顾及源图像质量的可见光和红外图像融合算法  

Algorithm of visible and infrared image fusion considering quality of source images

作　　者：厍向阳[1] 靳霏霏[1] 李爱国[1] 

机构地区：[1]西安科技大学计算机科学与技术学院,陕西西安710054

出　　处：《计算机工程与设计》2012年第12期4624-4628,4638,共6页Computer Engineering and Design

基　　金：陕西省自然科学基金项目(2009JM7007);陕西省教育厅专项科研计划基金项目(08JK354)

摘　　要：分析了目前图像融合算法存在的问题,提出顾及源图像质量的可见光和红外图像融合的算法。以图像融合理论方法为基础,引入图像质量评价方法,构建了顾及源图像质量的图像融合基本框架。以区域加权信息熵作为可见光和红外图像评价方法,并以图像质量评价结果作为小波变换的系数权值来进行图像融合,分别以图像的平均灰度、标准差、信息熵、空间频率作为评价指标对融合后的图像进行质量评价,提出了基于区域加权信息熵的可见光与红外图像融合算法。最后选取多组可见光和红外图像进行图像融合实验。实验结果表明:顾及源图像质量的可见光和红外图像融合算法是完全可行和有效的。The current problems in image fusion algorithm are analyzed, and the algorithm of visible and infrared image considering the quality of source images is put forward. Based on the theory of image fusion, the image quality assessment method is intro- duced, and the basic framework of image fusion considering the quality of source images is constructed. The comentropy in image local weight is as the visible and infrared source images quality assessment index, the assessment results are as the weights coef- ficients of wavelet transform for image fusion, and the average gray, standard deviation, entropy, spatial frequency are as the in- dexes of the fused image quality assessment. The algorithm of the visible and infrared image fusion based on the comentropy in image local weight is proposed. In the end, several groups of visible and infrared images are experimented. The algorithm of visi- ble and infrared image fusion considering the quality of source images is completely feasible and available.

关 键 词：图像融合 图像质量评价 可见光图像 红外图像 小波变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]