Improved Spiking Cortical Model Based Algorithm for Multi-focus Image Fusion

Abstract

How to extract focused information as efficiently as possible is always the key issue of the fusion algorithms for multi-focus images. As an improved version of the third generation of artificial neural networks (ANN), spiking cortical model (SCM) has been proved to be an effective tool for dealing with the issues of image processing. Under the above background, a novel multi-focus image fusion algorithm based on improved SCM is proposed in this paper. Specifically, firstly, the traditional SCM is improved to be a modified version. Secondly, the concrete parameters setting is given and introduced in detail. Finally, in order to verify the effectiveness and feasibility of the proposed algorithm, several registered groups of source images are used in this paper. Experimental results demonstrate that the proposed algorithm is superior to the existing work in terms of both subjective visual presentation and objective evaluations compared with current typical ANN models.