Abstract
We present a neural network model that learns to find correspondences. The network uses control units that gate feature information from an input to a model layer of neural feature detectors. The control units communicate via a network of lateral connections to coordinate the gating of feature information such that information about spatial feature arrangements can be used for correspondence finding. Using synaptic plasticity to modify the connections amongst control units, we show that the network can learn to find the relevant neighborhood relationship of features in a given class of input patterns. In numerical simulations we show quantitative results on pairs of one-dimensional artificial inputs and preliminary results on two-dimensional natural images. In both cases the system gradually learns the structure of feature neighborhood relations and uses this information to gradually improve in the task of correspondence finding.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hinton, G.E.: A parallel computation that assigns canonical object-based frames of reference. In: Proc. IJCAI, pp. 683–685 (1981)
Olshausen, B.A., Anderson, C.H., Van Essen, D.C.: A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. The Journal of Neuroscience 13(11), 4700–4719 (1993)
Wiskott, L., von der Malsburg, C.: Face recognition by dynamic link matching. In: Sirosh, J., Miikkulainen, R., Choe, Y. (eds.) Lateral Interactions in the Cortex: Structure and Function, ch. 4 (1995), www.cs.utexas.edu/users/nn/book/bwdraft.html ISBN 0-9647060-0-8
Zhu, J., von der Malsburg, C.: Maplets for correspondence-based object recognition. Neural Networks 17(8–9), 1311–1326 (2004)
Messer, K., Kittler, J., Sadeghi, M., Hamouz, M., Kostin, A., et al.: Face authentication test on the BANCA database. In: Proceedings of the International Conference on Pattern Recognition, Cambridge, vol. 4, pp. 523–532 (2004)
Weber, C., Wermter, S.: A self-organizing map of sigma-pi units. Neurocomputing 70(13-15), 2552–2560 (2007)
Lücke, J., Keck, C., von der Malsburg, C.: Rapid convergence to neural feature field correspondences. Neural Computation (page accepted, 2007)
Lücke, J., Bouecke, J.D.: Dynamics of cortical columns – self-organization of receptive fields. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 31–37. Springer, Heidelberg (2005)
Lücke, J., von der Malsburg, C.: Rapid correspondence finding in networks of cortical columns. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4131, pp. 668–677. Springer, Heidelberg (2006)
Lades, M., Vorbrüggen, J.C., Buhmann, J., Lange, J., von der Malsburg, C., Würtz, R.P., Konen, W.: Distortion invariant object recognition in the dynamic link architecture. IEEE Transactions on Computers 42(3), 300–311 (1993)
Mel, B.W.: SEEMORE: Combining color, shape, and texture histogramming in a neurally-inspired approach to visual object recognition. Neural Computation 9, 777–804 (1997)
Sali, E., Ullman, S.: Combining class-specific fragments for object classification. In: Pridmore, T.P., Elliman, D. (eds.) BMVC, British Machine Vision Association (1999)
Zhu, J., von der Malsburg, C.: Learning control units for invariant recognition. Neurocomputing 52–54, 447–453 (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bouecke, J.D., Lücke, J. (2008). Learning of Neural Information Routing for Correspondence Finding. In: Kůrková, V., Neruda, R., Koutník, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5164. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87559-8_58
Download citation
DOI: https://doi.org/10.1007/978-3-540-87559-8_58
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87558-1
Online ISBN: 978-3-540-87559-8
eBook Packages: Computer ScienceComputer Science (R0)