基于小波变换的图像融合  

Image fusion and it's evaluation based on wavelet transform

作　　者：黄洪琼[1] 温军燕[2] 

机构地区：[1]上海海事大学信息工程学院,上海200135 [2]杭州市市政设施监管中心,浙江杭州310006

出　　处：《上海海事大学学报》2006年第1期58-61,共4页Journal of Shanghai Maritime University

基　　金：上海市高等学校科学技术发展基金(05FZ0405FZ25)

摘　　要：提出一种基于树状小波的图像融合,其基本思想是首先对源图像进行树状小波分解,之后采用基于像素、区域的选择或边缘检测的融合算法来构造融合图像的小波系数,最后通过树状小波逆变换重构得到融合图像.此外,利用熵、图像均值、均方根误差、峰值信噪比等参量对该融合方法的融合性能进行评价与分析.实验结果表明该融合方法是有效的.An image fusion based on tree-wavelet is presented. Its basic thought is, to perform tree-wavelet decomposition of each source image firstly, then construct the wavelet coefficients of the fusion image by using pixel-based, area-based selection or edge-detect operator rules, finally obtain the fusion image by taking inverse tree-wavelet transformation. In addition, with the use of the parameters such as entropy, average of image, root mean square error, peak signal-to-noise ratio, the performance of the fusion scheme is evaluated and analyzed . The image fusion means is proved to be effective.

关 键 词：小波 图像融合 树状小波 

分 类 号：TN919.8[电子电信—通信与信息系统]