A no-reference perceptual blur metric based on complex edge analysis

This paper presents an efficient no-reference blur metric where image quality is quantified by perceptual-based edge analysis. Instead of statistical measurement of the whole image, it computes local statistics in the vicinity of detected edges at a largely reduced computational cost. Unlike existing objective no-reference blur metrics, the proposed metric is able to distinguish blurred edges in a cost-effective way. Evaluation of the proposed metric shows its high prediction accuracy when it is applied to Gaussian blurred images. Experiments using the LIVE blur database demonstrate that the proposed algorithm correlates well with subjective quality evaluations.