Image fusion algorithm based on redundant-lifting NSWMDA and adaptive PCNN

Abstract

Aiming at the applications of image fusion with high contrast and texture information, an effective image fusion method based on redundant-lifting non-separable wavelet multi-directional analysis (NSWMDA) and adaptive pulse coupled neural network (PCNN) has been proposed. The original images are firstly decomposed by using the NSWMDA into several subbands to retain texture detail and contrast information, then adaptive PCNN algorithm is applied on the high frequency directional subbands to extract the high frequency information, the low frequency subbands are evaluate by weighted average method based on Gaussian kernel. Experimental results show that the proposed method can make the fused image maintains more texture details and contrast information.