Abstract: In order to overcome the drawbacks of traditional contrast image fusion based on wavelet methods and combined the advantages of Nonsubsampled Contourlet Transform，a novel image fusion algorithm is proposed in this paper.Firstly，this algorithm decomposes original images by nonsubsampled contourlet transform，and then the low-frequency coefficients are fused by local area energy while for the high-frequency coefficient，the combination of weighting and selection based on the local contrast ratio matching is developed，which is also consistent with the characteristics of the human vision system.Finally，the fused image is obtained by performing the inverse nonsubsampled contourlet transform on the combined coefficients.The experimental results show that the proposed image fusion algorithm can more effectively descript the grey discontinuous information，and the fused image contains more abundant detail feature compared with traditional algorithms.

Key words: image fusion, nonsubsampled Contourlet transform, local area energy, region contrast

摘要： 针对传统的基于小波对比度图像融合方法的不足，结合非采样Contourlet变换的优点提出了一种新的基于非采样Contourlet变换的区域对比度图像融合方法。该方法对图像经非采样Contourlet变换后得到的低频分量采用基于区域能量的自适应加权融合；高频分量结合人眼的视觉特性，提出了一种新的基于区域对比度的加权与选择相结合的融合方法。通过非采样Contourlet变换的逆变换得到融合图像。实验结果表明，该融合方法较传统的方法具有更强的获取细节信息的能力，其融合效果优于传统的图像融合算法。

关键词: 图像融合, 非采样Contourlet变换, 区域能量, 区域对比度