Content based focus measure for robust auto-focusing of microscopy in biomedical applications

Auto-focusing is one of the key issues in motorized biological microscopes as it strongly affects the quality of the microscopic images. Auto-focusing is a difficult problem because the size of biological objects is as small as a few micrometers, and the problem is even more challenging when the density of the image content is low. In this paper, we propose a content based focus measure for guiding automatic search of the optimal focal plane with different image content densities. The proposed method adaptively assigns different weights to pixels based on the image content in the focus measure computation. Larger weights are assigned to pixels that represent interested objects, while smaller weights are given to debris and background pixels. Experimental investigation has been conducted to demonstrate superior performance of the proposed method over existing methods.