基于不可分离小波框架变换的多聚焦图像融合算法

Non-separable Wavelet Frame Transform Based Multifocus Image Fusion Algorithm

为解决多聚焦图像融合问题,提出了一种基于不可分离小波框架(NWF)变换的融合算法:首先,对各原图像进行NWF变换;然后,根据变换后系数计算图像的对比度量测,融合处理为基于对比度量测的系数选取过程,并对选取后的系数进行一致性校验;最后,对组合后的系数进行NWF逆变换,得到融合后的图像.实验结果表明,该算法能够较好地解决多聚焦图像融合问题.

This paper described a non-separable wavelet frame (NWF) transform based multifocus image fusion algorithm. The source images are first decomposed by the NWF transform. Contrast measures are calculated according to the transform coefficients. The fusion process is the combining of the NWF transform coefficients of the source images. After the composite coefficients are obtained, an inverse NWF transform is performed to get the fused image. The experiments show that the proposed algorithm works well in multifocus image fusion.