A method of image fusion using texture guidance based guided image filter and image statistics

Abstract

A technique of image fusion by means of a guided image filter is proposed in this paper. It employs image smoothing with a guided filter by making use of texture information as guidance for the guided filter. Then, image statistics-based pixel weight computation is utilized for generating the weight maps of the source images from detail layer features. Finally, the source images are integrated based on the weighted average combining strategy. The efficacy of the proposed algorithm is tested and compared with several state-of-the-art image fusion methods in terms of several objective image quality assessment parameters. The experimental result suggests the efficacy of the proposed algorithm in image fusion.