A no-reference perceptual blur metric based on the blur ratio of detected edges

In this paper, we present an efficient no-reference image blur metric which is based on the analysis of the spread of edge and the study of human blur perception for varying contrast values. Our method calculates blur ratio of significant edges and global vertical edges respectively, and final score is a weighted average of the two ratios because giving different edges different corresponding weights will improve prediction accuracy. Evaluation of the proposed metric shows its high prediction accuracy when it is applied to Gaussian blurred images. Experiments using the LIVE and TID Gaussian blur dataset demonstrate that the proposed algorithm correlates well with subjective quality evaluations.