Reduced reference stereoscopic image quality assessment based on entropy of classified primitives

Stereoscopic vision is a complex system which receives and integrates perceptual information from both monocular and binocular cues. In this paper, a novel reduced-reference stereoscopic image quality assessment scheme is proposed, based on the visual perceptual information measured by entropy of classified primitives (EoCP) and mutual information of classified primitives (MIoCP), named as DCprimary, sketch and texture primitives respectively, which is in accordance with the hierarchical progressive process of human visual perception. Specifically, EoCP of each-view image are calculated as monocular cue, and MIoCP between two-view images is derived as binocular cue. The Maximum (MAX) mechanism is applied to determine the perceptual information. The perceptual information differences between the original and distorted images are used to predict the stereoscopic image quality by support vector regression (SVR). Experimental results on LIVE phase II asymmetric database validate the proposed metric achieves significantly higher consistency with subjective ratings and outperforms state-of-the-art stereoscopic image quality assessment methods.