#include <RAosPeronaFabOp.hpp>
Inheritance diagram for RAosPeronaFabOp:
Purpose: FAB diffusion may be unstable if edges are too strong. It allow to blurr/deblurr adaptively. We reduce deblurring inversely to number of iterations. We replace the old Perona barrier by the combined forward/backward. The process can be instable. Fast Computation of Perona recursive flow. Thomas LU model. Semi-Implicit solver using AOS additive splitting (I - tau * A) * uNew= uOld Should be better than LOD: Rotation invariant. LOD is sequential (handelling each direction x y z in sequence) AOS is parallel (handelling each direction x y z at the same time) AOS build an average operator Both LOD and AOS are designed for large image restoration, O(N) in time ang space!!! Papers: "Forward and Backward Diffusion Processes for Adaptive Image Enhancement and Denoising.", Guy Gilboa, Nir Sochen and Yehoshua Y. Zeevi, IEEE Trans. on Image Processing, vol ?, no ? 2002 "Recursivity and PDE's in image processing", L. Alvarez, R. Deriche and F Santana, Spain 1998. "Efficient and Reliable Schemes for Nonlinear Diffusion Filtering", Joachim. Weickert & all, IEEE transactions on Image Processing, vol7, n3, March 1998.
@ Copyrights: Bernard De Cuyper & Eddy Fraiha 2002, Eggs & Pictures. MIT/Open BSD copyright model.
Public Methods | |
RAosPeronaFabOp (int iterations=8, double t=0.5, int nf=4, int nb=2, double gSigma=3.0, double rkf=0.1, double asigma=5.0, double rkb=6.0, double rw=2.0, bool iirFlag=false, bool nonLinearFlag=true) | |
virtual | ~RAosPeronaFabOp () |
virtual RImage * | filter (RImage *src, RImage *dest=0) |
Local full image filtering. | |
virtual void | report (FILE *file) |
Protected Methods | |
virtual double | g (int i, int j) |
Protected Attributes | |
RImage * | I0 |
double | gsigma |
RImage * | gradI0 |
int | nf |
double | kf |
int | nb |
double | alpha |
double | kb |
double | wb |
|
Local full image filtering.
Reimplemented from RSimpleAosOp. |