DEFORMOTION Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images

  • Stefano Soatto
  • Anthony J. Yezzi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2352)


What does it mean for a deforming object to be “moving” (see Fig.1)? How can we separate the overall motion (a finite-dimensional group action) from the more general deformation (a diffeomorphism)? In this paper we propose a definition of motion for a deforming object and introduce a notion of “shape average” as the entity that separates the motion from the deformation. Our definition allows us to derive novel and efficient algorithms to register non-equivalent shapes using region-based methods, and to simultaneously approximate and register structures in grey-scale images. We also extend the notion of shape average to that of a “moving average” in order to track moving and deforming objects through time.


Group Action Shape Average Signed Distance Function General Deformation Euclidean Group 
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.
    L. Alvarez and J. M. Morel. Morphological approach to multiscale analysis: From principles to equations. In In Geometric-Driven Diffusion in Computer Vision, 1994.Google Scholar
  2. 2.
    L. Alvarez, J. Weickert, and J. Sanchez. A scale-space approach to nonlocal optical flow calculations. In In ScaleSpace’ 99, pages 235–246, 1999.Google Scholar
  3. 3.
    R. Azencott, F. Coldefy, and L. Younes. A distance for elastic matching in object recognition. Proc. 13th Intl. Conf. on Patt. Recog, 1:687–691, 1996.CrossRefGoogle Scholar
  4. 4.
    S. Belongie, J. Malik, and J. Puzicha. Matching shapes. In Proc. of the IEEE Intl. Conf. on Computer Vision, 2001.Google Scholar
  5. 5.
    D. Bereziat, I. Herlin, and L. Younes. Motion detection in meteorological images sequences: Two methods and their comparison. In Proc. of the SPIE, 1997.Google Scholar
  6. 6.
    A. Blake and M. Isard. Active contours. Springer Verlag, 1998.Google Scholar
  7. 7.
    C. Bregler and S. Omohundro. Surface Learning with Applications to Lip Reading. In J. D. Cowan, G. Tesauro and J. Alspector (eds), Advances in Neural Information Processing Systems (6), San Francisco, CA: Morgan Kaufmann Publishers, 1994.Google Scholar
  8. 8.
    T. K. Carne. The geometry of shape spaces. Proc. of the London Math. Soc. (3) 61, 3(61):407–432, 1990.CrossRefMathSciNetGoogle Scholar
  9. 9.
    T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham. Active Shape Models-Their Training and Application. Computer Vision and Image Understanding, 61(1), 1995, 38–59.CrossRefGoogle Scholar
  10. 10.
    H. Chui and A. Rangarajan. A new algorithm for non-rigid point matching. In Proc. of the IEEE Intl. Conf. on Comp. Vis. and Patt. Recog., pages 44–51, 2000.Google Scholar
  11. 11.
    M. Fischler and R. Elschlager. The representation and matching of pictorial structures. IEEE Transactions on Computers, 22(1):67–92, 1973.CrossRefGoogle Scholar
  12. 12.
    U. Grenander. General Pattern Theory. Oxford University Press, 1993.Google Scholar
  13. 13.
    U. Grenander and M. I. Miller. Representation of knowledge in complex systems. J. Roy. Statist. Soc. Ser. B, 56:549–603, 1994.zbMATHMathSciNetGoogle Scholar
  14. 14.
    P.T. Jackway and R. Deriche. Scale-space properties of the multiscale morphological dilationerosion. IEEE Trans. PAMI, 18(1):38–51, 1996.Google Scholar
  15. 15.
    D. G. Kendall. Shape manifolds, procrustean metrics and complex projective spaces. Bull. London Math. Soc., 16, 1984.Google Scholar
  16. 16.
    B. Kimia, A. Tannenbaum, and S. Zucker. Shapes, shocks, and deformations i: the components of two-dimensional shape and the reaction-diffusion space. IJCV, 15:189–224, 1995.CrossRefGoogle Scholar
  17. 17.
    R. Kimmel. Intrinsic scale space for images on surfaces: The geodesic curvature flow. In Lecture Notes In Computer Science: First International Conference on Scale-Space Theory in Computer Vision, 1997.Google Scholar
  18. 18.
    R. Kimmel, N. Kiryati, and A. M. Bruckstein. Multivalued distance maps for motion planning on surfaces with moving obstacles. IEEE TAC, 14(3):427–435, 1998.Google Scholar
  19. 19.
    M. Lades, C. Borbruggen, J. Buhmann, J. Lange, C. von der Malsburg, R. Wurtz, and W. Konen. Distortion invariant object recognition in the dynamic link architecture. IEEE Trans. on Computers, 42(3):300–311, 1993.CrossRefGoogle Scholar
  20. 20.
    H. Le and D. G. Kendall. The Riemannian structure of Euclidean shape spaces: a novel environment for statistics. The Annals of Statistics, 21(3):1225–1271, 1993.zbMATHMathSciNetCrossRefGoogle Scholar
  21. 21.
    M. Leventon, E. Grimson, and O. Faugeras. Statistical shape influence in geodesic active contours, 2000.Google Scholar
  22. 22.
    R. Malladi, R. Kimmel, D. Adalsteinsson, V. Caselles G. Sapiro, and J. A. Sethian. A geometric approach to segmentation and analysis of 3d medical images. In Proc. Mathematical Methods in Biomedical Image Analysis Workshop, pages 21–22, 1996.Google Scholar
  23. 23.
    R. Malladi, J. A. Sethian, and B. C. Vemuri. Shape modeling with front propagation: A level set approach. IEEE PAMI, 17(2):158–175, 1995.Google Scholar
  24. 24.
    K. V. Mardia and I. L. Dryden. Shape distributions for landmark data. Adv. appl. prob., 21(4):742–755, 1989.zbMATHCrossRefMathSciNetGoogle Scholar
  25. 25.
    M. I. Miller and L. Younes. Group actions, diffeomorphisms and matching: a general framework. In Proc. of SCTV, 1999.Google Scholar
  26. 26.
    S. Osher and J. Sethian. Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi equations. J. of Comp. Physics, 79:12–49, 1988.zbMATHCrossRefMathSciNetGoogle Scholar
  27. 27.
    N. Paragios and R. Deriche. Geodesic active contours and level sets for the detection and tracking of moving objects. IEEE PAMI, 22(3):266–280, 2000.Google Scholar
  28. 28.
    C. Samson, L. Blanc-Feraud, G. Aubert, and J. Zerubia. A level set model for image classification. In in International Conference on Scale-Space Theories in Computer Vision, pages 306–317, 1999.Google Scholar
  29. 29.
    B. ter Haar Romeny, L. Florack, J. Koenderink, and M. Viergever (Eds.). Scale-space theory in computer vision. In LLNCS, Vol 1252. Springer Verlag, 1997.Google Scholar
  30. 30.
    P. Thompson and A. W. Toga. A surface-based technique for warping three-dimensional images of the brain. IEEE Trans. Med. Imaging, 15(4):402–417, 1996.CrossRefGoogle Scholar
  31. 31.
    K. Toyama and A. Blake. Probabilistic tracking in a Metric Space. In Proc. of the Eur. Conf. on Comp. Vision, 2001.Google Scholar
  32. 32.
    R. C. Veltkamp and M. Hagedoorn. State of the art in shape matching. Technical Report UU-CS-1999-27, University of Utrecht, 1999.Google Scholar
  33. 33.
    L. Younes. Computable elastic distances between shapes. SIAM J. of Appl. Math., 1998.Google Scholar
  34. 34.
    A. Yuille. Deformable templates for face recognition. J. of Cognitive Neurosci., 3(1):59–70, 1991.CrossRefGoogle Scholar
  35. 35.
    S. Zhu, T. Lee, and A. Yuille. Region competition: Unifying snakes, region growing, energy /bayes/mdl for multi-band image segmentation. In ICCV, pages 416–423, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Stefano Soatto
    • 1
  • Anthony J. Yezzi
    • 2
  1. 1.Department of Computer ScienceUniversity of California Los AngelesLos Angeles
  2. 2.Department of Electrical and Computer EngineeringGeorgia Institute of TechnologyAtlanta

Personalised recommendations