lti::curvatureFeature::parameters Class Reference

the parameters for the class curvatureFeature More...

#include <ltiCurvatureFeature.h>

Inheritance diagram for lti::curvatureFeature::parameters:

[legend]

Collaboration diagram for lti::curvatureFeature::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
int	gaussianSize
float	gaussianVariance
float	deltaLength
float	relevanceThreshold
bool	normalize
float	lowerLimit
float	upperLimit
int	size

Detailed Description

the parameters for the class curvatureFeature

Constructor & Destructor Documentation

lti::curvatureFeature::parameters::parameters ( )

default constructor

Reimplemented from lti::globalFeatureExtractor::parameters.

lti::curvatureFeature::parameters::parameters ( const parameters & other )

copy constructor

Parameters:

other

the parameters object to be copied

Reimplemented from lti::globalFeatureExtractor::parameters.

lti::curvatureFeature::parameters::~parameters ( ) [virtual]

destructor

Reimplemented from lti::globalFeatureExtractor::parameters.

Member Function Documentation

virtual functor::parameters* lti::curvatureFeature::parameters::clone ( ) const [virtual]

returns a pointer to a clone of the parameters

Reimplemented from lti::globalFeatureExtractor::parameters.

parameters& lti::curvatureFeature::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::globalFeatureExtractor::parameters.

const char* lti::curvatureFeature::parameters::getTypeName ( ) const [virtual]

returns name of this type

Reimplemented from lti::globalFeatureExtractor::parameters.

parameters& lti::curvatureFeature::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::curvatureFeature::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::curvatureFeature::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::curvatureFeature::parameters::deltaLength

Value used to get the orientation of the neighbour pixels.

int lti::curvatureFeature::parameters::gaussianSize

Size for the gaussian kernel used to smooth the orientation channel.

If you do not want to smooth the angles, use a gaussian size of 0 or 1.

Default value: 3

float lti::curvatureFeature::parameters::gaussianVariance

Variance for the gaussian filter used to smooth the orientation channel.

If you do not want to smooth the angles, use a gaussian size of 0 or 1.

Default value: -1 (i.e. let the constructor of the gaussian kernel choose a variance value appropriate for the kernel size)

float lti::curvatureFeature::parameters::lowerLimit

lower limit for the histogram.

All curvature values below this threshold will be ignored. This value MUST be lower than the upperLimit.

Valid value range: -Pi/2 .. Pi/2

Default value: -Pi/2

bool lti::curvatureFeature::parameters::normalize

if true, the feature vector will be normalized to have an area of one, i.e.

the feature vector can be interpreted as a probability distribution for the orientations. If false, the resulting values depend on the values of the magnitud channel. Default: true

float lti::curvatureFeature::parameters::relevanceThreshold

Minimal relevance value needed to consider a pixel in the computations.

int lti::curvatureFeature::parameters::size

size of the histogram.

The curvature values from -lowerLimit to upperLimit will be mapped between 0 and size-1.

Default value: 64

float lti::curvatureFeature::parameters::upperLimit

upper limit for the histogram.

All curvature values above this threshold will be ignored. This value MUST be higher than the lowerLimit

Valid value range: -Pi/2 .. Pi/2

Default value: Pi/2

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