net.semanticmetadata.lire.imageanalysis.features.local.sift

类 FloatArray2DSIFT

java.lang.Object

net.semanticmetadata.lire.imageanalysis.features.local.sift.FloatArray2DSIFT

public class FloatArray2DSIFT
extends java.lang.Object

构造器概要

构造器

构造器和说明
FloatArray2DSIFT(int feature_descriptor_size, int feature_descriptor_orientation_bins) Constructor

方法概要

限定符和类型	方法和说明
static java.util.Vector<PointMatch>	createMatches(java.util.List<SiftFeature> fs1, java.util.List<SiftFeature> fs2, float max_sd, Model model, float max_id) identify corresponding features using spatial constraints
static float[]	featureSizeHistogram(java.util.Vector<SiftFeature> features, float min, float max, int bins) get a histogram of feature sizes
long	getFeatureObjectSize() Returns the size in bytes of a Feature object.
static long	getFeatureObjectSize(int fdsize, int fdbins)
FloatArray2DScaleOctave	getOctave(int i)
FloatArray2DScaleOctave[]	getOctaves()
void	init(FloatArray2D src, int steps, float initial_sigma, int min_size, int max_size) initialize the scale space as a scale pyramid having octave stubs only
java.util.Vector<SiftFeature>	run() detect features in all scale octaves
java.util.Vector<SiftFeature>	run(int max_size) detect features in all scale octaves
java.util.Vector<SiftFeature>	runOctave(int o) detect features in the specified scale octave

从类继承的方法 java.lang.Object

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

构造器详细资料

FloatArray2DSIFT

public FloatArray2DSIFT(int feature_descriptor_size,
                        int feature_descriptor_orientation_bins)

Constructor

参数:

feature_descriptor_size -

feature_descriptor_size -

方法详细资料

getFeatureObjectSize

public long getFeatureObjectSize()

Returns the size in bytes of a Feature object.

getFeatureObjectSize

public static long getFeatureObjectSize(int fdsize,
                                        int fdbins)

getOctaves

public FloatArray2DScaleOctave[] getOctaves()

getOctave

public FloatArray2DScaleOctave getOctave(int i)

init

public void init(FloatArray2D src,
                 int steps,
                 float initial_sigma,
                 int min_size,
                 int max_size)

initialize the scale space as a scale pyramid having octave stubs only

参数:

src - image having a generating gaussian kernel of initial_sigma img must be a 2d-array of float values in range [0.0f, ..., 1.0f]

steps - gaussian smooth steps steps per scale octave

initial_sigma - sigma of the generating gaussian kernel of img

min_size - minimal size of a scale octave in pixel

max_size - maximal size of an octave to be taken into account Use this to save memory and procesing time, if processing higher resolutions is not necessary.

runOctave

public java.util.Vector<SiftFeature> runOctave(int o)

detect features in the specified scale octave

参数:

o - octave index

返回:

detected features

run

public java.util.Vector<SiftFeature> run()

detect features in all scale octaves

返回:

detected features

run

public java.util.Vector<SiftFeature> run(int max_size)

detect features in all scale octaves

返回:

detected features

createMatches

public static java.util.Vector<PointMatch> createMatches(java.util.List<SiftFeature> fs1,
                                                         java.util.List<SiftFeature> fs2,
                                                         float max_sd,
                                                         Model model,
                                                         float max_id)

identify corresponding features using spatial constraints

参数:

fs1 - feature collection from set 1 sorted by decreasing size

fs2 - feature collection from set 2 sorted by decreasing size

max_sd - maximal difference in size (ratio max/min)

model - transformation model to be applied to fs2

max_id - maximal distance in image space ($\sqrt{x^2+y^2}$)

返回:

matches

TODO implement the spatial constraints

featureSizeHistogram

public static float[] featureSizeHistogram(java.util.Vector<SiftFeature> features,
                                           float min,
                                           float max,
                                           int bins)

get a histogram of feature sizes