A multi-focus image fusion framework based on multi-scale sparse representation in gradient domain

Abstract

Existing multi-focus fusion methods cannot identify focus regions of multiple source images at a pixel level well, which limits the fusion performance. To solve this problem, we propose a novel multi-focus image fusion framework that performs focus region detection by a pixel-level focus measure. First, we propose the multi-scale sparse representation in gradient domain (MSSRGD) that combines the advantages of the sparse representation and the multi-scale approach to yield a data-driven and block-level focus measure. Second, the measure values are extended to the pixel level with the adaptive recursive filter (ARF) which can make full use of the original spatial information. Finally, the fused image is generated according to an accurate decision map estimated by a pixel-wise comparison. The experimental results demonstrate that the proposed method outperforms the conventional and state-of-the-art methods in terms of both visual perceptions and objective evaluations.