Infrared and visible image fusion based on intuitionistic fuzzy sets

Abstract

Infrared and visible image fusion plays a vital role in target tracking, surveillance, military, etc. In this paper, we put forward a new infrared and visible image fusion method employing non-subsampled contourlet transform (NSCT) with intuitionistic fuzzy sets. We use NSCT to decompose the pre-registered test images into low frequency and high frequency sub-bands. Furthermore, we introduce a new rule based on intuitionistic fuzzy sets for high frequency sub-bands fusion, and for low frequency sub-bands, the energy-based fusion rule is used. The fused image is obtained by inverse NSCT. Experiment results show that the proposed fusion method outperforms the advanced fusion methods in terms of objective assessment and visual quality.