Fast and Robust Video Copy Detection Schemes Based On Video Signature

摘要

Illegally copied video contents have been rising serious social problem as internet and multimedia technologies are developing. Therefore, effective and efficient copy detection techniques are required for content management and rights protection. In this paper, three robust video copy detection techniques are proposed that detect online distributions of illegally copied video. Particularly, the proposed three algorithms use key-frames with abrupt changes in luminance, then extract a compact feature from key-frames. Comparing with the preregistered features stored in the database of videos, the proposed approaches distinguish whether an uploaded video is illegally copied or not using the longest common subsequence and the longest common substring, fuzzy search and the Euclidean distance as matching signature techniques. The proposed techniques can perform the sequence matching in linear time while the complexity of conventional duplicate video detection algorithms grow at least quadratically with the video length. Comparison experiments are conducted on the benchmarked database of CIVR 2007 copy detection showcase [1] and demonstrate the promising results of the proposed techniques.