A content recognizability measure for image quality assessment considering the high frequency attenuating distortions

Abstract

The existing image quality assessment (IQA) techniques try to estimate image distortions regardless of their destructive effects on image contents. Analyzing the subjective scores of image quality databases shows that the worst opinions belong to distortions which make the images non-recognizable. In this paper, we investigate the effects of image contents clarity on human perception of quality. We found that among the several image distortions, the high frequency attenuating (HFA) ones are noticeable distortions which influence the image content recognizability, and accordingly the image understandability. To evaluate the severity of HFA distortions, we employ the non-negative matrix factorization (NMF), which has the ability to part-based image decomposition. When this decomposition is applied on an image, the resulting factors provide the latent information regarding the image parts. We employ the statistical characteristics of NMF factors to quantify the influence of HFA distortions on image contents. Our experiments performed on popular image quality databases show that the accuracy of our proposed measure is promising.