Advertisement

3D Assisted 2D Face Recognition: Methodology

  • J. Kittler
  • M. Hamouz
  • J. R. Tena
  • A. Hilton
  • J. Illingworth
  • M. Ruiz
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3773)

Abstract

We address the problem of pose and illumination invariance in face recognition and propose to use explicit 3D model and variants of existing algorithms for both pose [Fit01, MSCA04] and illumination normalization [ZS04] prior to applying 2D face recognition algorithm. However, contrary to prior work we will use person specific, rather than general 3D face models. The proposed solution is realistic as for many applications the additional cost of acquiring 3D face images during enrolment of the subjects is acceptable. 3D sensing is not required during normal operation of the face recognition system. The proposed methodology achieves illumination invariance by estimating the illumination sources using the 3D face model. By-product of this process is the recovery of the face skin albedo which can be used as a photometrically normalised face image. Standard face recognition techniques can then be applied to such illumination corrected images.

Keywords

Face Recognition Face Image Face Skin Normalise Face Face Recognition System 
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. Baj99.
    Bajaj, C., Xu, G.: Local Interpolation and Approximation using G k-Continuous Piecewise Real Algebraic Curves. Computer Aided Geometric Desing 16, 557–578 (1999)zbMATHCrossRefMathSciNetGoogle Scholar
  2. Baj01.
    Bajaj, C., Xu, G.: Regular algebraic curve sections (III) - Applications in interactive design and data fitting. Computer Aided Geometric Desing 18, 149–173 (2001)zbMATHCrossRefMathSciNetGoogle Scholar
  3. Beh01.
    Behar, S., Hernández, V., Alvarez, L., Estrada, J.: Computing a revolution shell using a G 2-continuous A-spline and a semidiscrete method for the EDPs. In: Proceedings IV, ITLA, 2001, pp. 241–250 (2001) ISBN: 959-7056-13-5Google Scholar
  4. Est05.
    Estrada, J., Martínez, D., León, D., Theisel, H.: Solving Geometric Problems using Subdivision Methods and Range Analysis. In: Daehlen, M., Morken, K., Shumaker, L.L. (eds.) Mathematical Methods for Curves and Surfaces: Tromso 2004, pp. 101–114. Nashboro Press, Brentwood (2005)Google Scholar
  5. Her02.
    Hernández, V., Martínez, D., Estrada, J.: Fitting a conic A-spline to contour image data. Revista Investigación Operacional 29, 55–64 (2002)Google Scholar
  6. Her01.
    Hernández, V., Behar, S., Estrada, J.: Geometric design by means of a G 2 continuous A-spline, Approximation, Optimization and Mathematical Economics, pp. 133–145. Physica-Verlag, Heidelberg (2001)Google Scholar
  7. Kass88.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: active contour models. International. J. Comput. Vision, 321–331 (1988)Google Scholar
  8. Pal94.
    Paluszny, M., Patterson, R.: G 2-continuous cubic algebraic splines and their efficient display. In: Laurent, P.J., Le Méhauté, A., Schumacker, L.L. (eds.) Curves and Surfaces II, pp. 353–359 (1994)Google Scholar
  9. Pal98.
    Paluszny, M., Patterson, R.: Geometric control of G 2-cubic A-splines. Computer Aided Geometric Design 15, 261–287 (1998)zbMATHCrossRefMathSciNetGoogle Scholar
  10. Ray94.
    Ray, B., Ray, K.: A non-parametric sequential method for polygonal approximation of digital curves. Pattern Recognition Letters 15, 161–167 (1994)zbMATHCrossRefGoogle Scholar
  11. Set96.
    Sethian, J.A.: Level Set Methods. Cambridge Univ. Press, Cambridge (1996)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • J. Kittler
    • 1
  • M. Hamouz
    • 1
  • J. R. Tena
    • 1
  • A. Hilton
    • 1
  • J. Illingworth
    • 1
  • M. Ruiz
    • 1
  1. 1.CVSSPSurrey UniversityGuildford, SurreyUK

Personalised recommendations