基于小波系数方向特性的图像融合新算法  

A Novel Image Fusion Algorithm Based on Directional Correlation of Wavelet Coefficients

作　　者：王相海[1,2] 周志光[1] 

机构地区：[1]辽宁师范大学计算机与信息技术学院,辽宁大连116029 [2]计算机软件新技术国家重点实验室(南京大学),江苏南京210093

出　　处：《吉林师范大学学报（自然科学版）》2008年第3期37-42,共6页Journal of Jilin Normal University:Natural Science Edition

基　　金：辽宁省自然基金项目(20072156);辽宁省高等学校优秀人才支持计划(RC-04-11)

摘　　要：介绍了图像的提升方案小波变换并统计了图像经小波变换后各高频子带系数的方向区域特性,据此提出了一种新的基于小波系数方向特性的图像融合方法.对于低频子带的每个系数,采用加权平均的融合规则确定低频融合系数;对于各高频子带的每个系数,根据其所在子带的方向特征,采用方向特性的融合规则确定高频融合系数.本文对多幅图像进行了融合仿真实验,并用信息熵和平均梯度对融合结果进行了客观的评价.实验结果表明,基于小波系数方向特性的图像融合算法要优于传统的融合算法,具有一定的实用性.The lifting wavelet transformation is introduced and the directional characteristic of the high-frequency coefficients is discussed and analyzed in this paper. Then, a novel algorithm of image fusion based on the directional correlation of wavelet coefficients is proposed. At first, for every coefficient of the low-frequency, the algorithm of this paper makes out the fusing coefficient by using the method of weighted averages. Then, for every coefficient of the high-frequency, the algorithm of this paper makes out the fusing coefficient by using the method of the directional characteristic. At last, the fused image is obtained through the reversely lifting wavelet transformation. Entropy and Average grads are used to judge the results of the proposed algorithms. Experimental results show that the proposed method is more outstanding than the conventional methods, and it has some application value.

关 键 词：图像融合 提升小波变换 方向特性 融合规则 

分 类 号：TP391.7[自动化与计算机技术—计算机应用技术]