Abstract
This paper presents a statistical approach to object recognition and scene analysis, and is motivated by semantic networks, a knowledge representation formalism that allows to represent world knowledge at different levels of abstraction. We show how this explicit knowledge representation scheme and statistical methods can be used to model objects, object groups, and scenes. The theoretical part deals with the construction of statistical models, and preliminary results demonstrate the use of these model densities for object recognition and localization in practice.
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.
Similar content being viewed by others
References
A.P. Dempster, N.M. Laird, and D.B. Rubin. Maximum Likelihood from Incomplete Data via the EM Algorithm.Journal of the Royal Statistical Society, Series B (Methodologicalj, 39(l):l–38, 1977.
R.O. Duda and P.E. Hart. Pattern Classification and Scene Analysis. J. Wiley, New York, 1972.
J. Hornegger. Statistische Modellierung, Klassifikation und Lokalisation von Objek-ten. Dissertation, Technische Fakultät, Universität Erlangen-Nürnberg, Erlangen, 1996.
H. Niemann, G. Sagerer, S. Schröder, and F. Kümmert. Ernest: A semantic network system for pattern analysis.IEEE Trans. Pattern Analysis and Machine Intelligence, 9:883–905, 1990.
M. Ross Quillian. Semantic Memory. In Marvin Minsky, editor, Semantic Information Processing, pages 216–270. MIT Press, Cambridge, 1968.
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
Hornegger, J., Nöth, E., Fischer, V., Niemann, H. (1996). Semantic Networks Meet Bayesian Classifiers. 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_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-80294-2_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61585-9
Online ISBN: 978-3-642-80294-2
eBook Packages: Springer Book Archive