Abstract
We present a neural implementation of a dynamical network hierarchy for data driven and knowledge controlled selective visual attention. The model architecture is composed of several interacting subsystems for different processing tasks. With the example of real-world scene analysis the proposed model demonstrates its abilities in preattentive search and in decomposition of a complex visual input into a sequence of striking local input segments. Based on its functional architecture our model is able to shift its focus of attention both driven by the input data and controlled by its internal processing state and the already acquired knowledge.
Supported by the German Federal Department of Research and Technology (BMFT), Grant No. 413–5839–01 IN 101D — NAMOS-Project
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
Koerner, E., Tsuda, L., Shimizu, H. Parallel in Sequence-Towards the Architecture of an Cortical Processor. In Parallel Algorithms and Architectures, Akad.-Verl. Berlin 1987, 37–47
Koerner, E., Boehme, H.-J. Organization of an Episodic Knowledge Data Base. In Proceedings of ICANN91, vol. 1, pp.873–878, North-Holland 1991
Koch, C., Ulimann, S. Shifts in selective visual attention: towards the underlying neural circuitry. Human Neurobiology 4(1985) p. 219–227
Orban, G.A. Neural operations in the visual cortex. Springer Bln., Hdbg., NY, Tokyo 1984
Giefing, G.-J., Janßen, H., Mallot, H.-P.A. Saccadic Camera Movement System for Object Recognition. In Proceedings of ICANN91, vol. 1, pp.63–68, North-Holland 1991
Dow, B.M. Colour Vision. In Vision and Visual Dysfunction, Vol. 4, The Neural Basis of Visual Function, (Ed.) G. Leventhal, pp. 316–338, The Macmillan Press, 1991
Gross, H.-M., Koerner, E., Pomierski, T. GNOM—A Modular Network Architecture for Adaptive Parallel-Sequential Pattern Recognition. Proc. of ICANN91, vol. 1, 747–752, North-Holland 1991
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gross, HM., Franke, R., Boehme, HJ., Beck, C. (1992). A Neural Network Hierarchy for Data Driven and Knowledge Controlled Selective Visual Attention. In: Fuchs, S., Hoffmann, R. (eds) Mustererkennung 1992. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-77785-1_43
Download citation
DOI: https://doi.org/10.1007/978-3-642-77785-1_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55936-8
Online ISBN: 978-3-642-77785-1
eBook Packages: Springer Book Archive