A No-Reference Image Quality Metric Sensitive to Blur
Hong Zhang, Feng Yuan, Ding, Yuan, Yuecheng Li, Mingui Sun · ASME Press eBooks · 2012
The quality of digital image is rarely perfect and images are usually subject to distortions during acquisition, compression, transmission, processing and reproduction. No-reference (NR) image quality assessment refers to the problem of evaluating the visual quality of an image without any reference. The aim of this paper is to develop a novel NR blur metric (NRBM) for quality evaluation of blurry image. The experimental results indicate that the proposed assessment method gives high correlation with subjective Mean Opinion Score (MOS).