Infrared and visible image fusion based on NSCT and fuzzy logic

Abstract

A novel infrared (IR) and visible image fusion method based on nonsubsampled contourlet transform (NSCT) and fuzzy logic is proposed. Input IR and visible images are decomposed into a series of low frequency and high frequency subbands by using NSCT. The degree of membership to the background and the target for each pixel in the low frequency subband of the IR image is determined by using fuzzy logic. An adaptive weighted average is then taken as the fusion of low frequency subband coefficients while maximum absolution selection is performed for the fusion of high frequency subband coefficients. The fused image is obtained by taking inverse NSCT of the fused coefficients. Experimental results with real IR and visible images show that the proposed method effectively enhances infrared targets and preserves details of the visible image.