cv::BOWKMeansTrainer Class Reference

kmeans -based class to train visual vocabulary using the bag of visual words approach. More...

#include <opencv2/features2d.hpp>

Inheritance diagram for cv::BOWKMeansTrainer:

Collaboration diagram for cv::BOWKMeansTrainer:

Public Member Functions
	BOWKMeansTrainer (int clusterCount, const TermCriteria &termcrit=TermCriteria(), int attempts=3, int flags=KMEANS_PP_CENTERS)
	The constructor. More...
virtual	~BOWKMeansTrainer ()
void	add (const Mat &descriptors)
	Adds descriptors to a training set. More...
virtual void	clear ()
virtual Mat	cluster () const CV_OVERRIDE
virtual Mat	cluster (const Mat &descriptors) const CV_OVERRIDE
	Clusters train descriptors. More...
int	descriptorsCount () const
	Returns the count of all descriptors stored in the training set. More...
const std::vector< Mat > &	getDescriptors () const
	Returns a training set of descriptors. More...

Protected Attributes
int	attempts
int	clusterCount
std::vector< Mat >	descriptors
int	flags
int	size
TermCriteria	termcrit

Detailed Description

kmeans -based class to train visual vocabulary using the bag of visual words approach.

:

Constructor & Destructor Documentation

BOWKMeansTrainer()

cv::BOWKMeansTrainer::BOWKMeansTrainer	(	int	clusterCount,
		const TermCriteria &	termcrit = TermCriteria(),
		int	attempts = 3,
		int	flags = KMEANS_PP_CENTERS
	)

The constructor.

See also

cv::kmeans

~BOWKMeansTrainer()

virtual cv::BOWKMeansTrainer::~BOWKMeansTrainer ( )

virtual

Member Function Documentation

add()

void cv::BOWTrainer::add ( const Mat &  descriptors )

inherited

Adds descriptors to a training set.

Parameters

descriptors

Descriptors to add to a training set. Each row of the descriptors matrix is a descriptor.

The training set is clustered using clustermethod to construct the vocabulary.

clear()

virtual void cv::BOWTrainer::clear ( )

virtualinherited

cluster() [1/2]

virtual Mat cv::BOWKMeansTrainer::cluster ( ) const

virtual

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

Implements cv::BOWTrainer.

cluster() [2/2]

virtual Mat cv::BOWKMeansTrainer::cluster ( const Mat &  descriptors ) const

virtual

Clusters train descriptors.

Parameters

descriptors

Descriptors to cluster. Each row of the descriptors matrix is a descriptor. Descriptors are not added to the inner train descriptor set.

The vocabulary consists of cluster centers. So, this method returns the vocabulary. In the first variant of the method, train descriptors stored in the object are clustered. In the second variant, input descriptors are clustered.

Implements cv::BOWTrainer.

descriptorsCount()

int cv::BOWTrainer::descriptorsCount ( ) const

inherited

Returns the count of all descriptors stored in the training set.

getDescriptors()

const std::vector<Mat>& cv::BOWTrainer::getDescriptors ( ) const

inherited

Returns a training set of descriptors.

Member Data Documentation

attempts

int cv::BOWKMeansTrainer::attempts

protected

clusterCount

int cv::BOWKMeansTrainer::clusterCount

protected

descriptors

std::vector<Mat> cv::BOWTrainer::descriptors

protectedinherited

flags

int cv::BOWKMeansTrainer::flags

protected

size

int cv::BOWTrainer::size

protectedinherited

termcrit

TermCriteria cv::BOWKMeansTrainer::termcrit

protected

---

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

• opencv2/features2d.hpp