Joint Entropy Degradation Based Blind Image Quality Assessment

Blind image quality assessment (BIQA), which needs nothing about the reference image, is greatly desired in the automatic visual signal processing system. However, without the guide of the reference image, BIQA is extremely difficult to be realized. Distortions degrade the visual contents and cause quality degradation during image perception. From the perspective of information theory, distortions decrease the amount of visual information that an image contains. Therefore, we attempt to measure the image quality with its visual entropy degradation. Inspired by the response in the local receptive field of the retina, the local orientation and intensity features are extracted for visual content representation. Next, the joint probability distributions of the two features are calculated for visual entropy estimation. By deducing the joint entropy equation, the joint probability distributions are decoupled and analyzed. Finally, by measuring the degradations on these decoupled distributions, a novel BIQA method is introduced. Experimental results on the publicly available databases demonstrate that the proposed BIQA performs hiahlv consistent with the human perception.