Quality Assessment of Stereo Images with Stereo Vision

A quality assessment method of stereo images is proposed firstly, which is based on the theories and methods of planar quality assessment-SSIM. It takes stereo (three-dimensional) vision into account, including the physiological stereoscopy and the psychological stereoscopy. Dense disparity of stereo images is extracted, then division into segments is carried out . The weighted structural similarity is achieved as the assessing index of stereo image quality. Experimental results show that the proposed method is more accurate than PPSNR, in accordance with human visual characteristic, and consistent with the result of subjective assessment.