lti::laplacianPyramid< T > Class Template Reference

LaplacianPyramid class. More...

#include <ltiLaplacianPyramid.h>

Inheritance diagram for lti::laplacianPyramid< T >:

[legend]

Collaboration diagram for lti::laplacianPyramid< T >:

[legend]

List of all members.

Public Member Functions
	laplacianPyramid (const int &resolutions=0, const int &gaussianSize=3, const double &variance=-1)
	laplacianPyramid (const laplacianPyramid &other)
virtual	~laplacianPyramid ()
void	getKernelParameters (int &size, double &variance) const
void	setKernelParameters (const int &size, const double &variance=-1)
const char *	getTypeName () const
laplacianPyramid< T > &	copy (const laplacianPyramid< T > &other)
virtual mathObject *	clone () const
void	generate (const T &src)
void	generate (const T &src, const int &theResolutions)
void	generate (const T &src, const lti::point &limit)
void	generate (const gaussianPyramid< T > &src)
T &	reconstruct (const int &i, T &result) const
pyramid< T > &	reconstruct (const int &i, pyramid< T > &result) const
Protected Member Functions
void	subtract (const T &a, const T &b, T &c) const
void	add (const T &a, const T &b, T &c) const
Protected Attributes
int	kernelSize
double	kernelVariance

---

Detailed Description

template<class T>
class lti::laplacianPyramid< T >

LaplacianPyramid class.

This class implements the Laplacian pyramids as described in Greenspan et.at. "Overcomplete Steerable Pyramid Filters and Rotation Invariance", Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Seattle, 1994

Each level corresponds to a difference of Gaussians, where the level distance is always one octave.

It allows an easy manipulation of the different resolutions.

See method generate() to an detailed explanation

---

Constructor & Destructor Documentation

template<class T>

lti::laplacianPyramid< T >::laplacianPyramid	(	const int &	resolutions = 0,
		const int &	gaussianSize = 3,
		const double &	variance = -1
	)

create a laplacian pyramid with the given number of resolutions

Parameters:

	resolutions	the number of resolutions that the pyramid can hold (default 0: an empty pyramid will be created)
	gaussianSize	the size of the laplacian kernel (default 3)
	variance	the variance of the laplacian kernel (default -1, meaning that the variance should be calculated as described in the lti::gaussKernel1D<T>)

template<class T>

lti::laplacianPyramid< T >::laplacianPyramid

(

const laplacianPyramid< T > &

other

)

create this laplacianPyramid as a copy of another laplacianPyramid

Parameters:

other

the laplacianPyramid to be copied.

template<class T>

virtual lti::laplacianPyramid< T >::~laplacianPyramid

(

)

[virtual]

destructor

---

Member Function Documentation

template<class T>

void lti::laplacianPyramid< T >::add	(	const T &	a,
		const T &	b,
		T &	c
	)			const [protected]

add a and b, and leave the result in c, which will have the size of a, even if the sizes of a and b differ.

template<class T>

virtual mathObject* lti::laplacianPyramid< T >::clone

(

)

const [virtual]

create a clone of this laplacianPyramid

Returns:

a pointer to a copy of this laplacianPyramid

Reimplemented from lti::pyramid< T >.

template<class T>

laplacianPyramid<T>& lti::laplacianPyramid< T >::copy

(

const laplacianPyramid< T > &

other

)

assigment operator.

copy the contents of other in this object.

Parameters:

other

the source laplacianPyramid to be copied.

Returns:

a reference to this object

Reimplemented from lti::pyramid< T >.

template<class T>

void lti::laplacianPyramid< T >::generate

(

const gaussianPyramid< T > &

src

)

generate the laplacian pyramid using the given gaussian pyramid

template<class T>

void lti::laplacianPyramid< T >::generate	(	const T &	src,
		const lti::point &	limit
	)

generate the laplacian pyramid of the given object.

Proceed, until given limit.x or limit.y is reached. smallest resolution will be > limit.

The resolution "0" corresponds to the original channel, and the resolution i+1 is always a factor 2 smaller than the resolution i.

template<class T>

void lti::laplacianPyramid< T >::generate	(	const T &	src,
		const int &	theResolutions
	)

generate the laplacian pyramid of the given object.

The pyramid will contain the number of resolutions specified by theResolutions. The resolution "0" will correspond the the original channel, and the resolution i+1 is always a factor 2 smaller than the resolution i.

template<class T>

void lti::laplacianPyramid< T >::generate

(

const T &

src

)

generate the laplacian pyramid of the given object.

The pyramid will contain the number of resolutions specified in the construction or in the resize() method. The resolution "0" will correspond the the original channel, and the resolution i+1 is always a factor 2 smaller than the resolution i.

template<class T>

void lti::laplacianPyramid< T >::getKernelParameters	(	int &	size,
		double &	variance
	)			const

return the size and variance of the used gaussian kernel

template<class T>

const char* lti::laplacianPyramid< T >::getTypeName

(

void

)

const [inline, virtual]

returns the name of this class: "laplacianPyramid"

Reimplemented from lti::pyramid< T >.

template<class T>

pyramid<T>& lti::laplacianPyramid< T >::reconstruct	(	const int &	i,
		pyramid< T > &	result
	)			const

reconstructs the resolution with index i.

All partial reconstructions will be stored at the given gaussian pyramid.

Parameters:

	i	the resolution to be reconstructed
	result	the resulting pyramid.

Returns:

a reference to the result pyramid

template<class T>

T& lti::laplacianPyramid< T >::reconstruct	(	const int &	i,
		T &	result
	)			const

reconstructs the resolution with index i.

Parameters:

	i	the resolution to be reconstructed
	result	the resulting object

Returns:

a reference to the result object.

template<class T>

void lti::laplacianPyramid< T >::setKernelParameters	(	const int &	size,
		const double &	variance = -1
	)

set the kernel parameters

Parameters:

	size	the size of the kernel
	variance	the variance for the laplacian kernel. A negative value will force the default variance of a laplacian kernel with size size.

template<class T>

void lti::laplacianPyramid< T >::subtract	(	const T &	a,
		const T &	b,
		T &	c
	)			const [protected]

subtract b from a, and leave the result in c, which will have the size of a, even if the sizes of a and b differ.

---

Member Data Documentation

template<class T>

int lti::laplacianPyramid< T >::kernelSize [protected]

kernel size

template<class T>

double lti::laplacianPyramid< T >::kernelVariance [protected]

kernel variance

---

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

• ltiLaplacianPyramid.h