PROJECT TITLE :

Reduced Reference Stereoscopic Image Quality Assessment Based on Binocular Perceptual Information

ABSTRACT:

In this paper, we propose a novel reduced reference stereoscopic image quality assessment (RR-SIQA) metric by using binocular perceptual information (BPI). BPI is represented by the distribution statistics of visual primitives in left and right views’ images, which are extracted by sparse coding and representation . Specifically, entropy of the left view’s image and entropy of the correct read’s image are used to represent monocular cue. Their mutual info is employed to represent binocular cue. Constructively, we have a tendency to represent BPI as 3 numerical indicators . The difference of the first and distorted pictures’ BPIs is taken as perceptual loss vector. The perceptual loss vector is employed to compute the standard score for a stereoscopic image by a prediction perform which is trained using support vector regression (SVR). Experimental results show that the proposed metric achieves considerably higher prediction accuracy than the state-of-the-art reduced reference SIQA strategies and higher than many state-of-the-art full reference SIQA strategies on the LIVE phase II uneven databases.