Abbass S. Abbass, Aliaa A.A. Youssif, and Atef Z. Ghalwash
Video fingerprinting, Compressed domain, Perceptual hash
“With the development of media technologies, more and more videos are digitally produced, stored and distributed. File sharing of video content on the internet, using hosting services like YouTube” which stated that the upload rate of their server is up to 20 hours of video materials per minute. Therefore, a video fingerprinting system to automatically identify the uploaded video is really is needed. “Illegal distribution of copyrighted videos online is a huge problem especially for commercial businesses. With digital processing tools; videos can be transformed into different versions and distributed on internet. The need for identification and management of video content grows proportionally with the widespread availability of digital videos. 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 simple but effective video fingerprinting technique that works directly in the compressed. Experimental results show that the proposed fingerprints are highly robust against most signal processing transformations.
Important Links:
Go Back
