Generalized image matching: Statistical learning of physically-based deformations

  • Chahab Nastar
  • Baback Moghaddam
  • Alex Pentland
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1064)


We describe a novel approach for image matching based on deformable intensity surfaces. In this approach, the intensity surface of the image is modeled as a deformable 3D mesh in the (x,y,I(x,y)) space. Each surface point has 3 degrees of freedom, thus capturing fine surface changes. A set of representative deformations within a class of objects (e.g. faces) are statistically learned through a Principal Components Analysis, thus providing a priori knowledge about object-specific deformations. We demonstrate the power of the approach by examples such as image matching and interpolation of missing data. Moreover this approach dramatically reduces the computational cost of solving the governing equation for the physically based system by approximately three orders of magnitude.


Optical Flow Image Match Intensity Surface Principal Subspace Deformable Mesh 
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.
    K. J. Bathe. Finite Element Procedures in Engineering Analysis. Prentice-Hall, 1982.Google Scholar
  2. 2.
    A. Baumberg and D. Hogg. Learning flexible models from image sequences. In Proceedings of the Third European Conference on Computer Vision 1994 (ECCV'94), Stockholm, Sweden, May 1994.Google Scholar
  3. 3.
    David Beymer. Vectorizing face images by interleaving shape and texture computations. A.I. Memo No. 1537, Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 1995.Google Scholar
  4. 4.
    T. Boult. Physics in a fantasy world vs. robust statistical estimation. In NSF/ARPA workshop on 3D Object Representation in Computer Vision, New York, USA, December 1994.Google Scholar
  5. 5.
    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), 1995.Google Scholar
  6. 6.
    T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Graham. Training models of shape from sets of examples. In Proceedings of the British Machine Vision Conference, Leeds, 1992.Google Scholar
  7. 7.
    P. E. Danielsson. Euclidean distance mapping. Computer Vision, Graphics, and Image Processing, 14:227–248, 1980.Google Scholar
  8. 8.
    B.K.P. Horn and G. Schunck. Determining optical flow. Artificial Intelligence, 17:185–203, 1981.Google Scholar
  9. 9.
    I.T. Jolliffe. Principal Component Analysis. Springer-Verlag, New York, 1986.Google Scholar
  10. 10.
    C. Kervrann and F. Heitz. Learning structure and deformation modes of nonrigid objects in long image sequences. In Proceedings of the International Workshop on Automatic Face-and Gesture-Recognition, 1995.Google Scholar
  11. 11.
    A. Lanitis, C. J. Taylor, and T. F. Cootes. A unified approach to coding and interpreting face images. In Proceedings of the International Conference on Computer Vision 1995 (ICCV'95), Cambridge, MA, June 1995.Google Scholar
  12. 12.
    M.M. Loeve. Probability Theory. Van Nostrand, Princeton, 1955.Google Scholar
  13. 13.
    J. Martin, A. Pentland, and R. Kikinis. Shape analysis of brain structures using physical and experimental modes. In IEEE Conference on Computer Vision and Pattern Recognition, Seattle, USA, June 1994.Google Scholar
  14. 14.
    B. Moghaddam and A. Pentland. Probabilistic visual learning for object detection. In IEEE Proceedings of the Fifth International Conference on Computer Vision, Cambridge, USA, june 1995.Google Scholar
  15. 15.
    H. Murase and S. K. Nayar. Visual learning and recognition of 3D objects from appearance. International Journal of Computer Vision, 14(5), 1995.Google Scholar
  16. 16.
    C. Nastar. Vibration modes for nonrigid motion analysis in 3D images. In Proceedings of the Third European Conference on Computer Vision (ECCV '94), Stockholm, May 1994.Google Scholar
  17. 17.
    C. Nastar and N. Ayache. Fast segmentation, tracking, and analysis of deformable objects. In Proceedings of the Fourth International Conference on Computer Vision (ICCV '93), Berlin, May 1993.Google Scholar
  18. 18.
    C. Nastar and A. Pentland. Matching and recognition using deformable intensity surfaces. In IEEE International Symposium on Computer Vision, Coral Gables, USA, November 1995.Google Scholar
  19. 19.
    A. Pentland, B. Moghaddam, T. Starner, and M. Turk. View based and modular eigenspaces for face recognition. In IEEE Proceedings of Computer Vision and Pattern Recognition, 1994.Google Scholar
  20. 20.
    A. Pentland and S. Sclaroff. Closed-form solutions for physically based shape modelling and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-13(7):715–729, July 1991.Google Scholar
  21. 21.
    M. Turk and A. Pentland. Face recognition using eigenfaces. In IEEE Proceedings of Computer Vision and Pattern Recognition, pages 586–591, 1991.Google Scholar
  22. 22.
    Q.Z. Ye. The signed euclidean distance transform and its applications. In International Conference on Pattern Recognition, pages 495–499, 1988.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Chahab Nastar
    • 1
  • Baback Moghaddam
    • 2
  • Alex Pentland
    • 2
  1. 1.INRIA RocquencourtLe Chesnay CédexFrance
  2. 2.MIT Media LaboratoryCambridgeUSA

Personalised recommendations