Infrared and visible image fusion through hybrid curvature filtering image decomposition

Abstract

To improve the saliency of the target in the integrated image and the ability to retain the information of detail, an infrared and visible image fusion algorithm based on image decomposition of hybrid curvature filtering is proposed. Firstly, we introduce the hybrid curvature filtering to decompose the input source images into three levels, and three image layers are acquired. According to the different attributes of the image layers, this paper adopts different fusion strategies to fuse the image layers. Finally, the fusion image is obtained by way of adding the image layers. Experimental results demonstrate that compared with other algorithms, the fusion image generated from this algorithm is more conducive to human visual perception and computer analysis.