SRcnn:神经网络重建图片的开山之作

% =========================================================================

% Test code for Super-Resolution Convolutional Neural Networks (SRCNN)

%

% Reference

%   Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang. Learning a Deep Convolutional Network for Image Super-Resolution,

%   in Proceedings of European Conference on Computer Vision (ECCV),

%

%   Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang. Image Super-Resolution Using Deep Convolutional Networks,

%   arXiv:1501.00092

%

% Chao Dong

% IE Department, The Chinese University of Hong Kong

% For any question, send email to [email protected]

% =========================================================================

close all;

clear all;

%% read ground truth image

im  = imread('Set5\butterfly_GT.bmp');

%im  = imread('Set14\zebra.bmp');

%% set parameters

up_scale = ;

model = 'model\9-5-5(ImageNet)\x3.mat';

% up_scale = ;

% model = 'model\9-3-5(ImageNet)\x3.mat';

% up_scale = ;

% model = 'model\9-1-5(91 images)\x3.mat';

% up_scale = ;

% model = 'model\9-5-5(ImageNet)\x2.mat';

% up_scale = ;

% model = 'model\9-5-5(ImageNet)\x4.mat';

%% work on illuminance only

if size(im,)>

    im = rgb2ycbcr(im);

    im = im(:, :, );

end

im_gnd = modcrop(im, up_scale);   %保证图像被up_scale整除

im_gnd = single(im_gnd)/;     %Single（单精度浮点型）变量存储为 IEEE  位（ 个字节）浮点数值的形式，它的范围在负数的时候是从 -3.402823E38 到 -1.401298E-45，而在正数的时候是从 1.401298E-45 到 3.402823E38。

%% bicubic interpolation

im_l = imresize(im_gnd, /up_scale, 'bicubic');    %缩小3倍

im_b = imresize(im_l, up_scale, 'bicubic');        %又放大三倍

%% SRCNN

im_h = SRCNN(model, im_b);               %用网络处理一下

%% remove border  %去除没有用的边界

im_h = shave(uint8(im_h * ), [up_scale, up_scale]);  %表示变量是无符号整数，范围是0到255.

im_gnd = shave(uint8(im_gnd * ), [up_scale, up_scale]);

im_b = shave(uint8(im_b * ), [up_scale, up_scale]);

%% compute PSNR

psnr_bic = compute_psnr(im_gnd,im_b);

psnr_srcnn = compute_psnr(im_gnd,im_h);

%% show results

fprintf('PSNR for Bicubic Interpolation: %f dB\n', psnr_bic);

fprintf('PSNR for SRCNN Reconstruction: %f dB\n', psnr_srcnn);

%保存 图片

imwrite(im_h,'img_h.png');

imwrite(im_b,'img_b.png');

imwrite(im_gnd,'img_gnd.png');

figure, imshow(im_b); title('Bicubic Interpolation');

figure, imshow(im_h); title('SRCNN Reconstruction');

%imwrite(im_b, ['Bicubic Interpolation' '.bmp']);

%imwrite(im_h, ['SRCNN Reconstruction' '.bmp']);

SRCNN的核心算法：

function im_h = SRCNN(model, im_b)

%% load CNN model parameters

load(model);

[conv1_patchsize2,conv1_filters] = size(weights_conv1);

conv1_patchsize = sqrt(conv1_patchsize2);

[conv2_channels,conv2_patchsize2,conv2_filters] = size(weights_conv2);

conv2_patchsize = sqrt(conv2_patchsize2);

[conv3_channels,conv3_patchsize2] = size(weights_conv3);

conv3_patchsize = sqrt(conv3_patchsize2);

[hei, wid] = size(im_b);

%% conv1

weights_conv1 = reshape(weights_conv1, conv1_patchsize, conv1_patchsize, conv1_filters);

conv1_data = zeros(hei, wid, conv1_filters);

for i =  : conv1_filters

    conv1_data(:,:,i) = imfilter(im_b, weights_conv1(:,:,i), 'same', 'replicate');

    conv1_data(:,:,i) = max(conv1_data(:,:,i) + biases_conv1(i), );

end

%% conv2

conv2_data = zeros(hei, wid, conv2_filters);

for i =  : conv2_filters

    for j =  : conv2_channels

        conv2_subfilter = reshape(weights_conv2(j,:,i), conv2_patchsize, conv2_patchsize);

        conv2_data(:,:,i) = conv2_data(:,:,i) + imfilter(conv1_data(:,:,j), conv2_subfilter, 'same', 'replicate');

    end

    conv2_data(:,:,i) = max(conv2_data(:,:,i) + biases_conv2(i), );

end

%% conv3

conv3_data = zeros(hei, wid);

for i =  : conv3_channels

    conv3_subfilter = reshape(weights_conv3(i,:), conv3_patchsize, conv3_patchsize);

    conv3_data(:,:) = conv3_data(:,:) + imfilter(conv2_data(:,:,i), conv3_subfilter, 'same', 'replicate');

end

%% SRCNN reconstruction

im_h = conv3_data(:,:) + biases_conv3;

图解里面变量和卷积