基于模糊自适应DT-CWT多聚焦图像融合算法  

Adaptive DT-CWT Multifocus Image Fusion Algorithm Based on Fuzzy

作　　者：周苑[1] 杨爱云[1] 

机构地区：[1]河南工程学院,郑州451191

出　　处：《激光杂志》2016年第1期120-123,共4页Laser Journal

基　　金：河南省科技攻关重点项目(142102210037)

摘　　要：本文针对对偶树复小波变换(DT-CWT)算法在图像融合过程中,为了度量拥有不同类型特征的图像与之对应的像素之间的关系,自适应的解决在图像融合过程中出现的不确定性等问题,提出了将模糊理论引入到DT-CWT的多聚焦图像融和算法中。通过引入模糊理论,用模糊隶属度对图像中的不同特征与像素灰度值寻找一定的关系,并在此基础上提出了一种基于Fisher判别与模糊理论融合在一起的方法对系数进行选择。仿真结果证明了该算法的可靠性,通过对比实验说明该算法能够在保留原始图像中的纹理和边缘等细节信息的同时,有效的去除了原始图像中的聚焦差异,具有更好的融合性能。In this paper,aiming at the dual-tree complex Wavelet transform（DT-CWT） algorithm in image fusion process, in order to measure the relationship between the different characteristics of the image the corresponding pixel, adaptively solving uncertainty problems in the process of image fusion, puts fuzzy theory to the DT-CWT integration al- gorithm of multi-focus images. By introducing fuzzy theory in images by fuzzy membership of different characteristics and pixel intensity value is looking for a relationship, and on this basis, a method based on Fisher discriminant and fuzzy coefficient is presented. Simulation results show that reliability of the algorithm, experiment indicates that the algo- rithm can retain the original image texture and edge details, effectively remove the focus differences in the original im- age, has a better performance of integration.

关 键 词：对偶树复小波变换 图像融合 模糊理论 像素灰度值 

分 类 号：TN911.73[电子电信—通信与信息系统]