lti::colorEdgesGS Class Reference

Gevers and Stokman color edges. More...

#include <ltiColorEdgesGS.h>

Inheritance diagram for lti::colorEdgesGS:

[legend]

Collaboration diagram for lti::colorEdgesGS:

[legend]

List of all members.

Classes
class	parameters
	the parameters for the class colorEdgesGS More...
Public Member Functions
	colorEdgesGS ()
	colorEdgesGS (const parameters &par)
	colorEdgesGS (const colorEdgesGS &other)
virtual	~colorEdgesGS ()
virtual const char *	getTypeName () const
colorEdgesGS &	copy (const colorEdgesGS &other)
colorEdgesGS &	operator= (const colorEdgesGS &other)
virtual functor *	clone () const
const parameters &	getParameters () const
Gray valued images.
This methods are supplied for completeness, but since the algorithms are designed to work with color images, the results won't be good. Use the lti::cannyEdges functor instead.
virtual bool	apply (channel8 &srcdest) const
virtual bool	apply (channel &srcdest) const
virtual bool	apply (const channel8 &src, channel8 &dest) const
virtual bool	apply (const channel &src, channel &dest) const
virtual bool	apply (const channel &src, channel8 &dest) const
Color Images

virtual bool	apply (image &srcdest) const
virtual bool	apply (const image &src, image &dest) const
virtual bool	apply (const image &src, channel8 &dest) const
Protected Member Functions
bool	getGradients (const channel &red, const channel &green, const channel &blue, const channel &o1, const channel &o2, const channel &c1, const channel &c2, const float &stdDevR, const float &stdDevG, const float &stdDevB, const float &stdDevO1, const float &stdDevO2, const channel &stdDevC1, const channel &stdDevC2, channel &gradRGB, channel &stdDevRGB, channel &gradO1O2, channel &stdDevO1O2, channel &gradC1C2, channel &stdDevC1C2) const
bool	constructUncertaintyKernels (sepKernel< float > &filterX, sepKernel< float > &filterY) const

Detailed Description

Gevers and Stokman color edges.

This functor implements the color edges detector described in:

Theo Gevers and Harro Stokman, "Classifying Color Edges in Video into Shadow-Geometry, Highlight or Material Transitions", IEEE Trans. on Multimedia, Vol. 5 No. 2, June 2003

Note that it is intended for color images only. If you use in on gray-valued image the results won't be good.

The edgeDetector::parameters::edgeValue attribute will be used to mark the material edges, which are usually the ones you really want to have.

This detector is in general slow, since it has to compute many color channels and gradients to classify the edges into material, highlight or shadow edges. If you are looking for a faster detector use the lti::cannyEdges functor, which uses the lti::colorContrastGradient to compute also edges of color images.

Constructor & Destructor Documentation

lti::colorEdgesGS::colorEdgesGS ( )

default constructor

lti::colorEdgesGS::colorEdgesGS ( const parameters & par )

Construct a functor using the given parameters.

lti::colorEdgesGS::colorEdgesGS ( const colorEdgesGS & other )

copy constructor

Parameters:

other

the object to be copied

virtual lti::colorEdgesGS::~colorEdgesGS ( ) [virtual]

destructor

Member Function Documentation

virtual bool lti::colorEdgesGS::apply	(	const image &	src,
		channel8 &	dest
	)			const `[virtual]`

Detect the edges in the given color image.

The edges will belong to one of three classes: material edge, highlight edge or shadow edge. Each one of them will be mark with the corresponding parameter value.

See also:: edgeDetector::parameters , parameters

Parameters:

	src	input color image
	dest	detected edges

Returns:: true if apply successful or false otherwise.

Reimplemented from lti::edgeDetector.

virtual bool lti::colorEdgesGS::apply	(	const image &	src,
		image &	dest
	)			const `[virtual]`

Compute the edges for the given image.

The material edges will be marked with a gray tone with the value edgeValue given in the parameters object.
The shadow edges will be red (with the shadow value given in the parameters)
The highlight edges will be green (with the highlight value given in the parameters. The background will be gray, with the value given as noEdgeValue in the parameters.

Parameters:

	src	input image
	dest	colored edges

Returns:: true if apply successful or false otherwise.

Reimplemented from lti::edgeDetector.

virtual bool lti::colorEdgesGS::apply ( image & srcdest ) const [virtual]

Compute the edges for the given image and leave the result there too.

See apply(const image&, image&) for more details.

Parameters:

srcdest

input and output image.

Returns:: true if apply successful or false otherwise.

Reimplemented from lti::edgeDetector.

virtual bool lti::colorEdgesGS::apply	(	const channel &	src,
		channel8 &	dest
	)			const `[virtual]`

operates on a copy of the given parameters.

Parameters:

	src	channel with the source data.
	dest	channel8 where the result will be left.

Returns:: true if apply successful or false otherwise.

Reimplemented from lti::edgeDetector.

virtual bool lti::colorEdgesGS::apply	(	const channel &	src,
		channel &	dest
	)			const `[virtual]`

operates on a copy of the given parameters.

Parameters:

	src	channel with the source data.
	dest	channel where the result will be left.

Returns:: true if apply successful or false otherwise.

Reimplemented from lti::edgeDetector.

virtual bool lti::colorEdgesGS::apply	(	const channel8 &	src,
		channel8 &	dest
	)			const `[virtual]`

operates on a copy of the given parameters.

Parameters:

	src	channel8 with the source data.
	dest	channel8 where the result will be left.

Returns:: true if apply successful or false otherwise.

Reimplemented from lti::edgeDetector.

virtual bool lti::colorEdgesGS::apply ( channel & srcdest ) const [virtual]

operates on the given parameter.

Parameters:

srcdest

channel with the source data. The result will be left here too.

Returns:: true if apply successful or false otherwise.

Reimplemented from lti::edgeDetector.

virtual bool lti::colorEdgesGS::apply ( channel8 & srcdest ) const [virtual]

operates on the given parameter.

Parameters:

srcdest

channel8 with the source data. The result will be left here too.

Returns:: true if apply successful or false otherwise.

Reimplemented from lti::edgeDetector.

virtual functor* lti::colorEdgesGS::clone ( ) const [virtual]

returns a pointer to a clone of this functor.

Implements lti::edgeDetector.

bool lti::colorEdgesGS::constructUncertaintyKernels	(	sepKernel< float > &	filterX,
		sepKernel< float > &	filterY
	)			const `[protected]`

Compute the kernels necessary to compute the uncertainty of the gradient.

colorEdgesGS& lti::colorEdgesGS::copy ( const colorEdgesGS & other )

copy data of "other" functor.

Parameters:

other

the functor to be copied

Returns:: a reference to this functor object

Reimplemented from lti::edgeDetector.

bool lti::colorEdgesGS::getGradients	(	const channel &	red,
		const channel &	green,
		const channel &	blue,
		const channel &	o1,
		const channel &	o2,
		const channel &	c1,
		const channel &	c2,
		const float &	stdDevR,
		const float &	stdDevG,
		const float &	stdDevB,
		const float &	stdDevO1,
		const float &	stdDevO2,
		const channel &	stdDevC1,
		const channel &	stdDevC2,
		channel &	gradRGB,
		channel &	stdDevRGB,
		channel &	gradO1O2,
		channel &	stdDevO1O2,
		channel &	gradC1C2,
		channel &	stdDevC1C2
	)			const `[protected]`

Get gradient modula and uncertainty values for each one of them.

const parameters& lti::colorEdgesGS::getParameters ( ) const

returns used parameters

Reimplemented from lti::edgeDetector.

virtual const char* lti::colorEdgesGS::getTypeName ( ) const [virtual]

returns the name of this type ("colorEdgesGS")

Reimplemented from lti::edgeDetector.

colorEdgesGS& lti::colorEdgesGS::operator= ( const colorEdgesGS & other )

alias for copy member

Parameters:

other

the functor to be copied

Returns:: a reference to this functor object

Reimplemented from lti::edgeDetector.

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

ltiColorEdgesGS.h

lti::colorEdgesGS Class Reference

Classes

Public Member Functions

Protected Member Functions

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation