紧支撑二维小波多尺度融合图像效果评价  

Objective effect evaluation of image fusion based on 2-D compact supported wavelet

作　　者：冼广铭[1] 王知衍[1] 黄鲲[1] 

机构地区：[1]华南理工大学计算机科学与工程学院,广东广州510640

出　　处：《计算机工程与设计》2006年第15期2740-2743,共4页Computer Engineering and Design

基　　金：科技部科技型中小型企业技术创新基金项目(O2C26214400224);广东省科技计划基金项目(2002A1020104)

摘　　要：针对图像融合的效果评价标准以及小波函数选择等热点研究问题,文中采用了紧支撑二维小波db3对图像进行了多尺度分解及重构的融合研究,并且通过亮度参数、细节参数和光谱信息参数等对融合尺度不同的图像进行了客观质量评价。实验证明,经过该方法融合后的图像能把源图像各自具有的信息融合在一起,亮度适中、信息熵增加、清晰度提高。理论分析结果、融合图像的视觉效果与所采用的客观质量评价标准的数值分析结果是相一致的,表明了该方法客观而有效。Aimed at heated research field of evaluation effect of fused image and selection of wavelet function, 2-D compact supported wavelet db3 is selected to decompose and reconstruct image at different level. And parameters of brightness, details information and spectrum are used to evaluate the fused image. Experimental results show that this approach can effectively fuse information from different source images. Brightness, entropy and definition of the fused image are improved. Theory analysis results and effect of vision of fused image are in accordance with effect of value analysis by using the objeetive effect evaluation method. It is demonstrated that the method above is objective and effective.

关 键 词：紧支撑二维小波 图像融合 多尺度分解 客观质量评价标准 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]