Learning 2D Hand Shapes Using the Topology Preservation Model GNG
Conference paper
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.
References
- 1.Bauer, H., Herrman, M., Villman, T.: Neural maps and topographic vector quantization. Neural Networks 12(4-5), 659–676 (1999)CrossRefGoogle Scholar
- 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.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.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.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)CrossRefMATHGoogle Scholar
- 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)CrossRefMATHGoogle Scholar
- 7.Ericsson, A., Åstróm, K.: Minimizing the description length using steepest descent. In: 14th British Machine Vision Conference, vol. 2 (2003)Google Scholar
- 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.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.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.Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. International Journal of Computer Vision 4(1), 321–331 (1987)Google Scholar
- 12.Kohonen, T.: Self-organising maps. Springer, Heidelberg (2001)CrossRefMATHGoogle Scholar
- 13.Martinez, T.: Competitive hebbian learning rule forms perfectly topology preserving maps. In: ICANN (1993)Google Scholar
- 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.Martinez, T., Schulten, K.: Topology representing networks. The Journal of Neural Networks 7(3), 507–522 (1994)CrossRefGoogle Scholar
- 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.Ritter, H., Schulten, K.: Topology conserving mappings for learning motor tasks. In: Neural Networks for Computing, AIP Conf. Proc. (1986)Google Scholar
- 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