Two-Stage Data Reduction for a SVM Classifier in a Face Recognition Algorithm Based on the Active Shape Model

  • Maciej Krol
  • Andrzej Florek
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 95)


In this paper, two stage data reduction method for face identification with use of Support Vector Machine (SVM) classifier is evaluated. SVM Classification was performed for data acquired from contour description of 2200 faces of 100 persons. Face contours were extracted from frontal face images with use of Active Shape Model (ASM) method. Two stage PCA+LDA data reduction performance is measured in comparison with single stage PCA or LDA reductions. We propose to replace first stage PCA reduction with much simpler and less computationally intensive contour decimation.


Support Vector Machine Active Shape Model Support Vector Machine Training Support Vector Machine Kernel Face Contour 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Belhumeur, P., Hespanha, J., Kriegman, D.J.: Eigenfaces versus fisherface: recognition using class specific linear projection. IEEE Trans. Pattern Analysis Machine Intelligence 19(7), 711–720 (1997)CrossRefGoogle Scholar
  2. 2.
    Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines (2001),
  3. 3.
    Chen, L., Liao, H., Ko, M., Lin, J., Yu, G.: A new LDA-based face recognition system which can solve the small sample size problem. Pattern Recognition 33(10), 1713–1726 (2000)CrossRefGoogle Scholar
  4. 4.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models - their training and application. Computer Vision and Image Understanding (61), 38–59 (1995)Google Scholar
  5. 5.
    Cootes, T.F., Taylor, C.J.: Statistical Models of Appearance for Computer Vision. Technical report, Imaging Science and Biomedical Engineering, University of Manchester (2001)Google Scholar
  6. 6.
    Vapnik, V., Cortes, C.: Support-Vector Networks. Machine Learning (20) (1995)Google Scholar
  7. 7.
    Kasinski, A., Florek, A., Schmidt, A.: The PUT face database. Image Processing and Communications 13(3-4), 59–64 (2008)Google Scholar
  8. 8.
    Yu, H., Yang, J.: A direct LDA algorithm for high-dimensional data – with application to face recognition. Pattern Recognition 34(10), 2067–2070 (2001)CrossRefzbMATHGoogle Scholar
  9. 9.
    Zhang, S., Sim, T.: Discriminant Subspace Analysis: A Fukunaga-Koontz Approach. IEEE Trans. Pattern Analysis Machine Intelligence 29(10), 1732–1745 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Maciej Krol
    • 1
  • Andrzej Florek
    • 1
  1. 1.Institute of Control and Information EngineeringPoznan University of TechnologyPoznanPoland

Personalised recommendations