Image Fusion Algorithm Based on Pulse Coupled Neural Networks and Nonsubsampled Contourlet Transform

Abstract

The principles and features of nonsubsampled contourlet transform (NSCT) and pulse coupled neural networks (PCNN) are described in brief. Combining their characteristics, in NSCT domain, a new image fusion algorithm based on PCNN is proposed in this paper. Directional contrast and regional spatial frequency in NSCT domain is input to motivate PCNN and coefficients in NSCT domain with large firing times are selected as coefficients of the fused image. The experimental results demonstrate that the proposed algorithm can extract the original image's features better. The fused image’s representation capacity in spatial detail is also improved. Compared with the other fusion algorithms such as contourlet-based, NSCT-based, and NSCT-PCNN-based (maximum firing-times), the proposed algorithm provides better subjective and objective visual effect.