Multi-focus image fusion algorithm based on shearlets  

作　　者：苗启广 石程 许鹏飞 杨眉 史耀波 

机构地区：[1]School of Computer Science,Xidian University [2]School of Economics and Management,Xi'an University of Technology

出　　处：《Chinese Optics Letters》2011年第4期25-29,共5页中国光学快报（英文版）

基　　金：jointly supported by the National Natural Science Foundation of China (Nos. 61072109 and 60702063);the Fundamental Research Funds for the Central Universities, and the Creative Project of the Science and Technology State of Xi'an under Grant (No. CXY1015(3);partly supported by the National Natural Science Foundation of China (Nos. 60804021 and 60802084)

摘　　要：Shearlets not only possess all properties that other transforms have, but also are equipped with a rich mathematical structure similar to wavelets, which are associated to a multi-resolution analysis. Recently, shearlets have been used in image denoising, sparse image representation, and edge detection. However, its application in image fusion is still under study. In this letter, we study the feasibility of image fusion using shearlets. Fusion rules of larger high-frequency coefficients based on regional energy, regional variance, and absolute value are proposed because shearlet transform can catch detailed information in any scale and any direction. The fusion accuracy is also further improved by a region consistency check. Several different experiments are adopted to prove that fusion results based on shearlet transform can acquire better fusion quality than any other method.Shearlets not only possess all properties that other transforms have, but also are equipped with a rich mathematical structure similar to wavelets, which are associated to a multi-resolution analysis. Recently, shearlets have been used in image denoising, sparse image representation, and edge detection. However, its application in image fusion is still under study. In this letter, we study the feasibility of image fusion using shearlets. Fusion rules of larger high-frequency coefficients based on regional energy, regional variance, and absolute value are proposed because shearlet transform can catch detailed information in any scale and any direction. The fusion accuracy is also further improved by a region consistency check. Several different experiments are adopted to prove that fusion results based on shearlet transform can acquire better fusion quality than any other method.

关 键 词：Edge detection Wavelet transforms 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TU753[自动化与计算机技术—计算机科学与技术]