Adaptive Representation of Objects Topology Deformations with Growing Neural Gas

  • José García-Rodríguez
  • Francisco Flórez-Revuelta
  • Juan Manuel García-Chamizo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4507)


Self-organising neural networks try to preserve the topology of an input space by means of their competitive learning. This capacity has been used, among others, for the representation of objects and their motion. In this work we use a kind of self-organising network, the Growing Neural Gas, to represent deformations in objects along a sequence of images. As a result of an adaptive process the objects are represented by a topology representing graph that constitutes an induced Delaunay triangulation of their shapes. These maps adapt the changes in the objects topology without reset the learning process.


topology preservation topology representation self-organising neural networks shape representation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Flórez, F., García, J.M., García, J., Hernández, A.: Representation of 2D Objects with a Topology Preserving Network. In: Proceedings of the 2nd International Workshop on Pattern Recognition in Information Systems (PRIS’02), Alicante, pp. 267–276. ICEIS Press (2001)Google Scholar
  2. 2.
    Flórez, F., García, J.M., García, J., Hernández, A.: Hand Gesture Recognition Following the Dynamics of a Topology-Preserving Network. In: Proc. of the 5th IEEE Intern. Conference on Automatic Face and Gesture Recognition, Washington, D.C., pp. 318–323. IEEE, Inc., Orlando (2001)Google Scholar
  3. 3.
    Fritzke, B.: A Growing Neural Gas Network Learns Topologies. In: Tesauro, G., Touretzky, D.S., Leen, T.K. (eds.) Advances in Neural Information Processing Systems 7, pp. 625–632. MIT Press, Cambridge (1995)Google Scholar
  4. 4.
    Kohonen, T.: Self-Organising Maps. Springer, Heidelberg (1995)Google Scholar
  5. 5.
    Martinetz, T., Schulten, K.: Topology Representing Networks. Neural Networks 7(3), 507–522 (1994)CrossRefGoogle Scholar
  6. 6.
    O’Rourke, J.: Computational Geometry in C. Cambridge University Press, Cambridge (2001)Google Scholar
  7. 7.
    Ritter, H., Schulten, K.: Topology conserving mappings for learning motor tasks. In: Neural Networks for Computing, AIP Conf. Proc. (1986)Google Scholar
  8. 8.
    Martinez, T., Ritter, H., Schulten, K.: Three dimensional neural net for learning visuomotor-condination of a robot arm. IEEE Transactions on Neural Networks 1, 131–136 (1990)CrossRefGoogle Scholar
  9. 9.
    Nasrabati, M., Feng, T.: Vector quantisation of images based upon kohonen self-organising feature maps. In: Proc. IEEE Int. Conf. Neural Networks, pp. 1101–1108 (1988)Google Scholar
  10. 10.
    Martinez, T.: Competitive hebbian learning rule forms perfectly topology preserving maps. In: ICANN (1993)Google Scholar
  11. 11.
    Cselényi, Z.: Mapping the dimensionality, density and topology of data: The growing adaptative gas. Computers Methods and Program in Biomedicine 78, 141–156 (2005)CrossRefGoogle Scholar
  12. 12.
    Cheng, G., Zell, A.: Double growing neural gas for disease diagnosis. In: Proceedings of ANNIMAB-1 Conference, pp. 309–314 (2000)Google Scholar
  13. 13.
    Qin, A.K., Suganthan, P.N.: Robust growing neural gas algorithm with application in cluster analysis. Neural Networks 17, 1135–1148 (2004)CrossRefzbMATHGoogle Scholar
  14. 14.
    Toshihiko, O., Iwasaki, K., Sato, C.: Topology representing network enables highly accurate classification of protein images taken by cryo electron-microscope without maskin. Journal of Structural Biology 143, 185–200 (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • José García-Rodríguez
    • 1
  • Francisco Flórez-Revuelta
    • 1
  • Juan Manuel García-Chamizo
    • 1
  1. 1.Department of Computer Technology. University of Alicante. Apdo. 99. 03080 AlicanteSpain

Personalised recommendations