Advertisement

A Growing Neural Gas Algorithm with Applications in Hand Modelling and Tracking

  • Anastassia Angelopoulou
  • Alexandra Psarrou
  • José García Rodríguez
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6692)

Abstract

Growing models have been widely used for clustering or topology learning. Traditionally these models work on stationary environments, grow incrementally and adapt their nodes to a given distribution based on global parameters. In this paper, we present an enhanced Growing Neural Gas (GNG) model for applications in hand modelling and tracking. The modified network consists of the geometric properties of the nodes, the underline local feature of the image, and an automatic criterion for maximum node growth based on the probability of the objects in the image. We present experimental results for hands and T1-weighted MRI images, and we measure topology preservation with the topographic product.

Keywords

Unsupervised Learning Topology preservation Self-organising networks Nonrigid Shapes 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Angelopoulou, A., Psarrou, A., Gupta, G., García, J.: Robust Modelling and Tracking of Nonrigid Objects Using Active-GNG. In: IEEE Workshop on Non-rigid Registration and Tracking through Learning, NRTL 2007, in conjuction with ICCV 2007, pp. 1–7 (2007)Google Scholar
  2. 2.
    Bauer, H., Pawelzik, K.: Quantifying the neighbourhood preservation of self-organizing feature maps. IEEE Transactions on Neural Networks 3(4), 570–579 (1992)CrossRefGoogle Scholar
  3. 3.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active Shape Models - Their Training and Application. Comp. Vision Image Underst. 61(1), 38–59 (1995)CrossRefGoogle Scholar
  4. 4.
    Cretu, A., Petriu, E., Payeur, P.: Evaluation of growing neural gas networks for selective 3D scanning. In: Proc. of IEEE International Workshop on Robotics and Sensors Environments, pp. 108–113 (2008)Google Scholar
  5. 5.
    Edwards, G., Taylor, C., Cootes, T.: Interpreting face images using active appearance models. In: Proc. of the International Conference on Face And Gesture Recognition, pp. 300–305 (1998)Google Scholar
  6. 6.
    Frezza-Buet, H.: Following non-stationary distributions by controlling the vector quantisation acccuracy of a growing neural gas network. Neurocomputing 71(7-9), 1191–1202 (2008)CrossRefGoogle Scholar
  7. 7.
    Fritzke, B.: A growing Neural Gas Network Learns Topologies. In: Advances in Neural Information Processing Systems 7, NIPS 1994, pp. 625–632 (1995)Google Scholar
  8. 8.
    García-Rodríguez, J., Flórez-Revuelta, F., García-Chamízo, M.: Image Compression Using Growing Neural Gas. In: Proc. of the International Joint Conference on Artificial Neural Networks, pp. 366–370 (2007)Google Scholar
  9. 9.
    Hans-Joachim, B., Anja, B., Ulf-dietrich, B., Markus, K., Horst-michael, G.: Neural Networks for Gesture-based Remote Control of a Mobile Robot. In: Proceedings of the IEEE World Congress on Computational Intelligence, vol. 1, pp. 372–377 (1998)Google Scholar
  10. 10.
    Holdstein, Y., Fischer, A.: Three-dimensional surface reconstruction using meshing growing neural gas (MG NG). The Visual Computer: International Journal of Computer Graphics 24(4), 295–302 (2008)CrossRefGoogle Scholar
  11. 11.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active Contour Models. In: Proc. of the 1st Internationl Conference on Computer Vision, pp. 259–268. IEEE Computer Society Press, Los Alamitos (1987)Google Scholar
  12. 12.
    Lankton, S., Tannenbaum, A.: Localizing region-based active contours. IEEE Transactions on Image Processing 17(11), 2029–2039 (2008)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Qin, A.K., Suganthan, P.N.: Robust growing neural gas algorithm with application in cluster analysis. Neural Networks 17(8-9), 1135–1148 (2004)CrossRefzbMATHGoogle Scholar
  14. 14.
    Rivera-Rovelo, J., Herold, S., Bayro-Corrochano, E.: Object segmentation using growing neural gas and generalized gradient vector flow in the geometric algebra framework. In: Martínez-Trinidad, J.F., Carrasco Ochoa, J.A., Kittler, J. (eds.) CIARP 2006. LNCS, vol. 4225, pp. 306–315. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Anastassia Angelopoulou
    • 1
  • Alexandra Psarrou
    • 1
  • José García Rodríguez
    • 2
  1. 1.School of Electronics and Computer ScienceUniversity of WestminsterUK
  2. 2.Department of Computing TechnologyUniversity of AlicanteSpain

Personalised recommendations