Feature Detection and Description

Classes
class	cv::KeyPointsFilter
	A class filters a vector of keypoints. More...
class	cv::Feature2D
	Abstract base class for 2D image feature detectors and descriptor extractors. More...
class	cv::AffineFeature
	Class for implementing the wrapper which makes detectors and extractors to be affine invariant, described as ASIFT in [YM11] . More...
class	cv::SIFT
	Class for extracting keypoints and computing descriptors using the Scale Invariant Feature Transform (SIFT) algorithm by D. Lowe [Lowe04] . More...
class	cv::BRISK
	Class implementing the BRISK keypoint detector and descriptor extractor, described in [LCS11] . More...
class	cv::ORB
	Class implementing the ORB (oriented BRIEF) keypoint detector and descriptor extractor. More...
class	cv::MSER
	Maximally stable extremal region extractor. More...
class	cv::FastFeatureDetector
	Wrapping class for feature detection using the FAST method. : More...
class	cv::AgastFeatureDetector
	Wrapping class for feature detection using the AGAST method. : More...
class	cv::GFTTDetector
	Wrapping class for feature detection using the goodFeaturesToTrack function. : More...
class	cv::SimpleBlobDetector
	Class for extracting blobs from an image. : More...
class	cv::KAZE
	Class implementing the KAZE keypoint detector and descriptor extractor, described in [ABD12] . More...
class	cv::AKAZE
	Class implementing the AKAZE keypoint detector and descriptor extractor, described in [ANB13]. More...
struct	cv::Accumulator< T >
struct	cv::Accumulator< unsigned char >
struct	cv::Accumulator< unsigned short >
struct	cv::Accumulator< char >
struct	cv::Accumulator< short >
struct	cv::SL2< T >
struct	cv::L2< T >
struct	cv::L1< T >

Typedefs
typedef Feature2D	cv::FeatureDetector
typedef Feature2D	cv::DescriptorExtractor
typedef AffineFeature	cv::AffineFeatureDetector
typedef AffineFeature	cv::AffineDescriptorExtractor
typedef SIFT	cv::SiftFeatureDetector
typedef SIFT	cv::SiftDescriptorExtractor

Functions
CV_EXPORTS void	cv::FAST (InputArray image, CV_OUT std::vector< KeyPoint > &keypoints, int threshold, bool nonmaxSuppression=true)
CV_EXPORTS void	cv::FAST (InputArray image, CV_OUT std::vector< KeyPoint > &keypoints, int threshold, bool nonmaxSuppression, FastFeatureDetector::DetectorType type)
	Detects corners using the FAST algorithm. More...
CV_EXPORTS void	cv::AGAST (InputArray image, CV_OUT std::vector< KeyPoint > &keypoints, int threshold, bool nonmaxSuppression=true)
CV_EXPORTS void	cv::AGAST (InputArray image, CV_OUT std::vector< KeyPoint > &keypoints, int threshold, bool nonmaxSuppression, AgastFeatureDetector::DetectorType type)
	Detects corners using the AGAST algorithm. More...
CV_EXPORTS void	cv::evaluateFeatureDetector (const Mat &img1, const Mat &img2, const Mat &H1to2, std::vector< KeyPoint > *keypoints1, std::vector< KeyPoint > *keypoints2, float &repeatability, int &correspCount, const Ptr< FeatureDetector > &fdetector=Ptr< FeatureDetector >())
CV_EXPORTS void	cv::computeRecallPrecisionCurve (const std::vector< std::vector< DMatch > > &matches1to2, const std::vector< std::vector< uchar > > &correctMatches1to2Mask, std::vector< Point2f > &recallPrecisionCurve)
CV_EXPORTS float	cv::getRecall (const std::vector< Point2f > &recallPrecisionCurve, float l_precision)
CV_EXPORTS int	cv::getNearestPoint (const std::vector< Point2f > &recallPrecisionCurve, float l_precision)

Detailed Description

Typedef Documentation

AffineDescriptorExtractor

typedef AffineFeature cv::AffineDescriptorExtractor

AffineFeatureDetector

typedef AffineFeature cv::AffineFeatureDetector

DescriptorExtractor

typedef Feature2D cv::DescriptorExtractor

Extractors of keypoint descriptors in OpenCV have wrappers with a common interface that enables you to easily switch between different algorithms solving the same problem. This section is devoted to computing descriptors represented as vectors in a multidimensional space. All objects that implement the vector descriptor extractors inherit the DescriptorExtractor interface.

FeatureDetector

typedef Feature2D cv::FeatureDetector

Feature detectors in OpenCV have wrappers with a common interface that enables you to easily switch between different algorithms solving the same problem. All objects that implement keypoint detectors inherit the FeatureDetector interface.

SiftDescriptorExtractor

typedef SIFT cv::SiftDescriptorExtractor

SiftFeatureDetector

typedef SIFT cv::SiftFeatureDetector

Function Documentation

AGAST() [1/2]

CV_EXPORTS void cv::AGAST	(	InputArray	image,
		CV_OUT std::vector< KeyPoint > &	keypoints,
		int	threshold,
		bool	nonmaxSuppression,
		AgastFeatureDetector::DetectorType	type
	)

Detects corners using the AGAST algorithm.

Parameters

image	grayscale image where keypoints (corners) are detected.
keypoints	keypoints detected on the image.
threshold	threshold on difference between intensity of the central pixel and pixels of a circle around this pixel.
nonmaxSuppression	if true, non-maximum suppression is applied to detected corners (keypoints).
type	one of the four neighborhoods as defined in the paper: AgastFeatureDetector::AGAST_5_8, AgastFeatureDetector::AGAST_7_12d, AgastFeatureDetector::AGAST_7_12s, AgastFeatureDetector::OAST_9_16

For non-Intel platforms, there is a tree optimised variant of AGAST with same numerical results. The 32-bit binary tree tables were generated automatically from original code using perl script. The perl script and examples of tree generation are placed in features2d/doc folder. Detects corners using the AGAST algorithm by [mair2010_agast] .

AGAST() [2/2]

CV_EXPORTS void cv::AGAST	(	InputArray	image,
		CV_OUT std::vector< KeyPoint > &	keypoints,
		int	threshold,
		bool	nonmaxSuppression = true
	)

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

computeRecallPrecisionCurve()

CV_EXPORTS void cv::computeRecallPrecisionCurve	(	const std::vector< std::vector< DMatch > > &	matches1to2,
		const std::vector< std::vector< uchar > > &	correctMatches1to2Mask,
		std::vector< Point2f > &	recallPrecisionCurve
	)

evaluateFeatureDetector()

CV_EXPORTS void cv::evaluateFeatureDetector	(	const Mat &	img1,
		const Mat &	img2,
		const Mat &	H1to2,
		std::vector< KeyPoint > *	keypoints1,
		std::vector< KeyPoint > *	keypoints2,
		float &	repeatability,
		int &	correspCount,
		const Ptr< FeatureDetector > &	fdetector = Ptr< FeatureDetector >()
	)

FAST() [1/2]

CV_EXPORTS void cv::FAST	(	InputArray	image,
		CV_OUT std::vector< KeyPoint > &	keypoints,
		int	threshold,
		bool	nonmaxSuppression,
		FastFeatureDetector::DetectorType	type
	)

Detects corners using the FAST algorithm.

Parameters

image	grayscale image where keypoints (corners) are detected.
keypoints	keypoints detected on the image.
threshold	threshold on difference between intensity of the central pixel and pixels of a circle around this pixel.
nonmaxSuppression	if true, non-maximum suppression is applied to detected corners (keypoints).
type	one of the three neighborhoods as defined in the paper: FastFeatureDetector::TYPE_9_16, FastFeatureDetector::TYPE_7_12, FastFeatureDetector::TYPE_5_8

Detects corners using the FAST algorithm by [Rosten06] .

Note

In Python API, types are given as cv.FAST_FEATURE_DETECTOR_TYPE_5_8, cv.FAST_FEATURE_DETECTOR_TYPE_7_12 and cv.FAST_FEATURE_DETECTOR_TYPE_9_16. For corner detection, use cv.FAST.detect() method.

FAST() [2/2]

CV_EXPORTS void cv::FAST	(	InputArray	image,
		CV_OUT std::vector< KeyPoint > &	keypoints,
		int	threshold,
		bool	nonmaxSuppression = true
	)

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

getNearestPoint()

CV_EXPORTS int cv::getNearestPoint	(	const std::vector< Point2f > &	recallPrecisionCurve,
		float	l_precision
	)

getRecall()

CV_EXPORTS float cv::getRecall	(	const std::vector< Point2f > &	recallPrecisionCurve,
		float	l_precision
	)