cv::quality::QualityBRISQUE Class Reference

BRISQUE (Blind/Referenceless Image Spatial Quality Evaluator) is a No Reference Image Quality Assessment (NR-IQA) algorithm. More...

#include <opencv2/quality/qualitybrisque.hpp>

Inheritance diagram for cv::quality::QualityBRISQUE:

Public Member Functions
cv::Scalar	compute (InputArrayOfArrays imgs) CV_OVERRIDE
	Computes BRISQUE quality score for input images.
Public Member Functions inherited from cv::quality::QualityBase
virtual	~QualityBase ()=default
	Destructor.
void	clear () CV_OVERRIDE
	Implements Algorithm::clear()
bool	empty () const CV_OVERRIDE
	Implements Algorithm::empty()
virtual void	getQualityMaps (OutputArrayOfArrays dst) const
	Returns output quality map images that were generated during computation, if supported by the algorithm.
Public Member Functions inherited from cv::Algorithm
	Algorithm ()
virtual	~Algorithm ()
virtual String	getDefaultName () const
virtual void	read (const FileNode &fn)
	Reads algorithm parameters from a file storage.
virtual void	save (const String &filename) const
virtual void	write (FileStorage &fs) const
	Stores algorithm parameters in a file storage.
void	write (const Ptr< FileStorage > &fs, const String &name=String()) const
	simplified API for language bindingsThis is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Static Public Member Functions
static cv::Scalar	compute (InputArrayOfArrays imgs, const cv::String &model_file_path, const cv::String &range_file_path)
	static method for computing quality
static void	computeFeatures (InputArray img, OutputArray features)
	static method for computing image features used by the BRISQUE algorithm
static Ptr< QualityBRISQUE >	create (const cv::String &model_file_path="", const cv::String &range_file_path="")
	Create an object which calculates quality.
static Ptr< QualityBRISQUE >	create (const cv::Ptr< cv::ml::SVM > &model, const cv::Mat &range)
	Create an object which calculates quality.

Protected Member Functions
	QualityBRISQUE (const cv::String &model_file_path, const cv::String &range_file_path)
	Internal constructor.
	QualityBRISQUE (const cv::Ptr< cv::ml::SVM > &model, const cv::Mat &range)
	Internal constructor.

Protected Attributes
cv::Ptr< cv::ml::SVM >	_model = nullptr
cv::Mat	_range
Protected Attributes inherited from cv::quality::QualityBase
std::vector< _quality_map_type >	_qualityMaps
	Output quality maps if generated by algorithm.

Additional Inherited Members
Protected Types inherited from cv::quality::QualityBase
using	_quality_map_type = cv::UMat
	internal quality map type default

Detailed Description

BRISQUE (Blind/Referenceless Image Spatial Quality Evaluator) is a No Reference Image Quality Assessment (NR-IQA) algorithm.

BRISQUE computes a score based on extracting Natural Scene Statistics (https://en.wikipedia.org/wiki/Scene_statistics) and calculating feature vectors. See Mittal et al.Mittal2 for original paper and original implementationMittal2_software .

A trained model is provided in the /samples/ directory and is trained on the LIVE-R2 databaseSheikh as in the original implementation. When evaluated against the TID2008 databasePonomarenko , the SROCC is -0.8424 versus the SROCC of -0.8354 in the original implementation. C++ code for the BRISQUE LIVE-R2 trainer and TID2008 evaluator are also provided in the /samples/ directory.

Constructor & Destructor Documentation

cv::quality::QualityBRISQUE::QualityBRISQUE ( const cv::String &  model_file_path, const cv::String &  range_file_path  )

protected

Internal constructor.

cv::quality::QualityBRISQUE::QualityBRISQUE ( const cv::Ptr< cv::ml::SVM > &  model, const cv::Mat &  range  )

inlineprotected

Internal constructor.

Member Function Documentation

cv::Scalar cv::quality::QualityBRISQUE::compute ( InputArrayOfArrays  imgs )

virtual

Python:
	retval	=	cv.quality_QualityBRISQUE.compute(	imgs	)
	retval	=	cv.quality_QualityBRISQUE.compute(	imgs, model_file_path, range_file_path	)
	retval	=	cv.quality.QualityBRISQUE_compute(	imgs, model_file_path, range_file_path	)

Computes BRISQUE quality score for input images.

Parameters

imgs	Images for which to compute quality (should be passed as a vector<Mat> in C++ and list of images in Python)

Returns

Score (averaged over individual scores of all images) ranging from 0 to 100 (0 denotes the best quality and 100 denotes the worst quality). The format of the score is: {score, 0., 0., 0.}

Implements cv::quality::QualityBase.

static cv::Scalar cv::quality::QualityBRISQUE::compute ( InputArrayOfArrays  imgs, const cv::String &  model_file_path, const cv::String &  range_file_path  )

static

Python:
	retval	=	cv.quality_QualityBRISQUE.compute(	imgs	)
	retval	=	cv.quality_QualityBRISQUE.compute(	imgs, model_file_path, range_file_path	)
	retval	=	cv.quality.QualityBRISQUE_compute(	imgs, model_file_path, range_file_path	)

static method for computing quality

Parameters

imgs	image(s) for which to compute quality (passed as Mat or vector<Mat> in C++ and as list of images in Python)
model_file_path	cv::String which contains a path to the BRISQUE model data. If empty, attempts to load from ${OPENCV_DIR}/testdata/contrib/quality/brisque_model_live.yml
range_file_path	cv::String which contains a path to the BRISQUE range data. If empty, attempts to load from ${OPENCV_DIR}/testdata/contrib/quality/brisque_range_live.yml

Returns

cv::Scalar result of format {std::double score, 0., 0., 0.}. Score ranges from 0 to 100 (100 means worst and 0 means best)

static void cv::quality::QualityBRISQUE::computeFeatures ( InputArray  img, OutputArray  features  )

static

Python:
	features	=	cv.quality.QualityBRISQUE_computeFeatures(	img[, features]	)

static method for computing image features used by the BRISQUE algorithm

Parameters

img	image (BGR(A) or grayscale) for which to compute features
features	output row vector of features to cv::Mat or cv::UMat

static Ptr<QualityBRISQUE> cv::quality::QualityBRISQUE::create ( const cv::String &  model_file_path = "", const cv::String &  range_file_path = ""  )

static

Python:
	retval	=	cv.quality.QualityBRISQUE_create(	[, model_file_path[, range_file_path]]	)
	retval	=	cv.quality.QualityBRISQUE_create(	model, range	)

Create an object which calculates quality.

Parameters

model_file_path	cv::String which contains a path to the BRISQUE model data. If empty, attempts to load from ${OPENCV_DIR}/testdata/contrib/quality/brisque_model_live.yml
range_file_path	cv::String which contains a path to the BRISQUE range data. If empty, attempts to load from ${OPENCV_DIR}/testdata/contrib/quality/brisque_range_live.yml

static Ptr<QualityBRISQUE> cv::quality::QualityBRISQUE::create ( const cv::Ptr< cv::ml::SVM > &  model, const cv::Mat &  range  )

static

Python:
	retval	=	cv.quality.QualityBRISQUE_create(	[, model_file_path[, range_file_path]]	)
	retval	=	cv.quality.QualityBRISQUE_create(	model, range	)

Create an object which calculates quality.

Parameters

model	cv::Ptr<cv::ml::SVM> which contains a loaded BRISQUE model
range	cv::Mat which contains BRISQUE range data

Member Data Documentation

cv::Ptr<cv::ml::SVM> cv::quality::QualityBRISQUE::_model = nullptr

protected

cv::Mat cv::quality::QualityBRISQUE::_range

protected

---

The documentation for this class was generated from the following file:

• qualitybrisque.hpp