图像压缩基于matlab二维图像压缩感知【含Matlab源码 3671期】.zip

% function [t, psnr] = Demo_CS_OMP(imageName, sub) imageName = 'lenna.pgm'; sub = 0.4; %------------ read in the image -------------- img=imread(imageName); % testing image %img = rgb2gray(img); img=double(img); [height,width]=size(img); % building the 1D-DCT basis (corresponding to each column) mat_dct_1d=zeros(height,height); for k=0:1:(height-1) dct_1d=cos([0:1:(height-1)]'*k*pi/height); if k>0 dct_1d=dct_1d-mean(dct_1d); end; mat_dct_1d(:,k+1)=dct_1d/norm(dct_1d); end trial_nums = 5; for j = 1:trial_nums %------------ form the measurement matrix and base matrix --------------- subrate = sub; Phi=randn(floor(height*subrate),height); % only keep ((subrate*height)*height numbers of the original data Phi = Phi./repmat(sqrt(sum(Phi.^2,2)),[1,height]); % normalize each column %--------- projection --------- img_cs_1d=Phi*img; % treat each column as a independent signal tic %-------- recover using omp ------------ sparse_rec_1d=zeros(height,width); Theta_1d=Phi*mat_dct_1d; for i=1:width column_rec=cs_omp(img_cs_1d(:,i),Theta_1d,height); sparse_rec_1d(:,i)=column_rec'; % sparse representation end img_rec_1d=mat_dct_1d*sparse_rec_1d; % inverse transform psnr(j) = 20*log10(255/sqrt(mean((img(:)-img_rec_1d(:)).^2))); t(j) = toc; end psnr = mean(psnr); t = mean(t); disp(['Elapsed Time = ' num2str(t) ' s']); disp(['OMP PSNR = ' num2str(psnr) ' dB']); %------------ show the results -------------------- subplot(2,2,1),imshow(uint8(img)),title('原始图像') subplot(2,2,1),imagesc(img),title('原始图像') subplot(2,2,2),imshow(uint8(img_rec_1d)),title(strcat('压缩后的图像 ','(',num2str(psnr),'dB',')')) % disp('over'); %************************************************************************%