Abstract
A prototype based hierarchical classifier is established as a link between subsymbolic and symbolic data processing. During learning the classifier generates a hierarchy of prototypes. These prototypes constitute a taxonomy of objects. By assigning confidence values to the prototypes a classification request may also return symbols with confidence values.
For performance evaluation the classifier was applied to the task of visual object categorization on two data sets, one real-world and one artificial. Orientation histograms on subimages were utilized as features. The hierarchy generated proved to be very stable across the different cross-validation runs. With the currently very simple feature extraction method, classification accuracies of about 80% to 90% were attained.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
C.M. Bishop. Neural Networks for Pattern Recognition. Clarendon Press, Oxford, 1995.
Leo Breiman,J. H Friedman,R A Olshen, and C. J. Stone.Classification and Regression TreesWadsworth Publishing Company, Belmont, California, U.S.A., 1984
T. Kohonen. Self Organizing Maps. Springer Verlag, 1995.
G. Palm and G. Kraetzschmar. SFB 527: Integration symbolischer und subsymbolischer In- formationsverarbeitung in adaptiven sensorimotorischen Systemen. In M. Jarke, K. Pasedach, and K. Pohl, editors, Informatik’97 – Informatik als Innovationsmotor, pages 111–120. Springer Verlag, 1997.
Persistence of vision raytracer (pov-ray). Webpage. http://www.povray.org/.
M. Roth and W.T. Freeman. Orientation histograms for hand gesture recognition. Technical Report 94–03, Mitsubishi Electric Research Laboratorys, Cambridge Research Center, 1995.
J. Schürmann. Pattern Classification. Wiley, New York, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kestler, H.A., Simon, S., Baune, A., Hagenbuchner, M., Schwenker, F., Palm, G. (1999). A Hierarchical Neural Object Classifier for Subsymbolic-Symbolic Coupling. In: Förstner, W., Buhmann, J.M., Faber, A., Faber, P. (eds) Mustererkennung 1999. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60243-6_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-60243-6_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66381-2
Online ISBN: 978-3-642-60243-6
eBook Packages: Springer Book Archive