Fast Classification in Incrementally Growing Spaces

  • Oscar Déniz-Suárez
  • Modesto Castrillón
  • Javier Lorenzo
  • Gloria Bueno
  • Mario Hernández
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6669)

Abstract

The classification speed of state-of-the-art classifiers such as SVM is an important aspect to be considered for emerging applications and domains such as data mining and human-computer interaction. Usually, a test-time speed increase in SVMs is achieved by somehow reducing the number of support vectors, which allows a faster evaluation of the decision function. In this paper a novel approach is described for fast classification in a PCA+SVM scenario. In the proposed approach, classification of an unseen sample is performed incrementally in increasingly larger feature spaces. As soon as the classification confidence is above a threshold the process stops and the class label is retrieved. Easy samples will thus be classified using less features, thus producing a faster decision. Experiments in a gender recognition problem show that the method is by itself able to give good speed-error tradeoffs, and that it can also be used in conjunction with other SV-reduction algorithms to produce tradeoffs that are better than with either approach alone.

Keywords

gender recognition Support Vector Machines Principal Component Analysis Eigenfaces 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Guyon, I.: SVM application list (2010), http://www.clopinet.com/isabelle/Projects/SVM/applist.html
  2. 2.
    Decoste, D., Mazzoni, D.: Fast query-optimized kernel machine classification via incremental approximate nearest support vectors. In: International Conference on Machine Learning, pp. 115–122 (2003)Google Scholar
  3. 3.
    Fehr, J., Zapien, K., Burkhardt, H.: Fast support vector machine classification of very large datasets. In: Proceedings of the GfKl Conference, Data Analysis, Machine Learning, and Applications. LNCS, Springer, University of Freiburg, Germany (2007)Google Scholar
  4. 4.
    Zhana, Y., Shen, D.: Design efficient support vector machine for fast classification. Pattern Recognition 38(1), 157–161 (2005)CrossRefGoogle Scholar
  5. 5.
    Arenas-García, J., Gómez-Verdejo, V., Figueiras-Vidal, A.R.: Fast evaluation of neural networks via confidence rating. Neurocomput 70(16-18), 2775–2782 (2007), http://dx.doi.org/10.1016/j.neucom.2006.04.014 CrossRefGoogle Scholar
  6. 6.
    Nguyen, D., Ho, T.: An efficient method for simplifying support vector machines. In: Procs. of the 22nd Int. Conf. on Machine Learning, pp. 617–624 (2005)Google Scholar
  7. 7.
    Guo, J., Takahashi, N., Nishi, T.: An efficient method for simplifying decision functions of support vector machines. IEICE Transactions 89-A(10), 2795–2802 (2006)CrossRefGoogle Scholar
  8. 8.
    Turk, M.A., Pentland, A.: Eigenfaces for Recognition. Cognitive Neuroscience 3(1), 71–86 (1991), ftp://whitechapel.media.mit.edu/pub/images/ CrossRefGoogle Scholar
  9. 9.
    Phillips, P., Moon, H., Rizvi, S., Rauss, P.: The FERET evaluation methodology for face-recognition algorithms. TPAMI 22(10), 1090–1104 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Oscar Déniz-Suárez
    • 1
  • Modesto Castrillón
    • 2
  • Javier Lorenzo
    • 2
  • Gloria Bueno
    • 1
  • Mario Hernández
    • 2
  1. 1.E.T.S.I.IndustrialesUniversidad de Castilla-La ManchaCiudad RealSpain
  2. 2.Dpto. Informatica y Sistemas. Edificio de InformaticaUniversidad de Las Palmas de Gran Canaria.Las PalmasSpain

Personalised recommendations