lti::loweGradientFeature::parameters Class Reference

The parameters for the class loweGradientFeature. More...

#include <ltiLoweGradientFeature.h>

Inheritance diagram for lti::loweGradientFeature::parameters:

[legend]

Collaboration diagram for lti::loweGradientFeature::parameters:

[legend]

List of all members.

Public Member Functions
	parameters ()
	parameters (const parameters &other)
	~parameters ()
const char *	getTypeName () const
parameters &	copy (const parameters &other)
parameters &	operator= (const parameters &other)
virtual functor::parameters *	clone () const
virtual bool	write (ioHandler &handler, const bool complete=true) const
virtual bool	read (ioHandler &handler, const bool complete=true)
Public Attributes
float	sigma
int	locationPartition
int	histogramPartition
int	orientationBins
colorContrastGradient::parameters	gradientParam
int	pyramidLevels
scaleSpacePyramid< channel > ::parameters	pyramidParam
float	locationRelativeRadius
bool	normalize
float	cutThreshold

---

Detailed Description

The parameters for the class loweGradientFeature.

---

Constructor & Destructor Documentation

lti::loweGradientFeature::parameters::parameters

(

)

Default constructor.

Reimplemented from lti::featureExtractor::parameters.

lti::loweGradientFeature::parameters::parameters

(

const parameters &

other

)

Copy constructor.

Parameters:

other

the parameters object to be copied

Reimplemented from lti::featureExtractor::parameters.

lti::loweGradientFeature::parameters::~parameters

(

)

[virtual]

Destructor.

Reimplemented from lti::featureExtractor::parameters.

---

Member Function Documentation

virtual functor::parameters* lti::loweGradientFeature::parameters::clone

(

)

const [virtual]

Returns a pointer to a clone of the parameters.

Reimplemented from lti::featureExtractor::parameters.

parameters& lti::loweGradientFeature::parameters::copy

(

const parameters &

other

)

Copy the contents of a parameters object.

Parameters:

other

the parameters object to be copied

Returns:

a reference to this parameters object

Reimplemented from lti::featureExtractor::parameters.

const char* lti::loweGradientFeature::parameters::getTypeName

(

)

const [virtual]

Returns name of this type.

Reimplemented from lti::featureExtractor::parameters.

parameters& lti::loweGradientFeature::parameters::operator=

(

const parameters &

other

)

Copy the contents of a parameters object.

Parameters:

other

the parameters object to be copied

Returns:

a reference to this parameters object

virtual bool lti::loweGradientFeature::parameters::read	(	ioHandler &	handler,
		const bool	complete = true
	)			[virtual]

Read the parameters from the given ioHandler.

Parameters:

	handler	the ioHandler to be used
	complete	if true (the default) the enclosing begin/end will be also written, otherwise only the data block will be written.

Returns:

true if write was successful

Reimplemented from lti::functor::parameters.

virtual bool lti::loweGradientFeature::parameters::write	(	ioHandler &	handler,
		const bool	complete = true
	)			const [virtual]

Write the parameters in the given ioHandler.

Parameters:

	handler	the ioHandler to be used
	complete	if true (the default) the enclosing begin/end will be also written, otherwise only the data block will be written.

Returns:

true if write was successful

Reimplemented from lti::functor::parameters.

---

Member Data Documentation

float lti::loweGradientFeature::parameters::cutThreshold

Cut threshold.

If normalize is set to true, then all histogram values greater to this value will be clipped also to this value. This is supposed to help compensating illumination changes. If you don't want to clip, just set this value to 1.0f.

After all values greater than cutThreshold have been clipped, the resulting vector will be normalized again.

Default value: 0.2f

colorContrastGradient::parameters lti::loweGradientFeature::parameters::gradientParam

Parameters for gradient computation.

Please ensure that the mode is "Polar" (the default). Otherwise the results will make no sense.

Default value: colorContrastGradient::parameters()

int lti::loweGradientFeature::parameters::histogramPartition

Histogram Partition.

Each histogram computed will use a number of samples equal to the square of this value.

Default value: 4 (i.e. a total of 16 samples will be used to compute the histogram).

int lti::loweGradientFeature::parameters::locationPartition

Location partition.

Each dimension of the location will be split in the given number of parts. The total number of histograms computed will be the square of the given value.

Default value: 4 (i.e. a total of 16 histograms will be computed).

float lti::loweGradientFeature::parameters::locationRelativeRadius

Location relative radius.

This parameter is necessary to gain the information which location belongs to which level.

You should use here exactly the same value given to the location selector functor. Since the real radius of a pixel at level zero is 0.5, you must ensure that the used radius for a location at level zero divide by the factor given here results in 0.5.

Default value: 7

bool lti::loweGradientFeature::parameters::normalize

Normalize histogram.

If set to true, each histogram will be normalized, representing a probability distribution.

Default value: true

int lti::loweGradientFeature::parameters::orientationBins

Number of Bins in the orientation histogram.

Default value: 8 (i.e. only 45 degree steps will be considered)

int lti::loweGradientFeature::parameters::pyramidLevels

Total number of levels in the pyramid.

This should be the same value used for the location extraction stage.

Default value: 15

scaleSpacePyramid<channel>::parameters lti::loweGradientFeature::parameters::pyramidParam

Parameters used to construct the pyramid.

For better results please ensure that this parameter set corresponds to the ones used in the location extraction.

Default value: scaleSpacePyramid::parameters()

float lti::loweGradientFeature::parameters::sigma

Sigma factor.

The samples at the center of the location will a stronger weighting than the ones farther from that center. The weight is computed as exp(-x^2/(2*sigma^2)), where x is the distance to the location center.

Default value: 3.5

---

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

• ltiLoweGradientFeature.h