Advertisement

Robust Design of Face Recognition Systems

  • Sunjin Yu
  • Hyobin Lee
  • Jaihie Kim
  • Sangyoun Lee
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3981)

Abstract

Currently, most face recognition methods provide a number of parameters to be optimized, leaving the selection and optimization of the right parameter set is necessary for the implementation. The choice of the right parameter set that is suitable for a rich enough class of input faces in pose and illumination variations is, however, quite difficult. We propose robust parameter estimation, using the Taguchi method, when applied to 2nd order mixture of eigenfaces method that allows effective (near optimal) performance under pose and illumination variations. A number of experimental results confirm the improvement (via robustness) vis-‘a-vis conventional parameter estimation methods, and these methods promise a solution to the design of efficient parameter sets that support many multi-variable face recognition systems.

Keywords

Face Recognition Face Image Orthogonal Array Taguchi Method Robust Design 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Wang, L., Tan, T.K.: Experimental results of face description based on the 2nd?order eigneface method. ISO/MPEG m6001, Geneva (May 2000)Google Scholar
  2. 2.
    Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3, 72–86 (1991)CrossRefGoogle Scholar
  3. 3.
    Kim, H.-C., Kim, D., Bang, S.Y., Lee, S.-Y.: Face recognition using the second-order mixture-of-eigenfaces method. Pattern Recognition 37(2), 337–349 (2004)MATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Montgomery, D.C.: Design and Analysis of Experiments. John Wiley & Sons, Chichester (1997)MATHGoogle Scholar
  5. 5.
    Phadke, M.S.: Quality Engineering using Robust Design. Prentice-Hall, Englewood Cliffs (1989)Google Scholar
  6. 6.
    Lee, S.: Design & Implementation of Robust Signal Proceesors with Applications to Video Coding. A thesis for Ph.D in Electrical Engineering, Georia Institute of Technology (1999)Google Scholar
  7. 7.
    Kim, H., Kim, D., Band, S.: A PCA Mixure model with an Efficient Model Selection Method. In: Proceedings IJCNN 2001 (2001)Google Scholar
  8. 8.
    Baule, L.: Call for Proposals for Face Recognition Technology. ISO/IEC JTC1/SC29/WG11/N3676, pp. 23–27 (October 2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sunjin Yu
    • 1
  • Hyobin Lee
    • 1
  • Jaihie Kim
    • 2
  • Sangyoun Lee
    • 2
  1. 1.Graduate Program in Biometrics, and of BERC 
  2. 2.Department of Electrical and Electronic Engineering, and of BERCYonsei UniversitySeoulKorea

Personalised recommendations