Multimedia Tools and Applications

, Volume 71, Issue 3, pp 1381–1409 | Cite as

Content-based copy detection by a subspace learning based video fingerprinting scheme

  • Ozgun CirakmanEmail author
  • Bilge Gunsel
  • Neslihan Serap Sengor
  • Sezer Kutluk


We propose a video copy detection scheme that employs a transform domain global video fingerprinting method. Video fingerprinting has been performed by the subspace learning based on nonnegative matrix factorization (NMF). It is shown that the binary video fingerprints extracted from the basis and gain matrices of the NMF representation enable us to efficiently represent the spatial and temporal content of a video segment respectively. An extensive performance evaluation has been carried out on the query and reference dataset of CBCD task of TRECVID 2011. Our results are compared with the average and the best performance reported for the task. Also NDCR and F1 rates are reported in comparison to the performance achieved via the global methods designed by the TRECVID 2011 participants. Results demonstrate that the proposed method achieves higher correct detection rates with good localization capability for the transformation of text/logo insertion, strong re-encoding, frame dropping, noise addition, gamma change or their mixtures; however there is still potential for improvement to detect copies with picture-in-picture transformations. It is also concluded that the introduced binary fingerprinting scheme is superior to the existing transform based methods in terms of the compactness.


Video fingerprinting Non-negative matrix factorization Content based copy detection 



This work is supported by The Scientific and Technological Research Council of Turkey (TÜBİTAK) under the project name TUBITAK EEEAG PNo 109E63.


  1. 1.
    Anguera X, Adamek T, Xu D, Barrios JM (2011) Telefonica research at TRECVID 2011 content-based copy detection. TRECVID Workshop: NISTGoogle Scholar
  2. 2.
    Barrios JM, Bustos B, Anguera X (2011) Combining features at search time: PRISMA at video copy detection task. TRECVID Workshop: NISTGoogle Scholar
  3. 3.
    Bay H, Ess A, Tuytelaars T, Gool LV (2008) SURF: Speeded Up Robust Features. Comp Vision Image Underst (CVIU) 110(3):346–359CrossRefGoogle Scholar
  4. 4.
    Bucak SS, Gunsel B (2007) Video content representation by incremental non-negative matrix factorization. Proc Int Conf Image Process ICIP 2:113–116Google Scholar
  5. 5.
    Cirakman O, Gunsel B, Sengör NS, Gursoy O (2010) Key-frame based video fingerprinting by NMF. Proceedings of International Conference on Image Processing ICIP, pp 2373–2376Google Scholar
  6. 6.
    Fridrich J, Goljan M (2000) Robust hash functions for digital watermarking. Proceedings of International Conference on Information Technology: Coding and Computing ITCC, pp 178–183Google Scholar
  7. 7.
    Gupta V, Varcheie PDZ, Gagnon L, Boulianne G (2011) CRIM at TRECVID 2011: content-based copy detection using nearest-neighbor mapping. TRECVID Workshop: NISTGoogle Scholar
  8. 8.
    Gursoy O, Gunsel B, Sengor NS (2009) Transform invariant video fingerprinting by NMF. Proceedings of 13th International Conference on Computer Analysis of Images and Patterns CAIP, pp 452–459Google Scholar
  9. 9.
    Hill M et al (2010) IBM research TRECVID-2010 video copy detection and multimedia event detection system. TRECVID Workshop: NIST 1:146–154Google Scholar
  10. 10.
    Hradiš M, Řezníček I, Behúň K, Otrusina L (2011) Brno University of Technology at TRECVid 2011 SIN, CCD. TRECVID Workshop: NISTGoogle Scholar
  11. 11.
    Jégou H, Douze M, Gravier G, Schmid C, Gros P (2010) INRIA LEAR-TEXMEX: video copy detection task. TRECVID Workshop: NIST 1:160–169Google Scholar
  12. 12.
    Jiang M, Fang S, Tian Y, Huang T, Gao W (2011) PKU-IDM @ TRECVid 2011 CBCD: content-based copy detection with cascade of multimodal features and temporal pyramid matching. TRECVID Workshop: NISTGoogle Scholar
  13. 13.
    Küçüktunç O, Baştan M, Güdükbay U, Ulusoy O (2010) Video copy detection using multiple visual cues and MPEG-7 descriptors. J Vis Commun Image Represent JVCI 21(8):838–849. doi: 10.1016/j.jvcir.2010.07.001 CrossRefGoogle Scholar
  14. 14.
    Law-To J, Chen L, Joly A, Laptev I, Buisson O (2007) Video copy detection: a comparative study. Proceedings of sixth ACM International Conference on Image and Video Retrieval CIVR, pp. 371–378Google Scholar
  15. 15.
    Lee D, Seung H (2001) Algorithms for non-negative matrix factorization. Proc Adv Neural Inf Process Syst NIPS 13:556–562Google Scholar
  16. 16.
    Lee S, Yoo CD (2006) Video fingerprinting based on centroids of gradient orientations. Proceedings of International Conference on Acoustics, Speech and Signal Processing ICASSP, Toulouse, France 2:401–404Google Scholar
  17. 17.
    Lee S, Yoo CD (2008) Robust video fingerprinting based on 2D-OPCA of affine covariant regions. Proceedings of the 2nd International Conference on Image Processing ICIP, San Diego, USA, pp 2156–2159Google Scholar
  18. 18.
    Lin Y et al (2010) Nanjing University at TRECVid 2010: content-based copy detection task. TRECVID Workshop: NIST 1:322–328Google Scholar
  19. 19.
    Liu Z, Zavesky E, Zhou N, Shahraray B (2011) AT&T Research at TRECVID 2011. TRECVID Workshop: NISTGoogle Scholar
  20. 20.
    Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  21. 21.
    Massoudi A, Lefebvre F, Demarty CH, Oisel L, Chupeau B (2006) A video fingerprint based on visual digest and local fingerprints. Proceedings of International Conference on Image Processing ICIP, Atlanta, pp 2297–2300Google Scholar
  22. 22.
    Monga V, Mıhçak MK (2007) Robust and secure image hashing via non-negative matrix factorizations. IEEE Trans Inf Forensics Secur 2(3–1):376–390CrossRefGoogle Scholar
  23. 23.
    Mukai R, Kurozumi T, Kawanishi T, Nagano H, Kashino K (2011) NTT communication science laboratories at TRECVID 2011 content-based copy detection. TRECVID Workshop: NISTGoogle Scholar
  24. 24.
    Naturel X, Gros P (2005) A fast shot matching strategy for detecting duplicate sequences in a television stream. Proceedings of the Second International Workshop on Computer Vision meets Databases CVDB, Baltimore, MD, pp 21–27Google Scholar
  25. 25.
    Oostveen J, Kalker T, Haitsma J (2002) Feature extraction and a database strategy for video fingerprinting. Proceedings of International Conference on Visual Information and Information Systems VISUAL, pp 117–128Google Scholar
  26. 26.
    Over P, George A, Fiscus J, Antonishek B, Michel M (2011) TRECVID 2011-goals, tasks, data, evaluation mechanisms and metrics. Proceedings of the TRECVID 2011 Workshop, NIST Gaithersburg, MD, USA, pp 1–56Google Scholar
  27. 27.
    Radhakrishnan R, Jiang W, Bauer C (2009) A review of video fingerprints invariant to geometric attacks. Proc SPIE 7254:725407. doi: 10.1117/12.805627 CrossRefGoogle Scholar
  28. 28.
    Rouhi AH, Thom JA (2011) RMIT University at TRECVID 2011 content-based copy detection. TRECVID Workshop: NISTGoogle Scholar
  29. 29.
    Sarkar A, Singh V, Ghosh P, Manjunath BS, Singh A (2010) Efficient and robust detection of duplicate videos in a large database. IEEE Trans Circ Syst Video Technol. doi: 10.1109/TCSVT.2010.2046056
  30. 30.
    Smeaton AF, Over P, Kraaij W (2006) Evaluation campaigns and TRECVid. In Proc. of the 8th ACM Int. Workshop on Multimedia Information Retrieval, Santa Barbara, CA, USA, MIR ‘06. ACM Press, New York, NY, 321–330. doi:
  31. 31.
    Sun C, Li J, Zhang B, Zhang Q (2010) THU-IMG at TRECVID 2010. TRECVID Workshop: NIST 1:404–409Google Scholar
  32. 32.
    Uchida Y, Takagi K, Sakazawa S (2011) KDDI Labs at TRECVID 2011: content-based copy detection. TRECVID Workshop: NISTGoogle Scholar
  33. 33.
    Zhao W, Borth D, Breuel TM (2011) Participation at TRECVID 2011 semantic ındexing & content-based copy detection tasks. TRECVID Workshop: NISTGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2012

Authors and Affiliations

  • Ozgun Cirakman
    • 1
    Email author
  • Bilge Gunsel
    • 1
  • Neslihan Serap Sengor
    • 1
  • Sezer Kutluk
    • 1
  1. 1.Multimedia Signal Processing and Pattern Recognition Lab., Department of Electronics and Communication EngineeringIstanbul Technical UniversityIstanbulTurkey

Personalised recommendations