Skip to Main Content
Content-based video copy detection aims at deciding whether there is a common segment between the query video and the video in the database. In this paper, a copy detection system is proposed based on local features that can deal with most video transformations and realize video searching in the database by using inverted file. Local features are first extracted and then clustered to visual words as index of the inverted file. The voting strategy makes use of the property of temporal consistence. The experimental results indicate that these visual features are robust and the searching in database is feasible.