Advertisement

Sketch Recognition Based on Topological Spatial Relationship

  • Binbin Peng
  • Yin Liu
  • Liu Wenyin
  • Guanglin Huang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3138)

Abstract

In recognition of composite graphic objects, topological spatial relationships of their components play an important role. Although most researchers focus on binary topological relationships, they cannot carry all information of the internal structure of the compound objects. Therefore, we introduce the ternary relationship, which is a complement to the binary relationship, to describe composite graphic objects. Moreover, we provide a constrained partial permutation algorithm based on both the binary and ternary topological spatial relationships to recognize the sketchy objects input by users in an online manner. Experimental results show that this approach is both efficient and effective for online composite graphics recognition in our sketch-based graphics input system–SmartSketchpad.

Keywords

Hide Markov Model Topological Relationship Graphic Object Binary Relationship Graphic Recognition 
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.

References

  1. 1.
    Tversky, B.: What do Sketches Say about Thinking? In: Proc. of AAAI Spring Symposium–Sketch Understanding, pp. 148–151 (2002)Google Scholar
  2. 2.
    Alvarado, C., Oltmans, M., Davis, R.: A Framework for Multi-Domain Sketch Recognition. In: Proc. of AAAI Spring Symposium–Sketch Understanding, pp. 1–8 (2002)Google Scholar
  3. 3.
    Skubic, M., Blisard, S., Carle, A., Matsakis, P.: Hand-Drawn Maps for Robot Navigation. In: Proc. of AAAI Spring Symposium–Sketch Understanding, pp. 140–147 (2002)Google Scholar
  4. 4.
    Liu, W.: On-Line Graphics Recognition. In: Lladós, J., Kwon, Y.-B. (eds.) GREC 2003. LNCS, vol. 3088, pp. 291–304. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  5. 5.
    Lee, S.W., Kim, Y.J.: A New Type of Recurrent Neural Network for Handwritten Character Recognition. In: Proc. of ICDAR 1995, vol. 1, pp. 38–42 (1995)Google Scholar
  6. 6.
    Bicego, M., Murino, V.: 2D Shape Recognition by Hidden Markov Models. In: Proc. of 11th International Conference on Image Analysis and Processing, pp. 20–25 (1991)Google Scholar
  7. 7.
    Lladós, J., Martí, E., José, J.: Symbol Recognition by Error-Tolerant Subgraph Matching Between Region Adjacency Graphs. IEEE Trans. on PAMI. 23(10), 1137–1143 (2001)Google Scholar
  8. 8.
    Xu, X., Liu, W., Jin, X., Sun, Z.: Sketch-Based User Interface for Creative Tasks. In: Proc. of 5th Asia Pacific Conference on Computer Human Interaction, pp. 560–570 (2002)Google Scholar
  9. 9.
    Alvarado, C., Davis, R.: Resolving Ambiguities to Create a Natural Sketch Based Interface. In: Proc. of IJCAI 2001 (2001)Google Scholar
  10. 10.
    Egenhofer, M.J., Franzosa, R.: Point-Set Topological Spatial Relations. International Journal of Geographical Information Systems 5(2), 161–174 (1991)CrossRefGoogle Scholar
  11. 11.
    Zhan, F.B.: Topological Relations Between Fuzzy Regions. In: Proc. of the 1997 ACM Symposium on Applied Computing, pp. 192–196 (1997)Google Scholar
  12. 12.
    Liu, W., Jin, X., Sun, Z.: Sketch-Based User Interface for Inputting Graphic Objects on Small Screen Devices. In: Blostein, D., Kwon, Y.-B. (eds.) GREC 2001. LNCS, vol. 2390, pp. 67–80. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  13. 13.
    Revankar, S., Yegnanarayana, B.: Machine Recognition and Correction of Freehand Geometric Line Sketches. In: Proc. of IEEE International Conference on Systems, Man, and Cybernetics, pp. 87–92 (1991)Google Scholar
  14. 14.
    Mehlhorn, K.: Graph Algorithm and NP-Completeness. Springer, Heidelberg (1984)Google Scholar
  15. 15.
    Xu, X., Sun, Z., Peng, B., Liu, W.: An Online Composite Graphics Recognition Approach Based on Matching of Spatial Relation Graphs. To appear in International Journal on Document Analysis and RecognitionGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Binbin Peng
    • 1
  • Yin Liu
    • 1
  • Liu Wenyin
    • 1
  • Guanglin Huang
    • 1
  1. 1.Dept. of Computer ScienceCity University of Hong KongHong Kong SARP.R. China

Personalised recommendations