Extended Image Processing

Modules
	Structured forests for fast edge detection
	EdgeBoxes
	Filters
	Superpixels
	Image segmentation
	Fast line detector
	EdgeDrawing
	Fourier descriptors
	Binary morphology on run-length encoded image

Functions
void	cv::ximgproc::anisotropicDiffusion (InputArray src, OutputArray dst, float alpha, float K, int niters)
	Performs anisotropic diffusion on an image. More...
void	cv::ximgproc::edgePreservingFilter (InputArray src, OutputArray dst, int d, double threshold)
	Smoothes an image using the Edge-Preserving filter. More...
void	cv::ximgproc::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. More...
void	cv::ximgproc::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. More...
Matx23d	cv::ximgproc::PeiLinNormalization (InputArray I)
	Calculates an affine transformation that normalize given image using Pei&Lin Normalization. More...
void	cv::ximgproc::PeiLinNormalization (InputArray I, OutputArray T)
void	cv::ximgproc::thinning (InputArray src, OutputArray dst, int thinningType=THINNING_ZHANGSUEN)
	Applies a binary blob thinning operation, to achieve a skeletization of the input image. More...

Detailed Description

Function Documentation

anisotropicDiffusion()

void cv::ximgproc::anisotropicDiffusion	(	InputArray	src,
		OutputArray	dst,
		float	alpha,
		float	K,
		int	niters
	)

Python:
	cv.ximgproc.anisotropicDiffusion(	src, alpha, K, niters[, dst]	) ->	dst

#include <opencv2/ximgproc.hpp>

Performs anisotropic diffusion on an image.

The function applies Perona-Malik anisotropic diffusion to an image. This is the solution to the partial differential equation:

\[{\frac {\partial I}{\partial t}}={\mathrm {div}}\left(c(x,y,t)\nabla I\right)=\nabla c\cdot \nabla I+c(x,y,t)\Delta I\]

Suggested functions for c(x,y,t) are:

\[c\left(\|\nabla I\|\right)=e^{{-\left(\|\nabla I\|/K\right)^{2}}}\]

or

\[ c\left(\|\nabla I\|\right)={\frac {1}{1+\left({\frac {\|\nabla I\|}{K}}\right)^{2}}} \]

Parameters

src	Source image with 3 channels.
dst	Destination image of the same size and the same number of channels as src .
alpha	The amount of time to step forward by on each iteration (normally, it's between 0 and 1).
K	sensitivity to the edges
niters	The number of iterations

edgePreservingFilter()

void cv::ximgproc::edgePreservingFilter	(	InputArray	src,
		OutputArray	dst,
		int	d,
		double	threshold
	)

Python:
	cv.ximgproc.edgePreservingFilter(	src, d, threshold[, dst]	) ->	dst

#include <opencv2/ximgproc/edgepreserving_filter.hpp>

Smoothes an image using the Edge-Preserving filter.

The function smoothes Gaussian noise as well as salt & pepper noise. For more details about this implementation, please see [ReiWoe18] Reich, S. and Wörgötter, F. and Dellen, B. (2018). A Real-Time Edge-Preserving Denoising Filter. Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP): Visapp, 85-94, 4. DOI: 10.5220/0006509000850094.

Parameters

src	Source 8-bit 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. Must be greater or equal 3.
threshold	Threshold, which distinguishes between noise, outliers, and data.

findEllipses()

void cv::ximgproc::findEllipses	(	InputArray	image,
		OutputArray	ellipses,
		float	scoreThreshold = 0.7f,
		float	reliabilityThreshold = 0.5f,
		float	centerDistanceThreshold = 0.05f
	)

Python:
	cv.ximgproc.findEllipses(	image[, ellipses[, scoreThreshold[, reliabilityThreshold[, centerDistanceThreshold]]]]	) ->	ellipses

#include <opencv2/ximgproc/find_ellipses.hpp>

Finds ellipses fastly in an image using projective invariant pruning.

The function detects ellipses in images using projective invariant pruning. For more details about this implementation, please see [125] Jia, Qi et al, (2017). A Fast Ellipse Detector using Projective Invariant Pruning. IEEE Transactions on Image Processing.

Parameters

image	input image, could be gray or color.
ellipses	output vector of found ellipses. each vector is encoded as five float $x, y, a, b, radius, score$.
scoreThreshold	float, the threshold of ellipse score.
reliabilityThreshold	float, the threshold of reliability.
centerDistanceThreshold	float, the threshold of center distance.

niBlackThreshold()

void cv::ximgproc::niBlackThreshold	(	InputArray	_src,
		OutputArray	_dst,
		double	maxValue,
		int	type,
		int	blockSize,
		double	k,
		int	binarizationMethod = BINARIZATION_NIBLACK,
		double	r = 128
	)

Python:
	cv.ximgproc.niBlackThreshold(	_src, maxValue, type, blockSize, k[, _dst[, binarizationMethod[, r]]]	) ->	_dst

#include <opencv2/ximgproc.hpp>

Performs thresholding on input images using Niblack's technique or some of the popular variations it inspired.

The function transforms a grayscale image to a binary image according to the formulae:

• THRESH_BINARY

  \[dst(x,y) = \fork{\texttt{maxValue}}{if \(src(x,y) > T(x,y)\)}{0}{otherwise}\]

• THRESH_BINARY_INV

  \[dst(x,y) = \fork{0}{if \(src(x,y) > T(x,y)\)}{\texttt{maxValue}}{otherwise}\]

  where \(T(x,y)\) is a threshold calculated individually for each pixel.

The threshold value \(T(x, y)\) is determined based on the binarization method chosen. For classic Niblack, it is the mean minus \( k \) times standard deviation of \(\texttt{blockSize} \times\texttt{blockSize}\) neighborhood of \((x, y)\).

The function can't process the image in-place.

Parameters

_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, used with the THRESH_BINARY and THRESH_BINARY_INV thresholding types.
type	Thresholding type, see cv::ThresholdTypes.
blockSize	Size of a pixel neighborhood that is used to calculate a threshold value for the pixel: 3, 5, 7, and so on.
k	The user-adjustable parameter used by Niblack and inspired techniques. For Niblack, this is normally a value between 0 and 1 that is multiplied with the standard deviation and subtracted from the mean.
binarizationMethod	Binarization method to use. By default, Niblack's technique is used. Other techniques can be specified, see cv::ximgproc::LocalBinarizationMethods.
r	The user-adjustable parameter used by Sauvola's technique. This is the dynamic range of standard deviation.

See also

threshold, adaptiveThreshold

PeiLinNormalization() [1/2]

Matx23d cv::ximgproc::PeiLinNormalization

(

InputArray

I

)

Python:
	cv.ximgproc.PeiLinNormalization(	I[, T]	) ->	T

#include <opencv2/ximgproc/peilin.hpp>

Calculates an affine transformation that normalize given image using Pei&Lin Normalization.

Assume given image \(I=T(\bar{I})\) where \(\bar{I}\) is a normalized image and \(T\) is an affine transformation distorting this image by translation, rotation, scaling and skew. The function returns an affine transformation matrix corresponding to the transformation \(T^{-1}\) described in [PeiLin95]. For more details about this implementation, please see [PeiLin95] Soo-Chang Pei and Chao-Nan Lin. Image normalization for pattern recognition. Image and Vision Computing, Vol. 13, N.10, pp. 711-723, 1995.

Parameters

I	Given transformed image.

Returns

Transformation matrix corresponding to inversed image transformation

PeiLinNormalization() [2/2]

void cv::ximgproc::PeiLinNormalization	(	InputArray	I,
		OutputArray	T
	)

Python:
	cv.ximgproc.PeiLinNormalization(	I[, T]	) ->	T

#include <opencv2/ximgproc/peilin.hpp>

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

thinning()

void cv::ximgproc::thinning	(	InputArray	src,
		OutputArray	dst,
		int	thinningType = THINNING_ZHANGSUEN
	)

Python:
	cv.ximgproc.thinning(	src[, dst[, thinningType]]	) ->	dst

#include <opencv2/ximgproc.hpp>

Applies a binary blob thinning operation, to achieve a skeletization of the input image.

The function transforms a binary blob image into a skeletized form using the technique of Zhang-Suen.

Parameters

src	Source 8-bit single-channel image, containing binary blobs, with blobs having 255 pixel values.
dst	Destination image of the same size and the same type as src. The function can work in-place.
thinningType	Value that defines which thinning algorithm should be used. See cv::ximgproc::ThinningTypes