src » Image

fancynorm.H File Reference

Detailed Description

Intrafeature competition with maxNormalize().

Definition in file fancynorm.H.

#include "Util/log.H"
#include <string>

Include dependency graph for fancynorm.H:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Types of normalization (normtyp)

#define NBMAXNORMTYPES   13

#define VCXNORM_DEFAULT   VCXNORM_FANCY

enum MaxNormType {
  VCXNORM_NONE = 0, VCXNORM_MAXNORM = 1, VCXNORM_FANCY = 2, VCXNORM_FANCYFAST = 3,
  VCXNORM_FANCYONE = 4, VCXNORM_FANCYLANDMARK = 5, VCXNORM_LANDMARK = 6, VCXNORM_FANCYWEAK = 7,
  VCXNORM_IGNORE = 8, VCXNORM_SURPRISE = 9, VCXNORM_FANCYVWEAK = 10, VCXNORM_STDEV = 11,
  VCXNORM_STDEV0 = 12
}

const char * maxNormTypeName (const MaxNormType m)

Get a name in clear for a given type.

Additional parameters for fancynorm versions of the algorithm.

const int FANCYITER = 5

default number of iterations

const double FANCYESIG = 2

excitatory sigma as % of image size

const double FANCYISIG = 25

inhibitory sigma as % of image size

const double FANCYCOEX = 0.5

excitatory coefficient (strength)

const double FANCYCOIN = 1.5

inhibitory coefficient (strength)

const double FANCYINHI = 2.0

strength of global inhibition

const double FANCYG = 2.1

for sigmoid normalization

const double FANCYH = 2.0

for sigmoid normalization

const double FANCYS = 1.0

for sigmoid normalization

const int LRLEVEL = 2

for tuned long-range excitation:

Standard min/max bounds for maxNormalize().

const float MAXNORMMAX = 10.0f

upper bound for maxNormalize()

const float MAXNORMMIN = 0.0f

lower bound for maxNormalize()

const float MAXNORMLANDMARK = 255.0f

upper bound for maxNormalizeFancyLandmark()

Functions

template<class T>

Image< T > maxNormalize (const Image< T > &src, const T mi, const T ma, const MaxNormType normtyp=VCXNORM_DEFAULT, int nbiter=FANCYITER, const Image< float > *lrexcit=0)

Generic implementation (select algorithm with normtyp).

template<class T>

Image< T > maxNormalizeNone (const Image< T > &src, const T mi, const T ma)

Specialized implementation (corresponds to VCXNORM_NONE).

template<class T>

Image< T > maxNormalizeStd (const Image< T > &src, const T mi, const T ma)

Specialized implementation (corresponds to VCXNORM_MAXNORM).

template<class T>

Image< T > maxNormalizeFancyFast (const Image< T > &src, const T mi, const T ma, const int nbiter=FANCYITER)

Specialized implementation (corresponds to VCXNORM_FANCYFAST).

template<class T>

Image< T > maxNormalizeFancy (const Image< T > &src, const T mi, const T ma, const int nbiter=FANCYITER, const double weakness=1.0, const Image< float > *lrexcit=0)

Specialized implementation (corresponds to VCXNORM_FANCY).

template<class T>

Image< T > maxNormalizeFancyLandmark (const Image< T > &src, const T mi, const T ma, const int nbiter=FANCYITER)

Specialized implementation (corresponds to VCXNORM_FANCY).

template<class T>

Image< T > maxNormalizeLandmark (const Image< T > &src, const T mi, const T ma)

Specialized implementation (corresponds to VCXNORM_LANDMARK).

template<class T>

int findPeaks (const Image< T > &src, const T mi, const T ma, double &sum)

to find number of peaks in the image (used in landmark detection)

template<class T>

float goodness_map (const Image< T > &src)

to find the goodness of a map (used in landmark detection)

template<class T>

Image< T > maxNormalizeStdev (const Image< T > &src)

Specialized implementation (corresponds to VCXNORM_STDEV).

template<class T>

Image< T > maxNormalizeStdev0 (const Image< T > &src)

Specialized implementation (corresponds to VCXNORM_STDEV0).

std::string convertToString (const MaxNormType val)

MaxNormType overload.

void convertFromString (const std::string &str, MaxNormType &val)

MaxNormType overload.

Define Documentation

#define NBMAXNORMTYPES 13

Have this value always equal to the largest of the VCXNORMs (used for range checking)
Definition at line 70 of file fancynorm.H.
Referenced by convertFromString(), and maxNormTypeName().

#define VCXNORM_DEFAULT VCXNORM_FANCY

Always points to the default maxnorm operation
Definition at line 88 of file fancynorm.H.
Referenced by main().

Enumeration Type Documentation

enum MaxNormType

Enumerator:

VCXNORM_NONE no max-normalization, but may change range

VCXNORM_MAXNORM non-iterative maxnorm

VCXNORM_FANCY full implementation of fancy maxnorm

VCXNORM_FANCYFAST fast implementation of fancy maxnorm

VCXNORM_FANCYONE one-iteration only of fancy maxnorm

VCXNORM_FANCYLANDMARK fancy maxnorm to find landmark

VCXNORM_LANDMARK to find landmarks

VCXNORM_FANCYWEAK Weak version of FancyOne.

VCXNORM_IGNORE Do absolutely nothing, not even change range.

VCXNORM_SURPRISE Like ignore but VCX will do something.

VCXNORM_FANCYVWEAK Very weak version of FancyOne.

VCXNORM_STDEV normalize map to have stdev=1, minval=0

VCXNORM_STDEV0 normalize map to have stdev=1, mean=0

Definition at line 51 of file fancynorm.H.

Function Documentation

void convertFromString ( const std::string & str,

MaxNormType & val

)

MaxNormType overload.
Format is "name" as defined by maxNormTypeName() in MaxNormTypes.H
Definition at line 638 of file fancynorm.C.
References GVX_TRACE, i, maxNormTypeName(), and NBMAXNORMTYPES.

std::string convertToString ( const MaxNormType val )

MaxNormType overload.
Format is "name" as defined by maxNormTypeName() in MaxNormTypes.H
Definition at line 632 of file fancynorm.C.
References GVX_TRACE, and maxNormTypeName().

template<class T>

int findPeaks ( const Image< T > & src,

const T mi,

const T ma,

double & sum

)

to find number of peaks in the image (used in landmark detection)

Definition at line 484 of file fancynorm.C.
References area, findMax(), GVX_TRACE, rutz::max(), maxNormalize(), segmentLandmark(), target, and VCXNORM_FANCY.
Referenced by goodness_map(), maxNormalizeLandmark(), SimulationViewerStats::save1(), and SimulationViewerNerdCam::writeStatusPage().

template<class T>

float goodness_map ( const Image< T > & src )

to find the goodness of a map (used in landmark detection)

Definition at line 518 of file fancynorm.C.
References ASSERT, findMax(), findPeaks(), goodness_map(), GVX_TRACE, Image< T >::initialized(), inplaceNormalize(), LINFO, rutz::max(), MAXNORMLANDMARK, MAXNORMMIN, segmentLandmark(), and target.
Referenced by ComplexChannel::combineOutputs(), SingleChannel::combineSubMaps(), goodness_map(), and maxNormalizeLandmark().

template<class T>

Image<T> maxNormalize ( const Image< T > & src,

const T mi,

const T ma,

const MaxNormType normtyp = VCXNORM_DEFAULT,

int nbiter = FANCYITER,

const Image< float > * lrexcit = 0

)

Generic implementation (select algorithm with normtyp).
Normalize between mi and ma and multiply by (ma - mean). Versions with more arguments implement the core within-feature spatial competition for salience. See papers for details.

template<class T>

Image<T> maxNormalizeFancy ( const Image< T > & src,

const T mi,

const T ma,

const int nbiter = FANCYITER,

const double weakness = 1.0,

const Image< float > * lrexcit = 0

)

Specialized implementation (corresponds to VCXNORM_FANCY).
fancyNorm from Itti et al, JEI, 2001; FULL implementation.

template<class T>

Image<T> maxNormalizeFancyFast ( const Image< T > & src,

const T mi,

const T ma,

const int nbiter = FANCYITER

)

Specialized implementation (corresponds to VCXNORM_FANCYFAST).
fancyNorm from Itti et al, JEI, 2001; FAST implementation.
Definition at line 206 of file fancynorm.C.
References ASSERT, buildPyrGaussian(), FANCYCOEX, FANCYCOIN, FANCYESIG, FANCYINHI, FANCYISIG, getMinMax(), GVX_TRACE, h, i, Image< T >::initialized(), inplaceAttenuateBorders(), inplaceNormalize(), inplaceRectify(), log(), rutz::max(), rescale(), sqrt(), and w.
Referenced by maxNormalize().

template<class T>

Image<T> maxNormalizeFancyLandmark ( const Image< T > & src,

const T mi,

const T ma,

const int nbiter = FANCYITER

)

Specialized implementation (corresponds to VCXNORM_FANCY).
fancyNorm from Itti et al, JEI, 2001; FULL implementation. adapted to find landmarks
Definition at line 331 of file fancynorm.C.
References ASSERT, CONV_BOUNDARY_CLEAN, FANCYCOEX, FANCYCOIN, FANCYINHI, getMinMax(), GVX_TRACE, h, i, Image< T >::initialized(), inplaceNormalize(), inplaceRectify(), rutz::max(), rutz::min(), sepFilter(), sqrt(), and w.
Referenced by maxNormalize().

template<class T>

Image<T> maxNormalizeLandmark ( const Image< T > & src,

const T mi,

const T ma

)

Specialized implementation (corresponds to VCXNORM_LANDMARK).
to find landmarks
Definition at line 382 of file fancynorm.C.
References ASSERT, findMax(), findPeaks(), Image< T >::getDims(), Image< T >::getVal(), goodness_map(), GVX_TRACE, Image< T >::initialized(), inplaceNormalize(), LINFO, rutz::max(), MAXNORMLANDMARK, MAXNORMMIN, Image< T >::resize(), segmentLandmark(), and target.
Referenced by maxNormalize().

template<class T>

Image<T> maxNormalizeNone ( const Image< T > & src,

const T mi,

const T ma

)

Specialized implementation (corresponds to VCXNORM_NONE).
No max-normalization, just normalize between mi and ma.
Definition at line 130 of file fancynorm.C.
References GVX_TRACE, inplaceNormalize(), and inplaceRectify().
Referenced by maxNormalize().

template<class T>

Image<T> maxNormalizeStd ( const Image< T > & src,

const T mi,

const T ma

)

Specialized implementation (corresponds to VCXNORM_MAXNORM).
maxNorm from Itti et al, IEEE-PAMI, 1998.
Definition at line 147 of file fancynorm.C.
References ASSERT, GVX_TRACE, h, i, Dlist::index(), Image< T >::initialized(), inplaceNormalize(), inplaceRectify(), and w.
Referenced by maxNormalize().

template<class T>

Image<T> maxNormalizeStdev ( const Image< T > & src )

Specialized implementation (corresponds to VCXNORM_STDEV).
The output image is the result of normalizing the input image to have stdev=1 and minval=0, by simply dividing by the stdev of the original image and then subtracting the minval of the resulting image. We set minval=0, rather than the more natural mean=0, because maxNormalize functions traditionally return images with only non-negative values, since negative values will likely eventually be subject to a rectification. The choice of minval=0 or mean=0 has no effect on the statistics of maps produced by summing several stdev-normalized maps; the resulting map itself will have the same stdev in either case, and the only difference will be a shift in its mean.
Definition at line 586 of file fancynorm.C.
References Image< T >::getDims(), getMinMax(), s, stdev(), and ZEROS.
Referenced by maxNormalize().

template<class T>

Image<T> maxNormalizeStdev0 ( const Image< T > & src )

Specialized implementation (corresponds to VCXNORM_STDEV0).
The output image is the result of normalizing the input image to have mean=0 and stdev=1, by simply subtracting the mean of the original image and then dividing by the stdev of the original image. Beware that the resulting image will have negative values, which may be truncated by later rectification steps.
Definition at line 608 of file fancynorm.C.
References Image< T >::getDims(), mean(), s, stdev(), u(), and ZEROS.
Referenced by maxNormalize().

const char* maxNormTypeName ( const MaxNormType m ) [inline]

Get a name in clear for a given type.

Definition at line 73 of file fancynorm.H.
References LFATAL, n, and NBMAXNORMTYPES.
Referenced by ComplexChannel::combineOutputs(), IntegerComplexChannel::combineOutputsInt(), SingleChannel::combineSubMaps(), HueChannel::combineSubMaps(), convertFromString(), convertToString(), IntegerSimpleChannel::getOutputInt(), IntegerSimpleChannel::getSubmapInt(), SingleChannel::postProcessMap(), VisualCortexSurprise::postProcessOutputMap(), RawVisualCortex::postProcessOutputMap(), and IntegerRawVisualCortex::postProcessOutputMap().

Variable Documentation

const double FANCYCOEX = 0.5

excitatory coefficient (strength)

Definition at line 97 of file fancynorm.H.
Referenced by cudaMaxNormalizeFancy(), maxNormalizeFancy(), maxNormalizeFancyFast(), and maxNormalizeFancyLandmark().

const double FANCYCOIN = 1.5

inhibitory coefficient (strength)

Definition at line 98 of file fancynorm.H.
Referenced by cudaMaxNormalizeFancy(), maxNormalizeFancy(), maxNormalizeFancyFast(), and maxNormalizeFancyLandmark().

const double FANCYESIG = 2

excitatory sigma as % of image size

Definition at line 95 of file fancynorm.H.
Referenced by cudaMaxNormalizeFancy(), maxNormalizeFancy(), and maxNormalizeFancyFast().

const double FANCYG = 2.1

for sigmoid normalization

Definition at line 101 of file fancynorm.H.

const double FANCYH = 2.0

for sigmoid normalization

Definition at line 102 of file fancynorm.H.

const double FANCYINHI = 2.0

strength of global inhibition

Definition at line 99 of file fancynorm.H.
Referenced by cudaMaxNormalizeFancy(), maxNormalizeFancy(), maxNormalizeFancyFast(), and maxNormalizeFancyLandmark().

const double FANCYISIG = 25

inhibitory sigma as % of image size

Definition at line 96 of file fancynorm.H.
Referenced by cudaMaxNormalizeFancy(), maxNormalizeFancy(), and maxNormalizeFancyFast().

const int FANCYITER = 5

default number of iterations

Definition at line 94 of file fancynorm.H.

const double FANCYS = 1.0

for sigmoid normalization

Definition at line 103 of file fancynorm.H.

const int LRLEVEL = 2

for tuned long-range excitation:

Definition at line 105 of file fancynorm.H.
Referenced by cudaMaxNormalizeFancy(), and maxNormalizeFancy().

const float MAXNORMLANDMARK = 255.0f

upper bound for maxNormalizeFancyLandmark()

Definition at line 117 of file fancynorm.H.
Referenced by goodness_map(), and maxNormalizeLandmark().

const float MAXNORMMAX = 10.0f

upper bound for maxNormalize()

Definition at line 113 of file fancynorm.H.
Referenced by SoxChannel::combineOutputs(), CMap_i::computeBiasCMAP(), ComputeCMAP(), computeCMAP(), CMap_i::computeCMAP(), BeoSubSaliency::computeCMAP(), SaliencyMT::computeCMAP(), CudaSaliency::cudaPostChannel(), ContourChannel::doInput(), IntegerSimpleChannel::getSubmapInt(), RegSaliency::postChannel(), SingleChannel::postProcessMap(), and BeobotBrainMT::threadCompute().

const float MAXNORMMIN = 0.0f

lower bound for maxNormalize()

Definition at line 115 of file fancynorm.H.
Referenced by SoxChannel::combineOutputs(), CMap_i::computeBiasCMAP(), ComputeCMAP(), computeCMAP(), CMap_i::computeCMAP(), BeoSubSaliency::computeCMAP(), SaliencyMT::computeCMAP(), CudaSaliency::cudaPostChannel(), ContourChannel::doInput(), IntegerSimpleChannel::getSubmapInt(), goodness_map(), maxNormalizeLandmark(), RegSaliency::postChannel(), SingleChannel::postProcessMap(), and BeobotBrainMT::threadCompute().

Generated on Sun Nov 22 13:44:05 2009 for iLab Neuromorphic Vision Toolkit by

1.4.4


Types of normalization (normtyp)
#define	NBMAXNORMTYPES 13
#define	VCXNORM_DEFAULT VCXNORM_FANCY
enum	MaxNormType { VCXNORM_NONE = 0, VCXNORM_MAXNORM = 1, VCXNORM_FANCY = 2, VCXNORM_FANCYFAST = 3, VCXNORM_FANCYONE = 4, VCXNORM_FANCYLANDMARK = 5, VCXNORM_LANDMARK = 6, VCXNORM_FANCYWEAK = 7, VCXNORM_IGNORE = 8, VCXNORM_SURPRISE = 9, VCXNORM_FANCYVWEAK = 10, VCXNORM_STDEV = 11, VCXNORM_STDEV0 = 12 }
const char *	maxNormTypeName (const MaxNormType m)
	Get a name in clear for a given type.
Additional parameters for fancynorm versions of the algorithm.
const int	FANCYITER = 5
	default number of iterations
const double	FANCYESIG = 2
	excitatory sigma as % of image size
const double	FANCYISIG = 25
	inhibitory sigma as % of image size
const double	FANCYCOEX = 0.5
	excitatory coefficient (strength)
const double	FANCYCOIN = 1.5
	inhibitory coefficient (strength)
const double	FANCYINHI = 2.0
	strength of global inhibition
const double	FANCYG = 2.1
	for sigmoid normalization
const double	FANCYH = 2.0
	for sigmoid normalization
const double	FANCYS = 1.0
	for sigmoid normalization
const int	LRLEVEL = 2
	for tuned long-range excitation:
Standard min/max bounds for maxNormalize().
const float	MAXNORMMAX = 10.0f
	upper bound for maxNormalize()
const float	MAXNORMMIN = 0.0f
	lower bound for maxNormalize()
const float	MAXNORMLANDMARK = 255.0f
	upper bound for maxNormalizeFancyLandmark()
Functions
template<class T>
Image< T >	maxNormalize (const Image< T > &src, const T mi, const T ma, const MaxNormType normtyp=VCXNORM_DEFAULT, int nbiter=FANCYITER, const Image< float > *lrexcit=0)
	Generic implementation (select algorithm with normtyp).
template<class T>
Image< T >	maxNormalizeNone (const Image< T > &src, const T mi, const T ma)
	Specialized implementation (corresponds to VCXNORM_NONE).
template<class T>
Image< T >	maxNormalizeStd (const Image< T > &src, const T mi, const T ma)
	Specialized implementation (corresponds to VCXNORM_MAXNORM).
template<class T>
Image< T >	maxNormalizeFancyFast (const Image< T > &src, const T mi, const T ma, const int nbiter=FANCYITER)
	Specialized implementation (corresponds to VCXNORM_FANCYFAST).
template<class T>
Image< T >	maxNormalizeFancy (const Image< T > &src, const T mi, const T ma, const int nbiter=FANCYITER, const double weakness=1.0, const Image< float > *lrexcit=0)
	Specialized implementation (corresponds to VCXNORM_FANCY).
template<class T>
Image< T >	maxNormalizeFancyLandmark (const Image< T > &src, const T mi, const T ma, const int nbiter=FANCYITER)
	Specialized implementation (corresponds to VCXNORM_FANCY).
template<class T>
Image< T >	maxNormalizeLandmark (const Image< T > &src, const T mi, const T ma)
	Specialized implementation (corresponds to VCXNORM_LANDMARK).
template<class T>
int	findPeaks (const Image< T > &src, const T mi, const T ma, double &sum)
	to find number of peaks in the image (used in landmark detection)
template<class T>
float	goodness_map (const Image< T > &src)
	to find the goodness of a map (used in landmark detection)
template<class T>
Image< T >	maxNormalizeStdev (const Image< T > &src)
	Specialized implementation (corresponds to VCXNORM_STDEV).
template<class T>
Image< T >	maxNormalizeStdev0 (const Image< T > &src)
	Specialized implementation (corresponds to VCXNORM_STDEV0).
std::string	convertToString (const MaxNormType val)
	MaxNormType overload.
void	convertFromString (const std::string &str, MaxNormType &val)
	MaxNormType overload.