A novel multi-focus image fusion method using PCNN in nonsubsampled contourlet transform domain

摘要

A novel multi-focus image fusion method using modified pulse coupled neural network (PCNN) in non-subsampled contourlet transform (NSCT) domain is presented in this study. Different scales and directions are obtained by image decomposition using the NSCT at first. Then to retain more edges and textures, the edge feature is used to motive the improved PCNN model. The coefficients in the NSCT domain with large firing times are selected as coefficients of the fused image. To testify the performance of our proposed algorithm, simulation experiments are conducted on it. The experimental results showed that the proposed algorithm produces better results compared to other state-of-the-art algorithms neither visual effects nor objective indicators. (C) 2015 Elsevier GmbH. All rights reserved.