An improved visible and Infrared image fusion based on local energy and fuzzy logic

Abstract

According to the different characteristics between Infrared (IR) and visible image, an improved image fusion algorithm is proposed in this paper by using Nonsubsampled Contourlet (NSCT) transform, combined with local energy and fuzzy logic. Firstly, an S-function is used to adaptively enhance the contrast of the IR image. Secondly, the IR and visible images are decomposed into a series of low frequency and high frequency sub-band coefficients with different scales and different directions by NSCT transform. For the fusion rule of low frequency sub-band coefficients, in order to reduce the interference of noise in IR image, the degree of membership to low frequency sub-band coefficients is obtained using region-based local energy combined with Gauss fuzzy membership function. Maximum absolution selection rule is applied to merge high frequency sub-band coefficients of IR and visible images. Experimental results show that the proposed algorithm with good anti-noise performance has better subjective visual effect and objective evaluations compared with the reference algorithms.