RESEARCH OF IMAGE FUSION ALGORITHM WHICH BASED ON HUMAN VISUAL PERCEPTION FEATURE
To solve the problem of multi-focus image fusion, a new multi-focus image fusion algorithm was proposed in this paper which based on the characteristic of visual perception. The research results have shown that the threshold of human visual contrast sensitivity was proportional to the background brightness of image. It adopted the visual contrast parameter as qualitative criteria to separate clear goals from the fuzzy goals which have been obtained by different focus sensor. Firstly, it separated the image to be fused at RGB level. Secondly, it divided the R, G, B single gray image into M*N blocks. The blocks which have higher contrast value should be adopted as the fusion results. It adopted the immune genetic algorithm to calculate the optimal value of M and N. The algorithm took the root-mean-square error, image entropy as the affinity function. The results have shown that the image fusion algorithm which proposed in this paper was suit for multi-focus image fusion and easy to reality.
Visual Perception Image Fusion Optimization
Wei Yaoguang Wang Jianqin Li daoliang Tu xuyan
College of Information and Electrical Engineering,China Agriculture University,Beijing,P.R China Col College of Information and Electrical Engineering,China Agriculture University,Beijing,P.R China College of Information and Engineering,University of Science and Technology Beijing,Beijing,P.R Chin
国际会议
北京
英文
1-6
2009-10-14（万方平台首次上网日期，不代表论文的发表时间）