A novel multi-focus image fusion method based on joint regularization optimization layering and sparse representation

Abstract

In this paper, we reported a novel Multi-Focus Image Fusion (MFIF) method based on regularization optimization and sparse representation model, which takes full advantages of the imaging characteristics of multi-focus images. First, a multi-source regularization optimization model was proposed to divide source images into a common background layer and respective detail layers jointly. This makes the focused details scattered in different sources are extracted in concert. Then the resulting detail layers are fused in sparse representation domain. To be more task-specific for MFIF, an atom focus degree measurement based fusion rule was proposed to highlight the focused atoms. Finally, the fusion result is reconstructed by combining the fused detail layer and the common background layer. Thorough experimental evaluations confirm the effectiveness of the proposed fusion approach both visually and quantitatively, and show that our approach outperforms some state-of-the-art fusion methods.