Videntifier™ forensic: robust and efficient detection of illegal multimedia

ABSTRACT

A large portion of the video material available on the Internet is distributed illegally. In this demonstration we present Videntifier Forensic, a new law enforcement solution for automatically identifying videos and images. Videntifier Forensic is very robust and efficient, even at a very large scale. We encourage ACM Multimedia participants to bring original videos and modified (yet visually acceptable) copies to challenge the capabilities of the system.

REFERENCES

• 1: K. Daðason, H. Lejsek, F. H. Ásmundsson, B. Þ. Jónsson, and L. Amsaleg. Eff2 Videntifier: Identifying pirated videos in real-time. In Proceedings of ACM Multimedia (demonstration paper), pages 471--472, Augsburg, Germany, 2007.
• 2: K. Daðason, H. Lejsek, B. T. Þ. Jónsson, and L. Amsaleg. Full {GPU} acceleration of local descriptors using {CUDA}. Technical report, Reykjavík University, 2009.
• 3: A. Joly, O. Buisson, and C. Frélicot. Content--based copy detection using distortion-based probabilistic similarity search. IEEE Transactions on Multimedia, 9(2):293--306, 2007.
• 4: H. Lejsek, F. H. Ásmundsson, K. Daðason, Á. Þ. Jóhannsson, B. Þ. Jónsson, and L. Amsaleg. Videntifier Forensic: A new law enforcement service for automatic identification of illegal video material. In Proc. Multimedia in Forensics (MiFor), Beijing, China, 2009.
• 5: H. Lejsek, F. H. Ásmundsson, B. Þ. Jónsson, and L. Amsaleg. NV-tree: An efficient disk-based index for approximate search in very large high-dimensional collections. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(5):869--883, 2009.

INDEX TERMS

Primary Classification:
  K. Computing Milieux
  K.4 COMPUTERS AND SOCIETY
      K.4.1 Public Policy Issues
          Subjects: Abuse and crime involving computers

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.4 Systems
          Subjects: Multimedia databases

General Terms:
Algorithms, Performance

Keywords:
robustness, scalability, video detection