An objective quality evaluation measure of asymmetric and symmetric distorted stereoscopic images is proposed. In the measure, stereoscopic features are first extracted from left and right images by using singular val...An objective quality evaluation measure of asymmetric and symmetric distorted stereoscopic images is proposed. In the measure, stereoscopic features are first extracted from left and right images by using singular value decomposition. Then, the relationship between the stereoscopic features and subjective scores is established by using support vector regression. Finally, the objective evaluation scores are tested on symmetric and asymmetric databases. Experimental results show that the proposed measure is more effective in quantifying image quality, compared with other two relevant quality evaluation measures.展开更多
文摘An objective quality evaluation measure of asymmetric and symmetric distorted stereoscopic images is proposed. In the measure, stereoscopic features are first extracted from left and right images by using singular value decomposition. Then, the relationship between the stereoscopic features and subjective scores is established by using support vector regression. Finally, the objective evaluation scores are tested on symmetric and asymmetric databases. Experimental results show that the proposed measure is more effective in quantifying image quality, compared with other two relevant quality evaluation measures.