cv::SIFT Class Reference

Class for extracting keypoints and computing descriptors using the Scale Invariant Feature Transform (SIFT) algorithm by D. Lowe [173] . More...

#include <opencv2/features2d.hpp>

Collaboration diagram for cv::SIFT:

Public Member Functions
virtual double	getContrastThreshold () const =0
virtual String	getDefaultName () const CV_OVERRIDE
virtual double	getEdgeThreshold () const =0
virtual int	getNFeatures () const =0
virtual int	getNOctaveLayers () const =0
virtual double	getSigma () const =0
virtual void	setContrastThreshold (double contrastThreshold)=0
virtual void	setEdgeThreshold (double edgeThreshold)=0
virtual void	setNFeatures (int maxFeatures)=0
virtual void	setNOctaveLayers (int nOctaveLayers)=0
virtual void	setSigma (double sigma)=0
Public Member Functions inherited from cv::Feature2D
virtual	~Feature2D ()
virtual void	compute (InputArray image, std::vector< KeyPoint > &keypoints, OutputArray descriptors)
	Computes the descriptors for a set of keypoints detected in an image (first variant) or image set (second variant).
virtual void	compute (InputArrayOfArrays images, std::vector< std::vector< KeyPoint > > &keypoints, OutputArrayOfArrays descriptors)
virtual int	defaultNorm () const
virtual int	descriptorSize () const
virtual int	descriptorType () const
virtual void	detect (InputArray image, std::vector< KeyPoint > &keypoints, InputArray mask=noArray())
	Detects keypoints in an image (first variant) or image set (second variant).
virtual void	detect (InputArrayOfArrays images, std::vector< std::vector< KeyPoint > > &keypoints, InputArrayOfArrays masks=noArray())
virtual void	detectAndCompute (InputArray image, InputArray mask, std::vector< KeyPoint > &keypoints, OutputArray descriptors, bool useProvidedKeypoints=false)
virtual bool	empty () const CV_OVERRIDE
	Return true if detector object is empty.
virtual void	read (const FileNode &) CV_OVERRIDE
	Reads algorithm parameters from a file storage.
void	read (const String &fileName)
void	write (const Ptr< FileStorage > &fs, const String &name) const
void	write (const String &fileName) const
virtual void	write (FileStorage &) const CV_OVERRIDE
	Stores algorithm parameters in a file storage.
void	write (FileStorage &fs, const String &name) const
Public Member Functions inherited from cv::Algorithm
	Algorithm ()
virtual	~Algorithm ()
virtual void	clear ()
	Clears the algorithm state.
virtual void	save (const String &filename) const
void	write (const Ptr< FileStorage > &fs, const String &name=String()) const
void	write (FileStorage &fs, const String &name) const

Static Public Member Functions
static Ptr< SIFT >	create (int nfeatures, int nOctaveLayers, double contrastThreshold, double edgeThreshold, double sigma, int descriptorType, bool enable_precise_upscale=false)
	Create SIFT with specified descriptorType.
static Ptr< SIFT >	create (int nfeatures=0, int nOctaveLayers=3, double contrastThreshold=0.04, double edgeThreshold=10, double sigma=1.6, bool enable_precise_upscale=false)
Static Public Member Functions inherited from cv::Algorithm
template<typename _Tp >
static Ptr< _Tp >	load (const String &filename, const String &objname=String())
	Loads algorithm from the file.
template<typename _Tp >
static Ptr< _Tp >	loadFromString (const String &strModel, const String &objname=String())
	Loads algorithm from a String.
template<typename _Tp >
static Ptr< _Tp >	read (const FileNode &fn)
	Reads algorithm from the file node.

Additional Inherited Members
Protected Member Functions inherited from cv::Algorithm
void	writeFormat (FileStorage &fs) const

Detailed Description

Class for extracting keypoints and computing descriptors using the Scale Invariant Feature Transform (SIFT) algorithm by D. Lowe [173] .

Member Function Documentation

create() [1/2]

static Ptr< SIFT > cv::SIFT::create ( int  nfeatures, int  nOctaveLayers, double  contrastThreshold, double  edgeThreshold, double  sigma, int  descriptorType, bool  enable_precise_upscale = false  )

static

Python:
	cv.SIFT.create(	[, nfeatures[, nOctaveLayers[, contrastThreshold[, edgeThreshold[, sigma[, enable_precise_upscale]]]]]]	) ->	retval
	cv.SIFT.create(	nfeatures, nOctaveLayers, contrastThreshold, edgeThreshold, sigma, descriptorType[, enable_precise_upscale]	) ->	retval
	cv.SIFT_create(	[, nfeatures[, nOctaveLayers[, contrastThreshold[, edgeThreshold[, sigma[, enable_precise_upscale]]]]]]	) ->	retval
	cv.SIFT_create(	nfeatures, nOctaveLayers, contrastThreshold, edgeThreshold, sigma, descriptorType[, enable_precise_upscale]	) ->	retval

Create SIFT with specified descriptorType.

Parameters

nfeatures	The number of best features to retain. The features are ranked by their scores (measured in SIFT algorithm as the local contrast)
nOctaveLayers	The number of layers in each octave. 3 is the value used in D. Lowe paper. The number of octaves is computed automatically from the image resolution.
contrastThreshold	The contrast threshold used to filter out weak features in semi-uniform (low-contrast) regions. The larger the threshold, the less features are produced by the detector.

Note

The contrast threshold will be divided by nOctaveLayers when the filtering is applied. When nOctaveLayers is set to default and if you want to use the value used in D. Lowe paper, 0.03, set this argument to 0.09.

Parameters

edgeThreshold	The threshold used to filter out edge-like features. Note that the its meaning is different from the contrastThreshold, i.e. the larger the edgeThreshold, the less features are filtered out (more features are retained).
sigma	The sigma of the Gaussian applied to the input image at the octave #0. If your image is captured with a weak camera with soft lenses, you might want to reduce the number.
descriptorType	The type of descriptors. Only CV_32F and CV_8U are supported.
enable_precise_upscale	Whether to enable precise upscaling in the scale pyramid, which maps index \(\texttt{x}\) to \(\texttt{2x}\). This prevents localization bias. The option is disabled by default.

create() [2/2]

static Ptr< SIFT > cv::SIFT::create ( int  nfeatures = 0, int  nOctaveLayers = 3, double  contrastThreshold = 0.04, double  edgeThreshold = 10, double  sigma = 1.6, bool  enable_precise_upscale = false  )

static

Python:
	cv.SIFT.create(	[, nfeatures[, nOctaveLayers[, contrastThreshold[, edgeThreshold[, sigma[, enable_precise_upscale]]]]]]	) ->	retval
	cv.SIFT.create(	nfeatures, nOctaveLayers, contrastThreshold, edgeThreshold, sigma, descriptorType[, enable_precise_upscale]	) ->	retval
	cv.SIFT_create(	[, nfeatures[, nOctaveLayers[, contrastThreshold[, edgeThreshold[, sigma[, enable_precise_upscale]]]]]]	) ->	retval
	cv.SIFT_create(	nfeatures, nOctaveLayers, contrastThreshold, edgeThreshold, sigma, descriptorType[, enable_precise_upscale]	) ->	retval

Parameters

nfeatures	The number of best features to retain. The features are ranked by their scores (measured in SIFT algorithm as the local contrast)
nOctaveLayers	The number of layers in each octave. 3 is the value used in D. Lowe paper. The number of octaves is computed automatically from the image resolution.
contrastThreshold	The contrast threshold used to filter out weak features in semi-uniform (low-contrast) regions. The larger the threshold, the less features are produced by the detector.

Note

The contrast threshold will be divided by nOctaveLayers when the filtering is applied. When nOctaveLayers is set to default and if you want to use the value used in D. Lowe paper, 0.03, set this argument to 0.09.

Parameters

edgeThreshold	The threshold used to filter out edge-like features. Note that the its meaning is different from the contrastThreshold, i.e. the larger the edgeThreshold, the less features are filtered out (more features are retained).
sigma	The sigma of the Gaussian applied to the input image at the octave #0. If your image is captured with a weak camera with soft lenses, you might want to reduce the number.
enable_precise_upscale	Whether to enable precise upscaling in the scale pyramid, which maps index \(\texttt{x}\) to \(\texttt{2x}\). This prevents localization bias. The option is disabled by default.

getContrastThreshold()

virtual double cv::SIFT::getContrastThreshold ( ) const

pure virtual

Python:
	cv.SIFT.getContrastThreshold(		) ->	retval

getDefaultName()

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

virtual

Python:
	cv.SIFT.getDefaultName(		) ->	retval

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 from cv::Feature2D.

getEdgeThreshold()

virtual double cv::SIFT::getEdgeThreshold ( ) const

pure virtual

Python:
	cv.SIFT.getEdgeThreshold(		) ->	retval

getNFeatures()

virtual int cv::SIFT::getNFeatures ( ) const

pure virtual

Python:
	cv.SIFT.getNFeatures(		) ->	retval

getNOctaveLayers()

virtual int cv::SIFT::getNOctaveLayers ( ) const

pure virtual

Python:
	cv.SIFT.getNOctaveLayers(		) ->	retval

getSigma()

virtual double cv::SIFT::getSigma ( ) const

pure virtual

Python:
	cv.SIFT.getSigma(		) ->	retval

setContrastThreshold()

virtual void cv::SIFT::setContrastThreshold ( double  contrastThreshold )

pure virtual

Python:
	cv.SIFT.setContrastThreshold(	contrastThreshold	) ->	None

setEdgeThreshold()

virtual void cv::SIFT::setEdgeThreshold ( double  edgeThreshold )

pure virtual

Python:
	cv.SIFT.setEdgeThreshold(	edgeThreshold	) ->	None

setNFeatures()

virtual void cv::SIFT::setNFeatures ( int  maxFeatures )

pure virtual

Python:
	cv.SIFT.setNFeatures(	maxFeatures	) ->	None

setNOctaveLayers()

virtual void cv::SIFT::setNOctaveLayers ( int  nOctaveLayers )

pure virtual

Python:
	cv.SIFT.setNOctaveLayers(	nOctaveLayers	) ->	None

setSigma()

virtual void cv::SIFT::setSigma ( double  sigma )

pure virtual

Python:
	cv.SIFT.setSigma(	sigma	) ->	None

---

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

• opencv2/features2d.hpp