Image blurred region detection based on RGB color space information and local standard deviation
Ku Pengsen, Zhenming Yu · 2017
In this paper we proposed a simple and effective method of image blurred region detection is based on RGB color space feature information and local standard deviation of image. According to re-blurred the partially blurred image by a Gaussian function, compare the difference of RGB feature information in different regions of image, and then combined with the local standard deviation of image as the blurred measures which can detect the blurred region accurately. Experimental results show that the proposed method can effectively detect the blurred region.