org.opencv.features2d

Class DescriptorExtractor

java.lang.Object

org.opencv.features2d.DescriptorExtractor

public class DescriptorExtractor
extends Object

Abstract base class for computing descriptors for image keypoints.

class CV_EXPORTS DescriptorExtractor

// C++ code:

public:

virtual ~DescriptorExtractor();

void compute(const Mat& image, vector& keypoints,

Mat& descriptors) const;

void compute(const vector& images, vector >& keypoints,

vector& descriptors) const;

virtual void read(const FileNode&);

virtual void write(FileStorage&) const;

virtual int descriptorSize() const = 0;

virtual int descriptorType() const = 0;

static Ptr create(const string& descriptorExtractorType);

protected:...

};

In this interface, a keypoint descriptor can be represented as a

dense, fixed-dimension vector of a basic type. Most descriptors follow this pattern as it simplifies computing distances between descriptors. Therefore, a collection of descriptors is represented as "Mat", where each row is a keypoint descriptor.

See Also:

org.opencv.features2d.DescriptorExtractor : public Algorithm

Field Summary

Fields

Modifier and Type	Field and Description
static int	BRIEF
static int	BRISK
static int	FREAK
protected long	nativeObj
static int	OPPONENT_BRIEF
static int	OPPONENT_BRISK
static int	OPPONENT_FREAK
static int	OPPONENT_ORB
static int	OPPONENT_SIFT
static int	OPPONENT_SURF
static int	ORB
static int	SIFT
static int	SURF

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	DescriptorExtractor(long addr)

Method Summary

Methods

Modifier and Type	Method and Description
void	compute(List<Mat> images, List<MatOfKeyPoint> keypoints, List<Mat> descriptors) Computes the descriptors for a set of keypoints detected in an image (first variant) or image set (second variant).
void	compute(Mat image, MatOfKeyPoint keypoints, Mat descriptors) Computes the descriptors for a set of keypoints detected in an image (first variant) or image set (second variant).
static DescriptorExtractor	create(int extractorType) Creates a descriptor extractor by name.
int	descriptorSize()
int	descriptorType()
boolean	empty()
protected void	finalize()
void	read(String fileName)
void	write(String fileName)

Methods inherited from class java.lang.Object

clone, equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

nativeObj

protected final long nativeObj

SIFT

public static final int SIFT

See Also:

Constant Field Values

SURF

public static final int SURF

See Also:

Constant Field Values

ORB

public static final int ORB

See Also:

Constant Field Values

BRIEF

public static final int BRIEF

See Also:

Constant Field Values

BRISK

public static final int BRISK

See Also:

Constant Field Values

FREAK

public static final int FREAK

See Also:

Constant Field Values

OPPONENT_SIFT

public static final int OPPONENT_SIFT

See Also:

Constant Field Values

OPPONENT_SURF

public static final int OPPONENT_SURF

See Also:

Constant Field Values

OPPONENT_ORB

public static final int OPPONENT_ORB

See Also:

Constant Field Values

OPPONENT_BRIEF

public static final int OPPONENT_BRIEF

See Also:

Constant Field Values

OPPONENT_BRISK

public static final int OPPONENT_BRISK

See Also:

Constant Field Values

OPPONENT_FREAK

public static final int OPPONENT_FREAK

See Also:

Constant Field Values

Constructor Detail

DescriptorExtractor

protected DescriptorExtractor(long addr)

Method Detail

compute

public void compute(Mat image,
           MatOfKeyPoint keypoints,
           Mat descriptors)

Computes the descriptors for a set of keypoints detected in an image (first variant) or image set (second variant).

Parameters:

image - Image.

keypoints - Input collection of keypoints. Keypoints for which a descriptor cannot be computed are removed and the remaining ones may be reordered. Sometimes new keypoints can be added, for example: SIFT duplicates a keypoint with several dominant orientations (for each orientation).

descriptors - Computed descriptors. In the second variant of the method descriptors[i] are descriptors computed for a keypoints[i]. Row j is the keypoints (or keypoints[i]) is the descriptor for keypoint j-th keypoint.

See Also:

org.opencv.features2d.DescriptorExtractor.compute

compute

public void compute(List<Mat> images,
           List<MatOfKeyPoint> keypoints,
           List<Mat> descriptors)

Computes the descriptors for a set of keypoints detected in an image (first variant) or image set (second variant).

Parameters:

images - Image set.

keypoints - Input collection of keypoints. Keypoints for which a descriptor cannot be computed are removed and the remaining ones may be reordered. Sometimes new keypoints can be added, for example: SIFT duplicates a keypoint with several dominant orientations (for each orientation).

descriptors - Computed descriptors. In the second variant of the method descriptors[i] are descriptors computed for a keypoints[i]. Row j is the keypoints (or keypoints[i]) is the descriptor for keypoint j-th keypoint.

See Also:

org.opencv.features2d.DescriptorExtractor.compute

create

public static DescriptorExtractor create(int extractorType)

Creates a descriptor extractor by name.

The current implementation supports the following types of a descriptor extractor:

• "SIFT" -- "SIFT"
• "SURF" -- "SURF"
• "BRIEF" -- "BriefDescriptorExtractor"
• "BRISK" -- "BRISK"
• "ORB" -- "ORB"
• "FREAK" -- "FREAK"

A combined format is also supported: descriptor extractor adapter name ("Opponent" -- "OpponentColorDescriptorExtractor") + descriptor extractor name (see above), for example: "OpponentSIFT".

Parameters:

extractorType - a extractorType

See Also:

org.opencv.features2d.DescriptorExtractor.create

descriptorSize

public int descriptorSize()

descriptorType

public int descriptorType()

empty

public boolean empty()

read

public void read(String fileName)

write

public void write(String fileName)

finalize

protected void finalize()
                 throws Throwable

Overrides:

finalize in class Object

Throws:

Throwable