Video fingerprinting is a newer research area. It is also called "content-based video copy detection" or "content-based video identification" in literature. The goal is to locate videos with segments substantially identical to segments of a query video while tolerating common artifacts in video processing. Its value as a tool to curb piracy and legally monetize contents becomes more and more apparent in recent years with the wide spread of Internet videos through user generated content (UGC) sites like YouTube. Its practical applications to a certain extent overlap with those of digital watermarking, which requires adding artificial information into the contents. Fingerprints are compact content-based signature that summarizes a video signal or another media signal. Several video fingerprinting methods have been proposed for identifying video, in which fingerprints are extracted by analyzing video in both spatial and temporal dimension. However, these conventional methods have one resemblance, in which video decompression is still required for extracting the fingerprint from a compressed video. In practical, faster computational time can be achieved if fingerprint is extracted directly from the compressed domain. So far, too fewer methods are known to propose video fingerprinting in compressed domain. This paper presents a video fingerprinting technique that works directly in the compressed domain. Experimental results show that the proposed fingerprint is highly robust against most signal processing transformations.

No abstract