Interpreting Sloppy Stick Figures by Graph Rectification and Constraint-Based Matching

  • James V. Mahoney
  • Markus P. J. Fromherz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2390)


Programs for understanding hand-drawn sketches and diagrams must interpret curvilinear configurations that are sloppily drawn and highly variable in form. We propose a two-stage subgraph matching framework for sketch recognition that can accommodate great variability in form and yet provide efficient matching and easy extensibility to new configurations. First, a rectification stage corrects the initial data graph for the common deviations of each kind of constituent local configuration from its ideal form. The model graph is then matched directly to the data by a constraint-based subgraph matching process, without the need for complex error-tolerance. We explore the approach in the domain of human stick figures in diverse poses.


Minimum Span Tree Constraint Satisfaction Problem Data Graph Mutual Exclusion Curve Segment 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    D. Bainbridge and T. Bell. An extensible optical music recognition system. In Proc. Nineteenth Australasian Computer Science Conf., 1996.Google Scholar
  2. 2.
    M. Carlsson, G. Ottosson, B. Carlson. An open-ended finite domain constraint solver. Proc. Programming Languages: Implementations, Logics, and Programs, 1997.Google Scholar
  3. 3.
    S. Chok, K. Marriot. Parsing visual languages. Proc. 18th Australasian Computer Science Conf., 27(1), 1995: 90–98.Google Scholar
  4. 4.
    T. Cormen, C. Leiserson, R. Rivest. Introduction to Algorithms. Cambridge, MA: M.I.T. Press, 1990.Google Scholar
  5. 5.
    B. Couasnon, P. Brisset, I. Stephan. Using logic programming languages for optical music recognition. Proc. 3rd Int. Conf. on Practical Application of Prolog, Paris, 1995.Google Scholar
  6. 6.
    H. Fahmy and D. Blostein. A graph-rewriting paradigm for discrete relaxation: application to sheet music recognition. Int. Journal of Pattern Recognition and Artificial Intelligence, Vol. 12, No. 6, Sept. 1998,pp. 763–799.CrossRefGoogle Scholar
  7. 7.
    M. Fromherz and J. Mahoney. Interpreting sloppy stick figures with constraint-based subgraph matching. 7th Int. Conf. on Principles and Practice of Constraint Programming. Paphos, Cyprus: 2001.Google Scholar
  8. 8.
    D. Isenor and S. Zaky. Fingerprint identification using graph matching. Pattern Recognition, vol. 19, no. 2, 1986, pp. 113–122.CrossRefGoogle Scholar
  9. 9.
    J. Larrosa and G. Valiente, Constraint satisfaction algorithms for graph pattern matching. Under consideration for publication in J. Math. Struct. in Computer Science, 2001.Google Scholar
  10. 10.
    J. Mahoney and M. Fromherz. Interpreting sloppy stick figures by graph rectification and constraint-based matching. 4th IAPR Int. Workshop on Graphics Recognition: Kingston, Ontario: Sept., 2001Google Scholar
  11. 11.
    B. Messmer. Efficient graph matching algorithms for preprocessed model graphs. PhD thesis. Bern Univ., Switzerland, 1995.Google Scholar
  12. 12.
    E. Saund. Perceptual organization in an interactive sketch editor. 5th Int. Conf. on Computer Vision. Cambridge, MA: 1995: 597–604.Google Scholar
  13. 13.
    E. Saund. Perceptually closed paths in sketches and drawings. Submitted for publication.Google Scholar
  14. 14.
    L. G. Shapiro and R. M. Haralick. Structural descriptions and inexact matching. In IEEE PAMI, vol. 3, no. 5, Sept. 1981, pp. 504–519.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • James V. Mahoney
    • 1
  • Markus P. J. Fromherz
    • 1
  1. 1.Xerox Palo Alto Research CenterPalo Alto

Personalised recommendations