Abstract: Based on the properties of the nonsubsampled Contourlet and the wavelet transform，and with an aim at the different features of high and low frequency sub-images，a new image fusion algorithm based on the nonsubsampled contourlet-wavelet transform is proposed in this paper.A low frequency fusion rule based on selection and weighted average method is used to fuse low frequency coefficients that are decomposed by the nonsubsampled contourlet-wavelet transform in this algorithm，while high frequency coefficients based on local region and weighted average method is used to fuse high frequency sub-images.The experiment results show that the new algorithm makes a better fusion result in improving information content and image articulation.

Key words: image fusion, non-subsampling, Contourlet transform, wavelet-contourlet transform

摘要： 在无下采样Contourlet变换和小波变换的基础上，针对低、高频系数的特点，提出一种新的基于无下采样轮廓小波变换的图像融合算法。该算法对无下采样轮廓小波分解后的低频部分采用了选择与加权平均的融合规则进行融合，而对各层高频系数采用局部区域加权平均融合规则进行融合。实验结果表明，该方法在包含信息量、清晰度上都有明显的提高。

关键词: 图像融合, 无下采样, Contourlet变换, 轮廓小波变换