基于Contourlet域的多聚焦图像融合方法

Multi-Focus Image Fusion Method Based on Contourlet Domain

提出一种基于Contourlet域的多聚焦图像融合方法。对分解后的图像低频子带采用区域方差法进行处理,高频子带统计系数各方向邻域能量和作为融合依据,利用系数局部相似的特点进行同层的一致性处理。该算法可以减少融合图像边缘处的斑块模糊现象,提高融合质量。仿真实验结果表明,所提出的算法能够更好地提取原始图像特征,融合后的图像具有更好的主观视觉效果。

This paper present a multi-focus image fusion method based on Contourlet_domain. The decomposed low frequency sub-band coefficients is fused with local variance statistics, and the high frequency sub-bands coefficient is fused with the sum energy of each direction local coefficients, and the same layer local coefficient is deled with same method. The algorithm can reduce the fuzzy phenomenon,and improve the quality of image . The simulation results show that the proposed method can detect image features more effectively and the fused image has better subjective visual effect.