Advertisement

Measuring GNG Topology Preservation in Computer Vision Applications

  • José García Rodríguez
  • Francisco Flórez-Revuelta
  • Juan Manuel García Chamizo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4253)

Abstract

Self-organizing 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 addition, these applications usually have real-time constraints. In this work we have study a kind of self-organizing network, the Growing Neural Gas with different parameters, to represent different objects. In some cases, topology preservation is lost and, therefore, the quality of the representation. So, we have made a study to quantify topology preservation to establish the most suitable learning parameters, depending on the kind of objects to represent and the size of the network.

Keywords

Input Space Gesture Recognition Competitive Learning Hand Gesture Recognition Computer Vision Application 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  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 2002), Alicante, pp. 267–276. ICEIS Press (2001)Google Scholar
  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., Los Alamitos (2001)Google Scholar
  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, vol. 7, pp. 625–632. MIT Press, Cambridge (1995)Google Scholar
  4. Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (1995)Google Scholar
  5. Martinetz, T., Schulten, K.: Topology Representing Networks. Neural Networks 7(3), 507–522 (1994)CrossRefGoogle Scholar
  6. Bauer, H.-U., Pawelzik, K.R.: Quantifying the Neighborhood Preservation of Self-Organizing Feature Maps. IEEE Transactions on Neural Networks 3(4), 570–578 (1992)CrossRefGoogle Scholar
  7. Rev, F.F., Chamizo, J.-M.G., Rodr, J.G., Saez, A.H.: Geodesic Topographic Product: An Improvement to Measure Topology Preservation of Self-Organizing Neural Networks. In: Lemaître, C., Reyes, C.A., González, J.A. (eds.) IBERAMIA 2004. LNCS, vol. 3315, pp. 841–850. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  8. Villmann, T., Der, R., Herrmann, M., Martinetz, T.M.: Topology Preservation in Self-Organizing Feature Maps: Exact Definition and Measurement. IEEE Transactions on Neu-ral Networks 8(2), 256–266 (1997)CrossRefGoogle Scholar
  9. Martinetz, T., Schulten, K.: A “Neural-Gas” Network Learns Topologies. In: Kohonen, T., Mäkisara, K., Simulay, O., Kangas, J. (eds.) Artificial Neural Networks, vol. 1, pp. 397–402 (1991)Google Scholar
  10. Marsland, S., Shapiro, J., Nehmzow, U.: A self-organising network that grows when required. Neural Networks 15, 1041–1058 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • José García Rodríguez
    • 1
  • Francisco Flórez-Revuelta
    • 1
  • Juan Manuel García Chamizo
    • 1
  1. 1.Department of Computer Technology and ComputationUniversity of AlicanteAlicanteSpain

Personalised recommendations