Package org.opencv.features

Class SIFT

java.lang.Object

org.opencv.core.Algorithm

org.opencv.features.Feature2D

org.opencv.features.SIFT

public class SIFT
extends Feature2D

Class for extracting keypoints and computing descriptors using the Scale Invariant Feature Transform (SIFT) algorithm by D. Lowe CITE: Lowe04 .

Field Summary

Fields inherited from class org.opencv.core.Algorithm

nativeObj

Constructor Summary

Constructors

Modifier	Constructor	Description
protected	SIFT(long addr)

Method Summary

Modifier and Type	Method	Description
static SIFT	__fromPtr__(long addr)
static SIFT	create()	(measured in SIFT algorithm as the local contrast) number of octaves is computed automatically from the image resolution.
static SIFT	create(int nfeatures)
static SIFT	create(int nfeatures, int nOctaveLayers)
static SIFT	create(int nfeatures, int nOctaveLayers, double contrastThreshold)
static SIFT	create(int nfeatures, int nOctaveLayers, double contrastThreshold, double edgeThreshold)
static SIFT	create(int nfeatures, int nOctaveLayers, double contrastThreshold, double edgeThreshold, double sigma)
static SIFT	create(int nfeatures, int nOctaveLayers, double contrastThreshold, double edgeThreshold, double sigma, boolean enable_precise_upscale)
static SIFT	create(int nfeatures, int nOctaveLayers, double contrastThreshold, double edgeThreshold, double sigma, int descriptorType)	Create SIFT with specified descriptorType.
static SIFT	create(int nfeatures, int nOctaveLayers, double contrastThreshold, double edgeThreshold, double sigma, int descriptorType, boolean enable_precise_upscale)	Create SIFT with specified descriptorType.
protected void	finalize()
double	getContrastThreshold()
java.lang.String	getDefaultName()	Returns the algorithm string identifier.
double	getEdgeThreshold()
int	getNFeatures()
int	getNOctaveLayers()
double	getSigma()
void	setContrastThreshold(double contrastThreshold)
void	setEdgeThreshold(double edgeThreshold)
void	setNFeatures(int maxFeatures)
void	setNOctaveLayers(int nOctaveLayers)
void	setSigma(double sigma)

Methods inherited from class org.opencv.features.Feature2D

compute, compute, defaultNorm, descriptorSize, descriptorType, detect, detect, detect, detect, detectAndCompute, detectAndCompute, empty, read, write

Methods inherited from class org.opencv.core.Algorithm

clear, getNativeObjAddr, save

Methods inherited from class java.lang.Object

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

Constructor Detail

SIFT

protected SIFT(long addr)

Method Detail

__fromPtr__

public static SIFT __fromPtr__(long addr)

create

public static SIFT create(int nfeatures,
                          int nOctaveLayers,
                          double contrastThreshold,
                          double edgeThreshold,
                          double sigma,
                          boolean enable_precise_upscale)

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.

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.

Returns:

automatically generated

create

public static SIFT create(int nfeatures,
                          int nOctaveLayers,
                          double contrastThreshold,
                          double edgeThreshold,
                          double sigma)

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.

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. index \(\texttt{x}\) to \(\texttt{2x}\). This prevents localization bias. The option is disabled by default.

Returns:

automatically generated

create

public static SIFT create(int nfeatures,
                          int nOctaveLayers,
                          double contrastThreshold,
                          double edgeThreshold)

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.

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). is captured with a weak camera with soft lenses, you might want to reduce the number. index \(\texttt{x}\) to \(\texttt{2x}\). This prevents localization bias. The option is disabled by default.

Returns:

automatically generated

create

public static SIFT create(int nfeatures,
                          int nOctaveLayers,
                          double contrastThreshold)

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. is different from the contrastThreshold, i.e. the larger the edgeThreshold, the less features are filtered out (more features are retained). is captured with a weak camera with soft lenses, you might want to reduce the number. index \(\texttt{x}\) to \(\texttt{2x}\). This prevents localization bias. The option is disabled by default.

Returns:

automatically generated

create

public static SIFT create(int nfeatures,
                          int nOctaveLayers)

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. (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. is different from the contrastThreshold, i.e. the larger the edgeThreshold, the less features are filtered out (more features are retained). is captured with a weak camera with soft lenses, you might want to reduce the number. index \(\texttt{x}\) to \(\texttt{2x}\). This prevents localization bias. The option is disabled by default.

Returns:

automatically generated

create

public static SIFT create(int nfeatures)

Parameters:

nfeatures - The number of best features to retain. The features are ranked by their scores (measured in SIFT algorithm as the local contrast) number of octaves is computed automatically from the image resolution. (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. is different from the contrastThreshold, i.e. the larger the edgeThreshold, the less features are filtered out (more features are retained). is captured with a weak camera with soft lenses, you might want to reduce the number. index \(\texttt{x}\) to \(\texttt{2x}\). This prevents localization bias. The option is disabled by default.

Returns:

automatically generated

create

public static SIFT create()

(measured in SIFT algorithm as the local contrast) number of octaves is computed automatically from the image resolution. (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. is different from the contrastThreshold, i.e. the larger the edgeThreshold, the less features are filtered out (more features are retained). is captured with a weak camera with soft lenses, you might want to reduce the number. index \(\texttt{x}\) to \(\texttt{2x}\). This prevents localization bias. The option is disabled by default.

Returns:

automatically generated

create

public static SIFT create(int nfeatures,
                          int nOctaveLayers,
                          double contrastThreshold,
                          double edgeThreshold,
                          double sigma,
                          int descriptorType,
                          boolean enable_precise_upscale)

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.

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.

Returns:

automatically generated

create

public static SIFT create(int nfeatures,
                          int nOctaveLayers,
                          double contrastThreshold,
                          double edgeThreshold,
                          double sigma,
                          int descriptorType)

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.

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. index \(\texttt{x}\) to \(\texttt{2x}\). This prevents localization bias. The option is disabled by default.

Returns:

automatically generated

getDefaultName

public java.lang.String getDefaultName()

Description copied from class: Algorithm

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.

Overrides:

getDefaultName in class Feature2D

Returns:

automatically generated

setNFeatures

public void setNFeatures(int maxFeatures)

getNFeatures

public int getNFeatures()

setNOctaveLayers

public void setNOctaveLayers(int nOctaveLayers)

getNOctaveLayers

public int getNOctaveLayers()

setContrastThreshold

public void setContrastThreshold(double contrastThreshold)

getContrastThreshold

public double getContrastThreshold()

setEdgeThreshold

public void setEdgeThreshold(double edgeThreshold)

getEdgeThreshold

public double getEdgeThreshold()

setSigma

public void setSigma(double sigma)

getSigma

public double getSigma()

finalize

protected void finalize()
                 throws java.lang.Throwable

Overrides:

finalize in class Feature2D

Throws:

java.lang.Throwable