Image fusion algorithm for visible and PMMW images based on Curvelet and improved PCNN

Aiming at the fusion of visible and Passive Millimeter Wave (PMMW) images, a novel algorithm based on second generation Curvelet and improved pulse coupled neural network (PCNN) is proposed. Firstly, the fast discrete Curvelet transform was applied to the visible and PMMW image, respectively, to obtain the coefficients at different scales and in various directions. For the coarse scale, the fusion coefficients are determined by the feature of PMMW image which is extracted by region growing. It ensured that the useless information was abandoned. On the other hand, for the fine scale, the fusion coefficients are selected by improved PCNN. Finally, the fusion results are obtained through the inverse Curvelet transform. The experimental result demonstrates that the proposed algorithm can integrate the important information of visible and PMMW image, and improve the performance of fusion from traditional Curvelet method and PCNN method.