Mercurial > hg > smallbox
view Problems/Pierre_reconstruct.m @ 207:233e75809e4a luisf_dev
Accelerated the code for LGD and optimal grandient descent
author | bmailhe |
---|---|
date | Wed, 21 Mar 2012 14:12:25 +0000 |
parents | 8e660fd14774 |
children |
line wrap: on
line source
function reconstructed=Pierre_reconstruct(y, Problem) %% Pierre Villars Example - reconstruction function % % This example is based on the experiment suggested by Professor Pierre % Vandergheynst on the SMALL meeting in Villars. % The function is using sparse representation y in dictionary Problem.A % to reconstruct the patches of the target image. % % Centre for Digital Music, Queen Mary, University of London. % This file copyright 2009 Ivan Damnjanovic. % % This program is free software; you can redistribute it and/or % modify it under the terms of the GNU General Public License as % published by the Free Software Foundation; either version 2 of the % License, or (at your option) any later version. See the file % COPYING included with this distribution for more information. %% imout=Problem.A*y; % combine the patches into reconstructed image im=col2im(imout,Problem.blocksize,size(Problem.imageTrg),'disctint'); % bound the pixel values to [0,255] range im(im<0)=0; im(im>255)=255; %% output structure image+psnr %% reconstructed.image=im; reconstructed.psnr = 20*log10(Problem.maxval * sqrt(numel(Problem.imageTrg(:))) / norm(Problem.imageTrg(:)-im(:))); end