No-reference perceptual quality assessment of stereoscopic images based on binocular visual characteristics

Perceptual quality assessment of distorted stereoscopic images has attracted considerable attention and become an important yet challenging task in 3D multimedia applications. In this paper, we propose a blind/no-reference stereoscopic 3D image quality assessment scheme that utilizes binocular visual characteristics. The design of this scheme is motivated by studies on the perception of distorted stereoscopic images. The major technical contribution of this paper is the introduction of binocular features and binocular energy for stereoscopic image quality prediction. To be more specific, the proposed scheme extracts the local magnitude, local phase and visual saliency from a stereopair as binocular features. In addition, the binocular energy responses are also obtained as quality-predictive features. After feature extraction, a statistical regression model is used to map the features of distorted stereoscopic image to its subjective quality score. The effectiveness of the designed metric is verified on the publicly available 3D image quality assessment databases. Experimental results show that the proposed scheme achieves superiority over other related algorithms in terms of consistent alignment with subjective assessment of stereoscopic 3D images.