Moment Invariants based Blur Detection and Estimation for Blind Image Restoration

Abstract

Restoring degraded images is a critical problem in the field of image processing. Although various techniques for image restoration have been proposed in literature, there is still no global solution for blind image restoration problem. In practical applications, the degradation function is unknown and it is to be estimated in order to restore the image. In this paper, we propose a method to detect the blur type present in an image using moment invariants. The proposed method is novel and provides significant contribution in this area and solves the primary steps of blur detection which is required in the framework of any blind image restoration algorithm. We have proposed a technique to estimate the parameters of motion blur using Hough transform. The simulation results show that our algorithm provides better quality images with less error in blur parameter estimation.