Tree Representation for Image Matching and Object Recognition

  • Julian Mattes
  • Mathieu Richard
  • Jacques Demongeot
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1568)


The problem of matching two images of the same objects but after movements or slight deformations arises in medical imaging, but also in the microscopic analysis of physical or biological structures. We present a new matching strategy consisting of two steps. We consider the grey level function (modulo a normalization) as a probability density function. First, we apply a density based clustering method in order to obtain a tree which classifies the points on which the grey level function is defined. Secondly, we use the identification of the hierarchical representations of the two images to guide the image matching or to define a distance between the images for object recognition. The transformation invariance properties of the representations allow to extract invariant image points. Using the identification of the trees, they allow, in addition, to find the correspondence between invariant points even if these have moved locally. Then, we obtain the transformation function as the thin plate interpolation of the corresponding point pairs. On the other hand, if we use tree identification, this enables us to propose several criterias to distinguish between real deformations and noise effects. In practice, we treat, for instance, first coarse trees (with few leaves) and pass to ever refining trees, after. The method’s results on real images will be discussed.


Object Recognition Image Match Tree Representation Real Deformation Unordered Tree 
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.
    Barrow, H.G., Poppelestone, R.J.: Relational Descriptions in Picture Processing. Machine Intelligence6 (1971) 377–396Google Scholar
  2. 2.
    Barthélemy, J.-P., Guénoche, A.: Les arbres et les représentations des proximités. Masson, Paris, (1988)Google Scholar
  3. 3.
    Black, M. Jepson, A.D.: Estimating optical flow in segmented images using variable-order parametric models with local deformations. IEEE Trans. PAMI18 (1996)Google Scholar
  4. 4.
    Bookstein, F.: Principal wraps: Thin-plate splines and the decomposition of deformations. IEEE Trans. PAMI11 (1989) 567–585zbMATHGoogle Scholar
  5. 5.
    Boorman, S.A., Olivier, D.C.:Metrics on spaces of finite trees. J. Math. Psych.10 (1973)Google Scholar
  6. 6.
    J. Canny: A computional approach to edge detection. IEEE Trans. PAMI8 (1986) 679–698Google Scholar
  7. 7.
    Cheng, Y.C., Lu, S.Y.: Waveform correlation by tree matching. IEEE Trans. PAMI7 (1985) 299–305Google Scholar
  8. 8.
    Demongeot, J., Cosnard, M., Jacob, C.: Attractors and confiners: Deterministic and stochastic approaches. In: Diner, S., Fargue, D., Lochak, G. (eds.): Dynamical systems-A renewal of mechanism. Centennial of Gorge David Birkhoff. World Scientific, Singapore (1986)Google Scholar
  9. 9.
    Farris, J.S.: A successive approximations approach to character weighting. J. Syst. Zool. 18 (1969) 374–385CrossRefGoogle Scholar
  10. 10.
    Finch, A.M., Wilson R.C., Hancock, E.R.: Matching Delaunay graphs. Pattern Recognition30 (1997) 123–140zbMATHCrossRefGoogle Scholar
  11. 11.
    Gaal, S.A.: Point set topology. Academic Press, New York, (1964)zbMATHGoogle Scholar
  12. 12.
    Gold, S., Rangarajan, A.: A graduated assignement algorithm for graph matching. IEEE Trans. PAMI18 (1996) 377–388Google Scholar
  13. 13.
    Hanusse, P., Guillataud, P.: Sémantique des images par analyse dendronique. In: AFECT, 8th Conf. Reconnaissance des Formes et Intelligence Artificielle, Vol. 2. Lyon (1992) 577–588Google Scholar
  14. 14.
    Hartigan, J.A.: Clustering algorithms. Wiley, New York, (1975)zbMATHGoogle Scholar
  15. 15.
    Hartigan, J.A.: Statistical theory in clustering. J. of Classification2 (1985) 63–76zbMATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Kok-Wiles, S.L., Brady, J.M., Highnam, R.: Comparing mammogram pairs for the detection of lesions. In: Karssemeijer, N. (ed.): 4th International Workshop of Digital Mammography, Nijmegen, Netherlands, June 1998. Kluwer (1998)Google Scholar
  17. 17.
    Lavallée, S., Szeliski, R.: Recovering the position and orientation of free-form objects from image contours using 3D distance maps. IEEE Trans. PAMI17 (1995) 378–390Google Scholar
  18. 18.
    Leu, J.G., Huang, I.N.: Planar shape matching based on binary tree shape representation. Pattern Recognition21 (1988) 607–622CrossRefGoogle Scholar
  19. 19.
    Lu, S.-Y.: A tree-to-tree distance and its application to cluster analysis. IEEE Trans. PAMI1 (1979) 210–224Google Scholar
  20. 20.
    Maintz, J.B.A., Viergever, M.A.: A survey of medical image registration. Medical Image Analysis2 (1998) 1–36CrossRefGoogle Scholar
  21. 21.
    Mattes, J., Demongeot, J.: Dynamic Quantization, Classification, and Imaging. In: 22nd Annual Conference of the Gesellschaft für Klassifikation e.V., Dresden, Germany, March 1998. Studies in Classification, Data Analysis, and Knowledge Organization. Springer-Verlag, Berlin Heidelberg New York (to appear)Google Scholar
  22. 22.
    Pavlidis, T.: Analysis of set patterns. Pattern Recognition1 (1968)Google Scholar
  23. 23.
    Rastal, J.S.: Graph family matching. Research Memorandum, MIP-R-62. Departement of Machine Intelligence and Perception Edinburgh (1969)Google Scholar
  24. 24.
    Samet, H.: The design and analysis of spatial data structures. Addison Wesley Publishing Company, Reading, Massachusetts (1990)Google Scholar
  25. 25.
    Shasha, D., Wang, J.T.-L., Zhang, K., Shih, F.Y.: Exact and approximate algorithms for unordered tree matching. IEEE Trans. Syst., Man, Cybern.24 (1994) 668–678CrossRefMathSciNetGoogle Scholar
  26. 26.
    Silverman, B.W.: Density estimation for statistics and data analysis. Chapman and Hall, London (1986)Google Scholar
  27. 27.
    Tanaka, E.: A metric between unrroted adn unordered trees and its bottom-up computing method. IEEE Trans. PAMI16 (1994) 1233–1238Google Scholar
  28. 28.
    Thirion, J.-P.: New feature points based on geometric invariants for 3D image registration. International Journal of Computer Vision18 (1996) 121–137CrossRefGoogle Scholar
  29. 29.
    Wishart, D.: Mode analysis: A generalization of the nearest neighbor which reduces chaining effects. In: Cole, A.J.(Ed.): Numerical Taxonomy.Academic Press, London (1969) 282–319Google Scholar
  30. 30.
    Zhang, K., Statman, R., Shasha, D.: On the editing distance between unordered labeled trees. Information Processing Letters42 (1992) 133139CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Julian Mattes
    • 1
  • Mathieu Richard
    • 1
  • Jacques Demongeot
    • 1
    • 2
  1. 1.Faculty of MedicineTIMC-IMAGLa TroncheFrance
  2. 2.Chaire de BiomathématiquesInstitut Universitaire de FranceFrance

Personalised recommendations