Abstract. In this paper we present the methods used for the analysis of video based on mutual information. We propose a novel method of abrupt cut detection and a novel objective method for measuring the quality of video. In the field of abrupt cut detection we improve the existing method based on mutual information. The novelty of our method is in combining the motion prediction and the mutual information. Our approach provides higher robustness to object and camera motion. According to the objective method for measuring the quality of video, it is based on calculation the mutual information between the frame from the original sequence and the corresponding frame from the test sequence. We compare results of the proposed method with commonly used objective methods for measuring the video quality. Results show that our method correlates with the standardized method and the distance metric, so it is possible to replace a more complex method with our simpler method.

Objective Video Quality Method Based on Mutual Information and Human Visual SystemIn this paper we present the objective video quality metric based on mutual information and Human Visual System. The calculation of proposed metric consists of two stages. In the first stage of quality evaluation whole original and test sequence are pre-processed by the Human Visual System. In the second stage we calculate mutual information which has been utilized as the quality evaluation criteria. The mutual information was calculated between the frame from original sequence and the corresponding frame from test sequence. For this testing purpose we choose Foreman video at CIF resolution. To prove reliability of our metric were compared it with some commonly used objective methods for measuring the video quality. The results show that presented objective video quality metric based on mutual information and Human Visual System provides relevant results in comparison with results of other objective methods so it is suitable candidate for measuring the video quality.

No abstract