Advertisement

Abstract

3-dimensional pattern recognition requires the definition of a similarity measure between 3-dimensional patterns. We discuss how to match 3-dimensional patterns, which are represented by a set of images taken from multiple directions and approximately represented by subspaces. The proposed method is to calculate the canonical angles, in particular the third smallest angle between two subspaces. We demonstrate the viability of the proposed method by performing a pilot study of face recognition.

Keywords

Face Recognition Face Image Large Eigenvalue Subspace Method Subspace Cluster 
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.

References

  1. 1.
    Murase, H., Nayar, S.K.: Illumination planning for object recognition in structured environments. In: Proc. of CVPR, pp. 31–38 (1994)Google Scholar
  2. 2.
    Oja, E.: Subspace Method of Pattern Recognition. Research Studies Press, Hertfordshire (1983)Google Scholar
  3. 3.
    Maeda, K., Watanabe, S.: A Pattern Matching Method with Local Structure. Trans. IECE J68-D 3, 345–352 (1984) (in Japanese)Google Scholar
  4. 4.
    Yamaguchi, O., Fukui, K., Maeda, K.: Face Recognition Using Temporal Image Sequence. In: Proc. of FG 1998, pp. 318–323 (1998)Google Scholar
  5. 5.
    Oja, E., Parkkinen, J.: On Subspace Clustering. In: Proc. of 7th ICPR, pp. 692–695 (1984)Google Scholar
  6. 6.
    Riittinen, H.: Short-cut Algorithms for the Learning Subspace Method. In: Proc. of ICASSP 1984 ,pp.17.2.1–17.2.4 (1984)Google Scholar
  7. 7.
    Dixmier, M.: Etude sur les Varietes et les Operaterns de Julia, avec Quelques Applications. Bull. Soc. Math. France 77, 11–101 (1949)zbMATHMathSciNetGoogle Scholar
  8. 8.
    Björck, Å., Golub, G.H.: Numerical Methods for Computing Angles between Linear Subspaces. Mathematics of Computation 27, 579–594 (1975)CrossRefGoogle Scholar
  9. 9.
    Chatelin, F.: Valeurs Propres de Matrices, Masson (1988)Google Scholar
  10. 10.
    Fukui, K., Yamaguchi, O.: Face Recognition Using Multi-viewpoint Patterns for Robot Vision. In: Proc. of ISRR 2003 (2003)Google Scholar
  11. 11.
    Epstein, R., et al.: 5 ± 2 Eigenimages Suffice: An Empirical Investigation of Low- Dimensional Lighting Models. In: Proc. of IEEE Workshop on Physics-based Modeling in CV, pp. 108–116 (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Ken-ichi Maeda
    • 1
  • Osamu Yamaguchi
    • 1
  • Kazuhiro Fukui
    • 1
  1. 1.Corporate Research & Development CenterTOSHIBA CorporationKawasakiJapan

Personalised recommendations