LTI-Lib latest version v1.9 - last update 10 Apr 2010

lti::curvatureScaleSpace::parameters Class Reference

the parameters for the class curvatureScaleSpace More...

#include <ltiCurvatureScaleSpace.h>

Inheritance diagram for lti::curvatureScaleSpace::parameters:
Inheritance graph
[legend]
Collaboration diagram for lti::curvatureScaleSpace::parameters:
Collaboration graph
[legend]

List of all members.

Public Member Functions

 parameters ()
 parameters (const parameters &other)
 ~parameters ()
const char * getTypeName () const
parameterscopy (const parameters &other)
parametersoperator= (const parameters &other)
virtual functor::parametersclone () const
virtual bool write (ioHandler &handler, const bool complete=true) const
virtual bool read (ioHandler &handler, const bool complete=true)

Public Attributes

bool geometricDelta
double deltaSigma
double startSigma
int gaussianSize
int normLength
int sigmaAxisBlock
ubyte posNegCross
ubyte negPosCross
ubyte nonCross
bool fastMethod

Detailed Description

the parameters for the class curvatureScaleSpace


Constructor & Destructor Documentation

lti::curvatureScaleSpace::parameters::parameters (  ) 

default constructor

Reimplemented from lti::transform::parameters.

lti::curvatureScaleSpace::parameters::parameters ( const parameters other  ) 

copy constructor

Parameters:
other the parameters object to be copied

Reimplemented from lti::transform::parameters.

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

destructor

Reimplemented from lti::functor::parameters.


Member Function Documentation

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

returns a pointer to a clone of the parameters

Reimplemented from lti::transform::parameters.

parameters& lti::curvatureScaleSpace::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::transform::parameters.

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

returns name of this type

Reimplemented from lti::transform::parameters.

parameters& lti::curvatureScaleSpace::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::curvatureScaleSpace::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::curvatureScaleSpace::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

Step for the std.

deviation to generate the CSS-image. This value will be added at each step to the previous sigma (if geometricDelta is false) or will be multiplied with the last sigma (if geometricDelta is true). For the last case please ensure that this value is greater than one, otherwise the results will be unpredictable.

Default value: 0.1

If false, the CSS will be computed evolving the x and y components of the border points using the derived gauss kernels.

If true, the components will be first low-pass filtered and after that the resulting vectors will be derived. This second method is much faster but for the geometricDelta mode and for small sigma regions it is not precise. If you need this functor for feature extraction, the fast method will provide you with the maxima of the CSS "blobs" with enough precision. (Default value: true)

Size for the first kernel being used.

Note that this is the first kernel size. As the std. deviation increases, the size of the kernel will be updated automatically. Default value: 9

if geometricDelta is true, the sigma increments will be multiplicative i.e.

sigma(1) = deltaSigma*sigma(0). If false, arithmetical increments will be done, (sigma(1) = deltaSigma + sigma(0) Please note that for the geometricDelta, the deltaSigma should be greater than one to get usefull results!

Default value: false

pixel value in the CSS image for a negative-positive zero crossing.

If you want to extract features, please ensure that this value is different than posNegCross, otherwise the features could be wrong.

(Default: 255)

value for non-zero crossing (background of the CSS image) (Default: 128)

Normalized length size.

This will be the number of columns of the resulting CSS image. If negative, the length will not be normalized and the number of columns of the resulting image will be equal to the number of elements of the borderPoint-list given in the apply method.

Default value: 128

pixel value in the CSS image for a positive-negative zero crossing.

If you want to extract features, please ensure that this value is different than negPosCross, otherwise the features could be wrong.

(Default: 0)

The sigmaAxisBlock specifies how many sigma steps will have a block.

The result image will have an integer number of blocks, which means, the number of rows of the resulting channel will be a multiple of this value. Default value: 128

The first std.

deviation for the gaussian kernel used.

Default value: 1.0


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

Generated on Sat Apr 10 15:27:11 2010 for LTI-Lib by Doxygen 1.6.1