Edge-based method of sharp region extraction from low depth of filed images

This paper presents a method for extracting blur/sharp regions of interest (ROI) that benefits of using a combination of edge and region based approaches. It can be considered as a preliminary step for many vision applications tending to focus only on the most salient areas in low depth-of-field images. To localize focused regions, we first classify each edge as either sharp or blurred based on gradient profile width estimation. Then a mean shift oversegmentation allows to label each region using the density of marked edge pixels inside. Finally, the proposed algorithm is tested on a dataset of high resolution images and the results are compared with the manually established ground truth. It is shown that the given method outperforms known state-of-the-art techniques in terms of F-measure. The robustness of the method is confirmed by means of additional experiments on images with different values of defocus degree.