An image fusion method based on wavelet and dual-channel pulse coupled neural network

Abstract

In this paper, we proposed a new image fusion method based on discrete wavelet transform (DWT) and dual-channel pulse coupled neural network (PCNN). The human visual features and characteristics are taken into account. The fusion methods of low and high frequency sub-bands of DWT are separately and differently designed. For the low frequency coefficients, we apply the maximum selection rule (MSR). For the high frequency coefficients, spatial frequency (SF) of each high frequency subband is considered as the gradient features of images to motivate dual-channel PCNN networks and generate pulse of neurons. At last, the proposed method uses the inverse DWT transform to obtain the final fused image. Experimental comparisons and results from different fusion methods demonstrate the effectiveness of proposed method.