Acquisition of 2-D shape models from scenes with overlapping objects using string matching

  • Horst Bunke
  • Marcel Zumbühl
Recognition of 2D and 3D Objects
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1451)


In this paper we describe a system that is able to acquire models of 2-D shapes from cluttered scenes. The input of the system is a sequence of images each of which shows an unknown number of overlapping unknown 2-D objects. The system identifies matching partial shapes across different images and combines them into complete 2-D shape models thus giving a complete interpretation of the input scenes. The identification of partial shapes is based on string matching, whereas a graph search procedure is used for shape model generation. The system has been fully implemented and tested on images containing parts of a jigsaw puzzle.


  1. [1]
    D.H. Ballard, Generalizing the Hough Transform to Detect Arbitrary Shapes, Pattern Recognition, Vol.13, 1981, pp. 111–122CrossRefGoogle Scholar
  2. [2]
    J.L. Turne, T.N. Mudge, R.A. Volz, Recognizing Partially Occluded Parts, IEEE Trans. Pattern Anal. Mach. Intell., Vol.7, No.4, 1985, pp. 410–421Google Scholar
  3. [3]
    W.E.L. Grimson and T. Lonyano-Perez, Localizing Overlapping Parts by Searching the Interpretation Tree, IEEE Transc. Pattern Anal. Mach. Intell., Vol.9, No.4, 1987, pp. 469–482Google Scholar
  4. [4]
    N. Ayache, O.D. Faugeras, HYPER: a New Approach for the Recognition and Positioning of two-dimensional Objects, IEEE Trans. Pattern Anal. Mach. Intell., Vol.8, No.1, 1986, pp. 44–54Google Scholar
  5. [5]
    Y.-T. Tsay, W.-H. Tsai, Model-guided Attributed String Matching by Split-and-merge for Shape Recognition, Int. J. Pattern Recognition Artif. Intell. No.3, 1989, pp. 159–179Google Scholar
  6. [6]
    H. Bunke, T. Glauser, Viewpoint Independent Representation and Recognition of Polygonal Faces in 3-D, IEEE Trans. Robotics Automat., Vol.9, No.4, 1993, pp. 457–462CrossRefGoogle Scholar
  7. [7]
    H.J. Wolfson, Model-based Object Recognition by Geometric Hashing, Proc. 1st Eur. Conf. Comput. Vision Antibes, 1990, pp. 526–536Google Scholar
  8. [8]
    D. Huttenlocher, G. Klaudermann, W. Ruckbfidge, Comparing Images Using the Hausdorff Distance, IEFF Trans. Pattern Anal. Mach. Intell., Vol.15, No.9, 1993, pp. 850–863CrossRefGoogle Scholar
  9. [9]
    K.Y. Kupeev, H.J. Wolfson, A New Method of Estimating Shape Similarity, Pattern Recognition Letters, No.17, 1996, pp. 873–887Google Scholar
  10. [10]
    A. Hutchinson, Algorithmic Learning, Oxford University Press, 1994Google Scholar
  11. [11]
    J.W. Shavlick, T.G. Dietterich (eds.), Readings in Machine Learning, Morgan Kaufman, San Mateo, 1990Google Scholar
  12. [12]
    Y. Kodratoff, S. Moscatelli, Machine Learning for Object Recognition and Scene Analysis, Int. Journal of Pattern Recognition and Artificial Intelligence, Vol.8, No.1, 1994, pp. 259–305CrossRefGoogle Scholar
  13. [13]
    B. Bhanu, T. Poggio (guest eds.), Special Section on Learning in Computer Vision, IEEE Trans. Pattern Anal. Mach. Intell., Vol.16, No.9, 1994, pp. 865–919Google Scholar
  14. [14]
    H. Bunke, U. Bühler, Applications of Approximate String Matching to 2D Shape Recognition, Pattern Recognition, Vol.26, No.12, 1993, pp. 1797–1812CrossRefGoogle Scholar
  15. [15]
    R.A. Wagner, M.J. Fischer, The String-to-string Correction Problem, Jour. ACM, Vol.21, 1994, pp. 168–173CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Horst Bunke
    • 1
  • Marcel Zumbühl
    • 1
  1. 1.Institut für Informatik und angewandte MathematikUniversity of BernBernSwitzerland

Personalised recommendations