LAUSR

Quality assessment of 3-D images encounters more challenges in better understanding of human visual system. In this paper, we propose a perceptual quality assessment approach for stereoscopic images by modeling visual properties of the primary visual cortex. For this purpose, we obtain a new feature encoding approach for the visual information, and define a new similarity measure approach to match the feature encoding to give more reliable and accurate quality assessment. Experimental results on three symmetrically, asymmetrically, and multiple distorted stereoscopic image quality assessment databases demonstrate that our method has high consistency with subjective assessment.