Reduced Reference Image Quality Assessment Based on Entropy of Classified Primitives

The human visual perception is a layered progressive process that brain assimilates visual information gradually, from primary information, structural information to detailed information. Recently, the visual primitives (atoms in the dictionary) extracted by sparse representation have been shown to be highly related to the layered progressive process of human visual perception. In this paper, the visual primitives are first classified into three categories: DCprirnary, sketch and texture in terms of their inherent properties regarding to the perceptual information. Then, we propose a novel reduced reference (RR) image quality assessment (IQA) metric using perceptual information represented by entropy of classified primitives (EoCP). Specifically, EoCP is a measurement of the distribution statistics of the visual primitives, which can represent the visual information. The differences of EoCPs between the reference image and its distorted version are calculated as features to characterize perceptual loss. The extracted features (only three scalars) are used to compute the quality score by a prediction function which is trained using support vector regression (SVR). Experimental results on LIVE, CSIQ and TID2013 image databases demonstrate that the proposed metric achieves high consistency with the human perception and show competitive performance with state-of-the-art IQA metrics.