Advertisement

Texton Correlation for Recognition

  • Thomas Leung
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3021)

Abstract

We study the problem of object, in particular face, recognition under varying imaging conditions. Objects are represented using local characteristic features called textons. Appearance variations due to changing conditions are encoded by the correlations between the textons. We propose two solutions to model these correlations. The first one assumes locational independence. We call it the conditional texton distribution model. The second captures the second order variations across locations using Fisher linear discriminant analysis. We call it the Fisher texton model. Our two models are effective in the problem of face recognition from a single image across a wide range of illuminations, poses, and time.

Keywords

Face Recognition Equal Error Rate Locational Independence Illumination Direction Conditional Probability Table 
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.
    Blanz, V., Vetter, T.: Face recognition basedo n fitting a 3d morphable model. IEEE Trans. Pattern Analysis and Machine Intelligence 25(9) (2003)Google Scholar
  2. 2.
    Chen, H., Belhumeur, P., Jacobs, D. In: search of illumination invariants. In: Proc. Conf. CVPR (2000)Google Scholar
  3. 3.
    Cootes, T., Walker, K., Taylor, C.J.: View-based active appearance models. In: Proc. Intl. Conf. Automatic Face and Gesture Recognition (2000)Google Scholar
  4. 4.
    Cula, O., Dana, K.: Compact representation of bidirectional texture functions. In: Proc. Computer Vision and Pattern Recognition, pp. 1041–10417 (2001)Google Scholar
  5. 5.
    Duda, R., Hart, P., Stork, D.: Pattern Classification. Wiley, Chichester (2001)zbMATHGoogle Scholar
  6. 6.
    Georghiades, A., Belhumeur, P., Kriegman, D.: From few to many: illumination cone models for face recognition under varying lighting and pose. IEEE Trans. Pattern Analysis and Machine Intelligence 23(6) (2001)Google Scholar
  7. 7.
    Gross, R., Matthews, L., Baker, S.: Eigen light-fields and face recognition across pose. In: Proc. Int’l. Conf. Automatic Face and Gesture Recognition (2002)Google Scholar
  8. 8.
    Ioffe, S.: Automatic red-eye reduction. In: Proc. Int. Conf. Image Processing (2003)Google Scholar
  9. 9.
    Julesz, B.: Textons, the elements of texture perception, and their interactions. Nature 290(5802), 91–97 (1981)CrossRefGoogle Scholar
  10. 10.
    Leung, T., Malik, J.: Representing and recognizing the visual appearance of materials using three-dimenional textons. Int. J. Computer Vision 43(1), 29–44 (2001)zbMATHCrossRefGoogle Scholar
  11. 11.
    Murase, H., Nayar, S.: Visual learning and recognition of 3-d objects from appearance. International Journal on Computer Vision 14(1), 5–24 (1995)CrossRefGoogle Scholar
  12. 12.
    Phillips, P., Wechsler, H., Huang, J., Rauss, P.: The feret database and evaluation procedure for face recognition algorithms. Image and Vision Computing 16(5), 295–306 (1998)CrossRefGoogle Scholar
  13. 13.
    Schmid, C.: Constructing models for content-based image retrieval. In: Proc. Conf. Computer Vision and Pattern Recognition (2001)Google Scholar
  14. 14.
    Varma, M., Zisserman, A.: Classifying images of materials: achieving viewpoint and illumination independence. In: Proc. European Conference Computer Vision, pp. 255–271 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Thomas Leung
    • 1
  1. 1.Fujifilm SoftwareSan JoseU.S.A.

Personalised recommendations