Transform Invariant Video Fingerprinting by NMF

  • Ozan Gursoy
  • Bilge Gunsel
  • Neslihan Sengor
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5702)


Video fingerprinting is introduced as an effective tool for identification and recognition of video content even after putative modifications. In this paper, we present a video fingerprinting scheme based on non-negative matrix factorization (NMF). NMF is shown to be capable of generating discriminative, parts-based representations while reducing the dimensionality of the data. NMF’s representation capacity can be fortified by incorporating geometric transformational duplicates of the base vectors into the factorization. Factorized base vectors are used as content based, representative features that uniquely describe the video content. Obtaining such base vectors by transformational NMF (T-NMF) is furthermore versatile in recognizing the attacked contents as copies of the original instead of considering them as a new content. Thus a novel approach for fingerprinting of video content based on T-NMF is introduced in this work and experimental results obtained on TRECVID data set are presented to demonstrate the robustness to geometric attacks and the improvement in the representation.


Video fingerprinting non-negative matrix factorization transformation invariance 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Massoudi, A., Lefebvre, F., Demarty, C.-H., Oisel, L., Chupeau, B.: A Video Fingerprint Based on Visual Digest and Local Fingerprints. In: Proc. of IEEE Int. Conf. on Image Processing, pp. 2297–2300 (2006)Google Scholar
  2. 2.
    Law-To, J., Chen, L., Joly, A., Laptev, I., Buisson, O., Gouet-Brunet, V., Boujemaa, N., Steintiford, F.: Video Copy Detection: A Comparative Study. In: Proc. of the 6th ACM Int. Conf. on Image and Video Retrieval, Netherlands, pp. 371–378 (2007)Google Scholar
  3. 3.
    Lee, S., Yoo, C.D.: Robust Video Fingerprinting Based on 2D-OPCA of Affine Covariant Regions. In: Proc. of IEEE Int. Conf. on Image Processing, USA, pp. 2156–2159 (2008)Google Scholar
  4. 4.
    Paatero, P., Tapper, U.: Positive Matrix Factorization: A Non-negative Factor Model with Optimal Utilization of Error Estimates of Data Values. Environmetrics 5, 11–126 (1994)CrossRefGoogle Scholar
  5. 5.
    Lee, D., Seung, H.: Learning the Parts of Objects by Non-negative Matrix Factorization. Nature 401, 788–791 (1999)CrossRefGoogle Scholar
  6. 6.
    Bucak, S.S., Gunsel, B.: Video Content Representation by Incremental Non-negative Matrix Factorization. In: Proc. of IEEE Int. Conf. on Image Processing, USA, pp. 113–116 (2007)Google Scholar
  7. 7.
    Bucak, S.S., Gunsel, B.: Incremental Clustering via Nonnegative Matrix Factorization. In: Proc. of 19th Int. Conf. on Pattern Recognition, ICPR, USA (2008)Google Scholar
  8. 8.
    Bucak, S.S., Gunsel, B.: Incremental Subspace Learning via Non-negative Matrix Factorization. Pattern Recognition 42, 788–798 (2009)zbMATHCrossRefGoogle Scholar
  9. 9.
    Eggert, J., Wersing, H., Körner, E.: Transformation-invariant Representation and NMF. In: Proc. IEEE Int. Joint Conf. on Neural Networks (2004)Google Scholar
  10. 10.
    Gunsel, B., Ferman, A., Tekalp, A.M.: Temporal Video Segmentation Using Unsupervised Clustering and Semantic Object Tracking. Electronic Imaging 64, 592–604 (1998)CrossRefGoogle Scholar
  11. 11.
    Wolf, W.: Key Frame Selection by Motion Analysis. In: Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol. 2, pp. 1228–1231 (1996)Google Scholar
  12. 12.
    TREC Video Retrieval Evaluation,

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Ozan Gursoy
    • 1
  • Bilge Gunsel
    • 1
  • Neslihan Sengor
    • 1
  1. 1.Istanbul Technical University, Electrical-Electronics Eng. FacultyDep. of Electronics and Communications EngineeringMaslakTurkey

Personalised recommendations