imagingbook.pub.sift

Class SiftDetector.Parameters

java.lang.Object

imagingbook.pub.sift.SiftDetector.Parameters

Enclosing class:

SiftDetector

public static class SiftDetector.Parameters
extends Object

Field Summary

Fields

Modifier and Type	Field and Description
boolean	DEBUG Set true to output debug information
int	n_Angl Number of angular descriptor bins
int	n_Orient Number of orientation bins in the feature descriptor (angular resolution)
int	n_Refine Max.
int	n_Smooth Number of smoothing steps applied to the orientation histogram
int	n_Spat Number of spatial descriptor bins along each x/y axis
SiftDetector.NeighborhoodType	nhType Type of neigborhood used for peak detection in 3D scale space
int	P Number of octaves in Gaussian/DoG scale space
int	Q Scale steps (levels) per octave
double	rho_Max Max.
double	s_Desc Spatial size factor of descriptor (relative to feature scale)
double	s_Fscale Scale factor for converting normalized features to byte values in [0,255]
double	sigma_0 Base scale of level 0 (base smoothing)
double	sigma_s Sampling scale (nominal smoothing level of the input image)
boolean	sortKeyPoints Set true to sort detected keypoints by response magnitude
double	t_DomOr Min.
double	t_Extrm Min.
double	t_Fclip Max.
double	t_Mag Min.
double	t_Peak Min.

Constructor Summary

Constructors

Constructor and Description
Parameters()

Method Summary

Methods inherited from class java.lang.Object

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

Field Detail

DEBUG

public boolean DEBUG

Set true to output debug information

nhType

public SiftDetector.NeighborhoodType nhType

Type of neigborhood used for peak detection in 3D scale space

sigma_s

public double sigma_s

Sampling scale (nominal smoothing level of the input image)

sigma_0

public double sigma_0

Base scale of level 0 (base smoothing)

P

public int P

Number of octaves in Gaussian/DoG scale space

Q

public int Q

Scale steps (levels) per octave

t_Mag

public double t_Mag

Min. magnitude required in DoG peak detection (abs. value)

t_Peak

public double t_Peak

Min. DoG magnitude required for extrapolated peaks (abs. value)

t_Extrm

public double t_Extrm

Min. difference to all neighbors in DoG peak detection (max. 0.0005)

n_Refine

public int n_Refine

Max. number of iterations for refining the position of a key point

rho_Max

public double rho_Max

Max. principal curvature ratio used to eliminate line-like structures (3..10)

n_Orient

public int n_Orient

Number of orientation bins in the feature descriptor (angular resolution)

n_Smooth

public int n_Smooth

Number of smoothing steps applied to the orientation histogram

t_DomOr

public double t_DomOr

Min. value in orientation histogram for dominant orientations (rel. to max. entry)

s_Desc

public double s_Desc

Spatial size factor of descriptor (relative to feature scale)

n_Spat

public int n_Spat

Number of spatial descriptor bins along each x/y axis

n_Angl

public int n_Angl

Number of angular descriptor bins

t_Fclip

public double t_Fclip

Max. value in normalized feature vector (0.2 recommended by Lowe)

s_Fscale

public double s_Fscale

Scale factor for converting normalized features to byte values in [0,255]

sortKeyPoints

public boolean sortKeyPoints

Set true to sort detected keypoints by response magnitude

Constructor Detail

Parameters

public Parameters()