Infrared and visible image fusion algorithm based on Contourlet transform and PCNN

A new image fusion method based on Contourlet transform and an improved pulse coupled neural network (PCNN) is introduced in this paper. The input infrared and visible images are processed with Contourlet decomposition which has multi-scale and multi-directional characteristics. The PCNN algorithm deriving from the neurophysiology is optimized in order to be compatible with the image fusion strategy. Owning to the global coupling and pulse synchronization characteristic of PCNN, this new fusion strategy utilizes the global features of source images and has several advantages in comparison with the traditional methods based on the single pixel or regional features. Multiple criteria and statistical indicators regarding. different aspects of image quality are presented for objective and quantitative evaluation of the fused images to understand the performance of image fusion algorithms. Experimental result shows that the new method can improve the quality of image fusion and can achieve an ideal fusing effect. The method would find its application in the aspects of optical imaging, target detection and safety monitoring, etc.