Multi-focus Image Fusion Scheme Using Adaptive Dual-Channel Pulse Coupled Neural Network

Abstract

Image fusion combines information from multiple images of the same scene to obtain a composite image which is more suitable for further image processing tasks. By analyzing the pulse coupled neural network(PCNN), and combining with the characteristics of multi-focus image, a novel PCNN model dual-channel PCNN(Dual-channel PCNN) was proposed in this paper. The mathematical model was first given, then a novel sum-modified-Laplacian(NSML) was selected as the focus measure to compute the sharpness of the source images, and then the sharpness of each pixel was used as the linking strength of the corresponding neuron. Experimental results show that the proposed method outperforms some previous fusion methods, both in visual effect and objective evaluation criteria.