cv::ximgproc Namespace Reference

Namespaces
namespace	rl
namespace	segmentation

Classes
class	AdaptiveManifoldFilter
	Interface for Adaptive Manifold Filter realizations. More...
struct	Box
class	ContourFitting
	Class for ContourFitting algorithms. ContourFitting match two contours \( z_a \) and \( z_b \) minimizing distance. More...
class	DisparityFilter
	Main interface for all disparity map filters. More...
class	DisparityWLSFilter
	Disparity map filter based on Weighted Least Squares filter (in form of Fast Global Smoother that is a lot faster than traditional Weighted Least Squares filter implementations) and optional use of left-right-consistency-based confidence to refine the results in half-occlusions and uniform areas. More...
class	DTFilter
	Interface for realizations of Domain Transform filter. More...
class	EdgeAwareInterpolator
	Sparse match interpolation algorithm based on modified locally-weighted affine estimator from [226] and Fast Global Smoother as post-processing filter. More...
class	EdgeBoxes
	Class implementing EdgeBoxes algorithm from [324] : More...
class	EdgeDrawing
	Class implementing the ED (EdgeDrawing) [273], EDLines [4], EDPF [5] and EDCircles [6] algorithms. More...
class	FastBilateralSolverFilter
	Interface for implementations of Fast Bilateral Solver. More...
class	FastGlobalSmootherFilter
	Interface for implementations of Fast Global Smoother filter. More...
class	FastLineDetector
	Class implementing the FLD (Fast Line Detector) algorithm described in [156] . More...
class	GuidedFilter
	Interface for realizations of (Fast) Guided Filter. More...
class	RFFeatureGetter
class	RICInterpolator
	Sparse match interpolation algorithm based on modified piecewise locally-weighted affine estimator called Robust Interpolation method of Correspondences or RIC from [130] and Variational and Fast Global Smoother as post-processing filter. The RICInterpolator is a extension of the EdgeAwareInterpolator. Main concept of this extension is an piece-wise affine model based on over-segmentation via SLIC superpixel estimation. The method contains an efficient propagation mechanism to estimate among the pieces-wise models. More...
class	RidgeDetectionFilter
	Applies Ridge Detection Filter to an input image. Implements Ridge detection similar to the one in Mathematica using the eigen values from the Hessian Matrix of the input image using Sobel Derivatives. Additional refinement can be done using Skeletonization and Binarization. Adapted from [79] and [187]. More...
class	ScanSegment
	Class implementing the F-DBSCAN (Accelerated superpixel image segmentation with a parallelized DBSCAN algorithm) superpixels algorithm by Loke SC, et al. [171] for original paper. More...
class	SparseMatchInterpolator
	Main interface for all filters, that take sparse matches as an input and produce a dense per-pixel matching (optical flow) as an output. More...
class	StructuredEdgeDetection
	Class implementing edge detection algorithm from [70] : More...
class	SuperpixelLSC
	Class implementing the LSC (Linear Spectral Clustering) superpixels algorithm described in [161]. More...
class	SuperpixelSEEDS
	Class implementing the SEEDS (Superpixels Extracted via Energy-Driven Sampling) superpixels algorithm described in [283] . More...
class	SuperpixelSLIC
	Class implementing the SLIC (Simple Linear Iterative Clustering) superpixels algorithm described in [1]. More...

Typedefs
typedef std::vector< Box >	Boxes

Enumerations
enum	AngleRangeOption {   ARO_0_45 = 0 ,   ARO_45_90 = 1 ,   ARO_90_135 = 2 ,   ARO_315_0 = 3 ,   ARO_315_45 = 4 ,   ARO_45_135 = 5 ,   ARO_315_135 = 6 ,   ARO_CTR_HOR = 7 ,   ARO_CTR_VER = 8 }
	Specifies the part of Hough space to calculate. More...
enum	EdgeAwareFiltersList {   DTF_NC ,   DTF_IC ,   DTF_RF ,   GUIDED_FILTER ,   AM_FILTER }
enum	HoughDeskewOption {   HDO_RAW = 0 ,   HDO_DESKEW = 1 }
	Specifies to do or not to do skewing of Hough transform image. More...
enum	HoughOp {   FHT_MIN = 0 ,   FHT_MAX = 1 ,   FHT_ADD = 2 ,   FHT_AVE = 3 }
	Specifies binary operations. More...
enum	LocalBinarizationMethods {   BINARIZATION_NIBLACK = 0 ,   BINARIZATION_SAUVOLA = 1 ,   BINARIZATION_WOLF = 2 ,   BINARIZATION_NICK = 3 }
	Specifies the binarization method to use in cv::ximgproc::niBlackThreshold. More...
enum	RulesOption {   RO_STRICT = 0x00 ,   RO_IGNORE_BORDERS = 0x01 }
	Specifies the degree of rules validation. More...
enum	SLICType {   SLIC = 100 ,   SLICO = 101 ,   MSLIC = 102 }
enum	ThinningTypes {   THINNING_ZHANGSUEN = 0 ,   THINNING_GUOHALL = 1 }
enum	WMFWeightType {   WMF_EXP = 1 ,   WMF_IV1 = 1 << 1 ,   WMF_IV2 = 1 << 2 ,   WMF_COS = 1 << 3 ,   WMF_JAC = 1 << 4 ,   WMF_OFF = 1 << 5 }
	Specifies weight types of weighted median filter. More...

Functions
void	amFilter (InputArray joint, InputArray src, OutputArray dst, double sigma_s, double sigma_r, bool adjust_outliers=false)
	Simple one-line Adaptive Manifold Filter call.
void	anisotropicDiffusion (InputArray src, OutputArray dst, float alpha, float K, int niters)
	Performs anisotropic diffusion on an image.
void	bilateralTextureFilter (InputArray src, OutputArray dst, int fr=3, int numIter=1, double sigmaAlpha=-1., double sigmaAvg=-1.)
	Applies the bilateral texture filter to an image. It performs structure-preserving texture filter. For more details about this filter see [56].
void	BrightEdges (Mat &_original, Mat &_edgeview, int contrast=1, int shortrange=3, int longrange=9)
void	colorMatchTemplate (InputArray img, InputArray templ, OutputArray result)
	Compares a color template against overlapped color image regions.
double	computeBadPixelPercent (InputArray GT, InputArray src, Rect ROI, int thresh=24)
	Function for computing the percent of "bad" pixels in the disparity map (pixels where error is higher than a specified threshold)
double	computeMSE (InputArray GT, InputArray src, Rect ROI)
	Function for computing mean square error for disparity maps.
void	contourSampling (InputArray src, OutputArray out, int nbElt)
	Contour sampling .
void	covarianceEstimation (InputArray src, OutputArray dst, int windowRows, int windowCols)
	Computes the estimated covariance matrix of an image using the sliding window forumlation.
Ptr< AdaptiveManifoldFilter >	createAMFilter (double sigma_s, double sigma_r, bool adjust_outliers=false)
	Factory method, create instance of AdaptiveManifoldFilter and produce some initialization routines.
Ptr< ContourFitting >	createContourFitting (int ctr=1024, int fd=16)
	create ContourFitting algorithm object
Ptr< DisparityWLSFilter >	createDisparityWLSFilter (Ptr< StereoMatcher > matcher_left)
	Convenience factory method that creates an instance of DisparityWLSFilter and sets up all the relevant filter parameters automatically based on the matcher instance. Currently supports only StereoBM and StereoSGBM.
Ptr< DisparityWLSFilter >	createDisparityWLSFilterGeneric (bool use_confidence)
	More generic factory method, create instance of DisparityWLSFilter and execute basic initialization routines. When using this method you will need to set-up the ROI, matchers and other parameters by yourself.
Ptr< DTFilter >	createDTFilter (InputArray guide, double sigmaSpatial, double sigmaColor, int mode=DTF_NC, int numIters=3)
	Factory method, create instance of DTFilter and produce initialization routines.
Ptr< EdgeAwareInterpolator >	createEdgeAwareInterpolator ()
	Factory method that creates an instance of the EdgeAwareInterpolator.
Ptr< EdgeBoxes >	createEdgeBoxes (float alpha=0.65f, float beta=0.75f, float eta=1, float minScore=0.01f, int maxBoxes=10000, float edgeMinMag=0.1f, float edgeMergeThr=0.5f, float clusterMinMag=0.5f, float maxAspectRatio=3, float minBoxArea=1000, float gamma=2, float kappa=1.5f)
	Creates a Edgeboxes.
Ptr< EdgeDrawing >	createEdgeDrawing ()
	Creates a smart pointer to a EdgeDrawing object and initializes it.
Ptr< FastBilateralSolverFilter >	createFastBilateralSolverFilter (InputArray guide, double sigma_spatial, double sigma_luma, double sigma_chroma, double lambda=128.0, int num_iter=25, double max_tol=1e-5)
	Factory method, create instance of FastBilateralSolverFilter and execute the initialization routines.
Ptr< FastGlobalSmootherFilter >	createFastGlobalSmootherFilter (InputArray guide, double lambda, double sigma_color, double lambda_attenuation=0.25, int num_iter=3)
	Factory method, create instance of FastGlobalSmootherFilter and execute the initialization routines.
Ptr< FastLineDetector >	createFastLineDetector (int length_threshold=10, float distance_threshold=1.414213562f, double canny_th1=50.0, double canny_th2=50.0, int canny_aperture_size=3, bool do_merge=false)
	Creates a smart pointer to a FastLineDetector object and initializes it.
Ptr< GuidedFilter >	createGuidedFilter (InputArray guide, int radius, double eps, double scale=1.0)
	Factory method, create instance of GuidedFilter and produce initialization routines.
void	createQuaternionImage (InputArray img, OutputArray qimg)
	creates a quaternion image.
Ptr< RFFeatureGetter >	createRFFeatureGetter ()
Ptr< RICInterpolator >	createRICInterpolator ()
	Factory method that creates an instance of the RICInterpolator.
Ptr< StereoMatcher >	createRightMatcher (Ptr< StereoMatcher > matcher_left)
	Convenience method to set up the matcher for computing the right-view disparity map that is required in case of filtering with confidence.
cv::Ptr< ScanSegment >	createScanSegment (int image_width, int image_height, int num_superpixels, int slices=8, bool merge_small=true)
	Initializes a ScanSegment object.
Ptr< StructuredEdgeDetection >	createStructuredEdgeDetection (const String &model, Ptr< const RFFeatureGetter > howToGetFeatures=Ptr< RFFeatureGetter >())
Ptr< SuperpixelLSC >	createSuperpixelLSC (InputArray image, int region_size=10, float ratio=0.075f)
	Class implementing the LSC (Linear Spectral Clustering) superpixels.
Ptr< SuperpixelSEEDS >	createSuperpixelSEEDS (int image_width, int image_height, int image_channels, int num_superpixels, int num_levels, int prior=2, int histogram_bins=5, bool double_step=false)
	Initializes a SuperpixelSEEDS object.
Ptr< SuperpixelSLIC >	createSuperpixelSLIC (InputArray image, int algorithm=SLICO, int region_size=10, float ruler=10.0f)
	Initialize a SuperpixelSLIC object.
void	dtFilter (InputArray guide, InputArray src, OutputArray dst, double sigmaSpatial, double sigmaColor, int mode=DTF_NC, int numIters=3)
	Simple one-line Domain Transform filter call. If you have multiple images to filter with the same guided image then use DTFilter interface to avoid extra computations on initialization stage.
void	edgePreservingFilter (InputArray src, OutputArray dst, int d, double threshold)
	Smoothes an image using the Edge-Preserving filter.
void	fastBilateralSolverFilter (InputArray guide, InputArray src, InputArray confidence, OutputArray dst, double sigma_spatial=8, double sigma_luma=8, double sigma_chroma=8, double lambda=128.0, int num_iter=25, double max_tol=1e-5)
	Simple one-line Fast Bilateral Solver filter call. If you have multiple images to filter with the same guide then use FastBilateralSolverFilter interface to avoid extra computations.
void	fastGlobalSmootherFilter (InputArray guide, InputArray src, OutputArray dst, double lambda, double sigma_color, double lambda_attenuation=0.25, int num_iter=3)
	Simple one-line Fast Global Smoother filter call. If you have multiple images to filter with the same guide then use FastGlobalSmootherFilter interface to avoid extra computations.
void	FastHoughTransform (InputArray src, OutputArray dst, int dstMatDepth, int angleRange=ARO_315_135, int op=FHT_ADD, int makeSkew=HDO_DESKEW)
	Calculates 2D Fast Hough transform of an image.
void	findEllipses (InputArray image, OutputArray ellipses, float scoreThreshold=0.7f, float reliabilityThreshold=0.5f, float centerDistanceThreshold=0.05f)
	Finds ellipses fastly in an image using projective invariant pruning.
void	fourierDescriptor (InputArray src, OutputArray dst, int nbElt=-1, int nbFD=-1)
	Fourier descriptors for planed closed curves.
void	getDisparityVis (InputArray src, OutputArray dst, double scale=1.0)
	Function for creating a disparity map visualization (clamped CV_8U image)
void	GradientDericheX (InputArray op, OutputArray dst, double alpha, double omega)
	Applies X Deriche filter to an image.
void	GradientDericheY (InputArray op, OutputArray dst, double alpha, double omega)
	Applies Y Deriche filter to an image.
void	GradientPaillouX (InputArray op, OutputArray _dst, double alpha, double omega)
void	GradientPaillouY (InputArray op, OutputArray _dst, double alpha, double omega)
	Applies Paillou filter to an image.
void	guidedFilter (InputArray guide, InputArray src, OutputArray dst, int radius, double eps, int dDepth=-1, double scale=1.0)
	Simple one-line (Fast) Guided Filter call.
Vec4i	HoughPoint2Line (const Point &houghPoint, InputArray srcImgInfo, int angleRange=ARO_315_135, int makeSkew=HDO_DESKEW, int rules=RO_IGNORE_BORDERS)
	Calculates coordinates of line segment corresponded by point in Hough space.
void	jointBilateralFilter (InputArray joint, InputArray src, OutputArray dst, int d, double sigmaColor, double sigmaSpace, int borderType=BORDER_DEFAULT)
	Applies the joint bilateral filter to an image.
void	l0Smooth (InputArray src, OutputArray dst, double lambda=0.02, double kappa=2.0)
	Global image smoothing via L0 gradient minimization.
void	niBlackThreshold (InputArray _src, OutputArray _dst, double maxValue, int type, int blockSize, double k, int binarizationMethod=BINARIZATION_NIBLACK, double r=128)
	Performs thresholding on input images using Niblack's technique or some of the popular variations it inspired.
Matx23d	PeiLinNormalization (InputArray I)
	Calculates an affine transformation that normalize given image using Pei&Lin Normalization.
void	PeiLinNormalization (InputArray I, OutputArray T)
void	qconj (InputArray qimg, OutputArray qcimg)
	calculates conjugate of a quaternion image.
void	qdft (InputArray img, OutputArray qimg, int flags, bool sideLeft)
	Performs a forward or inverse Discrete quaternion Fourier transform of a 2D quaternion array.
void	qmultiply (InputArray src1, InputArray src2, OutputArray dst)
	Calculates the per-element quaternion product of two arrays.
void	qunitary (InputArray qimg, OutputArray qnimg)
	divides each element by its modulus.
void	RadonTransform (InputArray src, OutputArray dst, double theta=1, double start_angle=0, double end_angle=180, bool crop=false, bool norm=false)
	Calculate Radon Transform of an image.
int	readGT (String src_path, OutputArray dst)
	Function for reading ground truth disparity maps. Supports basic Middlebury and MPI-Sintel formats. Note that the resulting disparity map is scaled by 16.
void	rollingGuidanceFilter (InputArray src, OutputArray dst, int d=-1, double sigmaColor=25, double sigmaSpace=3, int numOfIter=4, int borderType=BORDER_DEFAULT)
	Applies the rolling guidance filter to an image.
void	thinning (InputArray src, OutputArray dst, int thinningType=THINNING_ZHANGSUEN)
	Applies a binary blob thinning operation, to achieve a skeletization of the input image.
void	transformFD (InputArray src, InputArray t, OutputArray dst, bool fdContour=true)
	transform a contour
void	weightedMedianFilter (InputArray joint, InputArray src, OutputArray dst, int r, double sigma=25.5, int weightType=WMF_EXP, InputArray mask=noArray())
	Applies weighted median filter to an image.

Enumeration Type Documentation

AngleRangeOption

enum cv::ximgproc::AngleRangeOption

Specifies the part of Hough space to calculate.

The enum specifies the part of Hough space to calculate. Each member specifies primarily direction of lines (horizontal or vertical) and the direction of angle changes. Direction of angle changes is from multiples of 90 to odd multiples of 45. The image considered to be written top-down and left-to-right. Angles are started from vertical line and go clockwise. Separate quarters and halves are written in orientation they should be in full Hough space.

Enumerator
ARO_0_45  Python: cv.ximgproc.ARO_0_45
ARO_45_90  Python: cv.ximgproc.ARO_45_90
ARO_90_135  Python: cv.ximgproc.ARO_90_135
ARO_315_0  Python: cv.ximgproc.ARO_315_0
ARO_315_45  Python: cv.ximgproc.ARO_315_45
ARO_45_135  Python: cv.ximgproc.ARO_45_135
ARO_315_135  Python: cv.ximgproc.ARO_315_135
ARO_CTR_HOR  Python: cv.ximgproc.ARO_CTR_HOR
ARO_CTR_VER  Python: cv.ximgproc.ARO_CTR_VER

HoughDeskewOption

enum cv::ximgproc::HoughDeskewOption

Specifies to do or not to do skewing of Hough transform image.

The enum specifies to do or not to do skewing of Hough transform image so it would be no cycling in Hough transform image through borders of image.

Enumerator
HDO_RAW  Python: cv.ximgproc.HDO_RAW
HDO_DESKEW  Python: cv.ximgproc.HDO_DESKEW

HoughOp

enum cv::ximgproc::HoughOp

Specifies binary operations.

The enum specifies binary operations, that is such ones which involve two operands. Formally, a binary operation \( f \) on a set \( S \) is a binary relation that maps elements of the Cartesian product \( S \times S \) to \( S \):

\[ f: S \times S \to S \]

Enumerator
FHT_MIN  Python: cv.ximgproc.FHT_MIN
FHT_MAX  Python: cv.ximgproc.FHT_MAX
FHT_ADD  Python: cv.ximgproc.FHT_ADD
FHT_AVE  Python: cv.ximgproc.FHT_AVE

RulesOption

enum cv::ximgproc::RulesOption

Specifies the degree of rules validation.

The enum specifies the degree of rules validation. This can be used, for example, to choose a proper way of input arguments validation.

Enumerator
RO_STRICT	Validate each rule in a proper way.
RO_IGNORE_BORDERS	Skip validations of image borders.

WMFWeightType

enum cv::ximgproc::WMFWeightType

Specifies weight types of weighted median filter.

Enumerator
WMF_EXP  Python: cv.ximgproc.WMF_EXP	\(exp(-|I1-I2|^2/(2*sigma^2))\)
WMF_IV1  Python: cv.ximgproc.WMF_IV1	\((|I1-I2|+sigma)^-1\)
WMF_IV2  Python: cv.ximgproc.WMF_IV2	\((|I1-I2|^2+sigma^2)^-1\)
WMF_COS  Python: cv.ximgproc.WMF_COS	\(dot(I1,I2)/(|I1|*|I2|)\)
WMF_JAC  Python: cv.ximgproc.WMF_JAC	\((min(r1,r2)+min(g1,g2)+min(b1,b2))/(max(r1,r2)+max(g1,g2)+max(b1,b2))\)
WMF_OFF  Python: cv.ximgproc.WMF_OFF	unweighted

Function Documentation

BrightEdges()

void cv::ximgproc::BrightEdges	(	Mat &	_original,
		Mat &	_edgeview,
		int	contrast = 1,
		int	shortrange = 3,
		int	longrange = 9
	)

covarianceEstimation()

void cv::ximgproc::covarianceEstimation	(	InputArray	src,
		OutputArray	dst,
		int	windowRows,
		int	windowCols
	)

Python:
	cv.ximgproc.covarianceEstimation(	src, windowRows, windowCols[, dst]	) ->	dst

Computes the estimated covariance matrix of an image using the sliding window forumlation.

Parameters

src	The source image. Input image must be of a complex type.
dst	The destination estimated covariance matrix. Output matrix will be size (windowRows*windowCols, windowRows*windowCols).
windowRows	The number of rows in the window.
windowCols	The number of cols in the window. The window size parameters control the accuracy of the estimation. The sliding window moves over the entire image from the top-left corner to the bottom right corner. Each location of the window represents a sample. If the window is the size of the image, then this gives the exact covariance matrix. For all other cases, the sizes of the window will impact the number of samples and the number of elements in the estimated covariance matrix.

createScanSegment()

cv::Ptr< ScanSegment > cv::ximgproc::createScanSegment	(	int	image_width,
		int	image_height,
		int	num_superpixels,
		int	slices = 8,
		bool	merge_small = true
	)

Python:
	cv.ximgproc.createScanSegment(	image_width, image_height, num_superpixels[, slices[, merge_small]]	) ->	retval

Initializes a ScanSegment object.

The function initializes a ScanSegment object for the input image. It stores the parameters of the image: image_width and image_height. It also sets the parameters of the F-DBSCAN superpixel algorithm, which are: num_superpixels, threads, and merge_small.

Parameters

image_width	Image width.
image_height	Image height.
num_superpixels	Desired number of superpixels. Note that the actual number may be smaller due to restrictions (depending on the image size). Use getNumberOfSuperpixels() to get the actual number.
slices	Number of processing threads for parallelisation. Setting -1 uses the maximum number of threads. In practice, four threads is enough for smaller images and eight threads for larger ones.
merge_small	merge small segments to give the desired number of superpixels. Processing is much faster without merging, but many small segments will be left in the image.

FastHoughTransform()

void cv::ximgproc::FastHoughTransform	(	InputArray	src,
		OutputArray	dst,
		int	dstMatDepth,
		int	angleRange = ARO_315_135,
		int	op = FHT_ADD,
		int	makeSkew = HDO_DESKEW
	)

Python:
	cv.ximgproc.FastHoughTransform(	src, dstMatDepth[, dst[, angleRange[, op[, makeSkew]]]]	) ->	dst

Calculates 2D Fast Hough transform of an image.

Parameters

dst	The destination image, result of transformation.
src	The source (input) image.
dstMatDepth	The depth of destination image
op	The operation to be applied, see cv::HoughOp
angleRange	The part of Hough space to calculate, see cv::AngleRangeOption
makeSkew	Specifies to do or not to do image skewing, see cv::HoughDeskewOption

The function calculates the fast Hough transform for full, half or quarter range of angles.

HoughPoint2Line()

Vec4i cv::ximgproc::HoughPoint2Line	(	const Point &	houghPoint,
		InputArray	srcImgInfo,
		int	angleRange = ARO_315_135,
		int	makeSkew = HDO_DESKEW,
		int	rules = RO_IGNORE_BORDERS
	)

Python:
	cv.ximgproc.HoughPoint2Line(	houghPoint, srcImgInfo[, angleRange[, makeSkew[, rules]]]	) ->	retval

Calculates coordinates of line segment corresponded by point in Hough space.

Parameters

houghPoint	Point in Hough space.
srcImgInfo	The source (input) image of Hough transform.
angleRange	The part of Hough space where point is situated, see cv::AngleRangeOption
makeSkew	Specifies to do or not to do image skewing, see cv::HoughDeskewOption
rules	Specifies strictness of line segment calculating, see cv::RulesOption

Return values

[Vec4i]

Coordinates of line segment corresponded by point in Hough space.

Remarks

If rules parameter set to RO_STRICT then returned line cut along the border of source image.

If rules parameter set to RO_WEAK then in case of point, which belongs the incorrect part of Hough image, returned line will not intersect source image.

The function calculates coordinates of line segment corresponded by point in Hough space.

RadonTransform()

void cv::ximgproc::RadonTransform	(	InputArray	src,
		OutputArray	dst,
		double	theta = 1,
		double	start_angle = 0,
		double	end_angle = 180,
		bool	crop = false,
		bool	norm = false
	)

Python:
	cv.ximgproc.RadonTransform(	src[, dst[, theta[, start_angle[, end_angle[, crop[, norm]]]]]]	) ->	dst

Calculate Radon Transform of an image.

Parameters

src	The source (input) image.
dst	The destination image, result of transformation.
theta	Angle resolution of the transform in degrees.
start_angle	Start angle of the transform in degrees.
end_angle	End angle of the transform in degrees.
crop	Crop the source image into a circle.
norm	Normalize the output Mat to grayscale and convert type to CV_8U

This function calculates the Radon Transform of a given image in any range. See https://engineering.purdue.edu/~malcolm/pct/CTI_Ch03.pdf for detail. If the input type is CV_8U, the output will be CV_32S. If the input type is CV_32F or CV_64F, the output will be CV_64F The output size will be num_of_integral x src_diagonal_length. If crop is selected, the input image will be crop into square then circle, and output size will be num_of_integral x min_edge.

weightedMedianFilter()

void cv::ximgproc::weightedMedianFilter	(	InputArray	joint,
		InputArray	src,
		OutputArray	dst,
		int	r,
		double	sigma = 25.5,
		int	weightType = WMF_EXP,
		InputArray	mask = noArray()
	)

Python:
	cv.ximgproc.weightedMedianFilter(	joint, src, r[, dst[, sigma[, weightType[, mask]]]]	) ->	dst

Applies weighted median filter to an image.

For more details about this implementation, please see [319]

Parameters

joint	Joint 8-bit, 1-channel or 3-channel image.
src	Source 8-bit or floating-point, 1-channel or 3-channel image.
dst	Destination image.
r	Radius of filtering kernel, should be a positive integer.
sigma	Filter range standard deviation for the joint image.
weightType	weightType The type of weight definition, see WMFWeightType
mask	A 0-1 mask that has the same size with I. This mask is used to ignore the effect of some pixels. If the pixel value on mask is 0, the pixel will be ignored when maintaining the joint-histogram. This is useful for applications like optical flow occlusion handling.

See also

medianBlur, jointBilateralFilter