wedgeletapprox.m

来自「beamlet变化的工具箱」· M 代码 · 共 36 行

%  WedgeletApprox -- Approximate image by wedgelets
% 	Usage
% 		fit = WedgeletApprox(x,lambda)
% 	Inputs
% 		x		n*n array, n dyadic
% 		lambda		scalar, determining threshold
% 		W		Wedgelet Transform of x (optional)
% 	Outputs			
% 		fit		approximation to x
% 		W		Wedgelet Analysis of x
% 	Description
% 		This routine solves the problem
% 			min_P || y - Ave{y|P} ||_2^2 + lambda^2/2 #{P}
% 	minimizing the complexity-penalized sum of squares
% 	over all beamlet-decorated partitions of the image
% 	square.  It is suggested that 
% 			lambda = sqrt{4 log(n)} sigma
% 	is a good choice for data 
% 			x = f + z
% 	where f is a noiseless object with smooth sharp
% 	beams and z is N(0,sigma^2 I).
%
%
% Part of BeamLab Version:200
% Built:Friday,23-Aug-2002 00:00:00
% This is Copyrighted Material
% For Copying permissions see COPYING.m
% Comments? e-mail [e-mail]
%
%
% Part of BeamLab Version:200
% Built:Saturday,14-Sep-2002 00:00:00
% This is Copyrighted Material
% For Copying permissions see COPYING.m
% Comments? e-mail [e-mail]
%