Compressed Domain Video Fingerprinting Technique Using The Singular Value Decomposition

A vast amount of video data is generated around the world every day. Fast and efficient storage, indexing, browsing, and retrieval of video are necessary for the development of various multimedia database applications. Video fingerprinting is a proven and commercially available technique that can be used for content based copy detection. Fingerprints are compact content-based signatures that summarize a video signal or another media signal. The conventional video fingerprinting techniques have one resemblance, in which video decompression is still required for extracting the fingerprint from the compressed video. In practical, faster computational time can be achieved if the fingerprint is extracted directly from the compressed domain. This paper presents a spatio-temporal video fingerprinting technique that works directly in the compressed domain using the singular value decomposition of the macroblocks types. Experimental results show that the proposed fingerprint is highly robust against most signal processing transformations. Key-Words: Video FingerprintingCompressed Domain-SVDPerceptual Hash