Abstract
Content Based Copy Detection, one of the emerging areas on detection of video copies is an alternative approach to invisible watermarking. It depends on detection of copies with fingerprints extracted from the content, which are robust against attacks, yet discriminative. In this work, a video copy detection scheme, which will be used on large databases with two dimensional local image descriptors, is proposed. The method depends on clustering local descriptors and comparing them over their clusters. Proposed method has been tested with scale-invariant feature transform (SIFT) in TRECVID 2009 Content Based Copy Detection task. In this paper, the proposed method is explained and effects of alternative descriptors and cluster sizes on detection performance are investigated over experimental results. Furthermore, advantages and disadvantages of the method are discussed and recommendations for future works are made.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
