By Topic

Content based video copy detection with local descriptors

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

7 Author(s)

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.

Published in:

Signal Processing and Communications Applications Conference (SIU), 2010 IEEE 18th

Date of Conference:

22-24 April 2010