cv::LogPolar_Overlapping Class Reference

#include <contrib.hpp>

Classes
struct	kernel

Public Member Functions
	LogPolar_Overlapping ()
	LogPolar_Overlapping (int w, int h, Point2i center, int R=70, double ro0=3.0, int full=1, int S=117, int sp=1)
const Mat	to_cortical (const Mat &source)
const Mat	to_cartesian (const Mat &source)
	~LogPolar_Overlapping ()

Protected Member Functions
void	create_map (int M, int N, int R, int S, double ro0)

Protected Attributes
Mat	Rsri
Mat	Csri
vector< int >	Rsr
vector< int >	Csr
vector< double >	Wsr
int	S
int	R
int	M
int	N
int	ind1
int	top
int	bottom
int	left
int	right
double	ro0
double	romax
double	a
double	q
Mat	ETAyx
Mat	CSIyx
vector< kernel >	w_ker_2D

Detailed Description

Overlapping circular receptive fields technique

The Cartesian plane is divided in two regions: the fovea and the periphery. The fovea (oversampling) is handled by using the bilinear interpolation technique described above, whereas in the periphery we use the overlapping Gaussian circular RFs.

More details can be found in http://dx.doi.org/10.1007/978-3-642-23968-7_5

Constructor & Destructor Documentation

cv::LogPolar_Overlapping::LogPolar_Overlapping ( )

inline

cv::LogPolar_Overlapping::LogPolar_Overlapping	(	int	w,
		int	h,
		Point2i	center,
		int	R = 70,
		double	ro0 = 3.0,
		int	full = 1,
		int	S = 117,
		int	sp = 1
	)

Constructor

Parameters

w	the width of the input image
h	the height of the input image
center	the transformation center: where the output precision is maximal
R	the number of rings of the cortical image (default value 70 pixel)
ro0	the radius of the blind spot (default value 3 pixel)
full	1 (default value) means that the retinal image (the inverse transform) is computed within the circumscribing circle. 0 means that the retinal image is computed within the inscribed circle.
S	the number of sectors of the cortical image (default value 70 pixel). Its value is usually internally computed to obtain a pixel aspect ratio equals to 1.
sp	1 (default value) means that the parameter S is internally computed. 0 means that the parameter S is provided by the user.

cv::LogPolar_Overlapping::~LogPolar_Overlapping

(

)

Destructor

Member Function Documentation

void cv::LogPolar_Overlapping::create_map ( int  M, int  N, int  R, int  S, double  ro0  )

protected

const Mat cv::LogPolar_Overlapping::to_cartesian

(

const Mat &

source

)

Transformation from cortical image to retinal (inverse log-polar) image.

Parameters

source

the cortical image

Returns

the transformed image (retinal image)

const Mat cv::LogPolar_Overlapping::to_cortical

(

const Mat &

source

)

Transformation from Cartesian image to cortical (log-polar) image.

Parameters

source

the Cartesian image

Returns

the transformed image (cortical image)

Member Data Documentation

double cv::LogPolar_Overlapping::a

protected

int cv::LogPolar_Overlapping::bottom

protected

Mat cv::LogPolar_Overlapping::CSIyx

protected

vector<int> cv::LogPolar_Overlapping::Csr

protected

Mat cv::LogPolar_Overlapping::Csri

protected

Mat cv::LogPolar_Overlapping::ETAyx

protected

int cv::LogPolar_Overlapping::ind1

protected

int cv::LogPolar_Overlapping::left

protected

int cv::LogPolar_Overlapping::M

protected

int cv::LogPolar_Overlapping::N

protected

double cv::LogPolar_Overlapping::q

protected

int cv::LogPolar_Overlapping::R

protected

int cv::LogPolar_Overlapping::right

protected

double cv::LogPolar_Overlapping::ro0

protected

double cv::LogPolar_Overlapping::romax

protected

vector<int> cv::LogPolar_Overlapping::Rsr

protected

Mat cv::LogPolar_Overlapping::Rsri

protected

int cv::LogPolar_Overlapping::S

protected

int cv::LogPolar_Overlapping::top

protected

vector<kernel> cv::LogPolar_Overlapping::w_ker_2D

protected

vector<double> cv::LogPolar_Overlapping::Wsr

protected

---

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

• contrib.hpp