Multi-focus Image Fusion using Average Filter-based Relative Focus Measure

In an image taken by typical digital sensors, only those objects within the depth of field are in focus while the others are out of focus. Fusing multi-focused images is particularly useful for resolving this problem. This paper proposes a pixel-based multi-focus image fusion method. While most previous methods use the focus measure calculated independently for each source image, the proposed method calculates the relative focus measure between a pair of source images. This paper notes that a well-focused region in an image shows better contrast, sharpness, and details than the corresponding region that is defocused in another image. Based on the observation that the average filtered version of a wellfocused region in an image shows a higher correlation to the corresponding defocused region in another image than the original well-focused version, a new and fast multi-focus image fusion method is proposed. Experimental results of various sample image sequences show the superiority of the proposed method in terms of subjective evaluation. Keywords—multi-focus; image fusion; image enhancement; average filter;