Video Copy Detection Using TIRI-DCT Algorithm
Keywords:
Content based fingerprinting, multimedia fingerprinting, video hashing, video copy detection, video copy retrievalAbstract
The process of extracting a fingerprint from the video content is referred to as fingerprinting the video or
video fingerprinting. Proposed fingerprint extraction algorithm Temporally Informative Representative Image -Discrete
Cosine Transform (TIRI-DCT) extracts compact content based signatures from special images constructed from the
video. Each such image represents a short segment of the video and contains temporal as well as spatial information
about the video segment. Here we evaluate the Performance analysis of Video Fingerprints on different parameters such
as noise, contrast, brightness, time shift, spatial shift, frame shift, TPR,FPR & average etc. and analyzed for video Copy
Detection. This system is tested on a database of different videos in the presence of different types of distortions which
emphasize the robustness and discrimination properties of the copy detection system. The proposed fast approximate
search algorithm facilitates the online application of the system to a large video database of tens of millions of
fingerprints, so that a match (if it exists) is found in a few seconds.


