Abstract
We present ail architecture for object recognition based on artificial neural networks (ANN). The system can be trained on the holistic recognition of wooden toy pieces and aggregates composed of these pieces. However, the more complex aggregates become, the more difficult becomes holistic recognition. Therefore, after a “first glance” hypothesis by the holistic recognition module, the aggregate must be inspected visually for the single components. This can be done by a specialized holistic system, which is able to detect the basic toy pieces even within an aggregate. Another ANN, that can be looked upon as a model of the aggregate, can decide whether the geometric relations between the components found are correct. This approach is a step towards the integration of specialized holistic recognition modules to a recognition system for more complex aggregates.
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
G. Heidemann, F. Kümmert, H. Hitter, and G. Sagerer. A hybrid object recognition architecture. In Proceedings of ICANN 96. Springer Verlag, 1996. To appear.
G. Heidemann and H. Ritter. A Neural 3-D Object Recognition Architecture Using Optimized Gabor Filters. In Proceedings of 13th International Conference on Pattern Recognition, Vienna. IEEE Computer Society Press, 1996. To appear.
T. Kohonen. Self-organization and associative memory. In Springer Series in Information Sciences 8. Springer Verlag Heidelberg, 1984.
R. Moratz, G. Heidemann, S. Posch, H. Ritter, and G. Sagerer. Representing procedural knowledge for semantic networks using neural nets. In Proc. 9th Scandinavian Conference on Image Analysis, Uppsala, 1995.
H. Ritter. Parametrized self-organizing maps. In S. Gielen and B. Kappen, editors, ICANN93-Proceedings, Amsterdam, pages 568–575, Berlin, 1993. Springer Verlag.
H. Ritter, G. Sagerer, G. Heidemann, and R. Moratz. Hybride Wissensrepräsentation: neuronale und semantische Netzwerke für die Bildanalyse. In Arbeits- und Ergebnisbericht, pages 27–65. Universität Bielefeld, SFB 360, 1995.
H.J. Ritter, T.M. Martinetz, and K.J. Schulten. Neuronale Netze. Addison-Wesley, München, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Heidemann, G., Ritter, H. (1996). A Neural Recognition Architecture for Composed Objects. In: Jähne, B., Geißler, P., Haußecker, H., Hering, F. (eds) Mustererkennung 1996. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-80294-2_49
Download citation
DOI: https://doi.org/10.1007/978-3-642-80294-2_49
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61585-9
Online ISBN: 978-3-642-80294-2
eBook Packages: Springer Book Archive