中文摘要：

为有效融合多聚焦的可见光图像,提出一种基于结构相似度与区域能量的Curvelet域多聚焦图像融合方法.该方法首先对待融合图像进行Curvelet分解,得到图像的低频系数和高频系数,对低频部分采用加权平均法,高频部分则根据结构相似度与区域能量两个因素来确定,最后通过Curvelet逆变换重构融合图像.实验结果表明,该方法不仅能够自适应的对多聚焦图像进行有效融合,而且其融合图像的信息熵、标准差和清晰度等指标均优于主成分分析法、拉普拉斯金字塔法及小波变换法等常见的多种融合方法.

英文摘要：

In order to fuse multiple visible-light images with different focuses efficiently, a multi-focus image fusion method based on structural similarities and local energies in Curvelet domain is proposed.In this method,the original images are first decomposed with Curvelet transform and the coefficients of low-frequency and high-frequency in Curvelet domain are obtained.Then,the low-frequency coefficients are gained by averaging the two groups of low-frequency coefficients,while the high-frequency coefficients are decided by the structural similarity depending on their local energies.Finally,the fused image is reconstructed by inverse Curvelet transform.Experimental results indicate our method not only can efficiently integrate the detail information,but also is superior to some widely-used methods,such as principal component analysis method,Laplacian pyramid method,and wavelet transform based method,when the entropy,standard deviation and clarity of fused images are compared.