Feature Detection and Description

Detailed Description

Classes
struct	cv::Accumulator< T >
struct	cv::Accumulator< char >
struct	cv::Accumulator< short >
struct	cv::Accumulator< unsigned char >
struct	cv::Accumulator< unsigned short >
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::ALIKED
	ALIKED feature detector and descriptor extractor. More...
class	cv::DISK
	DISK feature detector and descriptor, based on a DNN model. More...
class	cv::FastFeatureDetector
	Wrapping class for feature detection using the FAST method. More...
class	cv::Feature2D
	Abstract base class for 2D image feature detectors and descriptor extractors. More...
class	cv::GFTTDetector
	Wrapping class for feature detection using the goodFeaturesToTrack function. : More...
class	cv::KeyPointsFilter
	A class filters a vector of keypoints. More...
struct	cv::L1< T >
struct	cv::L2< T >
class	cv::MSER
	Maximally stable extremal region extractor. More...
class	cv::ORB
	Class implementing the ORB (oriented BRIEF) keypoint detector and descriptor extractor. 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::SimpleBlobDetector
	Class for extracting blobs from an image. : More...
struct	cv::SL2< T >

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

Functions
void	cv::computeRecallPrecisionCurve (const std::vector< std::vector< DMatch > > &matches1to2, const std::vector< std::vector< uchar > > &correctMatches1to2Mask, std::vector< Point2f > &recallPrecisionCurve)
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 >())
void	cv::FAST (InputArray image, std::vector< KeyPoint > &keypoints, int threshold, bool nonmaxSuppression=true, FastFeatureDetector::DetectorType type=FastFeatureDetector::TYPE_9_16)
	Detects corners using the FAST algorithm.
int	cv::getNearestPoint (const std::vector< Point2f > &recallPrecisionCurve, float l_precision)
float	cv::getRecall (const std::vector< Point2f > &recallPrecisionCurve, float l_precision)
void	cv::goodFeaturesToTrack (InputArray image, OutputArray corners, int maxCorners, double qualityLevel, double minDistance, InputArray mask, int blockSize, int gradientSize, bool useHarrisDetector=false, double k=0.04)
void	cv::goodFeaturesToTrack (InputArray image, OutputArray corners, int maxCorners, double qualityLevel, double minDistance, InputArray mask, OutputArray cornersQuality, int blockSize=3, int gradientSize=3, bool useHarrisDetector=false, double k=0.04)
	Same as above, but returns also quality measure of the detected corners.
void	cv::goodFeaturesToTrack (InputArray image, OutputArray corners, int maxCorners, double qualityLevel, double minDistance, InputArray mask=noArray(), int blockSize=3, bool useHarrisDetector=false, double k=0.04)
	Determines strong corners on an image.

Typedef Documentation

AffineDescriptorExtractor

typedef AffineFeature cv::AffineDescriptorExtractor

#include <opencv2/features.hpp>

AffineFeatureDetector

typedef AffineFeature cv::AffineFeatureDetector

#include <opencv2/features.hpp>

DescriptorExtractor

typedef Feature2D cv::DescriptorExtractor

#include <opencv2/features.hpp>

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

#include <opencv2/features.hpp>

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

#include <opencv2/features.hpp>

SiftFeatureDetector

typedef SIFT cv::SiftFeatureDetector

#include <opencv2/features.hpp>

Function Documentation

computeRecallPrecisionCurve()

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

#include <opencv2/features.hpp>

evaluateFeatureDetector()

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 >() )

#include <opencv2/features.hpp>

FAST()

void cv::FAST	(	InputArray	image,
		std::vector< KeyPoint > &	keypoints,
		int	threshold,
		bool	nonmaxSuppression = true,
		FastFeatureDetector::DetectorType	type = FastFeatureDetector::TYPE_9_16 )

#include <opencv2/features.hpp>

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 keypoints (corners).
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] .

Check the corresponding tutorial for more details.

getNearestPoint()

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

#include <opencv2/features.hpp>

getRecall()

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

#include <opencv2/features.hpp>

goodFeaturesToTrack() [1/3]

void cv::goodFeaturesToTrack	(	InputArray	image,
		OutputArray	corners,
		int	maxCorners,
		double	qualityLevel,
		double	minDistance,
		InputArray	mask,
		int	blockSize,
		int	gradientSize,
		bool	useHarrisDetector = false,
		double	k = 0.04 )

Python:
	cv.goodFeaturesToTrack(	image, maxCorners, qualityLevel, minDistance[, corners[, mask[, blockSize[, useHarrisDetector[, k]]]]]	) ->	corners
	cv.goodFeaturesToTrack(	image, maxCorners, qualityLevel, minDistance, mask, blockSize, gradientSize[, corners[, useHarrisDetector[, k]]]	) ->	corners
	cv.goodFeaturesToTrackWithQuality(	image, maxCorners, qualityLevel, minDistance, mask[, corners[, cornersQuality[, blockSize[, gradientSize[, useHarrisDetector[, k]]]]]]	) ->	corners, cornersQuality

#include <opencv2/features.hpp>

goodFeaturesToTrack() [2/3]

void cv::goodFeaturesToTrack	(	InputArray	image,
		OutputArray	corners,
		int	maxCorners,
		double	qualityLevel,
		double	minDistance,
		InputArray	mask,
		OutputArray	cornersQuality,
		int	blockSize = 3,
		int	gradientSize = 3,
		bool	useHarrisDetector = false,
		double	k = 0.04 )

Python:
	cv.goodFeaturesToTrack(	image, maxCorners, qualityLevel, minDistance[, corners[, mask[, blockSize[, useHarrisDetector[, k]]]]]	) ->	corners
	cv.goodFeaturesToTrack(	image, maxCorners, qualityLevel, minDistance, mask, blockSize, gradientSize[, corners[, useHarrisDetector[, k]]]	) ->	corners
	cv.goodFeaturesToTrackWithQuality(	image, maxCorners, qualityLevel, minDistance, mask[, corners[, cornersQuality[, blockSize[, gradientSize[, useHarrisDetector[, k]]]]]]	) ->	corners, cornersQuality

#include <opencv2/features.hpp>

Same as above, but returns also quality measure of the detected corners.

Parameters

image	Input 8-bit or floating-point 32-bit, single-channel image.
corners	Output vector of detected corners.
maxCorners	Maximum number of corners to return. If there are more corners than are found, the strongest of them is returned. maxCorners <= 0 implies that no limit on the maximum is set and all detected corners are returned.
qualityLevel	Parameter characterizing the minimal accepted quality of image corners. The parameter value is multiplied by the best corner quality measure, which is the minimal eigenvalue (see cornerMinEigenVal ) or the Harris function response (see cornerHarris ). The corners with the quality measure less than the product are rejected. For example, if the best corner has the quality measure = 1500, and the qualityLevel=0.01 , then all the corners with the quality measure less than 15 are rejected.
minDistance	Minimum possible Euclidean distance between the returned corners.
mask	Region of interest. If the image is not empty (it needs to have the type CV_8UC1 and the same size as image ), it specifies the region in which the corners are detected.
cornersQuality	Output vector of quality measure of the detected corners.
blockSize	Size of an average block for computing a derivative covariation matrix over each pixel neighborhood. See cornerEigenValsAndVecs .
gradientSize	Aperture parameter for the Sobel operator used for derivatives computation. See cornerEigenValsAndVecs .
useHarrisDetector	Parameter indicating whether to use a Harris detector (see cornerHarris) or cornerMinEigenVal.
k	Free parameter of the Harris detector.

goodFeaturesToTrack() [3/3]

void cv::goodFeaturesToTrack	(	InputArray	image,
		OutputArray	corners,
		int	maxCorners,
		double	qualityLevel,
		double	minDistance,
		InputArray	mask = noArray(),
		int	blockSize = 3,
		bool	useHarrisDetector = false,
		double	k = 0.04 )

Python:
	cv.goodFeaturesToTrack(	image, maxCorners, qualityLevel, minDistance[, corners[, mask[, blockSize[, useHarrisDetector[, k]]]]]	) ->	corners
	cv.goodFeaturesToTrack(	image, maxCorners, qualityLevel, minDistance, mask, blockSize, gradientSize[, corners[, useHarrisDetector[, k]]]	) ->	corners
	cv.goodFeaturesToTrackWithQuality(	image, maxCorners, qualityLevel, minDistance, mask[, corners[, cornersQuality[, blockSize[, gradientSize[, useHarrisDetector[, k]]]]]]	) ->	corners, cornersQuality

#include <opencv2/features.hpp>

Determines strong corners on an image.

The function finds the most prominent corners in the image or in the specified image region, as described in [Shi94]

• Function calculates the corner quality measure at every source image pixel using the cornerMinEigenVal or cornerHarris .
• Function performs a non-maximum suppression (the local maximums in 3 x 3 neighborhood are retained).
• The corners with the minimal eigenvalue less than \(\texttt{qualityLevel} \cdot \max_{x,y} qualityMeasureMap(x,y)\) are rejected.
• The remaining corners are sorted by the quality measure in the descending order.
• Function throws away each corner for which there is a stronger corner at a distance less than maxDistance.

The function can be used to initialize a point-based tracker of an object.

Note

If the function is called with different values A and B of the parameter qualityLevel , and A > B, the vector of returned corners with qualityLevel=A will be the prefix of the output vector with qualityLevel=B .

Parameters

image	Input 8-bit or floating-point 32-bit, single-channel image.
corners	Output vector of detected corners.
maxCorners	Maximum number of corners to return. If there are more corners than are found, the strongest of them is returned. maxCorners <= 0 implies that no limit on the maximum is set and all detected corners are returned.
qualityLevel	Parameter characterizing the minimal accepted quality of image corners. The parameter value is multiplied by the best corner quality measure, which is the minimal eigenvalue (see cornerMinEigenVal ) or the Harris function response (see cornerHarris ). The corners with the quality measure less than the product are rejected. For example, if the best corner has the quality measure = 1500, and the qualityLevel=0.01 , then all the corners with the quality measure less than 15 are rejected.
minDistance	Minimum possible Euclidean distance between the returned corners.
mask	Optional region of interest. If the image is not empty (it needs to have the type CV_8UC1 and the same size as image ), it specifies the region in which the corners are detected.
blockSize	Size of an average block for computing a derivative covariation matrix over each pixel neighborhood. See cornerEigenValsAndVecs .
useHarrisDetector	Parameter indicating whether to use a Harris detector (see cornerHarris) or cornerMinEigenVal.
k	Free parameter of the Harris detector.

See also

cornerMinEigenVal, cornerHarris, calcOpticalFlowPyrLK, estimateRigidTransform,

Examples

samples/cpp/lkdemo.cpp.