On Utilising Template and Feature-based Correspondence in Multi-view Appearance Models

  • Sami Romdhani
  • Alexandra Psarrou
  • Shaogang Gong
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1842)


In principle, the recovery and reconstruction of a 3D object from its 2D view projections require the parameterisation of its shape structure and surface reflectance properties. Explicit representation and recovery of such 3D information is notoriously difficult to achieve. Alternatively, a linear combination of 2D views can be used which requires the establishment of dense correspondence between views. This in general, is difficult to compute and necessarily expensive. In this paper we examine the use of affine and local feature-based transformations in establishing correspondences between very large pose variations. In doing so, we utilise a generic-view template, a generic 3D surface model and Kernel PCA for modelling shape and texture nonlinearities across views. The abilities of both approaches to reconstruct and recover faces from any 2D image are evaluated and compared.


Appearance Model Kernel Principal Component Analysis Landmark Point Active Appearance Model Active Shape Model 
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.


  1. 1.
    J. J. Atick, P. A. Griffin, and A. N. Redlich. Statistical approach to shape from shading: Reconstruction of three-dimensional face surfaces from single two-dimensional images. Neural Computation, 8(6):1321–1340, 1996.CrossRefGoogle Scholar
  2. 2.
    D. Beymer. Feature correspondence by interleaving shape and texture computations. In cvpr, pages 921–928, 1996.Google Scholar
  3. 3.
    D. J. Beymer and T. Poggio. Image representations for visual learning. Science, 272:1905–1909, 28 June 1996.Google Scholar
  4. 4.
    T.F. Cootes, G.J. Edwards, and C.J. Taylor. Active appearance models. In ECCV98, pages 484–498, 1998.Google Scholar
  5. 5.
    T.F. Cootes and C.J. Taylor. A mixture model for representing shape variation. Image and Vision Computing, 17:567–573, 1999.CrossRefGoogle Scholar
  6. 6.
    F. de la Torre, S. Gong, and S. J. McKenna. View-based adaptive affine tracking. In ECCV, pages 828–842, Freiburg, Germany, June 1998.Google Scholar
  7. 7.
    S. Gong, E. J. Ong, and S. McKenna. Learning to associate faces across views in vector space of similarities to prototypes. In BMVC, pages 54–63, 1998.Google Scholar
  8. 8.
    S. Mika, B. Schölkopf, A. Smola, G. Ratsch, K. Müller, M. Scholz, and G. Rätsch. Kernel pca and de-noising in feature spaces. In NIPSS, 1998.Google Scholar
  9. 9.
    A. Pentland, B. Moghaddam, and T. Starner. View-based and modular eigenspaces for face recognition. In CVPR, pages 84–91, Seattle, July 1994.Google Scholar
  10. 10.
    S. Romdhani, S. Gong, and A. Psarrou. Multi-view nonlinear active shape model using kernel pca. In BMVC, pages 483–492, September 1999.Google Scholar
  11. 11.
    S. Romdhani, A. Psarrou, and S. Gong. Learning a single active shape model for faces across views. In IEEE International Workshop on Real Time Face and Gesture Recognition, pages 31–38, September 1999.Google Scholar
  12. 12.
    B. Schölkopf, S. Mika, A. Smola, G. Rätsch, and K. Müller. Kernel pca pattern reconstruction via approximate pre-images. In ICANN. Springer Verlag, 1998.Google Scholar
  13. 13.
    B. Schölkopf, A. Smola, and K. Müller. Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation, 10(5):1299–1319, 1998.CrossRefGoogle Scholar
  14. 14.
    A. Shashua. Geometry and Photometry in 3D Visual Recognition. PhD thesis, MIT, AI Lab., 1992.Google Scholar
  15. 15.
    A. Shashua. Algebraic functions for recognition. A. I. Memo 1452 (C.B.C.L. Paper 90), MIT, January 1994.Google Scholar
  16. 16.
    M. Turk and A. Pentland. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1):71–86, 1991.CrossRefGoogle Scholar
  17. 17.
    S. Ullman and R. Basri. Recognition by linear combinations of models. IEEE PAMI, 13(10):992–1006, October 1991.Google Scholar
  18. 18.
    V. Vapnik. The nature of statistical learning theory. Springer Verlag, 1995.Google Scholar
  19. 19.
    T. Vetter and T. Poggio. Linear object classes and image synthesis from a single example image. Technical Report 16, Max Planck Inst. fur Bio. Kybernetik, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Sami Romdhani
    • 1
  • Alexandra Psarrou
    • 1
  • Shaogang Gong
    • 2
  1. 1.Harrow School of Computer ScienceUniversity of WestminsterUK
  2. 2.Department of Computer ScienceQueen Mary and Westfield CollegeLondonUK

Personalised recommendations