for the hysteresis procedure.threshold2 - second threshold for the hysteresis procedure.
public static void Canny(Mat image,
Mat edges,
double threshold1,
double threshold2,
int apertureSize,
boolean L2gradient)
Finds edges in an image using the [Canny86] algorithm.
The function finds edges in the input image image and marks them
in the output map edges using the Canny algorithm. The smallest
value between threshold1 and threshold2 is used for
edge linking. The largest value is used to find initial segments of strong
edges. See http://en.wikipedia.org/wiki/Canny_edge_detector
image - single-channel 8-bit input image.edges - output edge map; it has the same size and type as
image.threshold1 - first threshold for the hysteresis procedure.threshold2 - second threshold for the hysteresis procedure.apertureSize - aperture size for the "Sobel" operator.L2gradient - a flag, indicating whether a more accurate L_2
norm =sqrt((dI/dx)^2 + (dI/dy)^2) should be used to calculate the
image gradient magnitude (L2gradient=true), or whether the
default L_1 norm =|dI/dx|+|dI/dy| is enough
(L2gradient=false).
public static double compareHist(Mat H1,
Mat H2,
int method)
Compares two histograms.
The functions compareHist compare two dense or two sparse
histograms using the specified method:
method=CV_COMP_CORREL)
d(H_1,H_2) = (sum_I(H_1(I) - H_1")(H_2(I) - H_2"))/(sqrt(sum_I(H_1(I) - H_1")^2 sum_I(H_2(I) - H_2")^2))
where
H_k" = 1/(N) sum _J H_k(J)
and N is a total number of histogram bins.
method=CV_COMP_CHISQR)
d(H_1,H_2) = sum _I((H_1(I)-H_2(I))^2)/(H_1(I))
method=CV_COMP_INTERSECT)
d(H_1,H_2) = sum _I min(H_1(I), H_2(I))
method=CV_COMP_BHATTACHARYYA or
method=CV_COMP_HELLINGER). In fact, OpenCV computes Hellinger
distance, which is related to Bhattacharyya coefficient.
d(H_1,H_2) = sqrt(1 - frac(1)(sqrt(H_1" H_2" N^2)) sum_I sqrt(H_1(I) * H_2(I)))
The function returns d(H_1, H_2).
While the function works well with 1-, 2-, 3-dimensional dense histograms, it may not be suitable for high-dimensional sparse histograms. In such histograms, because of aliasing and sampling problems, the coordinates of non-zero histogram bins can slightly shift. To compare such histograms or more general sparse configurations of weighted points, consider using the "EMD" function.
H1 - First compared histogram.H2 - Second compared histogram of the same size as H1.method - Comparison method that could be one of the following:
CV_COMP_BHATTACHARYYA
public static double contourArea(Mat contour)
Calculates a contour area.
The function computes a contour area. Similarly to "moments", the area is
computed using the Green formula. Thus, the returned area and the number of
non-zero pixels, if you draw the contour using "drawContours" or "fillPoly",
can be different.
Also, the function will most certainly give a wrong results for contours with
self-intersections.
Example:
// C++ code:
vector
contour.push_back(Point2f(0, 0));
contour.push_back(Point2f(10, 0));
contour.push_back(Point2f(10, 10));
contour.push_back(Point2f(5, 4));
double area0 = contourArea(contour);
vector
approxPolyDP(contour, approx, 5, true);
double area1 = contourArea(approx);
cout << "area0 =" << area0 << endl <<
"area1 =" << area1 << endl <<
"approx poly vertices" << approx.size() << endl;
contour - Input vector of 2D points (contour vertices), stored in
std.vector or Mat.
public static double contourArea(Mat contour,
boolean oriented)
Calculates a contour area.
The function computes a contour area. Similarly to "moments", the area is
computed using the Green formula. Thus, the returned area and the number of
non-zero pixels, if you draw the contour using "drawContours" or "fillPoly",
can be different.
Also, the function will most certainly give a wrong results for contours with
self-intersections.
Example:
// C++ code:
vector
contour.push_back(Point2f(0, 0));
contour.push_back(Point2f(10, 0));
contour.push_back(Point2f(10, 10));
contour.push_back(Point2f(5, 4));
double area0 = contourArea(contour);
vector
approxPolyDP(contour, approx, 5, true);
double area1 = contourArea(approx);
cout << "area0 =" << area0 << endl <<
"area1 =" << area1 << endl <<
"approx poly vertices" << approx.size() << endl;
contour - Input vector of 2D points (contour vertices), stored in
std.vector or Mat.oriented - Oriented area flag. If it is true, the function returns a
signed area value, depending on the contour orientation (clockwise or
counter-clockwise). Using this feature you can determine orientation of a
contour by taking the sign of an area. By default, the parameter is
false, which means that the absolute value is returned.
public static void convertMaps(Mat map1,
Mat map2,
Mat dstmap1,
Mat dstmap2,
int dstmap1type)
Converts image transformation maps from one representation to another.
The function converts a pair of maps for "remap" from one representation to
another. The following options ((map1.type(), map2.type())
-> (dstmap1.type(), dstmap2.type())) are supported:
nninterpolation=false)
contains indices in the interpolation tables.
map1 - The first input map of type CV_16SC2,
CV_32FC1, or CV_32FC2.map2 - The second input map of type CV_16UC1,
CV_32FC1, or none (empty matrix), respectively.dstmap1 - The first output map that has the type dstmap1type
and the same size as src.dstmap2 - The second output map.dstmap1type - Type of the first output map that should be
CV_16SC2, CV_32FC1, or CV_32FC2.remap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, int, org.opencv.core.Scalar),
initUndistortRectifyMap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, org.opencv.core.Mat, org.opencv.core.Mat),
undistort(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void convertMaps(Mat map1,
Mat map2,
Mat dstmap1,
Mat dstmap2,
int dstmap1type,
boolean nninterpolation)
Converts image transformation maps from one representation to another.
The function converts a pair of maps for "remap" from one representation to
another. The following options ((map1.type(), map2.type())
-> (dstmap1.type(), dstmap2.type())) are supported:
nninterpolation=false)
contains indices in the interpolation tables.
map1 - The first input map of type CV_16SC2,
CV_32FC1, or CV_32FC2.map2 - The second input map of type CV_16UC1,
CV_32FC1, or none (empty matrix), respectively.dstmap1 - The first output map that has the type dstmap1type
and the same size as src.dstmap2 - The second output map.dstmap1type - Type of the first output map that should be
CV_16SC2, CV_32FC1, or CV_32FC2.nninterpolation - Flag indicating whether the fixed-point maps are used
for the nearest-neighbor or for a more complex interpolation.remap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, int, org.opencv.core.Scalar),
initUndistortRectifyMap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, org.opencv.core.Mat, org.opencv.core.Mat),
undistort(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void convexHull(MatOfPoint points,
MatOfInt hull)
Finds the convex hull of a point set.
The functions find the convex hull of a 2D point set using the Sklansky's
algorithm [Sklansky82] that has *O(N logN)* complexity in the current
implementation. See the OpenCV sample convexhull.cpp that
demonstrates the usage of different function variants.
points - Input 2D point set, stored in std.vector or
Mat.hull - Output convex hull. It is either an integer vector of indices or
vector of points. In the first case, the hull elements are
0-based indices of the convex hull points in the original array (since the
set of convex hull points is a subset of the original point set). In the
second case, hull elements are the convex hull points
themselves.
public static void convexHull(MatOfPoint points,
MatOfInt hull,
boolean clockwise)
Finds the convex hull of a point set.
The functions find the convex hull of a 2D point set using the Sklansky's
algorithm [Sklansky82] that has *O(N logN)* complexity in the current
implementation. See the OpenCV sample convexhull.cpp that
demonstrates the usage of different function variants.
points - Input 2D point set, stored in std.vector or
Mat.hull - Output convex hull. It is either an integer vector of indices or
vector of points. In the first case, the hull elements are
0-based indices of the convex hull points in the original array (since the
set of convex hull points is a subset of the original point set). In the
second case, hull elements are the convex hull points
themselves.clockwise - Orientation flag. If it is true, the output convex hull is
oriented clockwise. Otherwise, it is oriented counter-clockwise. The usual
screen coordinate system is assumed so that the origin is at the top-left
corner, x axis is oriented to the right, and y axis is oriented downwards.
public static void convexityDefects(MatOfPoint contour,
MatOfInt convexhull,
MatOfInt4 convexityDefects)
Finds the convexity defects of a contour.
The function finds all convexity defects of the input contour and returns a
sequence of the CvConvexityDefect structures, where
CvConvexityDetect is defined as:
// C++ code:
struct CvConvexityDefect
CvPoint* start; // point of the contour where the defect begins
CvPoint* end; // point of the contour where the defect ends
CvPoint* depth_point; // the farthest from the convex hull point within the defect
float depth; // distance between the farthest point and the convex hull
};
The figure below displays convexity defects of a hand contour:
contour - Input contour.convexhull - Convex hull obtained using "convexHull" that should contain
indices of the contour points that make the hull.convexityDefects - The output vector of convexity defects. In C++ and
the new Python/Java interface each convexity defect is represented as
4-element integer vector (a.k.a. cv.Vec4i): (start_index,
end_index, farthest_pt_index, fixpt_depth), where indices are 0-based
indices in the original contour of the convexity defect beginning, end and
the farthest point, and fixpt_depth is fixed-point approximation
(with 8 fractional bits) of the distance between the farthest contour point
and the hull. That is, to get the floating-point value of the depth will be
fixpt_depth/256.0. In C interface convexity defect is
represented by CvConvexityDefect structure - see below.
public static void copyMakeBorder(Mat src,
Mat dst,
int top,
int bottom,
int left,
int right,
int borderType)
Forms a border around an image.
The function copies the source image into the middle of the destination
image. The areas to the left, to the right, above and below the copied source
image will be filled with extrapolated pixels. This is not what
"FilterEngine" or filtering functions based on it do (they extrapolate pixels
on-fly), but what other more complex functions, including your own, may do to
simplify image boundary handling.
The function supports the mode when src is already in the middle
of dst. In this case, the function does not copy
src itself but simply constructs the border, for example:
// C++ code:
// let border be the same in all directions
int border=2;
// constructs a larger image to fit both the image and the border
Mat gray_buf(rgb.rows + border*2, rgb.cols + border*2, rgb.depth());
// select the middle part of it w/o copying data
Mat gray(gray_canvas, Rect(border, border, rgb.cols, rgb.rows));
// convert image from RGB to grayscale
cvtColor(rgb, gray, CV_RGB2GRAY);
// form a border in-place
copyMakeBorder(gray, gray_buf, border, border,
border, border, BORDER_REPLICATE);
// now do some custom filtering......
Note:
When the source image is a part (ROI) of a bigger image, the function will
try to use the pixels outside of the ROI to form a border. To disable this
feature and always do extrapolation, as if src was not a ROI,
use borderType | BORDER_ISOLATED.
src - Source image.dst - Destination image of the same type as src and the
size Size(src.cols+left+right, src.rows+top+bottom).top - a topbottom - a bottomleft - a leftright - Parameter specifying how many pixels in each direction from the
source image rectangle to extrapolate. For example, top=1, bottom=1,
left=1, right=1 mean that 1 pixel-wide border needs to be built.borderType - Border type. See "borderInterpolate" for details.borderInterpolate(int, int, int)
public static void copyMakeBorder(Mat src,
Mat dst,
int top,
int bottom,
int left,
int right,
int borderType,
Scalar value)
Forms a border around an image.
The function copies the source image into the middle of the destination
image. The areas to the left, to the right, above and below the copied source
image will be filled with extrapolated pixels. This is not what
"FilterEngine" or filtering functions based on it do (they extrapolate pixels
on-fly), but what other more complex functions, including your own, may do to
simplify image boundary handling.
The function supports the mode when src is already in the middle
of dst. In this case, the function does not copy
src itself but simply constructs the border, for example:
// C++ code:
// let border be the same in all directions
int border=2;
// constructs a larger image to fit both the image and the border
Mat gray_buf(rgb.rows + border*2, rgb.cols + border*2, rgb.depth());
// select the middle part of it w/o copying data
Mat gray(gray_canvas, Rect(border, border, rgb.cols, rgb.rows));
// convert image from RGB to grayscale
cvtColor(rgb, gray, CV_RGB2GRAY);
// form a border in-place
copyMakeBorder(gray, gray_buf, border, border,
border, border, BORDER_REPLICATE);
// now do some custom filtering......
Note:
When the source image is a part (ROI) of a bigger image, the function will
try to use the pixels outside of the ROI to form a border. To disable this
feature and always do extrapolation, as if src was not a ROI,
use borderType | BORDER_ISOLATED.
src - Source image.dst - Destination image of the same type as src and the
size Size(src.cols+left+right, src.rows+top+bottom).top - a topbottom - a bottomleft - a leftright - Parameter specifying how many pixels in each direction from the
source image rectangle to extrapolate. For example, top=1, bottom=1,
left=1, right=1 mean that 1 pixel-wide border needs to be built.borderType - Border type. See "borderInterpolate" for details.value - Border value if borderType==BORDER_CONSTANT.borderInterpolate(int, int, int)
public static void cornerEigenValsAndVecs(Mat src,
Mat dst,
int blockSize,
int ksize)
Calculates eigenvalues and eigenvectors of image blocks for corner detection.
For every pixel p, the function cornerEigenValsAndVecs
considers a blockSize x blockSize
neighborhood S(p). It calculates the covariation matrix of
derivatives over the neighborhood as:
M = sum(by: S(p))(dI/dx)^2 sum(by: S(p))(dI/dx dI/dy)^2 sum(by: S(p))(dI/dx dI/dy)^2 sum(by: S(p))(dI/dy)^2
where the derivatives are computed using the "Sobel" operator.
After that, it finds eigenvectors and eigenvalues of M and stores them in the destination image as (lambda_1, lambda_2, x_1, y_1, x_2, y_2) where
The output of the function can be used for robust edge or corner detection.
src - Input single-channel 8-bit or floating-point image.dst - Image to store the results. It has the same size as
src and the type CV_32FC(6).blockSize - Neighborhood size (see details below).ksize - Aperture parameter for the "Sobel" operator.cornerHarris(org.opencv.core.Mat, org.opencv.core.Mat, int, int, double, int),
cornerMinEigenVal(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int),
preCornerDetect(org.opencv.core.Mat, org.opencv.core.Mat, int, int)
public static void cornerEigenValsAndVecs(Mat src,
Mat dst,
int blockSize,
int ksize,
int borderType)
Calculates eigenvalues and eigenvectors of image blocks for corner detection.
For every pixel p, the function cornerEigenValsAndVecs
considers a blockSize x blockSize
neighborhood S(p). It calculates the covariation matrix of
derivatives over the neighborhood as:
M = sum(by: S(p))(dI/dx)^2 sum(by: S(p))(dI/dx dI/dy)^2 sum(by: S(p))(dI/dx dI/dy)^2 sum(by: S(p))(dI/dy)^2
where the derivatives are computed using the "Sobel" operator.
After that, it finds eigenvectors and eigenvalues of M and stores them in the destination image as (lambda_1, lambda_2, x_1, y_1, x_2, y_2) where
The output of the function can be used for robust edge or corner detection.
src - Input single-channel 8-bit or floating-point image.dst - Image to store the results. It has the same size as
src and the type CV_32FC(6).blockSize - Neighborhood size (see details below).ksize - Aperture parameter for the "Sobel" operator.borderType - Pixel extrapolation method. See "borderInterpolate".cornerHarris(org.opencv.core.Mat, org.opencv.core.Mat, int, int, double, int),
cornerMinEigenVal(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int),
preCornerDetect(org.opencv.core.Mat, org.opencv.core.Mat, int, int)
public static void cornerHarris(Mat src,
Mat dst,
int blockSize,
int ksize,
double k)
Harris edge detector.
The function runs the Harris edge detector on the image. Similarly to "cornerMinEigenVal" and "cornerEigenValsAndVecs", for each pixel (x, y) it calculates a 2x2 gradient covariance matrix M^((x,y)) over a blockSize x blockSize neighborhood. Then, it computes the following characteristic:
dst(x,y) = det M^((x,y)) - k * (tr M^((x,y)))^2
Corners in the image can be found as the local maxima of this response map.
src - Input single-channel 8-bit or floating-point image.dst - Image to store the Harris detector responses. It has the type
CV_32FC1 and the same size as src.blockSize - Neighborhood size (see the details on "cornerEigenValsAndVecs").ksize - Aperture parameter for the "Sobel" operator.k - Harris detector free parameter. See the formula below.
public static void cornerHarris(Mat src,
Mat dst,
int blockSize,
int ksize,
double k,
int borderType)
Harris edge detector.
The function runs the Harris edge detector on the image. Similarly to "cornerMinEigenVal" and "cornerEigenValsAndVecs", for each pixel (x, y) it calculates a 2x2 gradient covariance matrix M^((x,y)) over a blockSize x blockSize neighborhood. Then, it computes the following characteristic:
dst(x,y) = det M^((x,y)) - k * (tr M^((x,y)))^2
Corners in the image can be found as the local maxima of this response map.
src - Input single-channel 8-bit or floating-point image.dst - Image to store the Harris detector responses. It has the type
CV_32FC1 and the same size as src.blockSize - Neighborhood size (see the details on "cornerEigenValsAndVecs").ksize - Aperture parameter for the "Sobel" operator.k - Harris detector free parameter. See the formula below.borderType - Pixel extrapolation method. See "borderInterpolate".
public static void cornerMinEigenVal(Mat src,
Mat dst,
int blockSize)
Calculates the minimal eigenvalue of gradient matrices for corner detection.
The function is similar to "cornerEigenValsAndVecs" but it calculates and stores only the minimal eigenvalue of the covariance matrix of derivatives, that is, min(lambda_1, lambda_2) in terms of the formulae in the "cornerEigenValsAndVecs" description.
src - Input single-channel 8-bit or floating-point image.dst - Image to store the minimal eigenvalues. It has the type
CV_32FC1 and the same size as src.blockSize - Neighborhood size (see the details on "cornerEigenValsAndVecs").
public static void cornerMinEigenVal(Mat src,
Mat dst,
int blockSize,
int ksize)
Calculates the minimal eigenvalue of gradient matrices for corner detection.
The function is similar to "cornerEigenValsAndVecs" but it calculates and stores only the minimal eigenvalue of the covariance matrix of derivatives, that is, min(lambda_1, lambda_2) in terms of the formulae in the "cornerEigenValsAndVecs" description.
src - Input single-channel 8-bit or floating-point image.dst - Image to store the minimal eigenvalues. It has the type
CV_32FC1 and the same size as src.blockSize - Neighborhood size (see the details on "cornerEigenValsAndVecs").ksize - Aperture parameter for the "Sobel" operator.
public static void cornerMinEigenVal(Mat src,
Mat dst,
int blockSize,
int ksize,
int borderType)
Calculates the minimal eigenvalue of gradient matrices for corner detection.
The function is similar to "cornerEigenValsAndVecs" but it calculates and stores only the minimal eigenvalue of the covariance matrix of derivatives, that is, min(lambda_1, lambda_2) in terms of the formulae in the "cornerEigenValsAndVecs" description.
src - Input single-channel 8-bit or floating-point image.dst - Image to store the minimal eigenvalues. It has the type
CV_32FC1 and the same size as src.blockSize - Neighborhood size (see the details on "cornerEigenValsAndVecs").ksize - Aperture parameter for the "Sobel" operator.borderType - Pixel extrapolation method. See "borderInterpolate".
public static void cornerSubPix(Mat image,
MatOfPoint2f corners,
Size winSize,
Size zeroZone,
TermCriteria criteria)
Refines the corner locations.
The function iterates to find the sub-pixel accurate location of corners or radial saddle points, as shown on the figure below.
Sub-pixel accurate corner locator is based on the observation that every vector from the center q to a point p located within a neighborhood of q is orthogonal to the image gradient at p subject to image and measurement noise. Consider the expression:
epsilon _i = (DI_(p_i))^T * (q - p_i)
where (DI_(p_i)) is an image gradient at one of the points p_i in a neighborhood of q. The value of q is to be found so that epsilon_i is minimized. A system of equations may be set up with epsilon_i set to zero:
sum _i(DI_(p_i) * (DI_(p_i))^T) - sum _i(DI_(p_i) * (DI_(p_i))^T * p_i)
where the gradients are summed within a neighborhood ("search window") of q. Calling the first gradient term G and the second gradient term b gives:
q = G^(-1) * b
The algorithm sets the center of the neighborhood window at this new center q and then iterates until the center stays within a set threshold.
image - Input image.corners - Initial coordinates of the input corners and refined
coordinates provided for output.winSize - Half of the side length of the search window. For example, if
winSize=Size(5,5), then a 5*2+1 x 5*2+1 = 11 x 11
search window is used.zeroZone - Half of the size of the dead region in the middle of the
search zone over which the summation in the formula below is not done. It is
used sometimes to avoid possible singularities of the autocorrelation matrix.
The value of (-1,-1) indicates that there is no such a size.criteria - Criteria for termination of the iterative process of corner
refinement. That is, the process of corner position refinement stops either
after criteria.maxCount iterations or when the corner position
moves by less than criteria.epsilon on some iteration.
public static void createHanningWindow(Mat dst,
Size winSize,
int type)
This function computes a Hanning window coefficients in two dimensions. See http://en.wikipedia.org/wiki/Hann_function and http://en.wikipedia.org/wiki/Window_function for more information.
An example is shown below:
// C++ code:
// create hanning window of size 100x100 and type CV_32F
Mat hann;
createHanningWindow(hann, Size(100, 100), CV_32F);
dst - Destination array to place Hann coefficients inwinSize - The window size specificationstype - Created array typephaseCorrelate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void cvtColor(Mat src,
Mat dst,
int code)
Converts an image from one color space to another.
The function converts an input image from one color space to another. In case of a transformation to-from RGB color space, the order of the channels should be specified explicitly (RGB or BGR). Note that the default color format in OpenCV is often referred to as RGB but it is actually BGR (the bytes are reversed). So the first byte in a standard (24-bit) color image will be an 8-bit Blue component, the second byte will be Green, and the third byte will be Red. The fourth, fifth, and sixth bytes would then be the second pixel (Blue, then Green, then Red), and so on.
The conventional ranges for R, G, and B channel values are:
CV_8U images
CV_16U images
CV_32F images
In case of linear transformations, the range does not matter.
But in case of a non-linear transformation, an input RGB image should be
normalized to the proper value range to get the correct results, for example,
for RGB-> L*u*v* transformation. For example, if you have a 32-bit
floating-point image directly converted from an 8-bit image without any
scaling, then it will have the 0..255 value range instead of 0..1 assumed by
the function. So, before calling cvtColor, you need first to
scale the image down:
// C++ code:
img *= 1./255;
cvtColor(img, img, CV_BGR2Luv);
If you use cvtColor with 8-bit images, the conversion will have
some information lost. For many applications, this will not be noticeable but
it is recommended to use 32-bit images in applications that need the full
range of colors or that convert an image before an operation and then convert
back.
The function can do the following transformations:
RGB[A] to Gray: Y <- 0.299 * R + 0.587 * G + 0.114 * B
and
Gray to RGB[A]: R <- Y, G <- Y, B <- Y, A <- 0
The conversion from a RGB image to gray is done with:
// C++ code:
cvtColor(src, bwsrc, CV_RGB2GRAY);
More advanced channel reordering can also be done with "mixChannels".
CV_BGR2XYZ, CV_RGB2XYZ, CV_XYZ2BGR, CV_XYZ2RGB):
X Z ltBR gt <- 0.412453 0.357580 0.180423 0.212671 0.715160 0.072169 0.019334 0.119193 0.950227 ltBR gt * R B ltBR gt
R B ltBR gt <- 3.240479 -1.53715 -0.498535 -0.969256 1.875991 0.041556 0.055648 -0.204043 1.057311 ltBR gt * X Z ltBR gt
X, Y and Z cover the whole value range (in case of floating-point images, Z may exceed 1).
CV_BGR2YCrCb,
CV_RGB2YCrCb, CV_YCrCb2BGR, CV_YCrCb2RGB)
Y <- 0.299 * R + 0.587 * G + 0.114 * B
Cr <- (R-Y) * 0.713 + delta
Cb <- (B-Y) * 0.564 + delta
R <- Y + 1.403 * (Cr - delta)
G <- Y - 0.714 * (Cr - delta) - 0.344 * (Cb - delta)
B <- Y + 1.773 * (Cb - delta)
where
delta = <= ft (128 for 8-bit images 32768 for 16-bit images 0.5 for floating-point images right.
Y, Cr, and Cb cover the whole value range.
CV_BGR2HSV, CV_RGB2HSV, CV_HSV2BGR,
CV_HSV2RGB) In case of 8-bit and 16-bit images, R, G, and B are
converted to the floating-point format and scaled to fit the 0 to 1 range.
V <- max(R,G,B)
S <- (V-min(R,G,B))/(V) if V != 0; 0 otherwise
H <- (60(G - B))/((V-min(R,G,B))) if V=R; (120+60(B - R))/((V-min(R,G,B))) if V=G; (240+60(R - G))/((V-min(R,G,B))) if V=B
If H<0 then H <- H+360. On output 0 <= V <= 1, 0 <= S <= 1, 0 <= H <= 360.
The values are then converted to the destination data type:
V <- 255 V, S <- 255 S, H <- H/2(to fit to 0 to 255)
V <- 65535 V, S <- 65535 S, H <- H
CV_BGR2HLS, CV_RGB2HLS, CV_HLS2BGR,
CV_HLS2RGB).
In case of 8-bit and 16-bit images, R, G, and B are converted to the floating-point format and scaled to fit the 0 to 1 range.
V_(max) <- (max)(R,G,B)
V_(min) <- (min)(R,G,B)
L <- (V_(max) + V_(min))/2
S <- fork ((V_(max) - V_(min))/(V_(max) + V_(min)))(if L < 0.5)<BR>((V_(max) - V_(min))/(2 - (V_(max) + V_(min))))(if L >= 0.5)
H <- forkthree ((60(G - B))/(S))(if V_(max)=R)<BR>((120+60(B - R))/(S))(if V_(max)=G)<BR>((240+60(R - G))/(S))(if V_(max)=B)
If H<0 then H <- H+360. On output 0 <= L <= 1, 0 <= S <= 1, 0 <= H <= 360.
The values are then converted to the destination data type:
V <- 255 * V, S <- 255 * S, H <- H/2(to fit to 0 to 255)
V <- 65535 * V, S <- 65535 * S, H <- H
CV_BGR2Lab, CV_RGB2Lab, CV_Lab2BGR,
CV_Lab2RGB).
In case of 8-bit and 16-bit images, R, G, and B are converted to the floating-point format and scaled to fit the 0 to 1 range.
[X Y Z] <- |0.412453 0.357580 0.180423| |0.212671 0.715160 0.072169| |0.019334 0.119193 0.950227|
X <- X/X_n, where X_n = 0.950456
Z <- Z/Z_n, where Z_n = 1.088754
L <- 116*Y^(1/3)-16 for Y>0.008856; 903.3*Y for Y <= 0.008856
a <- 500(f(X)-f(Y)) + delta
b <- 200(f(Y)-f(Z)) + delta
where
f(t)= t^(1/3) for t>0.008856; 7.787 t+16/116 for t <= 0.008856
and
delta = 128 for 8-bit images; 0 for floating-point images
This outputs 0 <= L <= 100, -127 <= a <= 127, -127 <= b <= 127. The values are then converted to the destination data type:
L <- L*255/100, a <- a + 128, b <- b + 128
CV_BGR2Luv, CV_RGB2Luv, CV_Luv2BGR,
CV_Luv2RGB).
In case of 8-bit and 16-bit images, R, G, and B are converted to the floating-point format and scaled to fit 0 to 1 range.
[X Y Z] <- |0.412453 0.357580 0.180423| |0.212671 0.715160 0.072169| |0.019334 0.119193 0.950227|
L <- 116 Y^(1/3) for Y>0.008856; 903.3 Y for Y <= 0.008856
u' <- 4*X/(X + 15*Y + 3 Z)
v' <- 9*Y/(X + 15*Y + 3 Z)
u <- 13*L*(u' - u_n) where u_n=0.19793943
v <- 13*L*(v' - v_n) where v_n=0.46831096
This outputs 0 <= L <= 100, -134 <= u <= 220, -140 <= v <= 122.
The values are then converted to the destination data type:
L <- 255/100 L, u <- 255/354(u + 134), v <- 255/256(v + 140)
The above formulae for converting RGB to/from various color spaces have been taken from multiple sources on the web, primarily from the Charles Poynton site http://www.poynton.com/ColorFAQ.html
CV_BayerBG2BGR, CV_BayerGB2BGR,
CV_BayerRG2BGR, CV_BayerGR2BGR, CV_BayerBG2RGB, CV_BayerGB2RGB,
CV_BayerRG2RGB, CV_BayerGR2RGB). The Bayer pattern is widely used in
CCD and CMOS cameras. It enables you to get color pictures from a single
plane where R,G, and B pixels (sensors of a particular component) are
interleaved as follows: The output RGB components of a pixel are interpolated
from 1, 2, or
// C++ code:
4 neighbors of the pixel having the same color. There are several
modifications of the above pattern that can be achieved by shifting
the pattern one pixel left and/or one pixel up. The two letters
C_1 and
C_2 in the conversion constants CV_Bayer C_1
C_2 2BGR and CV_Bayer C_1 C_2
2RGB indicate the particular pattern
type. These are components from the second row, second and third
columns, respectively. For example, the above pattern has a very
popular "BG" type.
src - input image: 8-bit unsigned, 16-bit unsigned (CV_16UC...),
or single-precision floating-point.dst - output image of the same size and depth as src.code - color space conversion code (see the description below).
public static void cvtColor(Mat src,
Mat dst,
int code,
int dstCn)
Converts an image from one color space to another.
The function converts an input image from one color space to another. In case of a transformation to-from RGB color space, the order of the channels should be specified explicitly (RGB or BGR). Note that the default color format in OpenCV is often referred to as RGB but it is actually BGR (the bytes are reversed). So the first byte in a standard (24-bit) color image will be an 8-bit Blue component, the second byte will be Green, and the third byte will be Red. The fourth, fifth, and sixth bytes would then be the second pixel (Blue, then Green, then Red), and so on.
The conventional ranges for R, G, and B channel values are:
CV_8U images
CV_16U images
CV_32F images
In case of linear transformations, the range does not matter.
But in case of a non-linear transformation, an input RGB image should be
normalized to the proper value range to get the correct results, for example,
for RGB-> L*u*v* transformation. For example, if you have a 32-bit
floating-point image directly converted from an 8-bit image without any
scaling, then it will have the 0..255 value range instead of 0..1 assumed by
the function. So, before calling cvtColor, you need first to
scale the image down:
// C++ code:
img *= 1./255;
cvtColor(img, img, CV_BGR2Luv);
If you use cvtColor with 8-bit images, the conversion will have
some information lost. For many applications, this will not be noticeable but
it is recommended to use 32-bit images in applications that need the full
range of colors or that convert an image before an operation and then convert
back.
The function can do the following transformations:
RGB[A] to Gray: Y <- 0.299 * R + 0.587 * G + 0.114 * B
and
Gray to RGB[A]: R <- Y, G <- Y, B <- Y, A <- 0
The conversion from a RGB image to gray is done with:
// C++ code:
cvtColor(src, bwsrc, CV_RGB2GRAY);
More advanced channel reordering can also be done with "mixChannels".
CV_BGR2XYZ, CV_RGB2XYZ, CV_XYZ2BGR, CV_XYZ2RGB):
X Z ltBR gt <- 0.412453 0.357580 0.180423 0.212671 0.715160 0.072169 0.019334 0.119193 0.950227 ltBR gt * R B ltBR gt
R B ltBR gt <- 3.240479 -1.53715 -0.498535 -0.969256 1.875991 0.041556 0.055648 -0.204043 1.057311 ltBR gt * X Z ltBR gt
X, Y and Z cover the whole value range (in case of floating-point images, Z may exceed 1).
CV_BGR2YCrCb,
CV_RGB2YCrCb, CV_YCrCb2BGR, CV_YCrCb2RGB)
Y <- 0.299 * R + 0.587 * G + 0.114 * B
Cr <- (R-Y) * 0.713 + delta
Cb <- (B-Y) * 0.564 + delta
R <- Y + 1.403 * (Cr - delta)
G <- Y - 0.714 * (Cr - delta) - 0.344 * (Cb - delta)
B <- Y + 1.773 * (Cb - delta)
where
delta = <= ft (128 for 8-bit images 32768 for 16-bit images 0.5 for floating-point images right.
Y, Cr, and Cb cover the whole value range.
CV_BGR2HSV, CV_RGB2HSV, CV_HSV2BGR,
CV_HSV2RGB) In case of 8-bit and 16-bit images, R, G, and B are
converted to the floating-point format and scaled to fit the 0 to 1 range.
V <- max(R,G,B)
S <- (V-min(R,G,B))/(V) if V != 0; 0 otherwise
H <- (60(G - B))/((V-min(R,G,B))) if V=R; (120+60(B - R))/((V-min(R,G,B))) if V=G; (240+60(R - G))/((V-min(R,G,B))) if V=B
If H<0 then H <- H+360. On output 0 <= V <= 1, 0 <= S <= 1, 0 <= H <= 360.
The values are then converted to the destination data type:
V <- 255 V, S <- 255 S, H <- H/2(to fit to 0 to 255)
V <- 65535 V, S <- 65535 S, H <- H
CV_BGR2HLS, CV_RGB2HLS, CV_HLS2BGR,
CV_HLS2RGB).
In case of 8-bit and 16-bit images, R, G, and B are converted to the floating-point format and scaled to fit the 0 to 1 range.
V_(max) <- (max)(R,G,B)
V_(min) <- (min)(R,G,B)
L <- (V_(max) + V_(min))/2
S <- fork ((V_(max) - V_(min))/(V_(max) + V_(min)))(if L < 0.5)<BR>((V_(max) - V_(min))/(2 - (V_(max) + V_(min))))(if L >= 0.5)
H <- forkthree ((60(G - B))/(S))(if V_(max)=R)<BR>((120+60(B - R))/(S))(if V_(max)=G)<BR>((240+60(R - G))/(S))(if V_(max)=B)
If H<0 then H <- H+360. On output 0 <= L <= 1, 0 <= S <= 1, 0 <= H <= 360.
The values are then converted to the destination data type:
V <- 255 * V, S <- 255 * S, H <- H/2(to fit to 0 to 255)
V <- 65535 * V, S <- 65535 * S, H <- H
CV_BGR2Lab, CV_RGB2Lab, CV_Lab2BGR,
CV_Lab2RGB).
In case of 8-bit and 16-bit images, R, G, and B are converted to the floating-point format and scaled to fit the 0 to 1 range.
[X Y Z] <- |0.412453 0.357580 0.180423| |0.212671 0.715160 0.072169| |0.019334 0.119193 0.950227|
X <- X/X_n, where X_n = 0.950456
Z <- Z/Z_n, where Z_n = 1.088754
L <- 116*Y^(1/3)-16 for Y>0.008856; 903.3*Y for Y <= 0.008856
a <- 500(f(X)-f(Y)) + delta
b <- 200(f(Y)-f(Z)) + delta
where
f(t)= t^(1/3) for t>0.008856; 7.787 t+16/116 for t <= 0.008856
and
delta = 128 for 8-bit images; 0 for floating-point images
This outputs 0 <= L <= 100, -127 <= a <= 127, -127 <= b <= 127. The values are then converted to the destination data type:
L <- L*255/100, a <- a + 128, b <- b + 128
CV_BGR2Luv, CV_RGB2Luv, CV_Luv2BGR,
CV_Luv2RGB).
In case of 8-bit and 16-bit images, R, G, and B are converted to the floating-point format and scaled to fit 0 to 1 range.
[X Y Z] <- |0.412453 0.357580 0.180423| |0.212671 0.715160 0.072169| |0.019334 0.119193 0.950227|
L <- 116 Y^(1/3) for Y>0.008856; 903.3 Y for Y <= 0.008856
u' <- 4*X/(X + 15*Y + 3 Z)
v' <- 9*Y/(X + 15*Y + 3 Z)
u <- 13*L*(u' - u_n) where u_n=0.19793943
v <- 13*L*(v' - v_n) where v_n=0.46831096
This outputs 0 <= L <= 100, -134 <= u <= 220, -140 <= v <= 122.
The values are then converted to the destination data type:
L <- 255/100 L, u <- 255/354(u + 134), v <- 255/256(v + 140)
The above formulae for converting RGB to/from various color spaces have been taken from multiple sources on the web, primarily from the Charles Poynton site http://www.poynton.com/ColorFAQ.html
CV_BayerBG2BGR, CV_BayerGB2BGR,
CV_BayerRG2BGR, CV_BayerGR2BGR, CV_BayerBG2RGB, CV_BayerGB2RGB,
CV_BayerRG2RGB, CV_BayerGR2RGB). The Bayer pattern is widely used in
CCD and CMOS cameras. It enables you to get color pictures from a single
plane where R,G, and B pixels (sensors of a particular component) are
interleaved as follows: The output RGB components of a pixel are interpolated
from 1, 2, or
// C++ code:
4 neighbors of the pixel having the same color. There are several
modifications of the above pattern that can be achieved by shifting
the pattern one pixel left and/or one pixel up. The two letters
C_1 and
C_2 in the conversion constants CV_Bayer C_1
C_2 2BGR and CV_Bayer C_1 C_2
2RGB indicate the particular pattern
type. These are components from the second row, second and third
columns, respectively. For example, the above pattern has a very
popular "BG" type.
src - input image: 8-bit unsigned, 16-bit unsigned (CV_16UC...),
or single-precision floating-point.dst - output image of the same size and depth as src.code - color space conversion code (see the description below).dstCn - number of channels in the destination image; if the parameter is
0, the number of the channels is derived automatically from src
and code.
public static void dilate(Mat src,
Mat dst,
Mat kernel)
Dilates an image by using a specific structuring element.
The function dilates the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the maximum is taken:
dst(x,y) = max _((x',y'): element(x',y') != 0) src(x+x',y+y')
The function supports the in-place mode. Dilation can be applied several
(iterations) times. In case of multi-channel images, each
channel is processed independently.
src - input image; the number of channels can be arbitrary, but the
depth should be one of CV_8U, CV_16U,
CV_16S, CV_32F" or CV_64F".dst - output image of the same size and type as src.kernel - a kernelerode(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar),
morphologyEx(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar)
public static void dilate(Mat src,
Mat dst,
Mat kernel,
Point anchor,
int iterations)
Dilates an image by using a specific structuring element.
The function dilates the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the maximum is taken:
dst(x,y) = max _((x',y'): element(x',y') != 0) src(x+x',y+y')
The function supports the in-place mode. Dilation can be applied several
(iterations) times. In case of multi-channel images, each
channel is processed independently.
src - input image; the number of channels can be arbitrary, but the
depth should be one of CV_8U, CV_16U,
CV_16S, CV_32F" or CV_64F".dst - output image of the same size and type as src.kernel - a kernelanchor - position of the anchor within the element; default value
(-1, -1) means that the anchor is at the element center.iterations - number of times dilation is applied.erode(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar),
morphologyEx(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar)
public static void dilate(Mat src,
Mat dst,
Mat kernel,
Point anchor,
int iterations,
int borderType,
Scalar borderValue)
Dilates an image by using a specific structuring element.
The function dilates the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the maximum is taken:
dst(x,y) = max _((x',y'): element(x',y') != 0) src(x+x',y+y')
The function supports the in-place mode. Dilation can be applied several
(iterations) times. In case of multi-channel images, each
channel is processed independently.
src - input image; the number of channels can be arbitrary, but the
depth should be one of CV_8U, CV_16U,
CV_16S, CV_32F" or CV_64F".dst - output image of the same size and type as src.kernel - a kernelanchor - position of the anchor within the element; default value
(-1, -1) means that the anchor is at the element center.iterations - number of times dilation is applied.borderType - pixel extrapolation method (see "borderInterpolate" for
details).borderValue - border value in case of a constant border (see
"createMorphologyFilter" for details).erode(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar),
morphologyEx(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar)
public static void distanceTransform(Mat src,
Mat dst,
int distanceType,
int maskSize)
Calculates the distance to the closest zero pixel for each pixel of the source image.
The functions distanceTransform calculate the approximate or
precise distance from every binary image pixel to the nearest zero pixel.
For zero image pixels, the distance will obviously be zero.
When maskSize == CV_DIST_MASK_PRECISE and distanceType ==
CV_DIST_L2, the function runs the algorithm described in
[Felzenszwalb04]. This algorithm is parallelized with the TBB library.
In other cases, the algorithm [Borgefors86] is used. This means that for a
pixel the function finds the shortest path to the nearest zero pixel
consisting of basic shifts: horizontal, vertical, diagonal, or knight's move
(the latest is available for a 5x 5 mask). The overall distance is
calculated as a sum of these basic distances. Since the distance function
should be symmetric, all of the horizontal and vertical shifts must have the
same cost (denoted as a), all the diagonal shifts must have the
same cost (denoted as b), and all knight's moves must have the
same cost (denoted as c). For the CV_DIST_C and
CV_DIST_L1 types, the distance is calculated precisely, whereas
for CV_DIST_L2 (Euclidean distance) the distance can be
calculated only with a relative error (a 5x 5 mask gives more
accurate results). For a,b, and c,
OpenCV uses the values suggested in the original paper:
============== =================== ======================
CV_DIST_C (3x 3) a = 1, b = 1 \
============== =================== ======================
CV_DIST_L1 (3x 3) a = 1, b = 2 \
CV_DIST_L2 (3x 3) a=0.955, b=1.3693 \
CV_DIST_L2 (5x 5) a=1, b=1.4, c=2.1969 \
============== =================== ======================
Typically, for a fast, coarse distance estimation CV_DIST_L2, a
3x 3 mask is used. For a more accurate distance estimation
CV_DIST_L2, a 5x 5 mask or the precise algorithm is
used.
Note that both the precise and the approximate algorithms are linear on the
number of pixels.
The second variant of the function does not only compute the minimum distance
for each pixel (x, y) but also identifies the nearest connected
component consisting of zero pixels (labelType==DIST_LABEL_CCOMP)
or the nearest zero pixel (labelType==DIST_LABEL_PIXEL). Index
of the component/pixel is stored in labels(x, y).
When labelType==DIST_LABEL_CCOMP, the function automatically
finds connected components of zero pixels in the input image and marks them
with distinct labels. When labelType==DIST_LABEL_CCOMP, the
function scans through the input image and marks all the zero pixels with
distinct labels.
In this mode, the complexity is still linear.
That is, the function provides a very fast way to compute the Voronoi diagram
for a binary image.
Currently, the second variant can use only the approximate distance transform
algorithm, i.e. maskSize=CV_DIST_MASK_PRECISE is not supported
yet.
src - 8-bit, single-channel (binary) source image.dst - Output image with calculated distances. It is a 32-bit
floating-point, single-channel image of the same size as src.distanceType - Type of distance. It can be CV_DIST_L1,
CV_DIST_L2, or CV_DIST_C.maskSize - Size of the distance transform mask. It can be 3, 5, or
CV_DIST_MASK_PRECISE (the latter option is only supported by the
first function). In case of the CV_DIST_L1 or CV_DIST_C
distance type, the parameter is forced to 3 because a 3x 3 mask
gives the same result as 5x 5 or any larger aperture.
public static void distanceTransformWithLabels(Mat src,
Mat dst,
Mat labels,
int distanceType,
int maskSize)
Calculates the distance to the closest zero pixel for each pixel of the source image.
The functions distanceTransform calculate the approximate or
precise distance from every binary image pixel to the nearest zero pixel.
For zero image pixels, the distance will obviously be zero.
When maskSize == CV_DIST_MASK_PRECISE and distanceType ==
CV_DIST_L2, the function runs the algorithm described in
[Felzenszwalb04]. This algorithm is parallelized with the TBB library.
In other cases, the algorithm [Borgefors86] is used. This means that for a
pixel the function finds the shortest path to the nearest zero pixel
consisting of basic shifts: horizontal, vertical, diagonal, or knight's move
(the latest is available for a 5x 5 mask). The overall distance is
calculated as a sum of these basic distances. Since the distance function
should be symmetric, all of the horizontal and vertical shifts must have the
same cost (denoted as a), all the diagonal shifts must have the
same cost (denoted as b), and all knight's moves must have the
same cost (denoted as c). For the CV_DIST_C and
CV_DIST_L1 types, the distance is calculated precisely, whereas
for CV_DIST_L2 (Euclidean distance) the distance can be
calculated only with a relative error (a 5x 5 mask gives more
accurate results). For a,b, and c,
OpenCV uses the values suggested in the original paper:
============== =================== ======================
CV_DIST_C (3x 3) a = 1, b = 1 \
============== =================== ======================
CV_DIST_L1 (3x 3) a = 1, b = 2 \
CV_DIST_L2 (3x 3) a=0.955, b=1.3693 \
CV_DIST_L2 (5x 5) a=1, b=1.4, c=2.1969 \
============== =================== ======================
Typically, for a fast, coarse distance estimation CV_DIST_L2, a
3x 3 mask is used. For a more accurate distance estimation
CV_DIST_L2, a 5x 5 mask or the precise algorithm is
used.
Note that both the precise and the approximate algorithms are linear on the
number of pixels.
The second variant of the function does not only compute the minimum distance
for each pixel (x, y) but also identifies the nearest connected
component consisting of zero pixels (labelType==DIST_LABEL_CCOMP)
or the nearest zero pixel (labelType==DIST_LABEL_PIXEL). Index
of the component/pixel is stored in labels(x, y).
When labelType==DIST_LABEL_CCOMP, the function automatically
finds connected components of zero pixels in the input image and marks them
with distinct labels. When labelType==DIST_LABEL_CCOMP, the
function scans through the input image and marks all the zero pixels with
distinct labels.
In this mode, the complexity is still linear.
That is, the function provides a very fast way to compute the Voronoi diagram
for a binary image.
Currently, the second variant can use only the approximate distance transform
algorithm, i.e. maskSize=CV_DIST_MASK_PRECISE is not supported
yet.
src - 8-bit, single-channel (binary) source image.dst - Output image with calculated distances. It is a 32-bit
floating-point, single-channel image of the same size as src.labels - Optional output 2D array of labels (the discrete Voronoi
diagram). It has the type CV_32SC1 and the same size as
src. See the details below.distanceType - Type of distance. It can be CV_DIST_L1,
CV_DIST_L2, or CV_DIST_C.maskSize - Size of the distance transform mask. It can be 3, 5, or
CV_DIST_MASK_PRECISE (the latter option is only supported by the
first function). In case of the CV_DIST_L1 or CV_DIST_C
distance type, the parameter is forced to 3 because a 3x 3 mask
gives the same result as 5x 5 or any larger aperture.
public static void distanceTransformWithLabels(Mat src,
Mat dst,
Mat labels,
int distanceType,
int maskSize,
int labelType)
Calculates the distance to the closest zero pixel for each pixel of the source image.
The functions distanceTransform calculate the approximate or
precise distance from every binary image pixel to the nearest zero pixel.
For zero image pixels, the distance will obviously be zero.
When maskSize == CV_DIST_MASK_PRECISE and distanceType ==
CV_DIST_L2, the function runs the algorithm described in
[Felzenszwalb04]. This algorithm is parallelized with the TBB library.
In other cases, the algorithm [Borgefors86] is used. This means that for a
pixel the function finds the shortest path to the nearest zero pixel
consisting of basic shifts: horizontal, vertical, diagonal, or knight's move
(the latest is available for a 5x 5 mask). The overall distance is
calculated as a sum of these basic distances. Since the distance function
should be symmetric, all of the horizontal and vertical shifts must have the
same cost (denoted as a), all the diagonal shifts must have the
same cost (denoted as b), and all knight's moves must have the
same cost (denoted as c). For the CV_DIST_C and
CV_DIST_L1 types, the distance is calculated precisely, whereas
for CV_DIST_L2 (Euclidean distance) the distance can be
calculated only with a relative error (a 5x 5 mask gives more
accurate results). For a,b, and c,
OpenCV uses the values suggested in the original paper:
============== =================== ======================
CV_DIST_C (3x 3) a = 1, b = 1 \
============== =================== ======================
CV_DIST_L1 (3x 3) a = 1, b = 2 \
CV_DIST_L2 (3x 3) a=0.955, b=1.3693 \
CV_DIST_L2 (5x 5) a=1, b=1.4, c=2.1969 \
============== =================== ======================
Typically, for a fast, coarse distance estimation CV_DIST_L2, a
3x 3 mask is used. For a more accurate distance estimation
CV_DIST_L2, a 5x 5 mask or the precise algorithm is
used.
Note that both the precise and the approximate algorithms are linear on the
number of pixels.
The second variant of the function does not only compute the minimum distance
for each pixel (x, y) but also identifies the nearest connected
component consisting of zero pixels (labelType==DIST_LABEL_CCOMP)
or the nearest zero pixel (labelType==DIST_LABEL_PIXEL). Index
of the component/pixel is stored in labels(x, y).
When labelType==DIST_LABEL_CCOMP, the function automatically
finds connected components of zero pixels in the input image and marks them
with distinct labels. When labelType==DIST_LABEL_CCOMP, the
function scans through the input image and marks all the zero pixels with
distinct labels.
In this mode, the complexity is still linear.
That is, the function provides a very fast way to compute the Voronoi diagram
for a binary image.
Currently, the second variant can use only the approximate distance transform
algorithm, i.e. maskSize=CV_DIST_MASK_PRECISE is not supported
yet.
src - 8-bit, single-channel (binary) source image.dst - Output image with calculated distances. It is a 32-bit
floating-point, single-channel image of the same size as src.labels - Optional output 2D array of labels (the discrete Voronoi
diagram). It has the type CV_32SC1 and the same size as
src. See the details below.distanceType - Type of distance. It can be CV_DIST_L1,
CV_DIST_L2, or CV_DIST_C.maskSize - Size of the distance transform mask. It can be 3, 5, or
CV_DIST_MASK_PRECISE (the latter option is only supported by the
first function). In case of the CV_DIST_L1 or CV_DIST_C
distance type, the parameter is forced to 3 because a 3x 3 mask
gives the same result as 5x 5 or any larger aperture.labelType - Type of the label array to build. If labelType==DIST_LABEL_CCOMP
then each connected component of zeros in src (as well as all
the non-zero pixels closest to the connected component) will be assigned the
same label. If labelType==DIST_LABEL_PIXEL then each zero pixel
(and all the non-zero pixels closest to it) gets its own label.
public static void drawContours(Mat image,
java.util.List<MatOfPoint> contours,
int contourIdx,
Scalar color)
Draws contours outlines or filled contours.
The function draws contour outlines in the image if thickness >= 0
or fills the area bounded by the contours ifthickness<0. The
example below shows how to retrieve connected components from the binary
image and label them:
// C++ code:
#include "cv.h"
#include "highgui.h"
using namespace cv;
int main(int argc, char argv)
Mat src;
// the first command-line parameter must be a filename of the binary
// (black-n-white) image
if(argc != 2 || !(src=imread(argv[1], 0)).data)
return -1;
Mat dst = Mat.zeros(src.rows, src.cols, CV_8UC3);
src = src > 1;
namedWindow("Source", 1);
imshow("Source", src);
vector
vector
findContours(src, contours, hierarchy,
CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE);
// iterate through all the top-level contours,
// draw each connected component with its own random color
int idx = 0;
for(; idx >= 0; idx = hierarchy[idx][0])
Scalar color(rand()&255, rand()&255, rand()&255);
drawContours(dst, contours, idx, color, CV_FILLED, 8, hierarchy);
namedWindow("Components", 1);
imshow("Components", dst);
waitKey(0);
image - Destination image.contours - All the input contours. Each contour is stored as a point
vector.contourIdx - Parameter indicating a contour to draw. If it is negative,
all the contours are drawn.color - Color of the contours.
public static void drawContours(Mat image,
java.util.List<MatOfPoint> contours,
int contourIdx,
Scalar color,
int thickness)
Draws contours outlines or filled contours.
The function draws contour outlines in the image if thickness >= 0
or fills the area bounded by the contours ifthickness<0. The
example below shows how to retrieve connected components from the binary
image and label them:
// C++ code:
#include "cv.h"
#include "highgui.h"
using namespace cv;
int main(int argc, char argv)
Mat src;
// the first command-line parameter must be a filename of the binary
// (black-n-white) image
if(argc != 2 || !(src=imread(argv[1], 0)).data)
return -1;
Mat dst = Mat.zeros(src.rows, src.cols, CV_8UC3);
src = src > 1;
namedWindow("Source", 1);
imshow("Source", src);
vector
vector
findContours(src, contours, hierarchy,
CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE);
// iterate through all the top-level contours,
// draw each connected component with its own random color
int idx = 0;
for(; idx >= 0; idx = hierarchy[idx][0])
Scalar color(rand()&255, rand()&255, rand()&255);
drawContours(dst, contours, idx, color, CV_FILLED, 8, hierarchy);
namedWindow("Components", 1);
imshow("Components", dst);
waitKey(0);
image - Destination image.contours - All the input contours. Each contour is stored as a point
vector.contourIdx - Parameter indicating a contour to draw. If it is negative,
all the contours are drawn.color - Color of the contours.thickness - Thickness of lines the contours are drawn with. If it is
negative (for example, thickness=CV_FILLED), the contour
interiors are drawn.
public static void drawContours(Mat image,
java.util.List<MatOfPoint> contours,
int contourIdx,
Scalar color,
int thickness,
int lineType,
Mat hierarchy,
int maxLevel,
Point offset)
Draws contours outlines or filled contours.
The function draws contour outlines in the image if thickness >= 0
or fills the area bounded by the contours ifthickness<0. The
example below shows how to retrieve connected components from the binary
image and label them:
// C++ code:
#include "cv.h"
#include "highgui.h"
using namespace cv;
int main(int argc, char argv)
Mat src;
// the first command-line parameter must be a filename of the binary
// (black-n-white) image
if(argc != 2 || !(src=imread(argv[1], 0)).data)
return -1;
Mat dst = Mat.zeros(src.rows, src.cols, CV_8UC3);
src = src > 1;
namedWindow("Source", 1);
imshow("Source", src);
vector
vector
findContours(src, contours, hierarchy,
CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE);
// iterate through all the top-level contours,
// draw each connected component with its own random color
int idx = 0;
for(; idx >= 0; idx = hierarchy[idx][0])
Scalar color(rand()&255, rand()&255, rand()&255);
drawContours(dst, contours, idx, color, CV_FILLED, 8, hierarchy);
namedWindow("Components", 1);
imshow("Components", dst);
waitKey(0);
image - Destination image.contours - All the input contours. Each contour is stored as a point
vector.contourIdx - Parameter indicating a contour to draw. If it is negative,
all the contours are drawn.color - Color of the contours.thickness - Thickness of lines the contours are drawn with. If it is
negative (for example, thickness=CV_FILLED), the contour
interiors are drawn.lineType - Line connectivity. See "line" for details.hierarchy - Optional information about hierarchy. It is only needed if
you want to draw only some of the contours (see maxLevel).maxLevel - Maximal level for drawn contours. If it is 0, only the
specified contour is drawn. If it is 1, the function draws the contour(s) and
all the nested contours. If it is 2, the function draws the contours, all the
nested contours, all the nested-to-nested contours, and so on. This parameter
is only taken into account when there is hierarchy available.offset - Optional contour shift parameter. Shift all the drawn contours
by the specified offset=(dx,dy).
public static void equalizeHist(Mat src,
Mat dst)
Equalizes the histogram of a grayscale image.
The function equalizes the histogram of the input image using the following algorithm:
src.
H'_i = sum(by: 0 <= j < i) H(j)
Transform the image using H' as a look-up table: dst(x,y) = H'(src(x,y))
The algorithm normalizes the brightness and increases the contrast of the image.
src - Source 8-bit single channel image.dst - Destination image of the same size and type as src.
public static void erode(Mat src,
Mat dst,
Mat kernel)
Erodes an image by using a specific structuring element.
The function erodes the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the minimum is taken:
dst(x,y) = min _((x',y'): element(x',y') != 0) src(x+x',y+y')
The function supports the in-place mode. Erosion can be applied several
(iterations) times. In case of multi-channel images, each
channel is processed independently.
src - input image; the number of channels can be arbitrary, but the
depth should be one of CV_8U, CV_16U,
CV_16S, CV_32F" or CV_64F".dst - output image of the same size and type as src.kernel - a kernelmorphologyEx(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar),
dilate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar)
public static void erode(Mat src,
Mat dst,
Mat kernel,
Point anchor,
int iterations)
Erodes an image by using a specific structuring element.
The function erodes the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the minimum is taken:
dst(x,y) = min _((x',y'): element(x',y') != 0) src(x+x',y+y')
The function supports the in-place mode. Erosion can be applied several
(iterations) times. In case of multi-channel images, each
channel is processed independently.
src - input image; the number of channels can be arbitrary, but the
depth should be one of CV_8U, CV_16U,
CV_16S, CV_32F" or CV_64F".dst - output image of the same size and type as src.kernel - a kernelanchor - position of the anchor within the element; default value
(-1, -1) means that the anchor is at the element center.iterations - number of times erosion is applied.morphologyEx(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar),
dilate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar)
public static void erode(Mat src,
Mat dst,
Mat kernel,
Point anchor,
int iterations,
int borderType,
Scalar borderValue)
Erodes an image by using a specific structuring element.
The function erodes the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the minimum is taken:
dst(x,y) = min _((x',y'): element(x',y') != 0) src(x+x',y+y')
The function supports the in-place mode. Erosion can be applied several
(iterations) times. In case of multi-channel images, each
channel is processed independently.
src - input image; the number of channels can be arbitrary, but the
depth should be one of CV_8U, CV_16U,
CV_16S, CV_32F" or CV_64F".dst - output image of the same size and type as src.kernel - a kernelanchor - position of the anchor within the element; default value
(-1, -1) means that the anchor is at the element center.iterations - number of times erosion is applied.borderType - pixel extrapolation method (see "borderInterpolate" for
details).borderValue - border value in case of a constant border (see
"createMorphologyFilter" for details).morphologyEx(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar),
dilate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar)
public static void filter2D(Mat src,
Mat dst,
int ddepth,
Mat kernel)
Convolves an image with the kernel.
The function applies an arbitrary linear filter to an image. In-place operation is supported. When the aperture is partially outside the image, the function interpolates outlier pixel values according to the specified border mode.
The function does actually compute correlation, not the convolution:
dst(x,y) = sum(by: 0 <= x' < kernel.cols, 0 <= y' < kernel.rows) kernel(x',y')* src(x+x'- anchor.x,y+y'- anchor.y)
That is, the kernel is not mirrored around the anchor point. If you need a
real convolution, flip the kernel using "flip" and set the new anchor to
(kernel.cols - anchor.x - 1, kernel.rows - anchor.y - 1).
The function uses the DFT-based algorithm in case of sufficiently large
kernels (~11 x 11 or larger) and the direct algorithm (that uses
the engine retrieved by "createLinearFilter") for small kernels.
src - input image.dst - output image of the same size and the same number of channels as
src.ddepth - desired depth of the destination image; if it is negative, it
will be the same as src.depth(); the following combinations of
src.depth() and ddepth are supported:
src.depth() = CV_8U, ddepth =
-1/CV_16S/CV_32F/CV_64F
src.depth() = CV_16U/CV_16S,
ddepth = -1/CV_32F/CV_64F
src.depth() = CV_32F, ddepth =
-1/CV_32F/CV_64F
src.depth() = CV_64F, ddepth =
-1/CV_64F
when ddepth=-1, the output image will have the same depth as the
source.
kernel - convolution kernel (or rather a correlation kernel), a
single-channel floating point matrix; if you want to apply different kernels
to different channels, split the image into separate color planes using
"split" and process them individually.matchTemplate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int),
Core.dft(org.opencv.core.Mat, org.opencv.core.Mat, int, int),
sepFilter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, double, int)
public static void filter2D(Mat src,
Mat dst,
int ddepth,
Mat kernel,
Point anchor,
double delta)
Convolves an image with the kernel.
The function applies an arbitrary linear filter to an image. In-place operation is supported. When the aperture is partially outside the image, the function interpolates outlier pixel values according to the specified border mode.
The function does actually compute correlation, not the convolution:
dst(x,y) = sum(by: 0 <= x' < kernel.cols, 0 <= y' < kernel.rows) kernel(x',y')* src(x+x'- anchor.x,y+y'- anchor.y)
That is, the kernel is not mirrored around the anchor point. If you need a
real convolution, flip the kernel using "flip" and set the new anchor to
(kernel.cols - anchor.x - 1, kernel.rows - anchor.y - 1).
The function uses the DFT-based algorithm in case of sufficiently large
kernels (~11 x 11 or larger) and the direct algorithm (that uses
the engine retrieved by "createLinearFilter") for small kernels.
src - input image.dst - output image of the same size and the same number of channels as
src.ddepth - desired depth of the destination image; if it is negative, it
will be the same as src.depth(); the following combinations of
src.depth() and ddepth are supported:
src.depth() = CV_8U, ddepth =
-1/CV_16S/CV_32F/CV_64F
src.depth() = CV_16U/CV_16S,
ddepth = -1/CV_32F/CV_64F
src.depth() = CV_32F, ddepth =
-1/CV_32F/CV_64F
src.depth() = CV_64F, ddepth =
-1/CV_64F
when ddepth=-1, the output image will have the same depth as the
source.
kernel - convolution kernel (or rather a correlation kernel), a
single-channel floating point matrix; if you want to apply different kernels
to different channels, split the image into separate color planes using
"split" and process them individually.anchor - anchor of the kernel that indicates the relative position of a
filtered point within the kernel; the anchor should lie within the kernel;
default value (-1,-1) means that the anchor is at the kernel center.delta - optional value added to the filtered pixels before storing them
in dst.matchTemplate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int),
Core.dft(org.opencv.core.Mat, org.opencv.core.Mat, int, int),
sepFilter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, double, int)
public static void filter2D(Mat src,
Mat dst,
int ddepth,
Mat kernel,
Point anchor,
double delta,
int borderType)
Convolves an image with the kernel.
The function applies an arbitrary linear filter to an image. In-place operation is supported. When the aperture is partially outside the image, the function interpolates outlier pixel values according to the specified border mode.
The function does actually compute correlation, not the convolution:
dst(x,y) = sum(by: 0 <= x' < kernel.cols, 0 <= y' < kernel.rows) kernel(x',y')* src(x+x'- anchor.x,y+y'- anchor.y)
That is, the kernel is not mirrored around the anchor point. If you need a
real convolution, flip the kernel using "flip" and set the new anchor to
(kernel.cols - anchor.x - 1, kernel.rows - anchor.y - 1).
The function uses the DFT-based algorithm in case of sufficiently large
kernels (~11 x 11 or larger) and the direct algorithm (that uses
the engine retrieved by "createLinearFilter") for small kernels.
src - input image.dst - output image of the same size and the same number of channels as
src.ddepth - desired depth of the destination image; if it is negative, it
will be the same as src.depth(); the following combinations of
src.depth() and ddepth are supported:
src.depth() = CV_8U, ddepth =
-1/CV_16S/CV_32F/CV_64F
src.depth() = CV_16U/CV_16S,
ddepth = -1/CV_32F/CV_64F
src.depth() = CV_32F, ddepth =
-1/CV_32F/CV_64F
src.depth() = CV_64F, ddepth =
-1/CV_64F
when ddepth=-1, the output image will have the same depth as the
source.
kernel - convolution kernel (or rather a correlation kernel), a
single-channel floating point matrix; if you want to apply different kernels
to different channels, split the image into separate color planes using
"split" and process them individually.anchor - anchor of the kernel that indicates the relative position of a
filtered point within the kernel; the anchor should lie within the kernel;
default value (-1,-1) means that the anchor is at the kernel center.delta - optional value added to the filtered pixels before storing them
in dst.borderType - pixel extrapolation method (see "borderInterpolate" for
details).matchTemplate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int),
Core.dft(org.opencv.core.Mat, org.opencv.core.Mat, int, int),
sepFilter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, double, int)
public static void findContours(Mat image,
java.util.List<MatOfPoint> contours,
Mat hierarchy,
int mode,
int method)
Finds contours in a binary image.
The function retrieves contours from the binary image using the algorithm
[Suzuki85]. The contours are a useful tool for shape analysis and object
detection and recognition. See squares.c in the OpenCV sample
directory.
Note: Source image is modified by this function. Also, the
function does not take into account 1-pixel border of the image (it's filled
with 0's and used for neighbor analysis in the algorithm), therefore the
contours touching the image border will be clipped.
Note: If you use the new Python interface then the CV_ prefix
has to be omitted in contour retrieval mode and contour approximation method
parameters (for example, use cv2.RETR_LIST and cv2.CHAIN_APPROX_NONE
parameters). If you use the old Python interface then these parameters have
the CV_ prefix (for example, use cv.CV_RETR_LIST
and cv.CV_CHAIN_APPROX_NONE).
image - Source, an 8-bit single-channel image. Non-zero pixels are
treated as 1's. Zero pixels remain 0's, so the image is treated as
binary. You can use "compare", "inRange", "threshold",
"adaptiveThreshold", "Canny", and others to create a binary image out of a
grayscale or color one. The function modifies the image while
extracting the contours.contours - Detected contours. Each contour is stored as a vector of
points.hierarchy - Optional output vector, containing information about the
image topology. It has as many elements as the number of contours. For each
i-th contour contours[i], the elements hierarchy[i][0],
hiearchy[i][1], hiearchy[i][2], and
hiearchy[i][3] are set to 0-based indices in contours
of the next and previous contours at the same hierarchical level, the first
child contour and the parent contour, respectively. If for the contour
i there are no next, previous, parent, or nested contours, the
corresponding elements of hierarchy[i] will be negative.mode - Contour retrieval mode (if you use Python see also a note below).
hierarchy[i][2]=hierarchy[i][3]=-1 for all the contours.
contours.c demo.
method - Contour approximation method (if you use Python see also a note
below).
(x1,y1) and (x2,y2) of
the contour will be either horizontal, vertical or diagonal neighbors, that
is, max(abs(x1-x2),abs(y2-y1))==1.
public static void findContours(Mat image,
java.util.List<MatOfPoint> contours,
Mat hierarchy,
int mode,
int method,
Point offset)
Finds contours in a binary image.
The function retrieves contours from the binary image using the algorithm
[Suzuki85]. The contours are a useful tool for shape analysis and object
detection and recognition. See squares.c in the OpenCV sample
directory.
Note: Source image is modified by this function. Also, the
function does not take into account 1-pixel border of the image (it's filled
with 0's and used for neighbor analysis in the algorithm), therefore the
contours touching the image border will be clipped.
Note: If you use the new Python interface then the CV_ prefix
has to be omitted in contour retrieval mode and contour approximation method
parameters (for example, use cv2.RETR_LIST and cv2.CHAIN_APPROX_NONE
parameters). If you use the old Python interface then these parameters have
the CV_ prefix (for example, use cv.CV_RETR_LIST
and cv.CV_CHAIN_APPROX_NONE).
image - Source, an 8-bit single-channel image. Non-zero pixels are
treated as 1's. Zero pixels remain 0's, so the image is treated as
binary. You can use "compare", "inRange", "threshold",
"adaptiveThreshold", "Canny", and others to create a binary image out of a
grayscale or color one. The function modifies the image while
extracting the contours.contours - Detected contours. Each contour is stored as a vector of
points.hierarchy - Optional output vector, containing information about the
image topology. It has as many elements as the number of contours. For each
i-th contour contours[i], the elements hierarchy[i][0],
hiearchy[i][1], hiearchy[i][2], and
hiearchy[i][3] are set to 0-based indices in contours
of the next and previous contours at the same hierarchical level, the first
child contour and the parent contour, respectively. If for the contour
i there are no next, previous, parent, or nested contours, the
corresponding elements of hierarchy[i] will be negative.mode - Contour retrieval mode (if you use Python see also a note below).
hierarchy[i][2]=hierarchy[i][3]=-1 for all the contours.
contours.c demo.
method - Contour approximation method (if you use Python see also a note
below).
(x1,y1) and (x2,y2) of
the contour will be either horizontal, vertical or diagonal neighbors, that
is, max(abs(x1-x2),abs(y2-y1))==1.
offset - Optional offset by which every contour point is shifted. This
is useful if the contours are extracted from the image ROI and then they
should be analyzed in the whole image context.public static RotatedRect fitEllipse(MatOfPoint2f points)
Fits an ellipse around a set of 2D points.
The function calculates the ellipse that fits (in a least-squares sense) a set of 2D points best of all. It returns the rotated rectangle in which the ellipse is inscribed. The algorithm [Fitzgibbon95] is used.
points - Input 2D point set, stored in:
std.vector<> or Mat (C++ interface)
CvSeq* or CvMat* (C interface)
public static void fitLine(Mat points,
Mat line,
int distType,
double param,
double reps,
double aeps)
Fits a line to a 2D or 3D point set.
The function fitLine fits a line to a 2D or 3D point set by
minimizing sum_i rho(r_i) where r_i is a distance between
the i^(th) point, the line and rho(r) is a distance
function, one of the following:
rho(r) = r^2/2(the simplest and the fastest least-squares method)
rho(r) = r
rho(r) = 2 * (sqrt(1 + frac(r^2)2) - 1)
rho(r) = C^2 * ((r)/(C) - log((1 + (r)/(C)))) where C=1.3998
rho(r) = (C^2)/2 * (1 - exp((-((r)/(C))^2))) where C=2.9846
rho(r) = r^2/2 if r < C; C * (r-C/2) otherwise where C=1.345
The algorithm is based on the M-estimator (http://en.wikipedia.org/wiki/M-estimator) technique that iteratively fits the line using the weighted least-squares algorithm. After each iteration the weights w_i are adjusted to be inversely proportional to rho(r_i).
points - Input vector of 2D or 3D points, stored in std.vector<>
or Mat.line - Output line parameters. In case of 2D fitting, it should be a
vector of 4 elements (like Vec4f) - (vx, vy, x0,
y0), where (vx, vy) is a normalized vector collinear to
the line and (x0, y0) is a point on the line. In case of 3D
fitting, it should be a vector of 6 elements (like Vec6f) -
(vx, vy, vz, x0, y0, z0), where (vx, vy, vz) is a
normalized vector collinear to the line and (x0, y0, z0) is a
point on the line.distType - Distance used by the M-estimator (see the discussion below).param - Numerical parameter (C) for some types of
distances. If it is 0, an optimal value is chosen.reps - Sufficient accuracy for the radius (distance between the
coordinate origin and the line).aeps - Sufficient accuracy for the angle. 0.01 would be a good default
value for reps and aeps.
public static int floodFill(Mat image,
Mat mask,
Point seedPoint,
Scalar newVal)
Fills a connected component with the given color.
The functions floodFill fill a connected component starting from
the seed point with the specified color. The connectivity is determined by
the color/brightness closeness of the neighbor pixels. The pixel at
(x,y) is considered to belong to the repainted domain if:
in case of a grayscale image and floating range
in case of a grayscale image and fixed range
src(x',y')_g- loDiff _g <= src(x,y)_g <= src(x',y')_g+ upDiff _g
and
src(x',y')_b- loDiff _b <= src(x,y)_b <= src(x',y')_b+ upDiff _b
in case of a color image and floating range
src(seedPoint.x, seedPoint.y)_g- loDiff _g <= src(x,y)_g <= src(seedPoint.x, seedPoint.y)_g+ upDiff _g
and
src(seedPoint.x, seedPoint.y)_b- loDiff _b <= src(x,y)_b <= src(seedPoint.x, seedPoint.y)_b+ upDiff _b
in case of a color image and fixed range
where src(x',y') is the value of one of pixel neighbors that is already known to belong to the component. That is, to be added to the connected component, a color/brightness of the pixel should be close enough to:
Use these functions to either mark a connected component with the specified
color in-place, or build a mask and then extract the contour, or copy the
region to another image, and so on. Various modes of the function are
demonstrated in the floodfill.cpp sample.
image - Input/output 1- or 3-channel, 8-bit, or floating-point image. It
is modified by the function unless the FLOODFILL_MASK_ONLY flag
is set in the second variant of the function. See the details below.mask - (For the second function only) Operation mask that should be a
single-channel 8-bit image, 2 pixels wider and 2 pixels taller. The function
uses and updates the mask, so you take responsibility of initializing the
mask content. Flood-filling cannot go across non-zero pixels in
the mask. For example, an edge detector output can be used as a mask to stop
filling at edges. It is possible to use the same mask in multiple calls to
the function to make sure the filled area does not overlap.
Note: Since the mask is larger than the filled image, a pixel (x, y)
in image corresponds to the pixel (x+1, y+1) in the
mask.
seedPoint - Starting point.newVal - New value of the repainted domain pixels.findContours(org.opencv.core.Mat, java.util.List, org.opencv.core.Mat, int, int, org.opencv.core.Point)
public static int floodFill(Mat image,
Mat mask,
Point seedPoint,
Scalar newVal,
Rect rect,
Scalar loDiff,
Scalar upDiff,
int flags)
Fills a connected component with the given color.
The functions floodFill fill a connected component starting from
the seed point with the specified color. The connectivity is determined by
the color/brightness closeness of the neighbor pixels. The pixel at
(x,y) is considered to belong to the repainted domain if:
in case of a grayscale image and floating range
in case of a grayscale image and fixed range
src(x',y')_g- loDiff _g <= src(x,y)_g <= src(x',y')_g+ upDiff _g
and
src(x',y')_b- loDiff _b <= src(x,y)_b <= src(x',y')_b+ upDiff _b
in case of a color image and floating range
src(seedPoint.x, seedPoint.y)_g- loDiff _g <= src(x,y)_g <= src(seedPoint.x, seedPoint.y)_g+ upDiff _g
and
src(seedPoint.x, seedPoint.y)_b- loDiff _b <= src(x,y)_b <= src(seedPoint.x, seedPoint.y)_b+ upDiff _b
in case of a color image and fixed range
where src(x',y') is the value of one of pixel neighbors that is already known to belong to the component. That is, to be added to the connected component, a color/brightness of the pixel should be close enough to:
Use these functions to either mark a connected component with the specified
color in-place, or build a mask and then extract the contour, or copy the
region to another image, and so on. Various modes of the function are
demonstrated in the floodfill.cpp sample.
image - Input/output 1- or 3-channel, 8-bit, or floating-point image. It
is modified by the function unless the FLOODFILL_MASK_ONLY flag
is set in the second variant of the function. See the details below.mask - (For the second function only) Operation mask that should be a
single-channel 8-bit image, 2 pixels wider and 2 pixels taller. The function
uses and updates the mask, so you take responsibility of initializing the
mask content. Flood-filling cannot go across non-zero pixels in
the mask. For example, an edge detector output can be used as a mask to stop
filling at edges. It is possible to use the same mask in multiple calls to
the function to make sure the filled area does not overlap.
Note: Since the mask is larger than the filled image, a pixel (x, y)
in image corresponds to the pixel (x+1, y+1) in the
mask.
seedPoint - Starting point.newVal - New value of the repainted domain pixels.rect - Optional output parameter set by the function to the minimum
bounding rectangle of the repainted domain.loDiff - Maximal lower brightness/color difference between the currently
observed pixel and one of its neighbors belonging to the component, or a seed
pixel being added to the component.upDiff - Maximal upper brightness/color difference between the currently
observed pixel and one of its neighbors belonging to the component, or a seed
pixel being added to the component.flags - Operation flags. Lower bits contain a connectivity value, 4
(default) or 8, used within the function. Connectivity determines which
neighbors of a pixel are considered. Upper bits can be 0 or a combination of
the following flags:
newVal is ignored), but fills the mask. The flag can be used
for the second variant only.
findContours(org.opencv.core.Mat, java.util.List, org.opencv.core.Mat, int, int, org.opencv.core.Point)
public static void GaussianBlur(Mat src,
Mat dst,
Size ksize,
double sigmaX)
Blurs an image using a Gaussian filter.
The function convolves the source image with the specified Gaussian kernel. In-place filtering is supported.
src - input image; the image can have any number of channels, which are
processed independently, but the depth should be CV_8U,
CV_16U, CV_16S, CV_32F or
CV_64F.dst - output image of the same size and type as src.ksize - Gaussian kernel size. ksize.width and
ksize.height can differ but they both must be positive and odd.
Or, they can be zero's and then they are computed from sigma*.sigmaX - Gaussian kernel standard deviation in X direction.sepFilter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, double, int),
medianBlur(org.opencv.core.Mat, org.opencv.core.Mat, int),
boxFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Size, org.opencv.core.Point, boolean, int),
blur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, int),
filter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, double, int),
bilateralFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, double, double, int)
public static void GaussianBlur(Mat src,
Mat dst,
Size ksize,
double sigmaX,
double sigmaY)
Blurs an image using a Gaussian filter.
The function convolves the source image with the specified Gaussian kernel. In-place filtering is supported.
src - input image; the image can have any number of channels, which are
processed independently, but the depth should be CV_8U,
CV_16U, CV_16S, CV_32F or
CV_64F.dst - output image of the same size and type as src.ksize - Gaussian kernel size. ksize.width and
ksize.height can differ but they both must be positive and odd.
Or, they can be zero's and then they are computed from sigma*.sigmaX - Gaussian kernel standard deviation in X direction.sigmaY - Gaussian kernel standard deviation in Y direction; if
sigmaY is zero, it is set to be equal to sigmaX, if
both sigmas are zeros, they are computed from ksize.width and
ksize.height, respectively (see "getGaussianKernel" for
details); to fully control the result regardless of possible future
modifications of all this semantics, it is recommended to specify all of
ksize, sigmaX, and sigmaY.sepFilter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, double, int),
medianBlur(org.opencv.core.Mat, org.opencv.core.Mat, int),
boxFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Size, org.opencv.core.Point, boolean, int),
blur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, int),
filter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, double, int),
bilateralFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, double, double, int)
public static void GaussianBlur(Mat src,
Mat dst,
Size ksize,
double sigmaX,
double sigmaY,
int borderType)
Blurs an image using a Gaussian filter.
The function convolves the source image with the specified Gaussian kernel. In-place filtering is supported.
src - input image; the image can have any number of channels, which are
processed independently, but the depth should be CV_8U,
CV_16U, CV_16S, CV_32F or
CV_64F.dst - output image of the same size and type as src.ksize - Gaussian kernel size. ksize.width and
ksize.height can differ but they both must be positive and odd.
Or, they can be zero's and then they are computed from sigma*.sigmaX - Gaussian kernel standard deviation in X direction.sigmaY - Gaussian kernel standard deviation in Y direction; if
sigmaY is zero, it is set to be equal to sigmaX, if
both sigmas are zeros, they are computed from ksize.width and
ksize.height, respectively (see "getGaussianKernel" for
details); to fully control the result regardless of possible future
modifications of all this semantics, it is recommended to specify all of
ksize, sigmaX, and sigmaY.borderType - pixel extrapolation method (see "borderInterpolate" for
details).sepFilter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, double, int),
medianBlur(org.opencv.core.Mat, org.opencv.core.Mat, int),
boxFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Size, org.opencv.core.Point, boolean, int),
blur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, int),
filter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, double, int),
bilateralFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, double, double, int)
public static Mat getAffineTransform(MatOfPoint2f src,
MatOfPoint2f dst)
Calculates an affine transform from three pairs of the corresponding points.
The function calculates the 2 x 3 matrix of an affine transform so that:
x'_i y'_i = map_matrix * x_i y_i 1
where
dst(i)=(x'_i,y'_i),<BR>src(i)=(x_i, y_i),<BR>i=0,1,2
src - Coordinates of triangle vertices in the source image.dst - Coordinates of the corresponding triangle vertices in the
destination image.warpAffine(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
Core.transform(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)public static Mat getDefaultNewCameraMatrix(Mat cameraMatrix)
Returns the default new camera matrix.
The function returns the camera matrix that is either an exact copy of the
input cameraMatrix (when centerPrinicipalPoint=false),
or the modified one (when centerPrincipalPoint=true).
In the latter case, the new camera matrix will be:
f_x 0(imgSize.width -1)*0.5 0 f_y(imgSize.height -1)*0.5 0 0 1,
where f_x and f_y are (0,0) and (1,1)
elements of cameraMatrix, respectively.
By default, the undistortion functions in OpenCV (see "initUndistortRectifyMap", "undistort") do not move the principal point. However, when you work with stereo, it is important to move the principal points in both views to the same y-coordinate (which is required by most of stereo correspondence algorithms), and may be to the same x-coordinate too. So, you can form the new camera matrix for each view where the principal points are located at the center.
cameraMatrix - Input camera matrix.
public static Mat getDefaultNewCameraMatrix(Mat cameraMatrix,
Size imgsize,
boolean centerPrincipalPoint)
Returns the default new camera matrix.
The function returns the camera matrix that is either an exact copy of the
input cameraMatrix (when centerPrinicipalPoint=false),
or the modified one (when centerPrincipalPoint=true).
In the latter case, the new camera matrix will be:
f_x 0(imgSize.width -1)*0.5 0 f_y(imgSize.height -1)*0.5 0 0 1,
where f_x and f_y are (0,0) and (1,1)
elements of cameraMatrix, respectively.
By default, the undistortion functions in OpenCV (see "initUndistortRectifyMap", "undistort") do not move the principal point. However, when you work with stereo, it is important to move the principal points in both views to the same y-coordinate (which is required by most of stereo correspondence algorithms), and may be to the same x-coordinate too. So, you can form the new camera matrix for each view where the principal points are located at the center.
cameraMatrix - Input camera matrix.imgsize - Camera view image size in pixels.centerPrincipalPoint - Location of the principal point in the new camera
matrix. The parameter indicates whether this location should be at the image
center or not.
public static void getDerivKernels(Mat kx,
Mat ky,
int dx,
int dy,
int ksize)
Returns filter coefficients for computing spatial image derivatives.
The function computes and returns the filter coefficients for spatial image
derivatives. When ksize=CV_SCHARR, the Scharr 3 x 3
kernels are generated (see "Scharr"). Otherwise, Sobel kernels are generated
(see "Sobel"). The filters are normally passed to "sepFilter2D" or to
"createSeparableLinearFilter".
kx - Output matrix of row filter coefficients. It has the type
ktype.ky - Output matrix of column filter coefficients. It has the type
ktype.dx - Derivative order in respect of x.dy - Derivative order in respect of y.ksize - Aperture size. It can be CV_SCHARR, 1, 3, 5, or 7.
public static void getDerivKernels(Mat kx,
Mat ky,
int dx,
int dy,
int ksize,
boolean normalize,
int ktype)
Returns filter coefficients for computing spatial image derivatives.
The function computes and returns the filter coefficients for spatial image
derivatives. When ksize=CV_SCHARR, the Scharr 3 x 3
kernels are generated (see "Scharr"). Otherwise, Sobel kernels are generated
(see "Sobel"). The filters are normally passed to "sepFilter2D" or to
"createSeparableLinearFilter".
kx - Output matrix of row filter coefficients. It has the type
ktype.ky - Output matrix of column filter coefficients. It has the type
ktype.dx - Derivative order in respect of x.dy - Derivative order in respect of y.ksize - Aperture size. It can be CV_SCHARR, 1, 3, 5, or 7.normalize - Flag indicating whether to normalize (scale down) the filter
coefficients or not. Theoretically, the coefficients should have the
denominator =2^(ksize*2-dx-dy-2). If you are going to filter
floating-point images, you are likely to use the normalized kernels. But if
you compute derivatives of an 8-bit image, store the results in a 16-bit
image, and wish to preserve all the fractional bits, you may want to set
normalize=false.ktype - Type of filter coefficients. It can be CV_32f or
CV_64F.
public static Mat getGaborKernel(Size ksize,
double sigma,
double theta,
double lambd,
double gamma)
public static Mat getGaborKernel(Size ksize,
double sigma,
double theta,
double lambd,
double gamma,
double psi,
int ktype)
public static Mat getGaussianKernel(int ksize,
double sigma)
Returns Gaussian filter coefficients.
The function computes and returns the ksize x 1 matrix of Gaussian filter coefficients:
G_i= alpha *e^(-(i-(ksize -1)/2)^2/(2* sigma)^2),
where i=0..ksize-1 and alpha is the scale factor chosen so that sum_i G_i=1.
Two of such generated kernels can be passed to "sepFilter2D" or to "createSeparableLinearFilter". Those functions automatically recognize smoothing kernels (a symmetrical kernel with sum of weights equal to 1) and handle them accordingly. You may also use the higher-level "GaussianBlur".
ksize - Aperture size. It should be odd (ksize mod 2 = 1) and
positive.sigma - Gaussian standard deviation. If it is non-positive, it is
computed from ksize as sigma = 0.3*((ksize-1)*0.5 - 1) +
0.8.GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
sepFilter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, double, int),
getStructuringElement(int, org.opencv.core.Size, org.opencv.core.Point),
getDerivKernels(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, boolean, int)
public static Mat getGaussianKernel(int ksize,
double sigma,
int ktype)
Returns Gaussian filter coefficients.
The function computes and returns the ksize x 1 matrix of Gaussian filter coefficients:
G_i= alpha *e^(-(i-(ksize -1)/2)^2/(2* sigma)^2),
where i=0..ksize-1 and alpha is the scale factor chosen so that sum_i G_i=1.
Two of such generated kernels can be passed to "sepFilter2D" or to "createSeparableLinearFilter". Those functions automatically recognize smoothing kernels (a symmetrical kernel with sum of weights equal to 1) and handle them accordingly. You may also use the higher-level "GaussianBlur".
ksize - Aperture size. It should be odd (ksize mod 2 = 1) and
positive.sigma - Gaussian standard deviation. If it is non-positive, it is
computed from ksize as sigma = 0.3*((ksize-1)*0.5 - 1) +
0.8.ktype - Type of filter coefficients. It can be CV_32f or
CV_64F.GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
sepFilter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, double, int),
getStructuringElement(int, org.opencv.core.Size, org.opencv.core.Point),
getDerivKernels(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, boolean, int)
public static Mat getPerspectiveTransform(Mat src,
Mat dst)
Calculates a perspective transform from four pairs of the corresponding points.
The function calculates the 3 x 3 matrix of a perspective transform so that:
t_i x'_i t_i y'_i t_i = map_matrix * x_i y_i 1
where
dst(i)=(x'_i,y'_i),<BR>src(i)=(x_i, y_i),<BR>i=0,1,2,3
src - Coordinates of quadrangle vertices in the source image.dst - Coordinates of the corresponding quadrangle vertices in the
destination image.Calib3d.findHomography(org.opencv.core.MatOfPoint2f, org.opencv.core.MatOfPoint2f, int, double, org.opencv.core.Mat),
Core.perspectiveTransform(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
warpPerspective(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar)
public static void getRectSubPix(Mat image,
Size patchSize,
Point center,
Mat patch)
Retrieves a pixel rectangle from an image with sub-pixel accuracy.
The function getRectSubPix extracts pixels from src
dst(x, y) = src(x + center.x - (dst.cols -1)*0.5, y + center.y - (dst.rows -1)*0.5)
where the values of the pixels at non-integer coordinates are retrieved using bilinear interpolation. Every channel of multi-channel images is processed independently. While the center of the rectangle must be inside the image, parts of the rectangle may be outside. In this case, the replication border mode (see "borderInterpolate") is used to extrapolate the pixel values outside of the image.
image - a imagepatchSize - Size of the extracted patch.center - Floating point coordinates of the center of the extracted
rectangle within the source image. The center must be inside the image.patch - a patchwarpAffine(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
warpPerspective(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar)
public static void getRectSubPix(Mat image,
Size patchSize,
Point center,
Mat patch,
int patchType)
Retrieves a pixel rectangle from an image with sub-pixel accuracy.
The function getRectSubPix extracts pixels from src
dst(x, y) = src(x + center.x - (dst.cols -1)*0.5, y + center.y - (dst.rows -1)*0.5)
where the values of the pixels at non-integer coordinates are retrieved using bilinear interpolation. Every channel of multi-channel images is processed independently. While the center of the rectangle must be inside the image, parts of the rectangle may be outside. In this case, the replication border mode (see "borderInterpolate") is used to extrapolate the pixel values outside of the image.
image - a imagepatchSize - Size of the extracted patch.center - Floating point coordinates of the center of the extracted
rectangle within the source image. The center must be inside the image.patch - a patchpatchType - Depth of the extracted pixels. By default, they have the
same depth as src.warpAffine(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
warpPerspective(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar)
public static Mat getRotationMatrix2D(Point center,
double angle,
double scale)
Calculates an affine matrix of 2D rotation.
The function calculates the following matrix:
alpha beta(1- alpha) * center.x - beta * center.y - beta alpha beta * center.x + (1- alpha) * center.y
where
alpha = scale * cos angle, beta = scale * sin angle
The transformation maps the rotation center to itself. If this is not the target, adjust the shift.
center - Center of the rotation in the source image.angle - Rotation angle in degrees. Positive values mean
counter-clockwise rotation (the coordinate origin is assumed to be the
top-left corner).scale - Isotropic scale factor.warpAffine(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
getAffineTransform(org.opencv.core.MatOfPoint2f, org.opencv.core.MatOfPoint2f),
Core.transform(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static Mat getStructuringElement(int shape,
Size ksize)
Returns a structuring element of the specified size and shape for morphological operations.
The function constructs and returns the structuring element that can be further passed to "createMorphologyFilter", "erode", "dilate" or "morphologyEx". But you can also construct an arbitrary binary mask yourself and use it as the structuring element.
Note: When using OpenCV 1.x C API, the created structuring element
IplConvKernel* element must be released in the end using
cvReleaseStructuringElement(&element).
shape - Element shape that could be one of the following:
E_(ij)=1
Rect(0, 0, esize.width,
0.esize.height)
E_(ij) = 1 if i=anchor.y or j=anchor.x; 0 otherwise
ksize - Size of the structuring element.
public static Mat getStructuringElement(int shape,
Size ksize,
Point anchor)
Returns a structuring element of the specified size and shape for morphological operations.
The function constructs and returns the structuring element that can be further passed to "createMorphologyFilter", "erode", "dilate" or "morphologyEx". But you can also construct an arbitrary binary mask yourself and use it as the structuring element.
Note: When using OpenCV 1.x C API, the created structuring element
IplConvKernel* element must be released in the end using
cvReleaseStructuringElement(&element).
shape - Element shape that could be one of the following:
E_(ij)=1
Rect(0, 0, esize.width,
0.esize.height)
E_(ij) = 1 if i=anchor.y or j=anchor.x; 0 otherwise
ksize - Size of the structuring element.anchor - Anchor position within the element. The default value (-1,
-1) means that the anchor is at the center. Note that only the shape of
a cross-shaped element depends on the anchor position. In other cases the
anchor just regulates how much the result of the morphological operation is
shifted.
public static void goodFeaturesToTrack(Mat image,
MatOfPoint corners,
int maxCorners,
double qualityLevel,
double minDistance)
Determines strong corners on an image.
The function finds the most prominent corners in the image or in the specified image region, as described in [Shi94]:
maxDistance.
The function can be used to initialize a point-based tracker of an object.
Note: If the function is called with different values A and
B of the parameter qualityLevel, and A
> {B}, the vector of returned corners with qualityLevel=A will
be the prefix of the output vector with qualityLevel=B.
image - Input 8-bit or floating-point 32-bit, single-channel image.corners - Output vector of detected corners.maxCorners - Maximum number of corners to return. If there are more
corners than are found, the strongest of them is returned.qualityLevel - Parameter characterizing the minimal accepted quality of
image corners. The parameter value is multiplied by the best corner quality
measure, which is the minimal eigenvalue (see "cornerMinEigenVal") or the
Harris function response (see "cornerHarris"). The corners with the quality
measure less than the product are rejected. For example, if the best corner
has the quality measure = 1500, and the qualityLevel=0.01, then
all the corners with the quality measure less than 15 are rejected.minDistance - Minimum possible Euclidean distance between the returned
corners.cornerHarris(org.opencv.core.Mat, org.opencv.core.Mat, int, int, double, int),
Video.estimateRigidTransform(org.opencv.core.Mat, org.opencv.core.Mat, boolean),
cornerMinEigenVal(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int),
Video.calcOpticalFlowPyrLK(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.MatOfPoint2f, org.opencv.core.MatOfPoint2f, org.opencv.core.MatOfByte, org.opencv.core.MatOfFloat, org.opencv.core.Size, int, org.opencv.core.TermCriteria, int, double)
public static void goodFeaturesToTrack(Mat image,
MatOfPoint corners,
int maxCorners,
double qualityLevel,
double minDistance,
Mat mask,
int blockSize,
boolean useHarrisDetector,
double k)
Determines strong corners on an image.
The function finds the most prominent corners in the image or in the specified image region, as described in [Shi94]:
maxDistance.
The function can be used to initialize a point-based tracker of an object.
Note: If the function is called with different values A and
B of the parameter qualityLevel, and A
> {B}, the vector of returned corners with qualityLevel=A will
be the prefix of the output vector with qualityLevel=B.
image - Input 8-bit or floating-point 32-bit, single-channel image.corners - Output vector of detected corners.maxCorners - Maximum number of corners to return. If there are more
corners than are found, the strongest of them is returned.qualityLevel - Parameter characterizing the minimal accepted quality of
image corners. The parameter value is multiplied by the best corner quality
measure, which is the minimal eigenvalue (see "cornerMinEigenVal") or the
Harris function response (see "cornerHarris"). The corners with the quality
measure less than the product are rejected. For example, if the best corner
has the quality measure = 1500, and the qualityLevel=0.01, then
all the corners with the quality measure less than 15 are rejected.minDistance - Minimum possible Euclidean distance between the returned
corners.mask - Optional region of interest. If the image is not empty (it needs
to have the type CV_8UC1 and the same size as image),
it specifies the region in which the corners are detected.blockSize - Size of an average block for computing a derivative
covariation matrix over each pixel neighborhood. See "cornerEigenValsAndVecs".useHarrisDetector - Parameter indicating whether to use a Harris
detector (see "cornerHarris") or "cornerMinEigenVal".k - Free parameter of the Harris detector.cornerHarris(org.opencv.core.Mat, org.opencv.core.Mat, int, int, double, int),
Video.estimateRigidTransform(org.opencv.core.Mat, org.opencv.core.Mat, boolean),
cornerMinEigenVal(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int),
Video.calcOpticalFlowPyrLK(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.MatOfPoint2f, org.opencv.core.MatOfPoint2f, org.opencv.core.MatOfByte, org.opencv.core.MatOfFloat, org.opencv.core.Size, int, org.opencv.core.TermCriteria, int, double)
public static void grabCut(Mat img,
Mat mask,
Rect rect,
Mat bgdModel,
Mat fgdModel,
int iterCount)
Runs the GrabCut algorithm.
The function implements the GrabCut image segmentation algorithm
(http://en.wikipedia.org/wiki/GrabCut).
See the sample grabcut.cpp to learn how to use the function.
img - Input 8-bit 3-channel image.mask - Input/output 8-bit single-channel mask. The mask is initialized
by the function when mode is set to GC_INIT_WITH_RECT.
Its elements may have one of following values:
rect - ROI containing a segmented object. The pixels outside of the ROI
are marked as "obvious background". The parameter is only used when
mode==GC_INIT_WITH_RECT.bgdModel - Temporary array for the background model. Do not modify it
while you are processing the same image.fgdModel - Temporary arrays for the foreground model. Do not modify it
while you are processing the same image.iterCount - Number of iterations the algorithm should make before
returning the result. Note that the result can be refined with further calls
with mode==GC_INIT_WITH_MASK or mode==GC_EVAL.
public static void grabCut(Mat img,
Mat mask,
Rect rect,
Mat bgdModel,
Mat fgdModel,
int iterCount,
int mode)
Runs the GrabCut algorithm.
The function implements the GrabCut image segmentation algorithm
(http://en.wikipedia.org/wiki/GrabCut).
See the sample grabcut.cpp to learn how to use the function.
img - Input 8-bit 3-channel image.mask - Input/output 8-bit single-channel mask. The mask is initialized
by the function when mode is set to GC_INIT_WITH_RECT.
Its elements may have one of following values:
rect - ROI containing a segmented object. The pixels outside of the ROI
are marked as "obvious background". The parameter is only used when
mode==GC_INIT_WITH_RECT.bgdModel - Temporary array for the background model. Do not modify it
while you are processing the same image.fgdModel - Temporary arrays for the foreground model. Do not modify it
while you are processing the same image.iterCount - Number of iterations the algorithm should make before
returning the result. Note that the result can be refined with further calls
with mode==GC_INIT_WITH_MASK or mode==GC_EVAL.mode - Operation mode that could be one of the following:
iterCount
iterations of the algorithm.
GC_INIT_WITH_RECT and GC_INIT_WITH_MASK
can be combined. Then, all the pixels outside of the ROI are automatically
initialized with GC_BGD.
public static void HoughCircles(Mat image,
Mat circles,
int method,
double dp,
double minDist)
Finds circles in a grayscale image using the Hough transform.
The function finds circles in a grayscale image using a modification of the
Hough transform.
Example:
// C++ code:
#include
#include
#include
using namespace cv;
int main(int argc, char argv)
Mat img, gray;
if(argc != 2 && !(img=imread(argv[1], 1)).data)
return -1;
cvtColor(img, gray, CV_BGR2GRAY);
// smooth it, otherwise a lot of false circles may be detected
GaussianBlur(gray, gray, Size(9, 9), 2, 2);
vector
HoughCircles(gray, circles, CV_HOUGH_GRADIENT,
2, gray->rows/4, 200, 100);
for(size_t i = 0; i < circles.size(); i++)
Point center(cvRound(circles[i][0]), cvRound(circles[i][1]));
int radius = cvRound(circles[i][2]);
// draw the circle center
circle(img, center, 3, Scalar(0,255,0), -1, 8, 0);
// draw the circle outline
circle(img, center, radius, Scalar(0,0,255), 3, 8, 0);
namedWindow("circles", 1);
imshow("circles", img);
return 0;
Note: Usually the function detects the centers of circles well. However, it
may fail to find correct radii. You can assist to the function by specifying
the radius range (minRadius and maxRadius) if you
know it. Or, you may ignore the returned radius, use only the center, and
find the correct radius using an additional procedure.
image - 8-bit, single-channel, grayscale input image.circles - Output vector of found circles. Each vector is encoded as a
3-element floating-point vector (x, y, radius).method - Detection method to use. Currently, the only implemented method
is CV_HOUGH_GRADIENT, which is basically *21HT*, described in
[Yuen90].dp - Inverse ratio of the accumulator resolution to the image
resolution. For example, if dp=1, the accumulator has the same
resolution as the input image. If dp=2, the accumulator has half
as big width and height.minDist - Minimum distance between the centers of the detected circles.
If the parameter is too small, multiple neighbor circles may be falsely
detected in addition to a true one. If it is too large, some circles may be
missed.minEnclosingCircle(org.opencv.core.MatOfPoint2f, org.opencv.core.Point, float[]),
fitEllipse(org.opencv.core.MatOfPoint2f)
public static void HoughCircles(Mat image,
Mat circles,
int method,
double dp,
double minDist,
double param1,
double param2,
int minRadius,
int maxRadius)
Finds circles in a grayscale image using the Hough transform.
The function finds circles in a grayscale image using a modification of the
Hough transform.
Example:
// C++ code:
#include
#include
#include
using namespace cv;
int main(int argc, char argv)
Mat img, gray;
if(argc != 2 && !(img=imread(argv[1], 1)).data)
return -1;
cvtColor(img, gray, CV_BGR2GRAY);
// smooth it, otherwise a lot of false circles may be detected
GaussianBlur(gray, gray, Size(9, 9), 2, 2);
vector
HoughCircles(gray, circles, CV_HOUGH_GRADIENT,
2, gray->rows/4, 200, 100);
for(size_t i = 0; i < circles.size(); i++)
Point center(cvRound(circles[i][0]), cvRound(circles[i][1]));
int radius = cvRound(circles[i][2]);
// draw the circle center
circle(img, center, 3, Scalar(0,255,0), -1, 8, 0);
// draw the circle outline
circle(img, center, radius, Scalar(0,0,255), 3, 8, 0);
namedWindow("circles", 1);
imshow("circles", img);
return 0;
Note: Usually the function detects the centers of circles well. However, it
may fail to find correct radii. You can assist to the function by specifying
the radius range (minRadius and maxRadius) if you
know it. Or, you may ignore the returned radius, use only the center, and
find the correct radius using an additional procedure.
image - 8-bit, single-channel, grayscale input image.circles - Output vector of found circles. Each vector is encoded as a
3-element floating-point vector (x, y, radius).method - Detection method to use. Currently, the only implemented method
is CV_HOUGH_GRADIENT, which is basically *21HT*, described in
[Yuen90].dp - Inverse ratio of the accumulator resolution to the image
resolution. For example, if dp=1, the accumulator has the same
resolution as the input image. If dp=2, the accumulator has half
as big width and height.minDist - Minimum distance between the centers of the detected circles.
If the parameter is too small, multiple neighbor circles may be falsely
detected in addition to a true one. If it is too large, some circles may be
missed.param1 - First method-specific parameter. In case of CV_HOUGH_GRADIENT,
it is the higher threshold of the two passed to the "Canny" edge detector
(the lower one is twice smaller).param2 - Second method-specific parameter. In case of CV_HOUGH_GRADIENT,
it is the accumulator threshold for the circle centers at the detection
stage. The smaller it is, the more false circles may be detected. Circles,
corresponding to the larger accumulator values, will be returned first.minRadius - Minimum circle radius.maxRadius - Maximum circle radius.minEnclosingCircle(org.opencv.core.MatOfPoint2f, org.opencv.core.Point, float[]),
fitEllipse(org.opencv.core.MatOfPoint2f)
public static void HoughLines(Mat image,
Mat lines,
double rho,
double theta,
int threshold)
Finds lines in a binary image using the standard Hough transform.
The function implements the standard or standard multi-scale Hough transform algorithm for line detection. See http://homepages.inf.ed.ac.uk/rbf/HIPR2/hough.htm for a good explanation of Hough transform. See also the example in "HoughLinesP" description.
image - 8-bit, single-channel binary source image. The image may be
modified by the function.lines - Output vector of lines. Each line is represented by a
two-element vector (rho, theta). rho is the distance from
the coordinate origin (0,0) (top-left corner of the image).
theta is the line rotation angle in radians (0 ~ vertical line,
pi/2 ~ horizontal line).rho - Distance resolution of the accumulator in pixels.theta - Angle resolution of the accumulator in radians.threshold - Accumulator threshold parameter. Only those lines are
returned that get enough votes (>threshold).
public static void HoughLines(Mat image,
Mat lines,
double rho,
double theta,
int threshold,
double srn,
double stn)
Finds lines in a binary image using the standard Hough transform.
The function implements the standard or standard multi-scale Hough transform algorithm for line detection. See http://homepages.inf.ed.ac.uk/rbf/HIPR2/hough.htm for a good explanation of Hough transform. See also the example in "HoughLinesP" description.
image - 8-bit, single-channel binary source image. The image may be
modified by the function.lines - Output vector of lines. Each line is represented by a
two-element vector (rho, theta). rho is the distance from
the coordinate origin (0,0) (top-left corner of the image).
theta is the line rotation angle in radians (0 ~ vertical line,
pi/2 ~ horizontal line).rho - Distance resolution of the accumulator in pixels.theta - Angle resolution of the accumulator in radians.threshold - Accumulator threshold parameter. Only those lines are
returned that get enough votes (>threshold).srn - For the multi-scale Hough transform, it is a divisor for the
distance resolution rho. The coarse accumulator distance
resolution is rho and the accurate accumulator resolution is
rho/srn. If both srn=0 and stn=0, the
classical Hough transform is used. Otherwise, both these parameters should be
positive.stn - For the multi-scale Hough transform, it is a divisor for the
distance resolution theta.
public static void HoughLinesP(Mat image,
Mat lines,
double rho,
double theta,
int threshold)
Finds line segments in a binary image using the probabilistic Hough transform.
The function implements the probabilistic Hough transform algorithm for line
detection, described in[Matas00]. See the line detection example below:
// C++ code:
/ * This is a standalone program. Pass an image name as the first parameter
of the program. Switch between standard and probabilistic Hough transform
by changing "#if 1" to "#if 0" and back * /
#include
#include
#include
using namespace cv;
int main(int argc, char argv)
Mat src, dst, color_dst;
if(argc != 2 || !(src=imread(argv[1], 0)).data)
return -1;
Canny(src, dst, 50, 200, 3);
cvtColor(dst, color_dst, CV_GRAY2BGR);
#if 0
vector
HoughLines(dst, lines, 1, CV_PI/180, 100);
for(size_t i = 0; i < lines.size(); i++)
float rho = lines[i][0];
float theta = lines[i][1];
double a = cos(theta), b = sin(theta);
double x0 = a*rho, y0 = b*rho;
Point pt1(cvRound(x0 + 1000*(-b)),
cvRound(y0 + 1000*(a)));
Point pt2(cvRound(x0 - 1000*(-b)),
cvRound(y0 - 1000*(a)));
line(color_dst, pt1, pt2, Scalar(0,0,255), 3, 8);
#else
vector
HoughLinesP(dst, lines, 1, CV_PI/180, 80, 30, 10);
for(size_t i = 0; i < lines.size(); i++)
line(color_dst, Point(lines[i][0], lines[i][1]),
Point(lines[i][2], lines[i][3]), Scalar(0,0,255), 3, 8);
#endif
namedWindow("Source", 1);
imshow("Source", src);
namedWindow("Detected Lines", 1);
imshow("Detected Lines", color_dst);
waitKey(0);
return 0;
This is a sample picture the function parameters have been tuned for:
And this is the output of the above program in case of the probabilistic Hough transform:
image - 8-bit, single-channel binary source image. The image may be
modified by the function.lines - Output vector of lines. Each line is represented by a 4-element
vector (x_1, y_1, x_2, y_2), where (x_1,y_1) and (x_2,
y_2) are the ending points of each detected line segment.rho - Distance resolution of the accumulator in pixels.theta - Angle resolution of the accumulator in radians.threshold - Accumulator threshold parameter. Only those lines are
returned that get enough votes (>threshold).
public static void HoughLinesP(Mat image,
Mat lines,
double rho,
double theta,
int threshold,
double minLineLength,
double maxLineGap)
Finds line segments in a binary image using the probabilistic Hough transform.
The function implements the probabilistic Hough transform algorithm for line
detection, described in[Matas00]. See the line detection example below:
// C++ code:
/ * This is a standalone program. Pass an image name as the first parameter
of the program. Switch between standard and probabilistic Hough transform
by changing "#if 1" to "#if 0" and back * /
#include
#include
#include
using namespace cv;
int main(int argc, char argv)
Mat src, dst, color_dst;
if(argc != 2 || !(src=imread(argv[1], 0)).data)
return -1;
Canny(src, dst, 50, 200, 3);
cvtColor(dst, color_dst, CV_GRAY2BGR);
#if 0
vector
HoughLines(dst, lines, 1, CV_PI/180, 100);
for(size_t i = 0; i < lines.size(); i++)
float rho = lines[i][0];
float theta = lines[i][1];
double a = cos(theta), b = sin(theta);
double x0 = a*rho, y0 = b*rho;
Point pt1(cvRound(x0 + 1000*(-b)),
cvRound(y0 + 1000*(a)));
Point pt2(cvRound(x0 - 1000*(-b)),
cvRound(y0 - 1000*(a)));
line(color_dst, pt1, pt2, Scalar(0,0,255), 3, 8);
#else
vector
HoughLinesP(dst, lines, 1, CV_PI/180, 80, 30, 10);
for(size_t i = 0; i < lines.size(); i++)
line(color_dst, Point(lines[i][0], lines[i][1]),
Point(lines[i][2], lines[i][3]), Scalar(0,0,255), 3, 8);
#endif
namedWindow("Source", 1);
imshow("Source", src);
namedWindow("Detected Lines", 1);
imshow("Detected Lines", color_dst);
waitKey(0);
return 0;
This is a sample picture the function parameters have been tuned for:
And this is the output of the above program in case of the probabilistic Hough transform:
image - 8-bit, single-channel binary source image. The image may be
modified by the function.lines - Output vector of lines. Each line is represented by a 4-element
vector (x_1, y_1, x_2, y_2), where (x_1,y_1) and (x_2,
y_2) are the ending points of each detected line segment.rho - Distance resolution of the accumulator in pixels.theta - Angle resolution of the accumulator in radians.threshold - Accumulator threshold parameter. Only those lines are
returned that get enough votes (>threshold).minLineLength - Minimum line length. Line segments shorter than that are
rejected.maxLineGap - Maximum allowed gap between points on the same line to link
them.
public static void HuMoments(Moments m,
Mat hu)
Calculates seven Hu invariants.
The function calculates seven Hu invariants (introduced in [Hu62]; see also http://en.wikipedia.org/wiki/Image_moment) defined as:
hu[0]= eta _20+ eta _02 hu[1]=(eta _20- eta _02)^2+4 eta _11^2 hu[2]=(eta _30-3 eta _12)^2+ (3 eta _21- eta _03)^2 hu[3]=(eta _30+ eta _12)^2+ (eta _21+ eta _03)^2 hu[4]=(eta _30-3 eta _12)(eta _30+ eta _12)[(eta _30+ eta _12)^2-3(eta _21+ eta _03)^2]+(3 eta _21- eta _03)(eta _21+ eta _03)[3(eta _30+ eta _12)^2-(eta _21+ eta _03)^2] hu[5]=(eta _20- eta _02)[(eta _30+ eta _12)^2- (eta _21+ eta _03)^2]+4 eta _11(eta _30+ eta _12)(eta _21+ eta _03) hu[6]=(3 eta _21- eta _03)(eta _21+ eta _03)[3(eta _30+ eta _12)^2-(eta _21+ eta _03)^2]-(eta _30-3 eta _12)(eta _21+ eta _03)[3(eta _30+ eta _12)^2-(eta _21+ eta _03)^2]
where eta_(ji) stands for Moments.nu_(ji).
These values are proved to be invariants to the image scale, rotation, and reflection except the seventh one, whose sign is changed by reflection. This invariance is proved with the assumption of infinite image resolution. In case of raster images, the computed Hu invariants for the original and transformed images are a bit different.
m - a mhu - Output Hu invariants.matchShapes(org.opencv.core.Mat, org.opencv.core.Mat, int, double)
public static void initUndistortRectifyMap(Mat cameraMatrix,
Mat distCoeffs,
Mat R,
Mat newCameraMatrix,
Size size,
int m1type,
Mat map1,
Mat map2)
Computes the undistortion and rectification transformation map.
The function computes the joint undistortion and rectification transformation
and represents the result in the form of maps for "remap". The undistorted
image looks like original, as if it is captured with a camera using the
camera matrix =newCameraMatrix and zero distortion. In case of a
monocular camera, newCameraMatrix is usually equal to
cameraMatrix, or it can be computed by "getOptimalNewCameraMatrix"
for a better control over scaling. In case of a stereo camera,
newCameraMatrix is normally set to P1 or
P2 computed by "stereoRectify".
Also, this new camera is oriented differently in the coordinate space,
according to R. That, for example, helps to align two heads of a
stereo camera so that the epipolar lines on both images become horizontal and
have the same y- coordinate (in case of a horizontally aligned stereo
camera).
The function actually builds the maps for the inverse mapping algorithm that is used by "remap". That is, for each pixel (u, v) in the destination (corrected and rectified) image, the function computes the corresponding coordinates in the source image (that is, in the original image from camera). The following process is applied:
x <- (u - (c')_x)/(f')_x y <- (v - (c')_y)/(f')_y ([X Y W]) ^T <- R^(-1)*[x y 1]^T x' <- X/W y' <- Y/W x" <- x' (1 + k_1 r^2 + k_2 r^4 + k_3 r^6) + 2p_1 x' y' + p_2(r^2 + 2 x'^2) y" <- y' (1 + k_1 r^2 + k_2 r^4 + k_3 r^6) + p_1(r^2 + 2 y'^2) + 2 p_2 x' y' map_x(u,v) <- x" f_x + c_x map_y(u,v) <- y" f_y + c_y
where (k_1, k_2, p_1, p_2[, k_3]) are the distortion coefficients.
In case of a stereo camera, this function is called twice: once for each
camera head, after "stereoRectify", which in its turn is called after
"stereoCalibrate". But if the stereo camera was not calibrated, it is still
possible to compute the rectification transformations directly from the
fundamental matrix using "stereoRectifyUncalibrated". For each camera, the
function computes homography H as the rectification
transformation in a pixel domain, not a rotation matrix R in 3D
space. R can be computed from H as
R = cameraMatrix ^(-1) * H * cameraMatrix
where cameraMatrix can be chosen arbitrarily.
cameraMatrix - Input camera matrix A=
|f_x 0 c_x| |0 f_y c_y| |0 0 1|
.distCoeffs - Input vector of distortion coefficients (k_1, k_2, p_1,
p_2[, k_3[, k_4, k_5, k_6]]) of 4, 5, or 8 elements. If the vector is
NULL/empty, the zero distortion coefficients are assumed.R - Optional rectification transformation in the object space (3x3
matrix). R1 or R2, computed by "stereoRectify" can
be passed here. If the matrix is empty, the identity transformation is
assumed. In cvInitUndistortMap R assumed to be an identity
matrix.newCameraMatrix - New camera matrix A'=
|f_x' 0 c_x'| |0 f_y' c_y'| |0 0 1|
.size - Undistorted image size.m1type - Type of the first output map that can be CV_32FC1
or CV_16SC2. See "convertMaps" for details.map1 - The first output map.map2 - The second output map.
public static float initWideAngleProjMap(Mat cameraMatrix,
Mat distCoeffs,
Size imageSize,
int destImageWidth,
int m1type,
Mat map1,
Mat map2)
public static float initWideAngleProjMap(Mat cameraMatrix,
Mat distCoeffs,
Size imageSize,
int destImageWidth,
int m1type,
Mat map1,
Mat map2,
int projType,
double alpha)
public static void integral(Mat src,
Mat sum)
Calculates the integral of an image.
The functions calculate one or more integral images for the source image as follows:
sum(X,Y) = sum(by: x<X,y<Y) image(x,y)
sqsum(X,Y) = sum(by: x<X,y<Y) image(x,y)^2
tilted(X,Y) = sum(by: y<Y,abs(x-X+1) <= Y-y-1) image(x,y)
Using these integral images, you can calculate sa um, mean, and standard deviation over a specific up-right or rotated rectangular region of the image in a constant time, for example:
sum(by: x_1 <= x < x_2, y_1 <= y < y_2) image(x,y) = sum(x_2,y_2)- sum(x_1,y_2)- sum(x_2,y_1)+ sum(x_1,y_1)
It makes possible to do a fast blurring or fast block correlation with a variable window size, for example. In case of multi-channel images, sums for each channel are accumulated independently.
As a practical example, the next figure shows the calculation of the integral
of a straight rectangle Rect(3,3,3,2) and of a tilted rectangle
Rect(5,1,2,3). The selected pixels in the original
image are shown, as well as the relative pixels in the integral
images sum and tilted.
src - a srcsum - integral image as (W+1)x(H+1), 32-bit integer or
floating-point (32f or 64f).
public static void integral(Mat src,
Mat sum,
int sdepth)
Calculates the integral of an image.
The functions calculate one or more integral images for the source image as follows:
sum(X,Y) = sum(by: x<X,y<Y) image(x,y)
sqsum(X,Y) = sum(by: x<X,y<Y) image(x,y)^2
tilted(X,Y) = sum(by: y<Y,abs(x-X+1) <= Y-y-1) image(x,y)
Using these integral images, you can calculate sa um, mean, and standard deviation over a specific up-right or rotated rectangular region of the image in a constant time, for example:
sum(by: x_1 <= x < x_2, y_1 <= y < y_2) image(x,y) = sum(x_2,y_2)- sum(x_1,y_2)- sum(x_2,y_1)+ sum(x_1,y_1)
It makes possible to do a fast blurring or fast block correlation with a variable window size, for example. In case of multi-channel images, sums for each channel are accumulated independently.
As a practical example, the next figure shows the calculation of the integral
of a straight rectangle Rect(3,3,3,2) and of a tilted rectangle
Rect(5,1,2,3). The selected pixels in the original
image are shown, as well as the relative pixels in the integral
images sum and tilted.
src - a srcsum - integral image as (W+1)x(H+1), 32-bit integer or
floating-point (32f or 64f).sdepth - desired depth of the integral and the tilted integral images,
CV_32S, CV_32F, or CV_64F.
public static void integral2(Mat src,
Mat sum,
Mat sqsum)
Calculates the integral of an image.
The functions calculate one or more integral images for the source image as follows:
sum(X,Y) = sum(by: x<X,y<Y) image(x,y)
sqsum(X,Y) = sum(by: x<X,y<Y) image(x,y)^2
tilted(X,Y) = sum(by: y<Y,abs(x-X+1) <= Y-y-1) image(x,y)
Using these integral images, you can calculate sa um, mean, and standard deviation over a specific up-right or rotated rectangular region of the image in a constant time, for example:
sum(by: x_1 <= x < x_2, y_1 <= y < y_2) image(x,y) = sum(x_2,y_2)- sum(x_1,y_2)- sum(x_2,y_1)+ sum(x_1,y_1)
It makes possible to do a fast blurring or fast block correlation with a variable window size, for example. In case of multi-channel images, sums for each channel are accumulated independently.
As a practical example, the next figure shows the calculation of the integral
of a straight rectangle Rect(3,3,3,2) and of a tilted rectangle
Rect(5,1,2,3). The selected pixels in the original
image are shown, as well as the relative pixels in the integral
images sum and tilted.
src - a srcsum - integral image as (W+1)x(H+1), 32-bit integer or
floating-point (32f or 64f).sqsum - integral image for squared pixel values; it is (W+1)x(H+1),
double-precision floating-point (64f) array.
public static void integral2(Mat src,
Mat sum,
Mat sqsum,
int sdepth)
Calculates the integral of an image.
The functions calculate one or more integral images for the source image as follows:
sum(X,Y) = sum(by: x<X,y<Y) image(x,y)
sqsum(X,Y) = sum(by: x<X,y<Y) image(x,y)^2
tilted(X,Y) = sum(by: y<Y,abs(x-X+1) <= Y-y-1) image(x,y)
Using these integral images, you can calculate sa um, mean, and standard deviation over a specific up-right or rotated rectangular region of the image in a constant time, for example:
sum(by: x_1 <= x < x_2, y_1 <= y < y_2) image(x,y) = sum(x_2,y_2)- sum(x_1,y_2)- sum(x_2,y_1)+ sum(x_1,y_1)
It makes possible to do a fast blurring or fast block correlation with a variable window size, for example. In case of multi-channel images, sums for each channel are accumulated independently.
As a practical example, the next figure shows the calculation of the integral
of a straight rectangle Rect(3,3,3,2) and of a tilted rectangle
Rect(5,1,2,3). The selected pixels in the original
image are shown, as well as the relative pixels in the integral
images sum and tilted.
src - a srcsum - integral image as (W+1)x(H+1), 32-bit integer or
floating-point (32f or 64f).sqsum - integral image for squared pixel values; it is (W+1)x(H+1),
double-precision floating-point (64f) array.sdepth - desired depth of the integral and the tilted integral images,
CV_32S, CV_32F, or CV_64F.
public static void integral3(Mat src,
Mat sum,
Mat sqsum,
Mat tilted)
Calculates the integral of an image.
The functions calculate one or more integral images for the source image as follows:
sum(X,Y) = sum(by: x<X,y<Y) image(x,y)
sqsum(X,Y) = sum(by: x<X,y<Y) image(x,y)^2
tilted(X,Y) = sum(by: y<Y,abs(x-X+1) <= Y-y-1) image(x,y)
Using these integral images, you can calculate sa um, mean, and standard deviation over a specific up-right or rotated rectangular region of the image in a constant time, for example:
sum(by: x_1 <= x < x_2, y_1 <= y < y_2) image(x,y) = sum(x_2,y_2)- sum(x_1,y_2)- sum(x_2,y_1)+ sum(x_1,y_1)
It makes possible to do a fast blurring or fast block correlation with a variable window size, for example. In case of multi-channel images, sums for each channel are accumulated independently.
As a practical example, the next figure shows the calculation of the integral
of a straight rectangle Rect(3,3,3,2) and of a tilted rectangle
Rect(5,1,2,3). The selected pixels in the original
image are shown, as well as the relative pixels in the integral
images sum and tilted.
src - a srcsum - integral image as (W+1)x(H+1), 32-bit integer or
floating-point (32f or 64f).sqsum - integral image for squared pixel values; it is (W+1)x(H+1),
double-precision floating-point (64f) array.tilted - integral for the image rotated by 45 degrees; it is
(W+1)x(H+1) array with the same data type as sum.
public static void integral3(Mat src,
Mat sum,
Mat sqsum,
Mat tilted,
int sdepth)
Calculates the integral of an image.
The functions calculate one or more integral images for the source image as follows:
sum(X,Y) = sum(by: x<X,y<Y) image(x,y)
sqsum(X,Y) = sum(by: x<X,y<Y) image(x,y)^2
tilted(X,Y) = sum(by: y<Y,abs(x-X+1) <= Y-y-1) image(x,y)
Using these integral images, you can calculate sa um, mean, and standard deviation over a specific up-right or rotated rectangular region of the image in a constant time, for example:
sum(by: x_1 <= x < x_2, y_1 <= y < y_2) image(x,y) = sum(x_2,y_2)- sum(x_1,y_2)- sum(x_2,y_1)+ sum(x_1,y_1)
It makes possible to do a fast blurring or fast block correlation with a variable window size, for example. In case of multi-channel images, sums for each channel are accumulated independently.
As a practical example, the next figure shows the calculation of the integral
of a straight rectangle Rect(3,3,3,2) and of a tilted rectangle
Rect(5,1,2,3). The selected pixels in the original
image are shown, as well as the relative pixels in the integral
images sum and tilted.
src - a srcsum - integral image as (W+1)x(H+1), 32-bit integer or
floating-point (32f or 64f).sqsum - integral image for squared pixel values; it is (W+1)x(H+1),
double-precision floating-point (64f) array.tilted - integral for the image rotated by 45 degrees; it is
(W+1)x(H+1) array with the same data type as sum.sdepth - desired depth of the integral and the tilted integral images,
CV_32S, CV_32F, or CV_64F.
public static float intersectConvexConvex(Mat _p1,
Mat _p2,
Mat _p12)
public static float intersectConvexConvex(Mat _p1,
Mat _p2,
Mat _p12,
boolean handleNested)
public static void invertAffineTransform(Mat M,
Mat iM)
Inverts an affine transformation.
The function computes an inverse affine transformation represented by 2 x
3 matrix M :
a_11 a_12 b_1 a_21 a_22 b_2
The result is also a 2 x 3 matrix of the same type as
M.
M - Original affine transformation.iM - Output reverse affine transformation.public static boolean isContourConvex(MatOfPoint contour)
Tests a contour convexity.
The function tests whether the input contour is convex or not. The contour must be simple, that is, without self-intersections. Otherwise, the function output is undefined.
contour - Input vector of 2D points, stored in:
std.vector<> or Mat (C++ interface)
CvSeq* or CvMat* (C interface)
public static void Laplacian(Mat src,
Mat dst,
int ddepth)
Calculates the Laplacian of an image.
The function calculates the Laplacian of the source image by adding up the second x and y derivatives calculated using the Sobel operator:
dst = Delta src = (d^2 src)/(dx^2) + (d^2 src)/(dy^2)
This is done when ksize > 1. When ksize == 1, the
Laplacian is computed by filtering the image with the following 3 x
3 aperture:
vecthreethree 0101(-4)1010
src - Source image.dst - Destination image of the same size and the same number of channels
as src.ddepth - Desired depth of the destination image.Scharr(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, double, double, int),
Sobel(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, int, double, double, int)
public static void Laplacian(Mat src,
Mat dst,
int ddepth,
int ksize,
double scale,
double delta)
Calculates the Laplacian of an image.
The function calculates the Laplacian of the source image by adding up the second x and y derivatives calculated using the Sobel operator:
dst = Delta src = (d^2 src)/(dx^2) + (d^2 src)/(dy^2)
This is done when ksize > 1. When ksize == 1, the
Laplacian is computed by filtering the image with the following 3 x
3 aperture:
vecthreethree 0101(-4)1010
src - Source image.dst - Destination image of the same size and the same number of channels
as src.ddepth - Desired depth of the destination image.ksize - Aperture size used to compute the second-derivative filters. See
"getDerivKernels" for details. The size must be positive and odd.scale - Optional scale factor for the computed Laplacian values. By
default, no scaling is applied. See "getDerivKernels" for details.delta - Optional delta value that is added to the results prior to
storing them in dst.Scharr(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, double, double, int),
Sobel(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, int, double, double, int)
public static void Laplacian(Mat src,
Mat dst,
int ddepth,
int ksize,
double scale,
double delta,
int borderType)
Calculates the Laplacian of an image.
The function calculates the Laplacian of the source image by adding up the second x and y derivatives calculated using the Sobel operator:
dst = Delta src = (d^2 src)/(dx^2) + (d^2 src)/(dy^2)
This is done when ksize > 1. When ksize == 1, the
Laplacian is computed by filtering the image with the following 3 x
3 aperture:
vecthreethree 0101(-4)1010
src - Source image.dst - Destination image of the same size and the same number of channels
as src.ddepth - Desired depth of the destination image.ksize - Aperture size used to compute the second-derivative filters. See
"getDerivKernels" for details. The size must be positive and odd.scale - Optional scale factor for the computed Laplacian values. By
default, no scaling is applied. See "getDerivKernels" for details.delta - Optional delta value that is added to the results prior to
storing them in dst.borderType - Pixel extrapolation method. See "borderInterpolate" for
details.Scharr(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, double, double, int),
Sobel(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, int, double, double, int)
public static double matchShapes(Mat contour1,
Mat contour2,
int method,
double parameter)
Compares two shapes.
The function compares two shapes. All three implemented methods use the Hu
invariants (see "HuMoments") as follows (A denotes object1,B
denotes object2):
I_1(A,B) = sum(by: i=1...7) <= ft|1/(m^A_i) - 1/(m^B_i) right|
I_2(A,B) = sum(by: i=1...7) <= ft|m^A_i - m^B_i right|
I_3(A,B) = max _(i=1...7)(<= ft| m^A_i - m^B_i right|)/(<= ft| m^A_i right|)
where
m^A_i = sign(h^A_i) * log(h^A_i) m^B_i = sign(h^B_i) * log(h^B_i)
and h^A_i, h^B_i are the Hu moments of A and B, respectively.
contour1 - a contour1contour2 - a contour2method - Comparison method: CV_CONTOURS_MATCH_I1,
CV_CONTOURS_MATCH_I2 \
or CV_CONTOURS_MATCH_I3 (see the details below).
parameter - Method-specific parameter (not supported now).
public static void matchTemplate(Mat image,
Mat templ,
Mat result,
int method)
Compares a template against overlapped image regions.
The function slides through image, compares the overlapped
patches of size w x h against templ using the specified
method and stores the comparison results in result. Here are the
formulae for the available comparison methods (I denotes
image, T template, R
result). The summation is done over template and/or the image
patch: x' = 0...w-1, y' = 0...h-1
R(x,y)= sum(by: x',y')(T(x',y')-I(x+x',y+y'))^2
R(x,y)= (sum_(x',y')(T(x',y')-I(x+x',y+y'))^2)/(sqrt(sum_(x',y')T(x',y')^2 * sum_(x',y') I(x+x',y+y')^2))
R(x,y)= sum(by: x',y')(T(x',y') * I(x+x',y+y'))
R(x,y)= (sum_(x',y')(T(x',y') * I(x+x',y+y')))/(sqrt(sum_(x',y')T(x',y')^2 * sum_(x',y') I(x+x',y+y')^2))
R(x,y)= sum(by: x',y')(T'(x',y') * I'(x+x',y+y'))
where
T'(x',y')=T(x',y') - 1/(w * h) * sum(by: x'',y'') T(x'',y'') I'(x+x',y+y')=I(x+x',y+y') - 1/(w * h) * sum(by: x'',y'') I(x+x'',y+y'')
R(x,y)= (sum_(x',y')(T'(x',y') * I'(x+x',y+y')))/(sqrt(sum_(x',y')T'(x',y')^2 * sum_(x',y') I'(x+x',y+y')^2))
After the function finishes the comparison, the best matches can be found as
global minimums (when CV_TM_SQDIFF was used) or maximums (when
CV_TM_CCORR or CV_TM_CCOEFF was used) using the
"minMaxLoc" function. In case of a color image, template summation in the
numerator and each sum in the denominator is done over all of the channels
and separate mean values are used for each channel. That is, the function can
take a color template and a color image. The result will still be a
single-channel image, which is easier to analyze.
image - Image where the search is running. It must be 8-bit or 32-bit
floating-point.templ - Searched template. It must be not greater than the source image
and have the same data type.result - Map of comparison results. It must be single-channel 32-bit
floating-point. If image is W x H and templ
is w x h, then result is (W-w+1) x(H-h+1).method - Parameter specifying the comparison method (see below).
public static void medianBlur(Mat src,
Mat dst,
int ksize)
Blurs an image using the median filter.
The function smoothes an image using the median filter with the ksize x ksize aperture. Each channel of a multi-channel image is processed independently. In-place operation is supported.
src - input 1-, 3-, or 4-channel image; when ksize is 3 or
5, the image depth should be CV_8U, CV_16U, or
CV_32F, for larger aperture sizes, it can only be
CV_8U.dst - destination array of the same size and type as src.ksize - aperture linear size; it must be odd and greater than 1, for
example: 3, 5, 7...boxFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Size, org.opencv.core.Point, boolean, int),
GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
bilateralFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, double, double, int),
blur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, int)public static RotatedRect minAreaRect(MatOfPoint2f points)
Finds a rotated rectangle of the minimum area enclosing the input 2D point set.
The function calculates and returns the minimum-area bounding rectangle
(possibly rotated) for a specified point set. See the OpenCV sample
minarea.cpp.
points - Input vector of 2D points, stored in:
std.vector<> or Mat (C++ interface)
CvSeq* or CvMat* (C interface)
public static void minEnclosingCircle(MatOfPoint2f points,
Point center,
float[] radius)
Finds a circle of the minimum area enclosing a 2D point set.
The function finds the minimal enclosing circle of a 2D point set using an
iterative algorithm. See the OpenCV sample minarea.cpp.
points - Input vector of 2D points, stored in:
std.vector<> or Mat (C++ interface)
CvSeq* or CvMat* (C interface)
center - Output center of the circle.radius - Output radius of the circle.public static Moments moments(Mat array)
Calculates all of the moments up to the third order of a polygon or rasterized shape.
The function computes moments, up to the 3rd order, of a vector shape or a
rasterized shape. The results are returned in the structure Moments
defined as:
// C++ code:
class Moments
public:
Moments();
Moments(double m00, double m10, double m01, double m20, double m11,
double m02, double m30, double m21, double m12, double m03);
Moments(const CvMoments& moments);
operator CvMoments() const;
// spatial moments
double m00, m10, m01, m20, m11, m02, m30, m21, m12, m03;
// central moments
double mu20, mu11, mu02, mu30, mu21, mu12, mu03;
// central normalized moments
double nu20, nu11, nu02, nu30, nu21, nu12, nu03;
In case of a raster image, the spatial moments Moments.m_(ji) are computed as:
m _(ji)= sum(by: x,y)(array(x,y) * x^j * y^i)
The central moments Moments.mu_(ji) are computed as:
mu _(ji)= sum(by: x,y)(array(x,y) * (x - x")^j * (y - y")^i)
where (x", y") is the mass center:
x" = (m_10)/(m_(00)), y" = (m_01)/(m_(00))
The normalized central moments Moments.nu_(ij) are computed as:
nu _(ji)= (mu_(ji))/(m_(00)^((i+j)/2+1)).
Note:
mu_00=m_00, nu_00=1 nu_10=mu_10=mu_01=mu_10=0, hence the values are not stored.
The moments of a contour are defined in the same way but computed using the Green's formula (see http://en.wikipedia.org/wiki/Green_theorem). So, due to a limited raster resolution, the moments computed for a contour are slightly different from the moments computed for the same rasterized contour.
Note:
Since the contour moments are computed using Green formula, you may get
seemingly odd results for contours with self-intersections, e.g. a zero area
(m00) for butterfly-shaped contours.
array - Raster image (single-channel, 8-bit or floating-point 2D array)
or an array (1 x N or N x 1) of 2D points (Point
or Point2f).contourArea(org.opencv.core.Mat, boolean),
arcLength(org.opencv.core.MatOfPoint2f, boolean)
public static Moments moments(Mat array,
boolean binaryImage)
Calculates all of the moments up to the third order of a polygon or rasterized shape.
The function computes moments, up to the 3rd order, of a vector shape or a
rasterized shape. The results are returned in the structure Moments
defined as:
// C++ code:
class Moments
public:
Moments();
Moments(double m00, double m10, double m01, double m20, double m11,
double m02, double m30, double m21, double m12, double m03);
Moments(const CvMoments& moments);
operator CvMoments() const;
// spatial moments
double m00, m10, m01, m20, m11, m02, m30, m21, m12, m03;
// central moments
double mu20, mu11, mu02, mu30, mu21, mu12, mu03;
// central normalized moments
double nu20, nu11, nu02, nu30, nu21, nu12, nu03;
In case of a raster image, the spatial moments Moments.m_(ji) are computed as:
m _(ji)= sum(by: x,y)(array(x,y) * x^j * y^i)
The central moments Moments.mu_(ji) are computed as:
mu _(ji)= sum(by: x,y)(array(x,y) * (x - x")^j * (y - y")^i)
where (x", y") is the mass center:
x" = (m_10)/(m_(00)), y" = (m_01)/(m_(00))
The normalized central moments Moments.nu_(ij) are computed as:
nu _(ji)= (mu_(ji))/(m_(00)^((i+j)/2+1)).
Note:
mu_00=m_00, nu_00=1 nu_10=mu_10=mu_01=mu_10=0, hence the values are not stored.
The moments of a contour are defined in the same way but computed using the Green's formula (see http://en.wikipedia.org/wiki/Green_theorem). So, due to a limited raster resolution, the moments computed for a contour are slightly different from the moments computed for the same rasterized contour.
Note:
Since the contour moments are computed using Green formula, you may get
seemingly odd results for contours with self-intersections, e.g. a zero area
(m00) for butterfly-shaped contours.
array - Raster image (single-channel, 8-bit or floating-point 2D array)
or an array (1 x N or N x 1) of 2D points (Point
or Point2f).binaryImage - If it is true, all non-zero image pixels are treated as
1's. The parameter is used for images only.contourArea(org.opencv.core.Mat, boolean),
arcLength(org.opencv.core.MatOfPoint2f, boolean)
public static void morphologyEx(Mat src,
Mat dst,
int op,
Mat kernel)
Performs advanced morphological transformations.
The function can perform advanced morphological transformations using an erosion and dilation as basic operations.
Opening operation:
dst = open(src, element)= dilate(erode(src, element))
Closing operation:
dst = close(src, element)= erode(dilate(src, element))
Morphological gradient:
dst = morph_grad(src, element)= dilate(src, element)- erode(src, element)
"Top hat":
dst = tophat(src, element)= src - open(src, element)
"Black hat":
dst = blackhat(src, element)= close(src, element)- src
Any of the operations can be done in-place. In case of multi-channel images, each channel is processed independently.
src - Source image. The number of channels can be arbitrary. The depth
should be one of CV_8U, CV_16U, CV_16S,
CV_32F" or CV_64F".dst - Destination image of the same size and type as src.op - Type of a morphological operation that can be one of the following:
kernel - a kernelerode(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar),
dilate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar)
public static void morphologyEx(Mat src,
Mat dst,
int op,
Mat kernel,
Point anchor,
int iterations)
Performs advanced morphological transformations.
The function can perform advanced morphological transformations using an erosion and dilation as basic operations.
Opening operation:
dst = open(src, element)= dilate(erode(src, element))
Closing operation:
dst = close(src, element)= erode(dilate(src, element))
Morphological gradient:
dst = morph_grad(src, element)= dilate(src, element)- erode(src, element)
"Top hat":
dst = tophat(src, element)= src - open(src, element)
"Black hat":
dst = blackhat(src, element)= close(src, element)- src
Any of the operations can be done in-place. In case of multi-channel images, each channel is processed independently.
src - Source image. The number of channels can be arbitrary. The depth
should be one of CV_8U, CV_16U, CV_16S,
CV_32F" or CV_64F".dst - Destination image of the same size and type as src.op - Type of a morphological operation that can be one of the following:
kernel - a kernelanchor - a anchoriterations - Number of times erosion and dilation are applied.erode(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar),
dilate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar)
public static void morphologyEx(Mat src,
Mat dst,
int op,
Mat kernel,
Point anchor,
int iterations,
int borderType,
Scalar borderValue)
Performs advanced morphological transformations.
The function can perform advanced morphological transformations using an erosion and dilation as basic operations.
Opening operation:
dst = open(src, element)= dilate(erode(src, element))
Closing operation:
dst = close(src, element)= erode(dilate(src, element))
Morphological gradient:
dst = morph_grad(src, element)= dilate(src, element)- erode(src, element)
"Top hat":
dst = tophat(src, element)= src - open(src, element)
"Black hat":
dst = blackhat(src, element)= close(src, element)- src
Any of the operations can be done in-place. In case of multi-channel images, each channel is processed independently.
src - Source image. The number of channels can be arbitrary. The depth
should be one of CV_8U, CV_16U, CV_16S,
CV_32F" or CV_64F".dst - Destination image of the same size and type as src.op - Type of a morphological operation that can be one of the following:
kernel - a kernelanchor - a anchoriterations - Number of times erosion and dilation are applied.borderType - Pixel extrapolation method. See "borderInterpolate" for
details.borderValue - Border value in case of a constant border. The default
value has a special meaning. See "createMorphologyFilter" for details.erode(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar),
dilate(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, int, int, org.opencv.core.Scalar)
public static Point phaseCorrelate(Mat src1,
Mat src2)
The function is used to detect translational shifts that occur between two images. The operation takes advantage of the Fourier shift theorem for detecting the translational shift in the frequency domain. It can be used for fast image registration as well as motion estimation. For more information please see http://en.wikipedia.org/wiki/Phase_correlation.
Calculates the cross-power spectrum of two supplied source arrays. The arrays are padded if needed with "getOptimalDFTSize".
Return value: detected phase shift (sub-pixel) between the two arrays.
The function performs the following equations
mathbf(G)_a = mathcal(F)(src_1), mathbf(G)_b = mathcal(F)(src_2)
where mathcal(F) is the forward DFT.
R = (mathbf(G)_a mathbf(G)_b^*)/(|mathbf(G)_a mathbf(G)_b^*|)
r = mathcal(F)^(-1)(R)
(Delta x, Delta y) = weightedCentroid (arg max_((x, y))(r))
src1 - Source floating point array (CV_32FC1 or CV_64FC1)src2 - Source floating point array (CV_32FC1 or CV_64FC1)createHanningWindow(org.opencv.core.Mat, org.opencv.core.Size, int),
Core.dft(org.opencv.core.Mat, org.opencv.core.Mat, int, int),
Core.mulSpectrums(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, boolean),
Core.getOptimalDFTSize(int),
Core.idft(org.opencv.core.Mat, org.opencv.core.Mat, int, int)
public static Point phaseCorrelate(Mat src1,
Mat src2,
Mat window)
The function is used to detect translational shifts that occur between two images. The operation takes advantage of the Fourier shift theorem for detecting the translational shift in the frequency domain. It can be used for fast image registration as well as motion estimation. For more information please see http://en.wikipedia.org/wiki/Phase_correlation.
Calculates the cross-power spectrum of two supplied source arrays. The arrays are padded if needed with "getOptimalDFTSize".
Return value: detected phase shift (sub-pixel) between the two arrays.
The function performs the following equations
mathbf(G)_a = mathcal(F)(src_1), mathbf(G)_b = mathcal(F)(src_2)
where mathcal(F) is the forward DFT.
R = (mathbf(G)_a mathbf(G)_b^*)/(|mathbf(G)_a mathbf(G)_b^*|)
r = mathcal(F)^(-1)(R)
(Delta x, Delta y) = weightedCentroid (arg max_((x, y))(r))
src1 - Source floating point array (CV_32FC1 or CV_64FC1)src2 - Source floating point array (CV_32FC1 or CV_64FC1)window - Floating point array with windowing coefficients to reduce edge
effects (optional).createHanningWindow(org.opencv.core.Mat, org.opencv.core.Size, int),
Core.dft(org.opencv.core.Mat, org.opencv.core.Mat, int, int),
Core.mulSpectrums(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, boolean),
Core.getOptimalDFTSize(int),
Core.idft(org.opencv.core.Mat, org.opencv.core.Mat, int, int)
public static Point phaseCorrelateRes(Mat src1,
Mat src2,
Mat window)
public static Point phaseCorrelateRes(Mat src1,
Mat src2,
Mat window,
double[] response)
public static double pointPolygonTest(MatOfPoint2f contour,
Point pt,
boolean measureDist)
Performs a point-in-contour test.
The function determines whether the point is inside a contour, outside, or
lies on an edge (or coincides with a vertex). It returns positive (inside),
negative (outside), or zero (on an edge) value, correspondingly. When
measureDist=false, the return value is +1, -1, and 0,
respectively. Otherwise, the return value is a signed distance between the
point and the nearest contour edge.
See below a sample output of the function where each image pixel is tested against the contour.
contour - Input contour.pt - Point tested against the contour.measureDist - If true, the function estimates the signed distance from
the point to the nearest contour edge. Otherwise, the function only checks if
the point is inside a contour or not.
public static void preCornerDetect(Mat src,
Mat dst,
int ksize)
Calculates a feature map for corner detection.
The function calculates the complex spatial derivative-based function of the source image
dst = (D_x src)^2 * D_(yy) src + (D_y src)^2 * D_(xx) src - 2 D_x src * D_y src * D_(xy) src
where D_x,D_y are the first image derivatives,
D_(xx),D_(yy) are the second image derivatives, and
D_(xy) is the mixed derivative.
The corners can be found as local maximums of the functions, as shown below:
// C++ code:
Mat corners, dilated_corners;
preCornerDetect(image, corners, 3);
// dilation with 3x3 rectangular structuring element
dilate(corners, dilated_corners, Mat(), 1);
Mat corner_mask = corners == dilated_corners;
src - Source single-channel 8-bit of floating-point image.dst - Output image that has the type CV_32F and the same
size as src.ksize - Aperture size of the "Sobel".
public static void preCornerDetect(Mat src,
Mat dst,
int ksize,
int borderType)
Calculates a feature map for corner detection.
The function calculates the complex spatial derivative-based function of the source image
dst = (D_x src)^2 * D_(yy) src + (D_y src)^2 * D_(xx) src - 2 D_x src * D_y src * D_(xy) src
where D_x,D_y are the first image derivatives,
D_(xx),D_(yy) are the second image derivatives, and
D_(xy) is the mixed derivative.
The corners can be found as local maximums of the functions, as shown below:
// C++ code:
Mat corners, dilated_corners;
preCornerDetect(image, corners, 3);
// dilation with 3x3 rectangular structuring element
dilate(corners, dilated_corners, Mat(), 1);
Mat corner_mask = corners == dilated_corners;
src - Source single-channel 8-bit of floating-point image.dst - Output image that has the type CV_32F and the same
size as src.ksize - Aperture size of the "Sobel".borderType - Pixel extrapolation method. See "borderInterpolate".
public static double PSNR(Mat src1,
Mat src2)
public static void pyrDown(Mat src,
Mat dst)
Blurs an image and downsamples it.
The function performs the downsampling step of the Gaussian pyramid construction. First, it convolves the source image with the kernel:
1/256 1 4 6 4 1 4 16 24 16 4 6 24 36 24 6 4 16 24 16 4 1 4 6 4 1
Then, it downsamples the image by rejecting even rows and columns.
src - input image.dst - output image; it has the specified size and the same type as
src.
public static void pyrDown(Mat src,
Mat dst,
Size dstsize)
Blurs an image and downsamples it.
The function performs the downsampling step of the Gaussian pyramid construction. First, it convolves the source image with the kernel:
1/256 1 4 6 4 1 4 16 24 16 4 6 24 36 24 6 4 16 24 16 4 1 4 6 4 1
Then, it downsamples the image by rejecting even rows and columns.
src - input image.dst - output image; it has the specified size and the same type as
src.dstsize - size of the output image; by default, it is computed as
Size((src.cols+1)/2, (src.rows+1)/2), but in any case, the
following conditions should be satisfied:
ltBR gt| dstsize.width *2-src.cols| <= 2 |dstsize.height *2-src.rows| <= 2
public static void pyrDown(Mat src,
Mat dst,
Size dstsize,
int borderType)
Blurs an image and downsamples it.
The function performs the downsampling step of the Gaussian pyramid construction. First, it convolves the source image with the kernel:
1/256 1 4 6 4 1 4 16 24 16 4 6 24 36 24 6 4 16 24 16 4 1 4 6 4 1
Then, it downsamples the image by rejecting even rows and columns.
src - input image.dst - output image; it has the specified size and the same type as
src.dstsize - size of the output image; by default, it is computed as
Size((src.cols+1)/2, (src.rows+1)/2), but in any case, the
following conditions should be satisfied:
ltBR gt| dstsize.width *2-src.cols| <= 2 |dstsize.height *2-src.rows| <= 2
borderType - a borderType
public static void pyrMeanShiftFiltering(Mat src,
Mat dst,
double sp,
double sr)
Performs initial step of meanshift segmentation of an image.
The function implements the filtering stage of meanshift segmentation, that
is, the output of the function is the filtered "posterized" image with color
gradients and fine-grain texture flattened. At every pixel (X,Y)
of the input image (or down-sized input image, see below) the function
executes meanshift iterations, that is, the pixel (X,Y)
neighborhood in the joint space-color hyperspace is considered:
(x,y): X- sp <= x <= X+ sp, Y- sp <= y <= Y+ sp, ||(R,G,B)-(r,g,b)|| <= sr
where (R,G,B) and (r,g,b) are the vectors of color
components at (X,Y) and (x,y), respectively
(though, the algorithm does not depend on the color space used, so any
3-component color space can be used instead). Over the neighborhood the
average spatial value (X',Y') and average color vector
(R',G',B') are found and they act as the neighborhood center on
the next iteration:
(X,Y)~(X',Y'), (R,G,B)~(R',G',B').
After the iterations over, the color components of the initial pixel (that is, the pixel from where the iterations started) are set to the final value (average color at the last iteration):
I(X,Y) <- (R*,G*,B*)
When maxLevel > 0, the gaussian pyramid of maxLevel+1
levels is built, and the above procedure is run on the smallest layer first.
After that, the results are propagated to the larger layer and the iterations
are run again only on those pixels where the layer colors differ by more than
sr from the lower-resolution layer of the pyramid. That makes
boundaries of color regions sharper. Note that the results will be actually
different from the ones obtained by running the meanshift procedure on the
whole original image (i.e. when maxLevel==0).
src - The source 8-bit, 3-channel image.dst - The destination image of the same format and the same size as the
source.sp - The spatial window radius.sr - The color window radius.
public static void pyrMeanShiftFiltering(Mat src,
Mat dst,
double sp,
double sr,
int maxLevel,
TermCriteria termcrit)
Performs initial step of meanshift segmentation of an image.
The function implements the filtering stage of meanshift segmentation, that
is, the output of the function is the filtered "posterized" image with color
gradients and fine-grain texture flattened. At every pixel (X,Y)
of the input image (or down-sized input image, see below) the function
executes meanshift iterations, that is, the pixel (X,Y)
neighborhood in the joint space-color hyperspace is considered:
(x,y): X- sp <= x <= X+ sp, Y- sp <= y <= Y+ sp, ||(R,G,B)-(r,g,b)|| <= sr
where (R,G,B) and (r,g,b) are the vectors of color
components at (X,Y) and (x,y), respectively
(though, the algorithm does not depend on the color space used, so any
3-component color space can be used instead). Over the neighborhood the
average spatial value (X',Y') and average color vector
(R',G',B') are found and they act as the neighborhood center on
the next iteration:
(X,Y)~(X',Y'), (R,G,B)~(R',G',B').
After the iterations over, the color components of the initial pixel (that is, the pixel from where the iterations started) are set to the final value (average color at the last iteration):
I(X,Y) <- (R*,G*,B*)
When maxLevel > 0, the gaussian pyramid of maxLevel+1
levels is built, and the above procedure is run on the smallest layer first.
After that, the results are propagated to the larger layer and the iterations
are run again only on those pixels where the layer colors differ by more than
sr from the lower-resolution layer of the pyramid. That makes
boundaries of color regions sharper. Note that the results will be actually
different from the ones obtained by running the meanshift procedure on the
whole original image (i.e. when maxLevel==0).
src - The source 8-bit, 3-channel image.dst - The destination image of the same format and the same size as the
source.sp - The spatial window radius.sr - The color window radius.maxLevel - Maximum level of the pyramid for the segmentation.termcrit - Termination criteria: when to stop meanshift iterations.
public static void pyrUp(Mat src,
Mat dst)
Upsamples an image and then blurs it.
The function performs the upsampling step of the Gaussian pyramid construction, though it can actually be used to construct the Laplacian pyramid. First, it upsamples the source image by injecting even zero rows and columns and then convolves the result with the same kernel as in "pyrDown" multiplied by 4.
src - input image.dst - output image. It has the specified size and the same type as
src.
public static void pyrUp(Mat src,
Mat dst,
Size dstsize)
Upsamples an image and then blurs it.
The function performs the upsampling step of the Gaussian pyramid construction, though it can actually be used to construct the Laplacian pyramid. First, it upsamples the source image by injecting even zero rows and columns and then convolves the result with the same kernel as in "pyrDown" multiplied by 4.
src - input image.dst - output image. It has the specified size and the same type as
src.dstsize - size of the output image; by default, it is computed as
Size(src.cols*2, (src.rows*2), but in any case, the following
conditions should be satisfied:
ltBR gt| dstsize.width -src.cols*2| <= (dstsize.width mod 2) |dstsize.height -src.rows*2| <= (dstsize.height mod 2)
public static void pyrUp(Mat src,
Mat dst,
Size dstsize,
int borderType)
Upsamples an image and then blurs it.
The function performs the upsampling step of the Gaussian pyramid construction, though it can actually be used to construct the Laplacian pyramid. First, it upsamples the source image by injecting even zero rows and columns and then convolves the result with the same kernel as in "pyrDown" multiplied by 4.
src - input image.dst - output image. It has the specified size and the same type as
src.dstsize - size of the output image; by default, it is computed as
Size(src.cols*2, (src.rows*2), but in any case, the following
conditions should be satisfied:
ltBR gt| dstsize.width -src.cols*2| <= (dstsize.width mod 2) |dstsize.height -src.rows*2| <= (dstsize.height mod 2)
borderType - a borderType
public static void remap(Mat src,
Mat dst,
Mat map1,
Mat map2,
int interpolation)
Applies a generic geometrical transformation to an image.
The function remap transforms the source image using the
specified map:
dst(x,y) = src(map_x(x,y),map_y(x,y))
where values of pixels with non-integer coordinates are computed using one of
available interpolation methods.
map_x and map_y can be encoded as separate floating-point
maps in map_1 and map_2 respectively, or interleaved
floating-point maps of (x,y) in map_1, or fixed-point maps
created by using "convertMaps". The reason you might want to convert from
floating to fixed-point representations of a map is that they can yield much
faster (~2x) remapping operations. In the converted case, map_1
contains pairs (cvFloor(x), cvFloor(y)) and map_2
contains indices in a table of interpolation coefficients.
This function cannot operate in-place.
src - Source image.dst - Destination image. It has the same size as map1 and
the same type as src.map1 - The first map of either (x,y) points or just
x values having the type CV_16SC2,
CV_32FC1, or CV_32FC2. See "convertMaps" for
details on converting a floating point representation to fixed-point for
speed.map2 - The second map of y values having the type
CV_16UC1, CV_32FC1, or none (empty map if
map1 is (x,y) points), respectively.interpolation - Interpolation method (see "resize"). The method
INTER_AREA is not supported by this function.
public static void remap(Mat src,
Mat dst,
Mat map1,
Mat map2,
int interpolation,
int borderMode,
Scalar borderValue)
Applies a generic geometrical transformation to an image.
The function remap transforms the source image using the
specified map:
dst(x,y) = src(map_x(x,y),map_y(x,y))
where values of pixels with non-integer coordinates are computed using one of
available interpolation methods.
map_x and map_y can be encoded as separate floating-point
maps in map_1 and map_2 respectively, or interleaved
floating-point maps of (x,y) in map_1, or fixed-point maps
created by using "convertMaps". The reason you might want to convert from
floating to fixed-point representations of a map is that they can yield much
faster (~2x) remapping operations. In the converted case, map_1
contains pairs (cvFloor(x), cvFloor(y)) and map_2
contains indices in a table of interpolation coefficients.
This function cannot operate in-place.
src - Source image.dst - Destination image. It has the same size as map1 and
the same type as src.map1 - The first map of either (x,y) points or just
x values having the type CV_16SC2,
CV_32FC1, or CV_32FC2. See "convertMaps" for
details on converting a floating point representation to fixed-point for
speed.map2 - The second map of y values having the type
CV_16UC1, CV_32FC1, or none (empty map if
map1 is (x,y) points), respectively.interpolation - Interpolation method (see "resize"). The method
INTER_AREA is not supported by this function.borderMode - Pixel extrapolation method (see "borderInterpolate"). When
borderMode=BORDER_TRANSPARENT, it means that the pixels in the
destination image that corresponds to the "outliers" in the source image are
not modified by the function.borderValue - Value used in case of a constant border. By default, it is
0.
public static void resize(Mat src,
Mat dst,
Size dsize)
Resizes an image.
The function resize resizes the image src down to
or up to the specified size.Note that the initial dst type or
size are not taken into account. Instead, the size and type are derived from
the src,dsize,fx, and fy.
If you want to resize src so that it fits the pre-created
dst, you may call the function as follows:
// C++ code:
// explicitly specify dsize=dst.size(); fx and fy will be computed from that.
resize(src, dst, dst.size(), 0, 0, interpolation);
If you want to decimate the image by factor of 2 in each direction, you can call the function this way:
// specify fx and fy and let the function compute the destination image size.
resize(src, dst, Size(), 0.5, 0.5, interpolation);
To shrink an image, it will generally look best with CV_INTER_AREA interpolation, whereas to enlarge an image, it will generally look best with CV_INTER_CUBIC (slow) or CV_INTER_LINEAR (faster but still looks OK).
src - input image.dst - output image; it has the size dsize (when it is
non-zero) or the size computed from src.size(), fx,
and fy; the type of dst is the same as of
src.dsize - output image size; if it equals zero, it is computed as:
dsize = Size(round(fx*src.cols), round(fy*src.rows))
Either dsize or both fx and fy must be
non-zero.
warpAffine(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
remap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, int, org.opencv.core.Scalar),
warpPerspective(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar)
public static void resize(Mat src,
Mat dst,
Size dsize,
double fx,
double fy,
int interpolation)
Resizes an image.
The function resize resizes the image src down to
or up to the specified size.Note that the initial dst type or
size are not taken into account. Instead, the size and type are derived from
the src,dsize,fx, and fy.
If you want to resize src so that it fits the pre-created
dst, you may call the function as follows:
// C++ code:
// explicitly specify dsize=dst.size(); fx and fy will be computed from that.
resize(src, dst, dst.size(), 0, 0, interpolation);
If you want to decimate the image by factor of 2 in each direction, you can call the function this way:
// specify fx and fy and let the function compute the destination image size.
resize(src, dst, Size(), 0.5, 0.5, interpolation);
To shrink an image, it will generally look best with CV_INTER_AREA interpolation, whereas to enlarge an image, it will generally look best with CV_INTER_CUBIC (slow) or CV_INTER_LINEAR (faster but still looks OK).
src - input image.dst - output image; it has the size dsize (when it is
non-zero) or the size computed from src.size(), fx,
and fy; the type of dst is the same as of
src.dsize - output image size; if it equals zero, it is computed as:
dsize = Size(round(fx*src.cols), round(fy*src.rows))
Either dsize or both fx and fy must be
non-zero.
fx - scale factor along the horizontal axis; when it equals 0, it is
computed as
(double)dsize.width/src.cols
fy - scale factor along the vertical axis; when it equals 0, it is
computed as
(double)dsize.height/src.rows
interpolation - interpolation method:
INTER_NEAREST
method.
warpAffine(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
remap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, int, org.opencv.core.Scalar),
warpPerspective(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar)
public static void Scharr(Mat src,
Mat dst,
int ddepth,
int dx,
int dy)
Calculates the first x- or y- image derivative using Scharr operator.
The function computes the first x- or y- spatial image derivative using the Scharr operator. The call
Scharr(src, dst, ddepth, dx, dy, scale, delta, borderType)
is equivalent to
Sobel(src, dst, ddepth, dx, dy, CV_SCHARR, scale, delta, borderType).
src - input image.dst - output image of the same size and the same number of channels as
src.ddepth - output image depth (see "Sobel" for the list of supported
combination of src.depth() and ddepth).dx - order of the derivative x.dy - order of the derivative y.Core.cartToPolar(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, boolean)
public static void Scharr(Mat src,
Mat dst,
int ddepth,
int dx,
int dy,
double scale,
double delta)
Calculates the first x- or y- image derivative using Scharr operator.
The function computes the first x- or y- spatial image derivative using the Scharr operator. The call
Scharr(src, dst, ddepth, dx, dy, scale, delta, borderType)
is equivalent to
Sobel(src, dst, ddepth, dx, dy, CV_SCHARR, scale, delta, borderType).
src - input image.dst - output image of the same size and the same number of channels as
src.ddepth - output image depth (see "Sobel" for the list of supported
combination of src.depth() and ddepth).dx - order of the derivative x.dy - order of the derivative y.scale - optional scale factor for the computed derivative values; by
default, no scaling is applied (see "getDerivKernels" for details).delta - optional delta value that is added to the results prior to
storing them in dst.Core.cartToPolar(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, boolean)
public static void Scharr(Mat src,
Mat dst,
int ddepth,
int dx,
int dy,
double scale,
double delta,
int borderType)
Calculates the first x- or y- image derivative using Scharr operator.
The function computes the first x- or y- spatial image derivative using the Scharr operator. The call
Scharr(src, dst, ddepth, dx, dy, scale, delta, borderType)
is equivalent to
Sobel(src, dst, ddepth, dx, dy, CV_SCHARR, scale, delta, borderType).
src - input image.dst - output image of the same size and the same number of channels as
src.ddepth - output image depth (see "Sobel" for the list of supported
combination of src.depth() and ddepth).dx - order of the derivative x.dy - order of the derivative y.scale - optional scale factor for the computed derivative values; by
default, no scaling is applied (see "getDerivKernels" for details).delta - optional delta value that is added to the results prior to
storing them in dst.borderType - pixel extrapolation method (see "borderInterpolate" for
details).Core.cartToPolar(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, boolean)
public static void sepFilter2D(Mat src,
Mat dst,
int ddepth,
Mat kernelX,
Mat kernelY)
Applies a separable linear filter to an image.
The function applies a separable linear filter to the image. That is, first,
every row of src is filtered with the 1D kernel
kernelX. Then, every column of the result is filtered with the
1D kernel kernelY. The final result shifted by delta
is stored in dst.
src - Source image.dst - Destination image of the same size and the same number of channels
as src.ddepth - Destination image depth. The following combination of
src.depth() and ddepth are supported:
src.depth() = CV_8U, ddepth =
-1/CV_16S/CV_32F/CV_64F
src.depth() = CV_16U/CV_16S,
ddepth = -1/CV_32F/CV_64F
src.depth() = CV_32F, ddepth =
-1/CV_32F/CV_64F
src.depth() = CV_64F, ddepth =
-1/CV_64F
when ddepth=-1, the destination image will have the same depth
as the source.
kernelX - Coefficients for filtering each row.kernelY - Coefficients for filtering each column.GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
Sobel(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, int, double, double, int),
boxFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Size, org.opencv.core.Point, boolean, int),
blur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, int),
filter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, double, int)
public static void sepFilter2D(Mat src,
Mat dst,
int ddepth,
Mat kernelX,
Mat kernelY,
Point anchor,
double delta)
Applies a separable linear filter to an image.
The function applies a separable linear filter to the image. That is, first,
every row of src is filtered with the 1D kernel
kernelX. Then, every column of the result is filtered with the
1D kernel kernelY. The final result shifted by delta
is stored in dst.
src - Source image.dst - Destination image of the same size and the same number of channels
as src.ddepth - Destination image depth. The following combination of
src.depth() and ddepth are supported:
src.depth() = CV_8U, ddepth =
-1/CV_16S/CV_32F/CV_64F
src.depth() = CV_16U/CV_16S,
ddepth = -1/CV_32F/CV_64F
src.depth() = CV_32F, ddepth =
-1/CV_32F/CV_64F
src.depth() = CV_64F, ddepth =
-1/CV_64F
when ddepth=-1, the destination image will have the same depth
as the source.
kernelX - Coefficients for filtering each row.kernelY - Coefficients for filtering each column.anchor - Anchor position within the kernel. The default value (-1,
1) means that the anchor is at the kernel center.delta - Value added to the filtered results before storing them.GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
Sobel(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, int, double, double, int),
boxFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Size, org.opencv.core.Point, boolean, int),
blur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, int),
filter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, double, int)
public static void sepFilter2D(Mat src,
Mat dst,
int ddepth,
Mat kernelX,
Mat kernelY,
Point anchor,
double delta,
int borderType)
Applies a separable linear filter to an image.
The function applies a separable linear filter to the image. That is, first,
every row of src is filtered with the 1D kernel
kernelX. Then, every column of the result is filtered with the
1D kernel kernelY. The final result shifted by delta
is stored in dst.
src - Source image.dst - Destination image of the same size and the same number of channels
as src.ddepth - Destination image depth. The following combination of
src.depth() and ddepth are supported:
src.depth() = CV_8U, ddepth =
-1/CV_16S/CV_32F/CV_64F
src.depth() = CV_16U/CV_16S,
ddepth = -1/CV_32F/CV_64F
src.depth() = CV_32F, ddepth =
-1/CV_32F/CV_64F
src.depth() = CV_64F, ddepth =
-1/CV_64F
when ddepth=-1, the destination image will have the same depth
as the source.
kernelX - Coefficients for filtering each row.kernelY - Coefficients for filtering each column.anchor - Anchor position within the kernel. The default value (-1,
1) means that the anchor is at the kernel center.delta - Value added to the filtered results before storing them.borderType - Pixel extrapolation method. See "borderInterpolate" for
details.GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
Sobel(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, int, double, double, int),
boxFilter(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Size, org.opencv.core.Point, boolean, int),
blur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, int),
filter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, double, int)
public static void Sobel(Mat src,
Mat dst,
int ddepth,
int dx,
int dy)
Calculates the first, second, third, or mixed image derivatives using an extended Sobel operator.
In all cases except one, the ksize x<BR>ksize separable kernel
is used to calculate the derivative. When ksize = 1, the 3 x
1 or 1 x 3 kernel is used (that is, no Gaussian smoothing is
done). ksize = 1 can only be used for the first or the second x-
or y- derivatives.
There is also the special value ksize = CV_SCHARR (-1) that
corresponds to the 3x3 Scharr filter that may give more accurate
results than the 3x3 Sobel. The Scharr aperture is
|-3 0 3| |-10 0 10| |-3 0 3|
for the x-derivative, or transposed for the y-derivative.
The function calculates an image derivative by convolving the image with the appropriate kernel:
dst = (d^(xorder+yorder) src)/(dx^(xorder) dy^(yorder))
The Sobel operators combine Gaussian smoothing and differentiation, so the
result is more or less resistant to the noise. Most often, the function is
called with (xorder = 1, yorder = 0,
ksize = 3) or (xorder = 0, yorder = 1,
ksize = 3) to calculate the first x- or y- image derivative. The
first case corresponds to a kernel of:
|-1 0 1| |-2 0 2| |-1 0 1|
The second case corresponds to a kernel of:
|-1 -2 -1| |0 0 0| |1 2 1|
src - input image.dst - output image of the same size and the same number of channels as
src.ddepth - output image depth; the following combinations of
src.depth() and ddepth are supported:
src.depth() = CV_8U, ddepth =
-1/CV_16S/CV_32F/CV_64F
src.depth() = CV_16U/CV_16S,
ddepth = -1/CV_32F/CV_64F
src.depth() = CV_32F, ddepth =
-1/CV_32F/CV_64F
src.depth() = CV_64F, ddepth =
-1/CV_64F
when ddepth=-1, the destination image will have the same depth
as the source; in the case of 8-bit input images it will result in truncated
derivatives.
dx - a dxdy - a dyGaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
Core.cartToPolar(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, boolean),
sepFilter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, double, int),
Laplacian(org.opencv.core.Mat, org.opencv.core.Mat, int, int, double, double, int),
Scharr(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, double, double, int),
filter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, double, int)
public static void Sobel(Mat src,
Mat dst,
int ddepth,
int dx,
int dy,
int ksize,
double scale,
double delta)
Calculates the first, second, third, or mixed image derivatives using an extended Sobel operator.
In all cases except one, the ksize x<BR>ksize separable kernel
is used to calculate the derivative. When ksize = 1, the 3 x
1 or 1 x 3 kernel is used (that is, no Gaussian smoothing is
done). ksize = 1 can only be used for the first or the second x-
or y- derivatives.
There is also the special value ksize = CV_SCHARR (-1) that
corresponds to the 3x3 Scharr filter that may give more accurate
results than the 3x3 Sobel. The Scharr aperture is
|-3 0 3| |-10 0 10| |-3 0 3|
for the x-derivative, or transposed for the y-derivative.
The function calculates an image derivative by convolving the image with the appropriate kernel:
dst = (d^(xorder+yorder) src)/(dx^(xorder) dy^(yorder))
The Sobel operators combine Gaussian smoothing and differentiation, so the
result is more or less resistant to the noise. Most often, the function is
called with (xorder = 1, yorder = 0,
ksize = 3) or (xorder = 0, yorder = 1,
ksize = 3) to calculate the first x- or y- image derivative. The
first case corresponds to a kernel of:
|-1 0 1| |-2 0 2| |-1 0 1|
The second case corresponds to a kernel of:
|-1 -2 -1| |0 0 0| |1 2 1|
src - input image.dst - output image of the same size and the same number of channels as
src.ddepth - output image depth; the following combinations of
src.depth() and ddepth are supported:
src.depth() = CV_8U, ddepth =
-1/CV_16S/CV_32F/CV_64F
src.depth() = CV_16U/CV_16S,
ddepth = -1/CV_32F/CV_64F
src.depth() = CV_32F, ddepth =
-1/CV_32F/CV_64F
src.depth() = CV_64F, ddepth =
-1/CV_64F
when ddepth=-1, the destination image will have the same depth
as the source; in the case of 8-bit input images it will result in truncated
derivatives.
dx - a dxdy - a dyksize - size of the extended Sobel kernel; it must be 1, 3, 5, or 7.scale - optional scale factor for the computed derivative values; by
default, no scaling is applied (see "getDerivKernels" for details).delta - optional delta value that is added to the results prior to
storing them in dst.GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
Core.cartToPolar(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, boolean),
sepFilter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, double, int),
Laplacian(org.opencv.core.Mat, org.opencv.core.Mat, int, int, double, double, int),
Scharr(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, double, double, int),
filter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, double, int)
public static void Sobel(Mat src,
Mat dst,
int ddepth,
int dx,
int dy,
int ksize,
double scale,
double delta,
int borderType)
Calculates the first, second, third, or mixed image derivatives using an extended Sobel operator.
In all cases except one, the ksize x<BR>ksize separable kernel
is used to calculate the derivative. When ksize = 1, the 3 x
1 or 1 x 3 kernel is used (that is, no Gaussian smoothing is
done). ksize = 1 can only be used for the first or the second x-
or y- derivatives.
There is also the special value ksize = CV_SCHARR (-1) that
corresponds to the 3x3 Scharr filter that may give more accurate
results than the 3x3 Sobel. The Scharr aperture is
|-3 0 3| |-10 0 10| |-3 0 3|
for the x-derivative, or transposed for the y-derivative.
The function calculates an image derivative by convolving the image with the appropriate kernel:
dst = (d^(xorder+yorder) src)/(dx^(xorder) dy^(yorder))
The Sobel operators combine Gaussian smoothing and differentiation, so the
result is more or less resistant to the noise. Most often, the function is
called with (xorder = 1, yorder = 0,
ksize = 3) or (xorder = 0, yorder = 1,
ksize = 3) to calculate the first x- or y- image derivative. The
first case corresponds to a kernel of:
|-1 0 1| |-2 0 2| |-1 0 1|
The second case corresponds to a kernel of:
|-1 -2 -1| |0 0 0| |1 2 1|
src - input image.dst - output image of the same size and the same number of channels as
src.ddepth - output image depth; the following combinations of
src.depth() and ddepth are supported:
src.depth() = CV_8U, ddepth =
-1/CV_16S/CV_32F/CV_64F
src.depth() = CV_16U/CV_16S,
ddepth = -1/CV_32F/CV_64F
src.depth() = CV_32F, ddepth =
-1/CV_32F/CV_64F
src.depth() = CV_64F, ddepth =
-1/CV_64F
when ddepth=-1, the destination image will have the same depth
as the source; in the case of 8-bit input images it will result in truncated
derivatives.
dx - a dxdy - a dyksize - size of the extended Sobel kernel; it must be 1, 3, 5, or 7.scale - optional scale factor for the computed derivative values; by
default, no scaling is applied (see "getDerivKernels" for details).delta - optional delta value that is added to the results prior to
storing them in dst.borderType - pixel extrapolation method (see "borderInterpolate" for
details).GaussianBlur(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
Core.cartToPolar(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, boolean),
sepFilter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Point, double, int),
Laplacian(org.opencv.core.Mat, org.opencv.core.Mat, int, int, double, double, int),
Scharr(org.opencv.core.Mat, org.opencv.core.Mat, int, int, int, double, double, int),
filter2D(org.opencv.core.Mat, org.opencv.core.Mat, int, org.opencv.core.Mat, org.opencv.core.Point, double, int)
public static double threshold(Mat src,
Mat dst,
double thresh,
double maxval,
int type)
Applies a fixed-level threshold to each array element.
The function applies fixed-level thresholding to a single-channel array. The
function is typically used to get a bi-level (binary) image out of a
grayscale image ("compare" could be also used for this purpose) or for
removing a noise, that is, filtering out pixels with too small or too large
values. There are several types of thresholding supported by the function.
They are determined by type :
dst(x,y) = maxval if src(x,y) > thresh; 0 otherwise
dst(x,y) = 0 if src(x,y) > thresh; maxval otherwise
dst(x,y) = threshold if src(x,y) > thresh; src(x,y) otherwise
dst(x,y) = src(x,y) if src(x,y) > thresh; 0 otherwise
dst(x,y) = 0 if src(x,y) > thresh; src(x,y) otherwise
Also, the special value THRESH_OTSU may be combined with one of
the above values. In this case, the function determines the optimal threshold
value using the Otsu's algorithm and uses it instead of the specified
thresh.
The function returns the computed threshold value.
Currently, the Otsu's method is implemented only for 8-bit images.
src - input array (single-channel, 8-bit or 32-bit floating point).dst - output array of the same size and type as src.thresh - threshold value.maxval - maximum value to use with the THRESH_BINARY and
THRESH_BINARY_INV thresholding types.type - thresholding type (see the details below).findContours(org.opencv.core.Mat, java.util.List, org.opencv.core.Mat, int, int, org.opencv.core.Point) ,
Core.max(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
adaptiveThreshold(org.opencv.core.Mat, org.opencv.core.Mat, double, int, int, int, double),
Core.compare(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int),
Core.min(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void undistort(Mat src,
Mat dst,
Mat cameraMatrix,
Mat distCoeffs)
Transforms an image to compensate for lens distortion.
The function transforms an image to compensate radial and tangential lens distortion.
The function is simply a combination of "initUndistortRectifyMap" (with unity
R) and "remap" (with bilinear interpolation). See the former
function for details of the transformation being performed.
Those pixels in the destination image, for which there is no correspondent pixels in the source image, are filled with zeros (black color).
A particular subset of the source image that will be visible in the corrected
image can be regulated by newCameraMatrix. You can use
"getOptimalNewCameraMatrix" to compute the appropriate newCameraMatrix
depending on your requirements.
The camera matrix and the distortion parameters can be determined using "calibrateCamera". If the resolution of images is different from the resolution used at the calibration stage, f_x, f_y, c_x and c_y need to be scaled accordingly, while the distortion coefficients remain the same.
src - Input (distorted) image.dst - Output (corrected) image that has the same size and type as
src.cameraMatrix - Input camera matrix A =
|f_x 0 c_x| |0 f_y c_y| |0 0 1|
.distCoeffs - Input vector of distortion coefficients (k_1, k_2, p_1,
p_2[, k_3[, k_4, k_5, k_6]]) of 4, 5, or 8 elements. If the vector is
NULL/empty, the zero distortion coefficients are assumed.
public static void undistort(Mat src,
Mat dst,
Mat cameraMatrix,
Mat distCoeffs,
Mat newCameraMatrix)
Transforms an image to compensate for lens distortion.
The function transforms an image to compensate radial and tangential lens distortion.
The function is simply a combination of "initUndistortRectifyMap" (with unity
R) and "remap" (with bilinear interpolation). See the former
function for details of the transformation being performed.
Those pixels in the destination image, for which there is no correspondent pixels in the source image, are filled with zeros (black color).
A particular subset of the source image that will be visible in the corrected
image can be regulated by newCameraMatrix. You can use
"getOptimalNewCameraMatrix" to compute the appropriate newCameraMatrix
depending on your requirements.
The camera matrix and the distortion parameters can be determined using "calibrateCamera". If the resolution of images is different from the resolution used at the calibration stage, f_x, f_y, c_x and c_y need to be scaled accordingly, while the distortion coefficients remain the same.
src - Input (distorted) image.dst - Output (corrected) image that has the same size and type as
src.cameraMatrix - Input camera matrix A =
|f_x 0 c_x| |0 f_y c_y| |0 0 1|
.distCoeffs - Input vector of distortion coefficients (k_1, k_2, p_1,
p_2[, k_3[, k_4, k_5, k_6]]) of 4, 5, or 8 elements. If the vector is
NULL/empty, the zero distortion coefficients are assumed.newCameraMatrix - Camera matrix of the distorted image. By default, it
is the same as cameraMatrix but you may additionally scale and
shift the result by using a different matrix.
public static void undistortPoints(MatOfPoint2f src,
MatOfPoint2f dst,
Mat cameraMatrix,
Mat distCoeffs)
Computes the ideal point coordinates from the observed point coordinates.
The function is similar to "undistort" and "initUndistortRectifyMap" but it
operates on a sparse set of points instead of a raster image. Also the
function performs a reverse transformation to"projectPoints". In case of a 3D
object, it does not reconstruct its 3D coordinates, but for a planar object,
it does, up to a translation vector, if the proper R is
specified.
// C++ code:
// (u,v) is the input point, (u', v') is the output point
// camera_matrix=[fx 0 cx; 0 fy cy; 0 0 1]
// P=[fx' 0 cx' tx; 0 fy' cy' ty; 0 0 1 tz]
x" = (u - cx)/fx
y" = (v - cy)/fy
(x',y') = undistort(x",y",dist_coeffs)
[X,Y,W]T = R*[x' y' 1]T
x = X/W, y = Y/W
// only performed if P=[fx' 0 cx' [tx]; 0 fy' cy' [ty]; 0 0 1 [tz]] is specified
u' = x*fx' + cx'
v' = y*fy' + cy',
where undistort() is an approximate iterative algorithm that
estimates the normalized original point coordinates out of the normalized
distorted point coordinates ("normalized" means that the coordinates do not
depend on the camera matrix).
The function can be used for both a stereo camera head or a monocular camera (when R is empty).
src - Observed point coordinates, 1xN or Nx1 2-channel (CV_32FC2 or
CV_64FC2).dst - Output ideal point coordinates after undistortion and reverse
perspective transformation. If matrix P is identity or omitted,
dst will contain normalized point coordinates.cameraMatrix - Camera matrix
|f_x 0 c_x| |0 f_y c_y| |0 0 1|
.distCoeffs - Input vector of distortion coefficients (k_1, k_2, p_1,
p_2[, k_3[, k_4, k_5, k_6]]) of 4, 5, or 8 elements. If the vector is
NULL/empty, the zero distortion coefficients are assumed.
public static void undistortPoints(MatOfPoint2f src,
MatOfPoint2f dst,
Mat cameraMatrix,
Mat distCoeffs,
Mat R,
Mat P)
Computes the ideal point coordinates from the observed point coordinates.
The function is similar to "undistort" and "initUndistortRectifyMap" but it
operates on a sparse set of points instead of a raster image. Also the
function performs a reverse transformation to"projectPoints". In case of a 3D
object, it does not reconstruct its 3D coordinates, but for a planar object,
it does, up to a translation vector, if the proper R is
specified.
// C++ code:
// (u,v) is the input point, (u', v') is the output point
// camera_matrix=[fx 0 cx; 0 fy cy; 0 0 1]
// P=[fx' 0 cx' tx; 0 fy' cy' ty; 0 0 1 tz]
x" = (u - cx)/fx
y" = (v - cy)/fy
(x',y') = undistort(x",y",dist_coeffs)
[X,Y,W]T = R*[x' y' 1]T
x = X/W, y = Y/W
// only performed if P=[fx' 0 cx' [tx]; 0 fy' cy' [ty]; 0 0 1 [tz]] is specified
u' = x*fx' + cx'
v' = y*fy' + cy',
where undistort() is an approximate iterative algorithm that
estimates the normalized original point coordinates out of the normalized
distorted point coordinates ("normalized" means that the coordinates do not
depend on the camera matrix).
The function can be used for both a stereo camera head or a monocular camera (when R is empty).
src - Observed point coordinates, 1xN or Nx1 2-channel (CV_32FC2 or
CV_64FC2).dst - Output ideal point coordinates after undistortion and reverse
perspective transformation. If matrix P is identity or omitted,
dst will contain normalized point coordinates.cameraMatrix - Camera matrix
|f_x 0 c_x| |0 f_y c_y| |0 0 1|
.distCoeffs - Input vector of distortion coefficients (k_1, k_2, p_1,
p_2[, k_3[, k_4, k_5, k_6]]) of 4, 5, or 8 elements. If the vector is
NULL/empty, the zero distortion coefficients are assumed.R - Rectification transformation in the object space (3x3 matrix).
R1 or R2 computed by "stereoRectify" can be passed
here. If the matrix is empty, the identity transformation is used.P - New camera matrix (3x3) or new projection matrix (3x4).
P1 or P2 computed by "stereoRectify" can be passed
here. If the matrix is empty, the identity new camera matrix is used.
public static void warpAffine(Mat src,
Mat dst,
Mat M,
Size dsize)
Applies an affine transformation to an image.
The function warpAffine transforms the source image using the
specified matrix:
dst(x,y) = src(M _11 x + M _12 y + M _13, M _21 x + M _22 y + M _23)
when the flag WARP_INVERSE_MAP is set. Otherwise, the
transformation is first inverted with "invertAffineTransform" and then put in
the formula above instead of M.
The function cannot operate in-place.
Note: cvGetQuadrangleSubPix is similar to cvWarpAffine,
but the outliers are extrapolated using replication border mode.
src - input image.dst - output image that has the size dsize and the same
type as src.M - 2x 3 transformation matrix.dsize - size of the output image.remap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, int, org.opencv.core.Scalar),
warpPerspective(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
getRectSubPix(org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, org.opencv.core.Mat, int),
resize(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
Core.transform(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void warpAffine(Mat src,
Mat dst,
Mat M,
Size dsize,
int flags)
Applies an affine transformation to an image.
The function warpAffine transforms the source image using the
specified matrix:
dst(x,y) = src(M _11 x + M _12 y + M _13, M _21 x + M _22 y + M _23)
when the flag WARP_INVERSE_MAP is set. Otherwise, the
transformation is first inverted with "invertAffineTransform" and then put in
the formula above instead of M.
The function cannot operate in-place.
Note: cvGetQuadrangleSubPix is similar to cvWarpAffine,
but the outliers are extrapolated using replication border mode.
src - input image.dst - output image that has the size dsize and the same
type as src.M - 2x 3 transformation matrix.dsize - size of the output image.flags - combination of interpolation methods (see "resize") and the
optional flag WARP_INVERSE_MAP that means that M is
the inverse transformation (dst->src).remap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, int, org.opencv.core.Scalar),
warpPerspective(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
getRectSubPix(org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, org.opencv.core.Mat, int),
resize(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
Core.transform(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void warpAffine(Mat src,
Mat dst,
Mat M,
Size dsize,
int flags,
int borderMode,
Scalar borderValue)
Applies an affine transformation to an image.
The function warpAffine transforms the source image using the
specified matrix:
dst(x,y) = src(M _11 x + M _12 y + M _13, M _21 x + M _22 y + M _23)
when the flag WARP_INVERSE_MAP is set. Otherwise, the
transformation is first inverted with "invertAffineTransform" and then put in
the formula above instead of M.
The function cannot operate in-place.
Note: cvGetQuadrangleSubPix is similar to cvWarpAffine,
but the outliers are extrapolated using replication border mode.
src - input image.dst - output image that has the size dsize and the same
type as src.M - 2x 3 transformation matrix.dsize - size of the output image.flags - combination of interpolation methods (see "resize") and the
optional flag WARP_INVERSE_MAP that means that M is
the inverse transformation (dst->src).borderMode - pixel extrapolation method (see "borderInterpolate"); when
borderMode=BORDER_TRANSPARENT, it means that the pixels in the
destination image corresponding to the "outliers" in the source image are not
modified by the function.borderValue - value used in case of a constant border; by default, it is
0.remap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, int, org.opencv.core.Scalar),
warpPerspective(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
getRectSubPix(org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, org.opencv.core.Mat, int),
resize(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int),
Core.transform(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat)
public static void warpPerspective(Mat src,
Mat dst,
Mat M,
Size dsize)
Applies a perspective transformation to an image.
The function warpPerspective transforms the source image using
the specified matrix:
dst(x,y) = src((M_11 x + M_12 y + M_13)/(M_(31) x + M_32 y + M_33),<BR>(M_21 x + M_22 y + M_23)/(M_(31) x + M_32 y + M_33))
when the flag WARP_INVERSE_MAP is set. Otherwise, the
transformation is first inverted with "invert" and then put in the formula
above instead of M.
The function cannot operate in-place.
src - input image.dst - output image that has the size dsize and the same
type as src.M - 3x 3 transformation matrix.dsize - size of the output image.warpAffine(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
remap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, int, org.opencv.core.Scalar),
Core.perspectiveTransform(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
getRectSubPix(org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, org.opencv.core.Mat, int),
resize(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int)
public static void warpPerspective(Mat src,
Mat dst,
Mat M,
Size dsize,
int flags)
Applies a perspective transformation to an image.
The function warpPerspective transforms the source image using
the specified matrix:
dst(x,y) = src((M_11 x + M_12 y + M_13)/(M_(31) x + M_32 y + M_33),<BR>(M_21 x + M_22 y + M_23)/(M_(31) x + M_32 y + M_33))
when the flag WARP_INVERSE_MAP is set. Otherwise, the
transformation is first inverted with "invert" and then put in the formula
above instead of M.
The function cannot operate in-place.
src - input image.dst - output image that has the size dsize and the same
type as src.M - 3x 3 transformation matrix.dsize - size of the output image.flags - combination of interpolation methods (INTER_LINEAR
or INTER_NEAREST) and the optional flag WARP_INVERSE_MAP,
that sets M as the inverse transformation (dst->src).warpAffine(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
remap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, int, org.opencv.core.Scalar),
Core.perspectiveTransform(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
getRectSubPix(org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, org.opencv.core.Mat, int),
resize(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int)
public static void warpPerspective(Mat src,
Mat dst,
Mat M,
Size dsize,
int flags,
int borderMode,
Scalar borderValue)
Applies a perspective transformation to an image.
The function warpPerspective transforms the source image using
the specified matrix:
dst(x,y) = src((M_11 x + M_12 y + M_13)/(M_(31) x + M_32 y + M_33),<BR>(M_21 x + M_22 y + M_23)/(M_(31) x + M_32 y + M_33))
when the flag WARP_INVERSE_MAP is set. Otherwise, the
transformation is first inverted with "invert" and then put in the formula
above instead of M.
The function cannot operate in-place.
src - input image.dst - output image that has the size dsize and the same
type as src.M - 3x 3 transformation matrix.dsize - size of the output image.flags - combination of interpolation methods (INTER_LINEAR
or INTER_NEAREST) and the optional flag WARP_INVERSE_MAP,
that sets M as the inverse transformation (dst->src).borderMode - pixel extrapolation method (BORDER_CONSTANT or
BORDER_REPLICATE).borderValue - value used in case of a constant border; by default, it
equals 0.warpAffine(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, int, int, org.opencv.core.Scalar),
remap(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat, int, int, org.opencv.core.Scalar),
Core.perspectiveTransform(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Mat),
getRectSubPix(org.opencv.core.Mat, org.opencv.core.Size, org.opencv.core.Point, org.opencv.core.Mat, int),
resize(org.opencv.core.Mat, org.opencv.core.Mat, org.opencv.core.Size, double, double, int)
public static void watershed(Mat image,
Mat markers)
Performs a marker-based image segmentation using the watershed algorithm.
The function implements one of the variants of watershed, non-parametric marker-based segmentation algorithm, described in [Meyer92].
Before passing the image to the function, you have to roughly outline the
desired regions in the image markers with positive
(>0) indices. So, every region is represented as one or more
connected components with the pixel values 1, 2, 3, and so on. Such markers
can be retrieved from a binary mask using "findContours" and "drawContours"
(see the watershed.cpp demo). The markers are "seeds" of the
future image regions. All the other pixels in markers, whose
relation to the outlined regions is not known and should be defined by the
algorithm, should be set to 0's. In the function output, each pixel in
markers is set to a value of the "seed" components or to -1 at boundaries
between the regions.
Visual demonstration and usage example of the function can be found in the
OpenCV samples directory (see the watershed.cpp demo).
Note: Any two neighbor connected components are not necessarily separated by a watershed boundary (-1's pixels); for example, they can touch each other in the initial marker image passed to the function.
image - Input 8-bit 3-channel image.markers - Input/output 32-bit single-channel image (map) of markers. It
should have the same size as image.findContours(org.opencv.core.Mat, java.util.List, org.opencv.core.Mat, int, int, org.opencv.core.Point)
|
OpenCV 2.4.4 Documentation | |||||||
| PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||
| SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD | |||||||