cv::LogPolar_Adjacent Class Reference

#include <contrib.hpp>

Classes
struct	pixel

Public Member Functions
	LogPolar_Adjacent ()
	LogPolar_Adjacent (int w, int h, Point2i center, int R=70, double ro0=3.0, double smin=0.25, int full=1, int S=117, int sp=1)
const Mat	to_cortical (const Mat &source)
const Mat	to_cartesian (const Mat &source)
	~LogPolar_Adjacent ()

Protected Member Functions
void	subdivide_recursively (double x, double y, int i, int j, double length, double smin)
bool	get_uv (double x, double y, int &u, int &v)
void	create_map (int M, int N, int R, int S, double ro0, double smin)

Protected Attributes
int	S
int	R
int	M
int	N
int	top
int	bottom
int	left
int	right
double	ro0
double	romax
double	a
double	q
vector< vector< pixel > >	L
vector< double >	A

Detailed Description

Adjacent receptive fields technique

All the Cartesian pixels, whose coordinates in the cortical domain share the same integer part, are assigned to the same RF. The precision of the boundaries of the RF can be improved by breaking each pixel into subpixels and assigning each of them to the correct RF. This technique is implemented from: Traver, V., Pla, F.: Log-polar mapping template design: From task-level requirements to geometry parameters. Image Vision Comput. 26(10) (2008) 1354-1370

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

Constructor & Destructor Documentation

LogPolar_Adjacent() [1/2]

cv::LogPolar_Adjacent::LogPolar_Adjacent ( )

inline

LogPolar_Adjacent() [2/2]

cv::LogPolar_Adjacent::LogPolar_Adjacent	(	int	w,
		int	h,
		Point2i	center,
		int	R = 70,
		double	ro0 = 3.0,
		double	smin = 0.25,
		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)
smin	the size of the subpixel (default value 0.25 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.

~LogPolar_Adjacent()

cv::LogPolar_Adjacent::~LogPolar_Adjacent

(

)

Destructor

Member Function Documentation

create_map()

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

protected

get_uv()

bool cv::LogPolar_Adjacent::get_uv ( double  x, double  y, int &  u, int &  v  )

protected

subdivide_recursively()

void cv::LogPolar_Adjacent::subdivide_recursively ( double  x, double  y, int  i, int  j, double  length, double  smin  )

protected

to_cartesian()

const Mat cv::LogPolar_Adjacent::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)

to_cortical()

const Mat cv::LogPolar_Adjacent::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

a

double cv::LogPolar_Adjacent::a

protected

A

vector<double> cv::LogPolar_Adjacent::A

protected

bottom

int cv::LogPolar_Adjacent::bottom

protected

L

vector<vector<pixel> > cv::LogPolar_Adjacent::L

protected

left

int cv::LogPolar_Adjacent::left

protected

M

int cv::LogPolar_Adjacent::M

protected

N

int cv::LogPolar_Adjacent::N

protected

q

double cv::LogPolar_Adjacent::q

protected

R

int cv::LogPolar_Adjacent::R

protected

right

int cv::LogPolar_Adjacent::right

protected

ro0

double cv::LogPolar_Adjacent::ro0

protected

romax

double cv::LogPolar_Adjacent::romax

protected

S

int cv::LogPolar_Adjacent::S

protected

top

int cv::LogPolar_Adjacent::top

protected

---

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

• contrib.hpp