Research on no-reference video quality evaluation algorithm based on H.264

Abstract

In this paper, no reference video quality evaluation algorithm is researched and analyzed, and we implement a two-domain no-reference video quality assessment method: First, a compressed domain sub video quality assessment model is implemented based on the encode information are extracted from bit streams, then the video similarity between the distortion and original videos is calculated, so the preliminary evaluation of video quality is obtained. Second, two distortion artifacts, namely, block effect and blur effect are detected in the pixel domain. Finally, the video quality is given considering both video similarity and distortion. In this paper, the effect of the algorithm is evaluated by using the Consumer Digital Video Library. Numerous experiment results demonstrate that our implemented the objective evaluation model achieves near optimal tradeoff between consistency of subjective evaluation results and computational complexity.