Multi-focus image fusion based on edges and focused region extraction

摘要

The aim of multi-focus image fusion is fusing multiple partially focused images into a sharper image. One of the keys to image fusion is how to detect the focused regions. This paper presents an image fusion method based on two different types of edges and focused region extraction. The first type of edges, called salient focused edges, only exist in the focused regions. They are detected from high-pass filtered images by a threshold method, and then used to distinguish focused regions from source images based on a quad-tree structure. The second type of edges synthesized by 'Canny' edges are used to refine the boundaries of focused regions. Finally, the extracted focused regions are combined into a clear fused image. Experiments show that the proposed algorithm can extract focused regions with proper boundaries. Therefore, the fused images can avoid distortion artifacts and well preserve the sharpness on the focused objects. The proposed method outperforms some state-of-the-art algorithms in terms of visual quality and quantitative indices.