Ring Fingerprint Based on Interest Points for Video Copy Detection

In the field of information security, assurance, copyright protection etc., content-based copy detection is more and more important, which consists of two technologies - fingerprint extraction and fingerprint matching. Fingerprints extracted from videos are mainly described as global video fingerprints and local video fingerprints. To make best use of the advantages and bypass the disadvantages of different video fingerprints, we propose the ring fingerprint based on interest points and ordinal measure in this paper. A last we examine the proposed method with lots of experiments and discuss the performance of approaches. The experimental results also demonstrate the effectiveness of the proposed method for video copy detection.