無參考圖片質量檢測BRISQUE在matlab上的代碼
0.png (41.44 KB, 下載次數: 29)
下載附件
2018-6-11 17:04 上傳
0.png (206.52 KB, 下載次數: 32)
下載附件
2018-6-11 17:04 上傳
0.png (8.21 KB, 下載次數: 27)
下載附件
2018-6-11 17:05 上傳
matlab源程序如下:
- function feat = brisque_feature(imdist)
- %------------------------------------------------
- % Feature Computation
- %-------------------------------------------------
- scalenum = 2;
- window = fspecial('gaussian',7,7/6);
- window = window/sum(sum(window));
- feat = [];
- tic
- for itr_scale = 1:scalenum
- mu = filter2(window, imdist, 'same');
- mu_sq = mu.*mu;
- sigma = sqrt(abs(filter2(window, imdist.*imdist, 'same') - mu_sq));
- structdis = (imdist-mu)./(sigma+1);
- [alpha overallstd] = estimateggdparam(structdis(:));
- feat = [feat alpha overallstd^2];
- shifts = [ 0 1;1 0 ; 1 1; -1 1];
-
- for itr_shift =1:4
-
- shifted_structdis = circshift(structdis,shifts(itr_shift,:));
- pair = structdis(:).*shifted_structdis(:);
- [alpha leftstd rightstd] = estimateaggdparam(pair);
- const =(sqrt(gamma(1/alpha))/sqrt(gamma(3/alpha)));
- meanparam =(rightstd-leftstd)*(gamma(2/alpha)/gamma(1/alpha))*const;
- feat =[feat alpha meanparam leftstd^2 rightstd^2];
- end
- imdist = imresize(imdist,0.5);
- end
- toc
所有資料51hei提供下載:
BRISQUE-master.zip
(2.83 MB, 下載次數: 14)
2018-6-11 14:12 上傳
點擊文件名下載附件
BRISQUE 下載積分: 黑幣 -5
|
QQ好友和群
QQ空間
騰訊微博
騰訊朋友
收藏
淘帖
頂
踩
