Combining Elastic and Statistical Models of Appearance Variation

  • T. F. Cootes
  • C. J. Taylor
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1842)


We propose a model of appearance and a matching method which combines ‘global’ models (in which a few parameters control global appearance) with local elastic or optical-flow-based methods, in which deformation is described by many local parameters together with some regularisation constraints. We use an Active Appearance Model (AAM) as the global model, which can match a statistical model of appearance to a new image rapidly. However, the amount of variation allowed is constrained by the modes of the model, which may be too restrictive (for instance when insufficient training examples are available, or the number of modes is deliberately truncated for effciency or memory conservation). To compensate for this, after global AAM convergence, we allow further local model deformation, driven by local AAMs around each model node. This is analogous to optical flow or ‘demon’ methods of non-linear image registration. We describe the technique in detail, and demonstrate that allowing this extra freedom can improve the accuracy of object location with only a modest increase in search time. We show the combined method is more accurate than either pure local or pure global model search.


Face Image Image Registration Local Deformation Model Point Appearance 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.
    G. Christensen. Consistent linear-elastic transformations for image matching. In 16th Conference on Information Processing in Medical Imaging, pages 224–237, Visegrád, Hungary, June 1999.Google Scholar
  2. 2.
    D. L. Collins, A. Zijdenbos, W. F. C. Baare, and A. C. Evans. Animal+insect: Improved cortical structure segmentation. In 16th Conference on Information Processing in Medical Imaging, pages 210–223, Visegrád, Hungary, June 1999.Google Scholar
  3. 3.
    T. F. Cootes, G. J. Edwards, and C. J. Taylor. Active appearance models. In H. Burkhardt and B. Neumann, editors, 5th European Conference on Computer Vision, volume 2, pages 484–498. Springer, Berlin, 1998.Google Scholar
  4. 4.
    T. F. Cootes and C. J. Taylor. Combining point distribution models with shape models based on finite-element analysis. Image and Vision Computing, 13(5):403–409, 1995.CrossRefGoogle Scholar
  5. 5.
    M. J. Jones and T. Poggio. Multidimensional morphable models: A framework for representing and matching object classes. International Journal of Computer Vision, 2(29):107–131, 1998.zbMATHCrossRefGoogle Scholar
  6. 6.
    A. Lanitis, C. J. Taylor, and T. F. Cootes. Automatic interpretation and coding of face images using flexible models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(7):743–756, 1997.CrossRefGoogle Scholar
  7. 7.
    H. Lester, S. A. Arridge, K. M. Jansons, L. Lemieux, J. V. Hajnal, and A. Oatridge. Non-linear registration with the variable viscosity fluid algorithm. In 16th Conference on Information Processing in Medical Imaging, pages 238–251, Visegrád, Hungary, June 1999.Google Scholar
  8. 8.
    J. B. A. Maintz and M. A. Viergever. A survey of medical image registration. Medical Image Analysis, 2(1):1–36, 1998.CrossRefGoogle Scholar
  9. 9.
    T. McInerney and D. Terzopoulos. Deformable models in medical image analysis: a survey. Medical Image Analysis, 1(2):91–108, 1996.CrossRefGoogle Scholar
  10. 10.
    C. Nastar, B. Moghaddam, and A. Pentland. Generalized image matching: Statistical learning of physically-based deformations. In 4th European Conference on Computer Vision, volume 1, pages 589–598, Cambridge, UK, 1996.Google Scholar
  11. 11.
    J. P. Thirion. Image matching as a diffusion process: an analogy with maxwell’s demons. Medical Image Analysis, 2(3):243–260, 1998.CrossRefGoogle Scholar
  12. 12.
    M. Turk and A. Pentland. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1):71–86, 1991.CrossRefGoogle Scholar
  13. 13.
    T. Vetter. Learning novel views to a single face image. In 2nd International Conference on Automatic Face and Gesture Recognition 1997, pages 22–27, Los Alamitos, California, Oct. 1996. IEEE Computer Society Press.Google Scholar
  14. 14.
    Y. Wang and L. H. Staib. Elastic model based non-rigid registration incorporating statistical shape information. In MICCAI, pages 1162–1173, 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • T. F. Cootes
    • 1
  • C. J. Taylor
    • 1
  1. 1.Department of Imaging Science and Biomedical EngineeringUniversity of ManchesterManchesterUK

Personalised recommendations