Brute-force descriptor matcher. More...

#include <opencv2/features2d.hpp>

Inheritance diagram for cv::BFMatcher:

Collaboration diagram for cv::BFMatcher:

[legend]

Public Types
enum	MatcherType { FLANNBASED = 1, BRUTEFORCE = 2, BRUTEFORCE_L1 = 3, BRUTEFORCE_HAMMING = 4, BRUTEFORCE_HAMMINGLUT = 5, BRUTEFORCE_SL2 = 6 }

Public Member Functions
	BFMatcher (int normType=NORM_L2, bool crossCheck=false)
	Brute-force matcher constructor (obsolete). More...

virtual	~BFMatcher ()

virtual void	add (InputArrayOfArrays descriptors)
	Adds descriptors to train a CPU(trainDescCollectionis) or GPU(utrainDescCollectionis) descriptor collection. More...

virtual void	clear () CV_OVERRIDE
	Clears the train descriptor collections. More...

virtual Ptr< DescriptorMatcher >	clone (bool emptyTrainData=false) const CV_OVERRIDE
	Clones the matcher. More...

virtual bool	empty () const CV_OVERRIDE
	Returns true if there are no train descriptors in the both collections. More...

virtual String	getDefaultName () const
	Returns the algorithm string identifier. More...

const std::vector< Mat > &	getTrainDescriptors () const
	Returns a constant link to the train descriptor collection trainDescCollection . More...

virtual bool	isMaskSupported () const CV_OVERRIDE
	Returns true if the descriptor matcher supports masking permissible matches. More...

void	knnMatch (InputArray queryDescriptors, InputArray trainDescriptors, std::vector< std::vector< DMatch > > &matches, int k, InputArray mask=noArray(), bool compactResult=false) const
	Finds the k best matches for each descriptor from a query set. More...

void	knnMatch (InputArray queryDescriptors, std::vector< std::vector< DMatch > > &matches, int k, InputArrayOfArrays masks=noArray(), bool compactResult=false)
	This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. More...

void	match (InputArray queryDescriptors, InputArray trainDescriptors, std::vector< DMatch > &matches, InputArray mask=noArray()) const
	Finds the best match for each descriptor from a query set. More...

void	match (InputArray queryDescriptors, std::vector< DMatch > &matches, InputArrayOfArrays masks=noArray())
	This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. More...

void	radiusMatch (InputArray queryDescriptors, InputArray trainDescriptors, std::vector< std::vector< DMatch > > &matches, float maxDistance, InputArray mask=noArray(), bool compactResult=false) const
	For each query descriptor, finds the training descriptors not farther than the specified distance. More...

void	radiusMatch (InputArray queryDescriptors, std::vector< std::vector< DMatch > > &matches, float maxDistance, InputArrayOfArrays masks=noArray(), bool compactResult=false)
	This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. More...

void	read (const String &fileName)

virtual void	read (const FileNode &) CV_OVERRIDE
	Reads algorithm parameters from a file storage. More...

virtual void	save (const String &filename) const
	Saves the algorithm to a file. More...

virtual void	train ()
	Trains a descriptor matcher. More...

void	write (const String &fileName) const

virtual void	write (FileStorage &) const CV_OVERRIDE
	Stores algorithm parameters in a file storage. More...

void	write (const Ptr< FileStorage > &fs, const String &name=String()) const

Static Public Member Functions
static Ptr< DescriptorMatcher >	create (const String &descriptorMatcherType)
	Creates a descriptor matcher of a given type with the default parameters (using default constructor). More...

static Ptr< DescriptorMatcher >	create (const DescriptorMatcher::MatcherType &matcherType)

static Ptr< BFMatcher >	create (int normType=NORM_L2, bool crossCheck=false)
	Brute-force matcher create method. More...

template<typename _Tp >
static Ptr< _Tp >	load (const String &filename, const String &objname=String())
	Loads algorithm from the file. More...

template<typename _Tp >
static Ptr< _Tp >	loadFromString (const String &strModel, const String &objname=String())
	Loads algorithm from a String. More...

Protected Member Functions
void	checkMasks (InputArrayOfArrays masks, int queryDescriptorsCount) const

virtual void	knnMatchImpl (InputArray queryDescriptors, std::vector< std::vector< DMatch > > &matches, int k, InputArrayOfArrays masks=noArray(), bool compactResult=false) CV_OVERRIDE
	In fact the matching is implemented only by the following two methods. More...

virtual void	radiusMatchImpl (InputArray queryDescriptors, std::vector< std::vector< DMatch > > &matches, float maxDistance, InputArrayOfArrays masks=noArray(), bool compactResult=false) CV_OVERRIDE

void	writeFormat (FileStorage &fs) const

Static Protected Member Functions
static Mat	clone_op (Mat m)

static bool	isMaskedOut (InputArrayOfArrays masks, int queryIdx)

static bool	isPossibleMatch (InputArray mask, int queryIdx, int trainIdx)

Protected Attributes
bool	crossCheck

int	normType

std::vector< Mat >	trainDescCollection
	Collection of descriptors from train images. More...

std::vector< UMat >	utrainDescCollection

Detailed Description

Brute-force descriptor matcher.

For each descriptor in the first set, this matcher finds the closest descriptor in the second set by trying each one. This descriptor matcher supports masking permissible matches of descriptor sets.

Member Enumeration Documentation

◆ MatcherType

enum cv::DescriptorMatcher::MatcherType

inherited

Enumerator
FLANNBASED
BRUTEFORCE
BRUTEFORCE_L1
BRUTEFORCE_HAMMING
BRUTEFORCE_HAMMINGLUT
BRUTEFORCE_SL2

Constructor & Destructor Documentation

◆ BFMatcher()

cv::BFMatcher::BFMatcher	(	int	normType = `NORM_L2`,
		bool	crossCheck = `false`
	)

Brute-force matcher constructor (obsolete).

Please use BFMatcher.create()

◆ ~BFMatcher()

virtual cv::BFMatcher::~BFMatcher ( )

inlinevirtual

Member Function Documentation

◆ add()

virtual void cv::DescriptorMatcher::add ( InputArrayOfArrays descriptors )

virtualinherited

Adds descriptors to train a CPU(trainDescCollectionis) or GPU(utrainDescCollectionis) descriptor collection.

If the collection is not empty, the new descriptors are added to existing train descriptors.

Parameters

descriptors Descriptors to add. Each descriptors[i] is a set of descriptors from the same train image.

Reimplemented in cv::FlannBasedMatcher.

◆ checkMasks()

void cv::DescriptorMatcher::checkMasks	(	InputArrayOfArrays	masks,
		int	queryDescriptorsCount
	)		const

protectedinherited

◆ clear()

virtual void cv::DescriptorMatcher::clear ( )

virtualinherited

Clears the train descriptor collections.

Reimplemented from cv::Algorithm.

Reimplemented in cv::FlannBasedMatcher.

◆ clone()

virtual Ptr<DescriptorMatcher> cv::BFMatcher::clone ( bool emptyTrainData = false ) const

virtual

Clones the matcher.

Parameters

emptyTrainData If emptyTrainData is false, the method creates a deep copy of the object, that is, copies both parameters and train data. If emptyTrainData is true, the method creates an object copy with the current parameters but with empty train data.

Implements cv::DescriptorMatcher.

◆ clone_op()

static Mat cv::DescriptorMatcher::clone_op ( Mat m )

inlinestaticprotectedinherited

References cv::Mat::clone().

Here is the call graph for this function:

◆ create() [1/3]

static Ptr<DescriptorMatcher> cv::DescriptorMatcher::create ( const String & descriptorMatcherType )

staticinherited

Creates a descriptor matcher of a given type with the default parameters (using default constructor).

Parameters

descriptorMatcherType

Descriptor matcher type. Now the following matcher types are supported:

BruteForce (it uses L2 )
BruteForce-L1
BruteForce-Hamming
BruteForce-Hamming(2)
FlannBased

◆ create() [2/3]

static Ptr<DescriptorMatcher> cv::DescriptorMatcher::create ( const DescriptorMatcher::MatcherType & matcherType )

staticinherited

◆ create() [3/3]

static Ptr<BFMatcher> cv::BFMatcher::create	(	int	normType = `NORM_L2`,
		bool	crossCheck = `false`
	)

static

Brute-force matcher create method.

Parameters

normType One of NORM_L1, NORM_L2, NORM_HAMMING, NORM_HAMMING2. L1 and L2 norms are preferable choices for SIFT and SURF descriptors, NORM_HAMMING should be used with ORB, BRISK and BRIEF, NORM_HAMMING2 should be used with ORB when WTA_K==3 or 4 (see ORB::ORB constructor description).

crossCheck If it is false, this is will be default BFMatcher behaviour when it finds the k nearest neighbors for each query descriptor. If crossCheck==true, then the knnMatch() method with k=1 will only return pairs (i,j) such that for i-th query descriptor the j-th descriptor in the matcher's collection is the nearest and vice versa, i.e. the BFMatcher will only return consistent pairs. Such technique usually produces best results with minimal number of outliers when there are enough matches. This is alternative to the ratio test, used by D. Lowe in SIFT paper.

◆ empty()

virtual bool cv::DescriptorMatcher::empty ( ) const

virtualinherited

Returns true if there are no train descriptors in the both collections.

Reimplemented from cv::Algorithm.

◆ getDefaultName()

virtual String cv::Algorithm::getDefaultName ( ) const

virtualinherited

Returns the algorithm string identifier.

This string is used as top level xml/yml node tag when the object is saved to a file or string.

Reimplemented in cv::AKAZE, cv::KAZE, cv::SimpleBlobDetector, cv::GFTTDetector, cv::AgastFeatureDetector, cv::FastFeatureDetector, cv::MSER, cv::ORB, cv::BRISK, and cv::Feature2D.

◆ getTrainDescriptors()

const std::vector<Mat>& cv::DescriptorMatcher::getTrainDescriptors ( ) const

inherited

Returns a constant link to the train descriptor collection trainDescCollection .

◆ isMaskedOut()

static bool cv::DescriptorMatcher::isMaskedOut	(	InputArrayOfArrays	masks,
		int	queryIdx
	)

staticprotectedinherited

◆ isMaskSupported()

virtual bool cv::BFMatcher::isMaskSupported ( ) const

inlinevirtual

Returns true if the descriptor matcher supports masking permissible matches.

Implements cv::DescriptorMatcher.

References CV_OVERRIDE, CV_WRAP, cv::noArray(), and cv::NORM_L2.

Here is the call graph for this function:

◆ isPossibleMatch()

static bool cv::DescriptorMatcher::isPossibleMatch	(	InputArray	mask,
		int	queryIdx,
		int	trainIdx
	)

staticprotectedinherited

◆ knnMatch() [1/2]

void cv::DescriptorMatcher::knnMatch	(	InputArray	queryDescriptors,
		InputArray	trainDescriptors,
		std::vector< std::vector< DMatch > > &	matches,
		int	k,
		InputArray	mask = `noArray()`,
		bool	compactResult = `false`
	)		const

inherited

Finds the k best matches for each descriptor from a query set.

Parameters

queryDescriptors	Query set of descriptors.
trainDescriptors	Train set of descriptors. This set is not added to the train descriptors collection stored in the class object.
mask	Mask specifying permissible matches between an input query and train matrices of descriptors.
matches	Matches. Each matches[i] is k or less matches for the same query descriptor.
k	Count of best matches found per each query descriptor or less if a query descriptor has less than k possible matches in total.
compactResult	Parameter used when the mask (or masks) is not empty. If compactResult is false, the matches vector has the same size as queryDescriptors rows. If compactResult is true, the matches vector does not contain matches for fully masked-out query descriptors.

These extended variants of DescriptorMatcher::match methods find several best matches for each query descriptor. The matches are returned in the distance increasing order. See DescriptorMatcher::match for the details about query and train descriptors.

◆ knnMatch() [2/2]

void cv::DescriptorMatcher::knnMatch	(	InputArray	queryDescriptors,
		std::vector< std::vector< DMatch > > &	matches,
		int	k,
		InputArrayOfArrays	masks = `noArray()`,
		bool	compactResult = `false`
	)

inherited

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

Parameters

queryDescriptors	Query set of descriptors.
matches	Matches. Each matches[i] is k or less matches for the same query descriptor.
k	Count of best matches found per each query descriptor or less if a query descriptor has less than k possible matches in total.
masks	Set of masks. Each masks[i] specifies permissible matches between the input query descriptors and stored train descriptors from the i-th image trainDescCollection[i].
compactResult	Parameter used when the mask (or masks) is not empty. If compactResult is false, the matches vector has the same size as queryDescriptors rows. If compactResult is true, the matches vector does not contain matches for fully masked-out query descriptors.

◆ knnMatchImpl()

virtual void cv::BFMatcher::knnMatchImpl	(	InputArray	queryDescriptors,
		std::vector< std::vector< DMatch > > &	matches,
		int	k,
		InputArrayOfArrays	masks = `noArray()`,
		bool	compactResult = `false`
	)

protectedvirtual

In fact the matching is implemented only by the following two methods.

These methods suppose that the class object has been trained already. Public match methods call these methods after calling train().

Implements cv::DescriptorMatcher.

◆ load()

template<typename _Tp >

static Ptr<_Tp> cv::Algorithm::load	(	const String &	filename,
		const String &	objname = `String()`
	)

inlinestaticinherited

Loads algorithm from the file.

Parameters

filename	Name of the file to read.
objname	The optional name of the node to read (if empty, the first top-level node will be used)

This is static template method of Algorithm. It's usage is following (in the case of SVM):

Ptr<SVM> svm = Algorithm::load<SVM>("my_svm_model.xml");

In order to make this method work, the derived class must overwrite Algorithm::read(const FileNode& fn).

References CV_Assert, cv::FileNode::empty(), cv::FileStorage::getFirstTopLevelNode(), cv::FileStorage::isOpened(), and cv::FileStorage::READ.

Here is the call graph for this function:

◆ loadFromString()

template<typename _Tp >

static Ptr<_Tp> cv::Algorithm::loadFromString	(	const String &	strModel,
		const String &	objname = `String()`
	)

inlinestaticinherited

Loads algorithm from a String.

Parameters

strModel	The string variable containing the model you want to load.
objname	The optional name of the node to read (if empty, the first top-level node will be used)

This is static template method of Algorithm. It's usage is following (in the case of SVM):

Ptr<SVM> svm = Algorithm::loadFromString<SVM>(myStringModel);

References CV_WRAP, cv::FileNode::empty(), cv::FileStorage::getFirstTopLevelNode(), cv::FileStorage::MEMORY, and cv::FileStorage::READ.

Here is the call graph for this function:

◆ match() [1/2]

void cv::DescriptorMatcher::match	(	InputArray	queryDescriptors,
		InputArray	trainDescriptors,
		std::vector< DMatch > &	matches,
		InputArray	mask = `noArray()`
	)		const

inherited

Finds the best match for each descriptor from a query set.

Parameters

queryDescriptors	Query set of descriptors.
trainDescriptors	Train set of descriptors. This set is not added to the train descriptors collection stored in the class object.
matches	Matches. If a query descriptor is masked out in mask , no match is added for this descriptor. So, matches size may be smaller than the query descriptors count.
mask	Mask specifying permissible matches between an input query and train matrices of descriptors.

In the first variant of this method, the train descriptors are passed as an input argument. In the second variant of the method, train descriptors collection that was set by DescriptorMatcher::add is used. Optional mask (or masks) can be passed to specify which query and training descriptors can be matched. Namely, queryDescriptors[i] can be matched with trainDescriptors[j] only if mask.at<uchar>(i,j) is non-zero.

◆ match() [2/2]

void cv::DescriptorMatcher::match	(	InputArray	queryDescriptors,
		std::vector< DMatch > &	matches,
		InputArrayOfArrays	masks = `noArray()`
	)

inherited

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

Parameters

queryDescriptors	Query set of descriptors.
matches	Matches. If a query descriptor is masked out in mask , no match is added for this descriptor. So, matches size may be smaller than the query descriptors count.
masks	Set of masks. Each masks[i] specifies permissible matches between the input query descriptors and stored train descriptors from the i-th image trainDescCollection[i].

◆ radiusMatch() [1/2]

void cv::DescriptorMatcher::radiusMatch	(	InputArray	queryDescriptors,
		InputArray	trainDescriptors,
		std::vector< std::vector< DMatch > > &	matches,
		float	maxDistance,
		InputArray	mask = `noArray()`,
		bool	compactResult = `false`
	)		const

inherited

For each query descriptor, finds the training descriptors not farther than the specified distance.

Parameters

queryDescriptors	Query set of descriptors.
trainDescriptors	Train set of descriptors. This set is not added to the train descriptors collection stored in the class object.
matches	Found matches.
compactResult	Parameter used when the mask (or masks) is not empty. If compactResult is false, the matches vector has the same size as queryDescriptors rows. If compactResult is true, the matches vector does not contain matches for fully masked-out query descriptors.
maxDistance	Threshold for the distance between matched descriptors. Distance means here metric distance (e.g. Hamming distance), not the distance between coordinates (which is measured in Pixels)!
mask	Mask specifying permissible matches between an input query and train matrices of descriptors.

For each query descriptor, the methods find such training descriptors that the distance between the query descriptor and the training descriptor is equal or smaller than maxDistance. Found matches are returned in the distance increasing order.

◆ radiusMatch() [2/2]

void cv::DescriptorMatcher::radiusMatch	(	InputArray	queryDescriptors,
		std::vector< std::vector< DMatch > > &	matches,
		float	maxDistance,
		InputArrayOfArrays	masks = `noArray()`,
		bool	compactResult = `false`
	)

inherited

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

Parameters

queryDescriptors	Query set of descriptors.
matches	Found matches.
maxDistance	Threshold for the distance between matched descriptors. Distance means here metric distance (e.g. Hamming distance), not the distance between coordinates (which is measured in Pixels)!
masks	Set of masks. Each masks[i] specifies permissible matches between the input query descriptors and stored train descriptors from the i-th image trainDescCollection[i].
compactResult	Parameter used when the mask (or masks) is not empty. If compactResult is false, the matches vector has the same size as queryDescriptors rows. If compactResult is true, the matches vector does not contain matches for fully masked-out query descriptors.

◆ radiusMatchImpl()

virtual void cv::BFMatcher::radiusMatchImpl	(	InputArray	queryDescriptors,
		std::vector< std::vector< DMatch > > &	matches,
		float	maxDistance,
		InputArrayOfArrays	masks = `noArray()`,
		bool	compactResult = `false`
	)

protectedvirtual

Implements cv::DescriptorMatcher.

◆ read() [1/2]

void cv::DescriptorMatcher::read ( const String & fileName )

inlineinherited

References CV_OVERRIDE, CV_WRAP, cv::FileStorage::READ, and cv::FileStorage::root().

Here is the call graph for this function:

◆ read() [2/2]

virtual void cv::DescriptorMatcher::read ( const FileNode & fn )

virtualinherited

Reads algorithm parameters from a file storage.

Reimplemented from cv::Algorithm.

Reimplemented in cv::FlannBasedMatcher.

◆ save()

virtual void cv::Algorithm::save ( const String & filename ) const

virtualinherited

Saves the algorithm to a file.

In order to make this method work, the derived class must implement Algorithm::write(FileStorage& fs).

◆ train()

virtual void cv::DescriptorMatcher::train ( )

virtualinherited

Trains a descriptor matcher.

Trains a descriptor matcher (for example, the flann index). In all methods to match, the method train() is run every time before matching. Some descriptor matchers (for example, BruteForceMatcher) have an empty implementation of this method. Other matchers really train their inner structures (for example, FlannBasedMatcher trains flann::Index ).

Reimplemented in cv::FlannBasedMatcher.

◆ write() [1/3]

void cv::DescriptorMatcher::write ( const String & fileName ) const

inlineinherited

References cv::FileStorage::WRITE.

◆ write() [2/3]

virtual void cv::DescriptorMatcher::write ( FileStorage & fs ) const

virtualinherited

Stores algorithm parameters in a file storage.

Reimplemented from cv::Algorithm.

Reimplemented in cv::FlannBasedMatcher.

◆ write() [3/3]

void cv::DescriptorMatcher::write	(	const Ptr< FileStorage > &	fs,
		const String &	name = `String()`
	)		const

inlineinherited

References cv::Algorithm::write().

Here is the call graph for this function:

◆ writeFormat()

void cv::Algorithm::writeFormat ( FileStorage & fs ) const

protectedinherited

Member Data Documentation

◆ crossCheck

bool cv::BFMatcher::crossCheck

protected

◆ normType

int cv::BFMatcher::normType

protected

◆ trainDescCollection

std::vector<Mat> cv::DescriptorMatcher::trainDescCollection

protectedinherited

Collection of descriptors from train images.

◆ utrainDescCollection

std::vector<UMat> cv::DescriptorMatcher::utrainDescCollection

protectedinherited

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

opencv2/features2d.hpp

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Static Protected Member Functions

Protected Attributes

Detailed Description

Member Enumeration Documentation

◆ MatcherType

Constructor & Destructor Documentation

◆ BFMatcher()

◆ ~BFMatcher()

Member Function Documentation

◆ add()

◆ checkMasks()

◆ clear()

◆ clone()

◆ clone_op()

◆ create() [1/3]

◆ create() [2/3]

◆ create() [3/3]

◆ empty()

◆ getDefaultName()

◆ getTrainDescriptors()

◆ isMaskedOut()

◆ isMaskSupported()

◆ isPossibleMatch()

◆ knnMatch() [1/2]

◆ knnMatch() [2/2]

◆ knnMatchImpl()

◆ load()

◆ loadFromString()

◆ match() [1/2]

◆ match() [2/2]

◆ radiusMatch() [1/2]

◆ radiusMatch() [2/2]

◆ radiusMatchImpl()

◆ read() [1/2]

◆ read() [2/2]

◆ save()

◆ train()

◆ write() [1/3]

◆ write() [2/3]

◆ write() [3/3]

◆ writeFormat()

Member Data Documentation

◆ crossCheck

◆ normType

◆ trainDescCollection

◆ utrainDescCollection