Blind image quality assessment with complete pixel-level information

Abstract

In this paper, we develop a novel method for blind image quality assessment (BIQA) based on image complete pixel level information. First, traditional rotation invariant uniform local binary pattern (LBP) histogram is extracted from grayscale image as perceptual quality aware feature. Second, except for the signs of local pixel differences, the magnitudes of local pixel differences in grayscale image are also encoded by LBP, and the joint histogram between the signs and magnitudes of local pixel differences is also calculated as part of the perceptual feature. Finally, the support vector regression (SVR) is utilized to learn the mapping between the combined perceptual feature and human opinion scores. Experimental results show that the proposed method is highly correlated with human opinion scores and achieves competitive performance with state-of-the-art methods for quality evaluation and distortion classification.