Video copy detection based on temporal features of key frames

In this paper, an effective and efficient content-based video copy detection method is proposed. This method is based on temporal features of key frames. Firstly, each video is divided into shots, and each shot is represented by its key frame. Secondly, each key frame is divided into several sub-blocks, and variations of corresponding sub-blocks along key frame series are extracted as video fingerprint. Finally, fingerprints of query video and target video are compared to determine whether they are copies. Experimental results show that the proposed method is promising.