ICIP 2006, Atlanta, GA

Slide Show

Atlanta Conv. & Vis. Bureau


Technical Program

Paper Detail

Time:Wednesday, October 11, 11:20 - 11:40
Presentation: Lecture
Authors: Shan He; University of Maryland, College Park 
 Min Wu; University of Maryland, College Park 
Abstract: Digital fingerprinting protects multimedia content from illegal redistribution by uniquely marking copies of the content distributed to each user. Most existing multimedia fingerprinting schemes consider userset on the scale of thousands for evaluation. However, in real applications such as cable TV and DVD distribution, the potential users can be as many as 10~100 million. This large scale user set demands not only high collusion resistance but also high efficiency in the fingerprint construction and detection, which makes most existing schemes incapable of practical application. A recently proposed joint coding and embedding fingerprinting framework provides a promising balance between collusion resistance, efficient construction and detection. In this paper, we explore how to employ such a framework and develop practical algorithms to fingerprint video in such challenging practical settings as to accommodate more than ten million users and resisting hundreds of users' collusion. Both analysis and experimental results show the great potential of joint coding and embedding fingerprinting for real video fingerprinting applications.