Video copy detection based on median of key frames

Video copy detection is an important technology with many applications, especially since detecting copies becomes an alternative to watermarking. In this paper, an effective and efficient content-based video copy detection method is proposed, which is based on median features of key frames. Firstly, we extract the key frames of a video. Secondly, each key frame is divided into several blocks and the feature of the key frame is extracted based on the median of each block. Thirdly, we use the consecutive frame features as the fingerprint of a video. Finally, features of the query video and the reference video are compared to determine whether they are copies. The experimental results show the proposed scheme is effective in both copy detection and beginning localization.