Blind Image Quality Assessment Using Joint Statistics 

Multimedia, including audio, image, and video, etc., is a ubiquitous part of modern life. Quality evaluation, both objective and subjective, is of fundamental importance for various multimedia applications. In this letter, a novel quality-aware feature is proposed for blind/no-reference (NR)image quality assessment (IQA). The new quality-aware feature is generated from the proposed joint generalized local binary pattern (GLBP) statistics. In this method, using the Laplacian of Gaussian (LOG) filters, the images are first decomposed into multi-scale subband images.

Then, the subband images are encoded with the proposed GLBP operator and the quality-aware features are formed from the joint GLBP histograms from the encoding maps of each subband image. Finally, using support vector regression (SVR), the quality-aware features are mapped to the image’s subjective quality score for NR-IQA. The experimental results for two representative databases show that the proposed method is strongly correlated to subjective quality evaluations and competitive to the state-of-the-art NR-IQA methods.