Image Fusion Algorithm Based on Simplified PCNN in Nonsubsampled Contourlet Transform Domain

Abstract

Pulse Coupled Neural Networks(PCNN) have characteristics in accord with human vision properties,Nonsubsampled Contourlet Transform (NSCT) can overcome the lacking of Shift-invariance in Contourlet Transform. So NSCT was used associated with PCNN in image fusion algorithms to make full use of their characteristics. Original images were decomposed to get the coefficients of low frequency subbands and high frequency subbands. The coefficients of low and high frequency subbands were processed by a modified PCNN. Matching degree of original images and spatial frequency were defined and used respectively in fusion rules. Fusion image was obtained by NSCT inverse transformation. Experimental result shows this method is better than Wavelet, Contourlet and traditional PCNN methods; it has bigger mutual information, so the fusion image include more information about original images.