PROJECT TITLE :

LBP-based segmentation of defocus blur. - 2016

ABSTRACT:

Defocus blur is extremely common in images captured using optical imaging systems. It may be undesirable, but may conjointly be an intentional artistic effect, therefore it will either enhance or inhibit our visual perception of the image scene. For tasks, such as image restoration and object recognition, one might wish to phase a partially blurred image into blurred and non-blurred regions. During this paper, we tend to propose a sharpness metric primarily based on native binary patterns and a sturdy segmentation algorithm to separate in- and out-of-focus image regions. The proposed sharpness metric exploits the observation that the majority local image patches in blurry regions have considerably fewer of bound native binary patterns compared with those in sharp regions. Using this metric together with image matting and multi-scale inference, we have a tendency to obtained high-quality sharpness maps. Tests on hundreds of partially blurred pictures were used to evaluate our blur segmentation algorithm and 6 comparator strategies. The results show that our algorithm achieves comparative segmentation results with the state-of-the-art and have huge speed advantage over the others.