lti::grayWorldNormalization::parameters Class Reference

The parameters for the class grayWorldNormalization. More...

#include <ltiGrayWorldNormalization.h>

Inheritance diagram for lti::grayWorldNormalization::parameters:

[legend]

Collaboration diagram for lti::grayWorldNormalization::parameters:

[legend]

List of all members.

Public Member Functions
	parameters ()
	parameters (const parameters &other)
	~parameters ()
const char *	getTypeName () const
parameters &	copy (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
Computation of normalization constant.

float	kappa
float	nu
float	gamma
General options

bool	ignoreColorFlag
rgbPixel	ignoreColor
bool	allowOverflow
Local normalization

bool	localNormalization
int	windowSize

Detailed Description

The parameters for the class grayWorldNormalization.

This class provides mainly the parameters to implement the normalization equation:

$c_n \rightarrow \frac{c} {(1-\gamma) + \gamma(\nu \cdot c_\mu + \kappa \cdot c_\sigma)} *$

With:

$c_\mu$ : mean value of the c channel.
$c_\sigma$ : standard deviation of the c channel.
$\gamma$ : normalization strength between 0 (no normalization) and 1 (complete normalization) (gamma)
$\nu$ : mean value scaling factor (nu).
$\kappa$ : standard deviation scaling factor (kappa).

Constructor & Destructor Documentation

lti::grayWorldNormalization::parameters::parameters ( )

default constructor

Reimplemented from lti::colorNormalizationBase::parameters.

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

copy constructor

Parameters:

other

the parameters object to be copied

Reimplemented from lti::colorNormalizationBase::parameters.

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

destructor

Reimplemented from lti::colorNormalizationBase::parameters.

Member Function Documentation

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

returns a pointer to a clone of the parameters

Reimplemented from lti::colorNormalizationBase::parameters.

parameters& lti::grayWorldNormalization::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::colorNormalizationBase::parameters.

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

returns name of this type

Reimplemented from lti::colorNormalizationBase::parameters.

virtual bool lti::grayWorldNormalization::parameters::read	(	ioHandler &	handler,
		const bool	complete = `true`
	)			`[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::colorNormalizationBase::parameters.

virtual bool lti::grayWorldNormalization::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::colorNormalizationBase::parameters.

Member Data Documentation

bool lti::grayWorldNormalization::parameters::allowOverflow

default is false.

Set this to true, if you want to allow overflow values in the normalized channels. Otherwise over- and underflows will be set to the allowed max resp. min values.

float lti::grayWorldNormalization::parameters::gamma

Some times a "total" normalization will damage the color information in a way, that this cannot be used in recognition processes.

In order to avoid to strong normalizations, this gamma factor can be used. Its value MUST be between 0 and 1. 0 means no normalization at all and 1 the best normalization to be achieved.

Default value: 1

rgbPixel lti::grayWorldNormalization::parameters::ignoreColor

This color will be ignored in the computations of the norm, if the ignoreColorFlag is true.

This way, the background can be ignored if it was "markt" with a specific color (usually black).

Default value: rgbPixel(0,0,0) (Black)

bool lti::grayWorldNormalization::parameters::ignoreColorFlag

Flag to indicate if a specific color should be ignored (true) or if the whole image should be considered to determine the normalization factors (false).

Please note that this flag will have effect if and only if the localNormalization is deactivated!

Default value: false

float lti::grayWorldNormalization::parameters::kappa

Scaling factor for the standard deviation.

Default = 3.0

bool lti::grayWorldNormalization::parameters::localNormalization

if true, the normalization constants are computed for each pixel using the given window size.

If false, only one normalization constant is used for the whole image.

Default: false

float lti::grayWorldNormalization::parameters::nu

Scaling factor for the channel mean.

Default value: 1