A 3D Visual Comfort Metric Based on Binocular Asymmetry Factor

How to evaluate 3D visual discomfort is a challenging problem in stereoscopic image quality assessment. This is due to an existing gap between human binocular visual perception and current stereoscopic image representation techniques. As an indicator of binocular images' relationship for stereoscopic image, binocular asymmetry has been found that it is one of the most important discomfort-induced factors. Based on the factor, this paper proposes an objective stereoscopic visual comfort assessment (SVCA) model for stereoscopic images. Specifically, binocular asymmetry is interpreted as the two views' image texture features which are represented by the histograms of oriented gradient (HOG) feature and local binary pattern (LBP) feature. The HOG/LBP are integrated into an overall visual comfort score by support vector regression (SVR). Two stereoscopic image databases are chosen to evaluate the applicability of the proposed metric. The experimental results show that the proposed SVCA metric can efficiently predict visual discomfort for stereoscopic image.