一种新的像素级多聚焦图像融合算法

该文在小波变换的基础上提出了一种将一维自组织特征映射(SOFM)网络和进化策略相结合的多聚焦图像融合算法。该方法对不同聚焦点的图像进行冗余小波分解，再分别将其各方向、各尺度的高频信息进行叠加，并在高频信息叠加层上提取反映图像清晰度差异的归一化特征图，依据此特征图，使用SOFM网络对原始图像像素进行分类，并利用进化策略对各类像素求出最优的融合系数。实验结果表明该算法比拉普拉斯变换法和小波变换法具有更好的融合效果。

A New Pixel-Level Multi-focus Image Fusion Algorithm

A new fusion method for fusing two spatially registered multi-focus images is proposed in this paper.It is based on multi-resolution wavelet decomposition,Self-Organizing Feature Map(SOFM) neural networks and Evolutionary Strategies(ES).First,a normalized feature image,which represents the local region clarity difference of two source images,is extracted by redundant wavelet transform,then the feature image is clustered by SOFM learning algorithm and every pixel pair in source images is classified into a certain class which indicates different clarity differences.Finally,to each pixel pair in different classes,different fusion factors are used to fuse it;these fusion factors are determined by evolution strategies to achieve the best fusion performance.Experimental results show that the proposed method outperforms the Laplace transform and wavelet transform methods.