A perceptual stereoscopic image quality assessment model accounting for binocular combination behavior

• An effective human binocular combination model for cyclopean image is proposed.
• A full-reference SIQA model is built based on human binocular characteristics.
• It has less computing complexity and higher consistency with the subjective values.
• It can precisely assess the quality of images with different types of distortions.

Stereoscopic image quality assessment (SIQA) plays an important role in the development of 3D image processing. In this paper, a full-reference object SIQA model is built based on binocular summation channel and binocular difference channel. In our frame work, binocular combination behavior and how to experience the depth perception are thought to be the key factors to evaluate the quality of stereoscopic images. Differing from the current depth map methods, this method focuses on a new aspect, and an effective combination model is proposed based on the physiological findings in the Human Visual System (HVS). Experimental results demonstrate that the proposed quality assessment metric significantly outperforms the existing metrics and can achieve higher consistency with subject quality assessment when predicting the quality of stereoscopic images that have been symmetrically distorted.