Assessment of Color Video Quality with Singular Value Decomposition of Complex Matrix

Most proposed video quality assessment approaches in the literature are only applied to the luminance layer of frame. Others are applied to luminance and chrominance layers respectively and then pooling by means of grayscale image quality metrics. In this paper, we proposed a full-reference objective video quality assessment called CMSVD,which treats luminance and chrominance parts as a whole and considers multiple factors of the human visual system (HVS)and video features. The algorithm is tested on the video quality experts group (VQEG) phase I FR-TV test data set.Experiments show that it has good correlation with perceived video quality.