Fork me on GitHub

【图像算法】图像特征:三个图像显著性区域特征提取方法

-------------------------------------------------------------------------------------------------------------------------

【图像算法】图像特征:三个图像显著性区域特征提取方法

 SkySeraph Aug 11st 2011  HQU

Email:zgzhaobo@gmail.com    QQ:452728574

Latest Modified Date:Aug 11st 2011  HQU

-------------------------------------------------------------------------------------------------------------------------

 图像算法系列: http://skyseraph.com/2011/08/27/CV/图像算法专题/ 

》第一种方法:

原理:Frequency-tuned Salient Region Detection.CVPR.2009

定义:

简述

三步,滤波+颜色空间转换+计算SaliencyMap(见源码)

效果

待测试图(后同)

结果1:(原作者代码测试结果)

 

 

结果2:(我用OpenCV改写的代码测试结果)

 

 

结果3:(我的改进测试(空间选择不同))

源码(matlab):

%---------------------------------------------------------
% Read image and blur it with a 3x3 or 5x5 Gaussian filter
%---------------------------------------------------------
img = imread('input_image.jpg');%Provide input image path
gfrgb = imfilter(img, fspecial('gaussian', 3, 3), 'symmetric', 'conv');
%---------------------------------------------------------
% Perform sRGB to CIE Lab color space conversion (using D65)
%---------------------------------------------------------
cform = makecform('srgb2lab', 'whitepoint', whitepoint('d65'));
lab = applycform(gfrgb,cform);
%---------------------------------------------------------
% Compute Lab average values (note that in the paper this
% average is found from the unblurred original image, but
% the results are quite similar)
%---------------------------------------------------------
l = double(lab(:,:,1)); lm = mean(mean(l));
a = double(lab(:,:,2)); am = mean(mean(a));
b = double(lab(:,:,3)); bm = mean(mean(b));
%---------------------------------------------------------
% Finally compute the saliency map and display it.
%---------------------------------------------------------
sm = (l-lm).^2 + (a-am).^2 + (b-bm).^2;
imshow(sm,[]);
%--------------------------------------------------------

------------------------------------------------------------------------------------------------------------------------------

》第二种方法:

原理:

Y. Zhai and M. Shah. Visual attention detection in video sequences using spatiotemporal cues. In ACM Multimedia, pages 815–824. ACM,2006.

定义:

效果:

------------------------------------------------------------------------------------------------------------------------------

》第三种方法:

原理:http://www.klab.caltech.edu/~xhou/projects/spectralResidual/spectralresidual.html

源码(matlab):

clear
clc

%% Read image from file 
inImg = im2double(rgb2gray(imread('yourImage.jpg')));
inImg = imresize(inImg, 64/size(inImg, 2));

%% Spectral Residual
myFFT = fft2(inImg); 
myLogAmplitude = log(abs(myFFT));
myPhase = angle(myFFT);
mySpectralResidual = myLogAmplitude - imfilter(myLogAmplitude, fspecial('average', 3), 'replicate'); 
saliencyMap = abs(ifft2(exp(mySpectralResidual + i*myPhase))).^2; 

%% After Effect
saliencyMap = mat2gray(imfilter(saliencyMap, fspecial('gaussian', [10, 10], 2.5)));
imshow(saliencyMap);

 

效果: 

 

 

 

SYNC (www.skyseraph.com)

------------------------------------------------------------------------------------------------------------------------------

 

Author:         SKySeraph

 

Email/GTalk: zgzhaobo@gmail.com    QQ:452728574

 

From:         http://www.cnblogs.com/skyseraph/

 

本文版权归作者和博客园共有,欢迎转载,但未经作者同意必须保留此段声明,且在文章页面明显位置给出原文连接,否则保留追究法律责任的权利.

 

 -----------------------------------------------------------------------------------------------------------------------------

 

posted @ 2011-08-11 17:21  SkySeraph  阅读(27860)  评论(66编辑  收藏  举报