Document Type : Research Paper
Image Processing and Data Mining (IPDM) Research Lab, Faculty of Computer Engineering and Information Technology, Shahrood University of Technology
Faculty of Electrical Engineering & Robotics, Shahrood University of Technology
Blur is one of the common image distortions in which fraction of a pixel value, depending on the severity of blur, is added to one or more neighboring pixels. Knowledge about the severity of blurriness in a given image is very important for image enhancement purposes. Since blur severity is not generally constant at all pixels, it is necessary to accurately estimate the blurriness value of pixels in the image (the so called blur map). In this paper, a method is proposed for this purpose. The proposed method in this paper provides the blur map via estimating the blurriness of the pixels based on the difference between surrounding block of the pixel and its blurred version. Our investigations indicate that, in general, the blur image regions have lower frequency content than the un-blur (sharp) regions. The results of extensive experiments on a large database including motion and defocus blurred images confirm the superiority of the proposed approach over the existing methods.