Advertisement

Learning 2D Hand Shapes Using the Topology Preservation Model GNG

  • Anastassia Angelopoulou
  • José García Rodríguez
  • Alexandra Psarrou
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3951)

Abstract

Recovering the shape of a class of objects requires establishing correct correspondences between manually or automatically annotated landmark points. In this study, we utilise a novel approach to automatically recover the shape of hand outlines from a series of 2D training images. Automated landmark extraction is accomplished through the use of the self-organising model the growing neural gas (GNG) network which is able to learn and preserve the topological relations of a given set of input patterns without requiring a priori knowledge of the structure of the input space. To measure the quality of the mapping throughout the adaptation process we use the topographic product. Results are given for the training set of hand outlines.

Keywords

Input Space Input Pattern Minimum Description Length Active Contour Model Statistical Shape Model 
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. 1.
    Bauer, H., Herrman, M., Villman, T.: Neural maps and topographic vector quantization. Neural Networks 12(4-5), 659–676 (1999)CrossRefGoogle Scholar
  2. 2.
    Bauer, H.U., Pawelzik, K.R.: Quantifying the neighbourhood preservation of self-organizing feature maps. IEEE Trans. on Neural Networks 3(4), 570–579 (1992)CrossRefGoogle Scholar
  3. 3.
    Baumberg, A., Hogg, D.: Learning flexible models from image sequences. In: 3rd European Conference on Computer Vision, vol. 1, pp. 299–308 (1994)Google Scholar
  4. 4.
    Cootes, T.F., Taylor, C.J., Cooper, D.H.: Graham J. Training models of shape from sets of examples. In: 3rd British Machine Vision Conference, pp. 9–18 (1992)Google Scholar
  5. 5.
    Cremers, D., Schnorr, C., Weickert, J.: Diffusion-snakes: Introducing statistical shape knowledge into the mumford-shah functional. International Journal of Computer Vision 50(3), 295–313 (2002)CrossRefzbMATHGoogle Scholar
  6. 6.
    Rhodies Davies, H., Carole Twining, J., Tim Cootes, F., John Waterton, C., Chris Taylor, J.: A minimum description length approach to statistical shape modeling. IEEE Transaction on Medical Imaging 21(5), 525–537 (2002)CrossRefzbMATHGoogle Scholar
  7. 7.
    Ericsson, A., Åstróm, K.: Minimizing the description length using steepest descent. In: 14th British Machine Vision Conference, vol. 2 (2003)Google Scholar
  8. 8.
    Fatemizadeh, E., Lucas, C., Soltania-Zadeh, H.: Automatic landmark extraction from image data using modified growing neural gas network. IEEE Transactions on Information Technology in Biomedicine 7(2), 77–85 (2003)CrossRefGoogle Scholar
  9. 9.
    Fritzke, B.: A growing neural gas network learns topologies. In: Advances in Neural Information Processing Systems, vol. 7, pp. 625–632 (1995)Google Scholar
  10. 10.
    Geoffrey, J., Goodhill, F., Terrence, J.: A unifying measure for neighbourhood preservation in topographic mappings. In: Proceedings of the 2nd Joint Symposium on Neural Computation, vol. 5, pp. 191–202 (1997)Google Scholar
  11. 11.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. International Journal of Computer Vision 4(1), 321–331 (1987)Google Scholar
  12. 12.
    Kohonen, T.: Self-organising maps. Springer, Heidelberg (2001)CrossRefzbMATHGoogle Scholar
  13. 13.
    Martinez, T.: Competitive hebbian learning rule forms perfectly topology preserving maps. In: ICANN (1993)Google Scholar
  14. 14.
    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
  15. 15.
    Martinez, T., Schulten, K.: Topology representing networks. The Journal of Neural Networks 7(3), 507–522 (1994)CrossRefGoogle Scholar
  16. 16.
    Nasrabati, M., Feng, Y.: Vector quantisation of images based upon kohonen self-organizing feature maps. In: Proc. IEEE Int. Conf. Neural Networks, pp. 1101–1108 (1988)Google Scholar
  17. 17.
    Ritter, H., Schulten, K.: Topology conserving mappings for learning motor tasks. In: Neural Networks for Computing, AIP Conf. Proc. (1986)Google Scholar
  18. 18.
    Thodberg, H.H., Olafsdottir, H.: Adding curvature to minimum description length shape models. In: 14th British Machine Vision Conference, vol. 2, pp. 251–260 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Anastassia Angelopoulou
    • 1
  • José García Rodríguez
    • 2
  • Alexandra Psarrou
    • 1
  1. 1.Harrow School of Computer ScienceUniversity of WestminsterHarrowUnited Kingdom
  2. 2.Departamento de Tecnología Informática y ComputaciónUniversidad de AlicanteAlicanteSpain

Personalised recommendations