Denoising

Detailed Description

Functions
void	cv::denoise_TVL1 (const std::vector< Mat > &observations, Mat &result, double lambda=1.0, int niters=30)
	Primal-dual algorithm is an algorithm for solving special types of variational problems (that is, finding a function to minimize some functional). As the image denoising, in particular, may be seen as the variational problem, primal-dual algorithm then can be used to perform denoising and this is exactly what is implemented.
void	cv::cuda::fastNlMeansDenoising (const GpuMat &src, GpuMat &dst, float h, int search_window=21, int block_size=7, Stream &stream=Stream::Null())
void	cv::fastNlMeansDenoising (InputArray src, OutputArray dst, const std::vector< float > &h, int templateWindowSize=7, int searchWindowSize=21, int normType=NORM_L2)
	Perform image denoising using Non-local Means Denoising algorithm http://www.ipol.im/pub/algo/bcm_non_local_means_denoising/ with several computational optimizations. Noise expected to be a gaussian white noise.
void	cv::cuda::fastNlMeansDenoising (InputArray src, OutputArray dst, float h, int search_window=21, int block_size=7, Stream &stream=Stream::Null())
	Perform image denoising using Non-local Means Denoising algorithm http://www.ipol.im/pub/algo/bcm_non_local_means_denoising with several computational optimizations. Noise expected to be a gaussian white noise.
void	cv::fastNlMeansDenoising (InputArray src, OutputArray dst, float h=3, int templateWindowSize=7, int searchWindowSize=21)
	Perform image denoising using Non-local Means Denoising algorithm http://www.ipol.im/pub/algo/bcm_non_local_means_denoising/ with several computational optimizations. Noise expected to be a gaussian white noise.
void	cv::cuda::fastNlMeansDenoisingColored (const GpuMat &src, GpuMat &dst, float h_luminance, float photo_render, int search_window=21, int block_size=7, Stream &stream=Stream::Null())
void	cv::fastNlMeansDenoisingColored (InputArray src, OutputArray dst, float h=3, float hColor=3, int templateWindowSize=7, int searchWindowSize=21)
	Modification of fastNlMeansDenoising function for colored images.
void	cv::cuda::fastNlMeansDenoisingColored (InputArray src, OutputArray dst, float h_luminance, float photo_render, int search_window=21, int block_size=7, Stream &stream=Stream::Null())
	Modification of fastNlMeansDenoising function for colored images.
void	cv::fastNlMeansDenoisingColoredMulti (InputArrayOfArrays srcImgs, OutputArray dst, int imgToDenoiseIndex, int temporalWindowSize, float h=3, float hColor=3, int templateWindowSize=7, int searchWindowSize=21)
	Modification of fastNlMeansDenoisingMulti function for colored images sequences.
void	cv::fastNlMeansDenoisingMulti (InputArrayOfArrays srcImgs, OutputArray dst, int imgToDenoiseIndex, int temporalWindowSize, const std::vector< float > &h, int templateWindowSize=7, int searchWindowSize=21, int normType=NORM_L2)
	Modification of fastNlMeansDenoising function for images sequence where consecutive images have been captured in small period of time. For example video. This version of the function is for grayscale images or for manual manipulation with colorspaces. See [44] for more details (open access here).
void	cv::fastNlMeansDenoisingMulti (InputArrayOfArrays srcImgs, OutputArray dst, int imgToDenoiseIndex, int temporalWindowSize, float h=3, int templateWindowSize=7, int searchWindowSize=21)
	Modification of fastNlMeansDenoising function for images sequence where consecutive images have been captured in small period of time. For example video. This version of the function is for grayscale images or for manual manipulation with colorspaces. See [44] for more details (open access here).
void	cv::cuda::nonLocalMeans (const GpuMat &src, GpuMat &dst, float h, int search_window=21, int block_size=7, int borderMode=BORDER_DEFAULT, Stream &stream=Stream::Null())
void	cv::cuda::nonLocalMeans (InputArray src, OutputArray dst, float h, int search_window=21, int block_size=7, int borderMode=BORDER_DEFAULT, Stream &stream=Stream::Null())
	Performs pure non local means denoising without any simplification, and thus it is not fast.

Function Documentation

denoise_TVL1()

void cv::denoise_TVL1	(	const std::vector< Mat > &	observations,
		Mat &	result,
		double	lambda = 1.0,
		int	niters = 30
	)

Python:
	cv.denoise_TVL1(	observations, result[, lambda_[, niters]]	) ->	None

#include <opencv2/photo.hpp>

Primal-dual algorithm is an algorithm for solving special types of variational problems (that is, finding a function to minimize some functional). As the image denoising, in particular, may be seen as the variational problem, primal-dual algorithm then can be used to perform denoising and this is exactly what is implemented.

It should be noted, that this implementation was taken from the July 2013 blog entry [199] , which also contained (slightly more general) ready-to-use source code on Python. Subsequently, that code was rewritten on C++ with the usage of openCV by Vadim Pisarevsky at the end of July 2013 and finally it was slightly adapted by later authors.

Although the thorough discussion and justification of the algorithm involved may be found in [49], it might make sense to skim over it here, following [199] . To begin with, we consider the 1-byte gray-level images as the functions from the rectangular domain of pixels (it may be seen as set \(\left\{(x,y)\in\mathbb{N}\times\mathbb{N}\mid 1\leq x\leq n,\;1\leq y\leq m\right\}\) for some \(m,\;n\in\mathbb{N}\)) into \(\{0,1,\dots,255\}\). We shall denote the noised images as \(f_i\) and with this view, given some image \(x\) of the same size, we may measure how bad it is by the formula

\[\left\|\left\|\nabla x\right\|\right\| + \lambda\sum_i\left\|\left\|x-f_i\right\|\right\|\]

\(\|\|\cdot\|\|\) here denotes \(L_2\)-norm and as you see, the first addend states that we want our image to be smooth (ideally, having zero gradient, thus being constant) and the second states that we want our result to be close to the observations we've got. If we treat \(x\) as a function, this is exactly the functional what we seek to minimize and here the Primal-Dual algorithm comes into play.

Parameters

observations	This array should contain one or more noised versions of the image that is to be restored.
result	Here the denoised image will be stored. There is no need to do pre-allocation of storage space, as it will be automatically allocated, if necessary.
lambda	Corresponds to \(\lambda\) in the formulas above. As it is enlarged, the smooth (blurred) images are treated more favorably than detailed (but maybe more noised) ones. Roughly speaking, as it becomes smaller, the result will be more blur but more sever outliers will be removed.
niters	Number of iterations that the algorithm will run. Of course, as more iterations as better, but it is hard to quantitatively refine this statement, so just use the default and increase it if the results are poor.

fastNlMeansDenoising() [1/4]

void cv::cuda::fastNlMeansDenoising ( const GpuMat &  src, GpuMat &  dst, float  h, int  search_window = 21, int  block_size = 7, Stream &  stream = Stream::Null()  )

inline

Python:
	cv.cuda.fastNlMeansDenoising(	src, h[, dst[, search_window[, block_size[, stream]]]]	) ->	dst

#include <opencv2/photo/cuda.hpp>

Here is the call graph for this function:

fastNlMeansDenoising() [2/4]

void cv::fastNlMeansDenoising	(	InputArray	src,
		OutputArray	dst,
		const std::vector< float > &	h,
		int	templateWindowSize = 7,
		int	searchWindowSize = 21,
		int	normType = NORM_L2
	)

Python:
	cv.fastNlMeansDenoising(	src[, dst[, h[, templateWindowSize[, searchWindowSize]]]]	) ->	dst
	cv.fastNlMeansDenoising(	src, h[, dst[, templateWindowSize[, searchWindowSize[, normType]]]]	) ->	dst

#include <opencv2/photo.hpp>

Perform image denoising using Non-local Means Denoising algorithm http://www.ipol.im/pub/algo/bcm_non_local_means_denoising/ with several computational optimizations. Noise expected to be a gaussian white noise.

Parameters

src	Input 8-bit or 16-bit (only with NORM_L1) 1-channel, 2-channel, 3-channel or 4-channel image.
dst	Output image with the same size and type as src .
templateWindowSize	Size in pixels of the template patch that is used to compute weights. Should be odd. Recommended value 7 pixels
searchWindowSize	Size in pixels of the window that is used to compute weighted average for given pixel. Should be odd. Affect performance linearly: greater searchWindowsSize - greater denoising time. Recommended value 21 pixels
h	Array of parameters regulating filter strength, either one parameter applied to all channels or one per channel in dst. Big h value perfectly removes noise but also removes image details, smaller h value preserves details but also preserves some noise
normType	Type of norm used for weight calculation. Can be either NORM_L2 or NORM_L1

This function expected to be applied to grayscale images. For colored images look at fastNlMeansDenoisingColored. Advanced usage of this functions can be manual denoising of colored image in different colorspaces. Such approach is used in fastNlMeansDenoisingColored by converting image to CIELAB colorspace and then separately denoise L and AB components with different h parameter.

fastNlMeansDenoising() [3/4]

void cv::cuda::fastNlMeansDenoising	(	InputArray	src,
		OutputArray	dst,
		float	h,
		int	search_window = 21,
		int	block_size = 7,
		Stream &	stream = Stream::Null()
	)

Python:
	cv.cuda.fastNlMeansDenoising(	src, h[, dst[, search_window[, block_size[, stream]]]]	) ->	dst

#include <opencv2/photo/cuda.hpp>

Perform image denoising using Non-local Means Denoising algorithm http://www.ipol.im/pub/algo/bcm_non_local_means_denoising with several computational optimizations. Noise expected to be a gaussian white noise.

Parameters

src	Input 8-bit 1-channel, 2-channel or 3-channel image.
dst	Output image with the same size and type as src .
h	Parameter regulating filter strength. Big h value perfectly removes noise but also removes image details, smaller h value preserves details but also preserves some noise
search_window	Size in pixels of the window that is used to compute weighted average for given pixel. Should be odd. Affect performance linearly: greater search_window - greater denoising time. Recommended value 21 pixels
block_size	Size in pixels of the template patch that is used to compute weights. Should be odd. Recommended value 7 pixels
stream	Stream for the asynchronous invocations.

This function expected to be applied to grayscale images. For colored images look at FastNonLocalMeansDenoising::labMethod.

See also

fastNlMeansDenoising

fastNlMeansDenoising() [4/4]

void cv::fastNlMeansDenoising	(	InputArray	src,
		OutputArray	dst,
		float	h = 3,
		int	templateWindowSize = 7,
		int	searchWindowSize = 21
	)

Python:
	cv.fastNlMeansDenoising(	src[, dst[, h[, templateWindowSize[, searchWindowSize]]]]	) ->	dst
	cv.fastNlMeansDenoising(	src, h[, dst[, templateWindowSize[, searchWindowSize[, normType]]]]	) ->	dst

#include <opencv2/photo.hpp>

Perform image denoising using Non-local Means Denoising algorithm http://www.ipol.im/pub/algo/bcm_non_local_means_denoising/ with several computational optimizations. Noise expected to be a gaussian white noise.

Parameters

src	Input 8-bit 1-channel, 2-channel, 3-channel or 4-channel image.
dst	Output image with the same size and type as src .
templateWindowSize	Size in pixels of the template patch that is used to compute weights. Should be odd. Recommended value 7 pixels
searchWindowSize	Size in pixels of the window that is used to compute weighted average for given pixel. Should be odd. Affect performance linearly: greater searchWindowsSize - greater denoising time. Recommended value 21 pixels
h	Parameter regulating filter strength. Big h value perfectly removes noise but also removes image details, smaller h value preserves details but also preserves some noise

This function expected to be applied to grayscale images. For colored images look at fastNlMeansDenoisingColored. Advanced usage of this functions can be manual denoising of colored image in different colorspaces. Such approach is used in fastNlMeansDenoisingColored by converting image to CIELAB colorspace and then separately denoise L and AB components with different h parameter.

fastNlMeansDenoisingColored() [1/3]

void cv::cuda::fastNlMeansDenoisingColored ( const GpuMat &  src, GpuMat &  dst, float  h_luminance, float  photo_render, int  search_window = 21, int  block_size = 7, Stream &  stream = Stream::Null()  )

inline

Python:
	cv.cuda.fastNlMeansDenoisingColored(	src, h_luminance, photo_render[, dst[, search_window[, block_size[, stream]]]]	) ->	dst

#include <opencv2/photo/cuda.hpp>

Here is the call graph for this function:

fastNlMeansDenoisingColored() [2/3]

void cv::fastNlMeansDenoisingColored	(	InputArray	src,
		OutputArray	dst,
		float	h = 3,
		float	hColor = 3,
		int	templateWindowSize = 7,
		int	searchWindowSize = 21
	)

Python:
	cv.fastNlMeansDenoisingColored(	src[, dst[, h[, hColor[, templateWindowSize[, searchWindowSize]]]]]	) ->	dst

#include <opencv2/photo.hpp>

Modification of fastNlMeansDenoising function for colored images.

Parameters

src	Input 8-bit 3-channel image.
dst	Output image with the same size and type as src .
templateWindowSize	Size in pixels of the template patch that is used to compute weights. Should be odd. Recommended value 7 pixels
searchWindowSize	Size in pixels of the window that is used to compute weighted average for given pixel. Should be odd. Affect performance linearly: greater searchWindowsSize - greater denoising time. Recommended value 21 pixels
h	Parameter regulating filter strength for luminance component. Bigger h value perfectly removes noise but also removes image details, smaller h value preserves details but also preserves some noise
hColor	The same as h but for color components. For most images value equals 10 will be enough to remove colored noise and do not distort colors

The function converts image to CIELAB colorspace and then separately denoise L and AB components with given h parameters using fastNlMeansDenoising function.

fastNlMeansDenoisingColored() [3/3]

void cv::cuda::fastNlMeansDenoisingColored	(	InputArray	src,
		OutputArray	dst,
		float	h_luminance,
		float	photo_render,
		int	search_window = 21,
		int	block_size = 7,
		Stream &	stream = Stream::Null()
	)

Python:
	cv.cuda.fastNlMeansDenoisingColored(	src, h_luminance, photo_render[, dst[, search_window[, block_size[, stream]]]]	) ->	dst

#include <opencv2/photo/cuda.hpp>

Modification of fastNlMeansDenoising function for colored images.

Parameters

src	Input 8-bit 3-channel image.
dst	Output image with the same size and type as src .
h_luminance	Parameter regulating filter strength. Big h value perfectly removes noise but also removes image details, smaller h value preserves details but also preserves some noise
photo_render	float The same as h but for color components. For most images value equals 10 will be enough to remove colored noise and do not distort colors
search_window	Size in pixels of the window that is used to compute weighted average for given pixel. Should be odd. Affect performance linearly: greater search_window - greater denoising time. Recommended value 21 pixels
block_size	Size in pixels of the template patch that is used to compute weights. Should be odd. Recommended value 7 pixels
stream	Stream for the asynchronous invocations.

The function converts image to CIELAB colorspace and then separately denoise L and AB components with given h parameters using FastNonLocalMeansDenoising::simpleMethod function.

See also

fastNlMeansDenoisingColored

fastNlMeansDenoisingColoredMulti()

void cv::fastNlMeansDenoisingColoredMulti	(	InputArrayOfArrays	srcImgs,
		OutputArray	dst,
		int	imgToDenoiseIndex,
		int	temporalWindowSize,
		float	h = 3,
		float	hColor = 3,
		int	templateWindowSize = 7,
		int	searchWindowSize = 21
	)

Python:
	cv.fastNlMeansDenoisingColoredMulti(	srcImgs, imgToDenoiseIndex, temporalWindowSize[, dst[, h[, hColor[, templateWindowSize[, searchWindowSize]]]]]	) ->	dst

#include <opencv2/photo.hpp>

Modification of fastNlMeansDenoisingMulti function for colored images sequences.

Parameters

srcImgs	Input 8-bit 3-channel images sequence. All images should have the same type and size.
imgToDenoiseIndex	Target image to denoise index in srcImgs sequence
temporalWindowSize	Number of surrounding images to use for target image denoising. Should be odd. Images from imgToDenoiseIndex - temporalWindowSize / 2 to imgToDenoiseIndex + temporalWindowSize / 2 from srcImgs will be used to denoise srcImgs[imgToDenoiseIndex] image.
dst	Output image with the same size and type as srcImgs images.
templateWindowSize	Size in pixels of the template patch that is used to compute weights. Should be odd. Recommended value 7 pixels
searchWindowSize	Size in pixels of the window that is used to compute weighted average for given pixel. Should be odd. Affect performance linearly: greater searchWindowsSize - greater denoising time. Recommended value 21 pixels
h	Parameter regulating filter strength for luminance component. Bigger h value perfectly removes noise but also removes image details, smaller h value preserves details but also preserves some noise.
hColor	The same as h but for color components.

The function converts images to CIELAB colorspace and then separately denoise L and AB components with given h parameters using fastNlMeansDenoisingMulti function.

fastNlMeansDenoisingMulti() [1/2]

void cv::fastNlMeansDenoisingMulti	(	InputArrayOfArrays	srcImgs,
		OutputArray	dst,
		int	imgToDenoiseIndex,
		int	temporalWindowSize,
		const std::vector< float > &	h,
		int	templateWindowSize = 7,
		int	searchWindowSize = 21,
		int	normType = NORM_L2
	)

Python:
	cv.fastNlMeansDenoisingMulti(	srcImgs, imgToDenoiseIndex, temporalWindowSize[, dst[, h[, templateWindowSize[, searchWindowSize]]]]	) ->	dst
	cv.fastNlMeansDenoisingMulti(	srcImgs, imgToDenoiseIndex, temporalWindowSize, h[, dst[, templateWindowSize[, searchWindowSize[, normType]]]]	) ->	dst

#include <opencv2/photo.hpp>

Modification of fastNlMeansDenoising function for images sequence where consecutive images have been captured in small period of time. For example video. This version of the function is for grayscale images or for manual manipulation with colorspaces. See [44] for more details (open access here).

Parameters

srcImgs	Input 8-bit or 16-bit (only with NORM_L1) 1-channel, 2-channel, 3-channel or 4-channel images sequence. All images should have the same type and size.
imgToDenoiseIndex	Target image to denoise index in srcImgs sequence
temporalWindowSize	Number of surrounding images to use for target image denoising. Should be odd. Images from imgToDenoiseIndex - temporalWindowSize / 2 to imgToDenoiseIndex + temporalWindowSize / 2 from srcImgs will be used to denoise srcImgs[imgToDenoiseIndex] image.
dst	Output image with the same size and type as srcImgs images.
templateWindowSize	Size in pixels of the template patch that is used to compute weights. Should be odd. Recommended value 7 pixels
searchWindowSize	Size in pixels of the window that is used to compute weighted average for given pixel. Should be odd. Affect performance linearly: greater searchWindowsSize - greater denoising time. Recommended value 21 pixels
h	Array of parameters regulating filter strength, either one parameter applied to all channels or one per channel in dst. Big h value perfectly removes noise but also removes image details, smaller h value preserves details but also preserves some noise
normType	Type of norm used for weight calculation. Can be either NORM_L2 or NORM_L1

fastNlMeansDenoisingMulti() [2/2]

void cv::fastNlMeansDenoisingMulti	(	InputArrayOfArrays	srcImgs,
		OutputArray	dst,
		int	imgToDenoiseIndex,
		int	temporalWindowSize,
		float	h = 3,
		int	templateWindowSize = 7,
		int	searchWindowSize = 21
	)

Python:
	cv.fastNlMeansDenoisingMulti(	srcImgs, imgToDenoiseIndex, temporalWindowSize[, dst[, h[, templateWindowSize[, searchWindowSize]]]]	) ->	dst
	cv.fastNlMeansDenoisingMulti(	srcImgs, imgToDenoiseIndex, temporalWindowSize, h[, dst[, templateWindowSize[, searchWindowSize[, normType]]]]	) ->	dst

#include <opencv2/photo.hpp>

Modification of fastNlMeansDenoising function for images sequence where consecutive images have been captured in small period of time. For example video. This version of the function is for grayscale images or for manual manipulation with colorspaces. See [44] for more details (open access here).

Parameters

srcImgs	Input 8-bit 1-channel, 2-channel, 3-channel or 4-channel images sequence. All images should have the same type and size.
imgToDenoiseIndex	Target image to denoise index in srcImgs sequence
temporalWindowSize	Number of surrounding images to use for target image denoising. Should be odd. Images from imgToDenoiseIndex - temporalWindowSize / 2 to imgToDenoiseIndex + temporalWindowSize / 2 from srcImgs will be used to denoise srcImgs[imgToDenoiseIndex] image.
dst	Output image with the same size and type as srcImgs images.
templateWindowSize	Size in pixels of the template patch that is used to compute weights. Should be odd. Recommended value 7 pixels
searchWindowSize	Size in pixels of the window that is used to compute weighted average for given pixel. Should be odd. Affect performance linearly: greater searchWindowsSize - greater denoising time. Recommended value 21 pixels
h	Parameter regulating filter strength. Bigger h value perfectly removes noise but also removes image details, smaller h value preserves details but also preserves some noise

nonLocalMeans() [1/2]

void cv::cuda::nonLocalMeans ( const GpuMat &  src, GpuMat &  dst, float  h, int  search_window = 21, int  block_size = 7, int  borderMode = BORDER_DEFAULT, Stream &  stream = Stream::Null()  )

inline

Python:
	cv.cuda.nonLocalMeans(	src, h[, dst[, search_window[, block_size[, borderMode[, stream]]]]]	) ->	dst

#include <opencv2/photo/cuda.hpp>

Here is the call graph for this function:

nonLocalMeans() [2/2]

void cv::cuda::nonLocalMeans	(	InputArray	src,
		OutputArray	dst,
		float	h,
		int	search_window = 21,
		int	block_size = 7,
		int	borderMode = BORDER_DEFAULT,
		Stream &	stream = Stream::Null()
	)

Python:
	cv.cuda.nonLocalMeans(	src, h[, dst[, search_window[, block_size[, borderMode[, stream]]]]]	) ->	dst

#include <opencv2/photo/cuda.hpp>

Performs pure non local means denoising without any simplification, and thus it is not fast.

Parameters

src	Source image. Supports only CV_8UC1, CV_8UC2 and CV_8UC3.
dst	Destination image.
h	Filter sigma regulating filter strength for color.
search_window	Size of search window.
block_size	Size of block used for computing weights.
borderMode	Border type. See borderInterpolate for details. BORDER_REFLECT101 , BORDER_REPLICATE , BORDER_CONSTANT , BORDER_REFLECT and BORDER_WRAP are supported for now.
stream	Stream for the asynchronous version.

See also

fastNlMeansDenoising