基于累加梯度和PCA变换的图像融合算法  

Pixel level image fusion algorithm based on cumulative gradient and PCA transform

作　　者：李波[1] 吕海莲[1] 

机构地区：[1]平顶山学院软件学院,河南平顶山467002

出　　处：《计算机工程与设计》2010年第3期574-576,581,共4页Computer Engineering and Design

基　　金：国家自然科学基金项目(60873104)

摘　　要：为了从不同源图像获取互补信息,获得一幅比任何源图像更准确、全面、可靠的复合图像,提出了一种基于局部累加梯度和PCA变换的图像融合算法。该算法在对源图像进行双树复小波变换的基础上,运用局部累加梯度准则实现融合图像的局部细节系数选取,运用基于PCA变换的选择或平均准则实现融合图像的局部逼近系数选取,并对获得的融合细节系数和逼近系数进行双树复小波反变换得到相应的融合图像。通过计算机仿真,从视觉效果和定量分析可以看出该图像融合算法是有效的。To extract complementary information from different sensor images and obtain one composite image that is more accurate, more comprehensive and more credible than each sensor image,an image fusion algorithm is presented based on local accumulated gradient and PCA transform.By taking the dual tree complex wavelet transform to the source images,the fused local detailed coefficients are chosen according to local accumulated gradient rule,and the fused approximate coefficients are acquired by selection or averaging rule based on PCA.Finally,the fused image is obtained by taking the inverse dual tree complex wavelet transform of the fused detailed coefficients and the fused approximate coefficients.By design of computer simulation,the proposed image fusion algorithm is demonstrated to be effective in terms of the visual effects and the quantitative analysis rule.

关 键 词：图像融合 双树复小波变换 累加梯度 PCA变换 互信息 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]