New reduced-reference objective stereo image quality assessment model based on human visual system

With rapid development in three dimensional video technologies, quality assessment plays an important role in the field of stereo image processing. In this paper, a new reduced-reference stereo image quality assessment model based on binocular human visual system is proposed. The stereos images are divided into binocular fusion portion and binocular rivalry portion with the guide of internal generative mechanism. Then the binocular fusion portion is fused to cyclopean view. By extracting reduced singular value decomposition feature of cyclopean view and reduced generalized Gaussian distribution feature in binocular rivalry portion, the quality indicators of binocular fusion portion and binocular rivalry portion can be obtained. Experimental result shows that the proposed model outperforms some other models, and its correlation coefficients of assessment versus the subjective perception are satisfactory over five types of distortion, including JPEG, JPEG2000, Gaussian blur, white Gaussian noise and Fast-fading.