Abstract
Current computer systems still suffer from the inability to transform sensory image data into a meaningful symbolic description of what the image contains. It is argued that such a capability is of paramount importance for robust AI systems. As a step in that direction, several systems for the recognition of human faces and technical objects are presented. They consist of three steps: feature extraction, solving the correspondence problem (matching), and the actual comparison with stored models of known objects. Two of them are implemented in the Dynamic Link Architecture and are, therefore, close to biological hardware, the others are more technical in nature but also have some biological plausibility.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Mark Becker, Efthimia Kefalea, Eric Maёl, Christoph von der Malsburg, Mike Pagel, Jochen Triesch, Jan C. Vorbrüggen, Rolf P. Würtz, and Stefan Zadel. GripSee: A gesture-controlled robot for object perception and manipulation. Autonomous Robots, 1998. Submitted.
Irving Biedermann. Recognition-by-components: A theory of human image under-standing. Psychological Review, 94 (2): 115–147, 1987.
W. Konen and E. Schulze-Krüger. ZN-Face: A system for access control using automated face recognition. In Martin Bichsel, editor, Proceedings of IWAFGR95, Zürich, June 1995, pages 18–23, 1995.
Martin Lades, Jan C. Vorbrüggen, Joachim Buhmann, Jörg Lange, Christoph von der Malsburg, Rolf P. Würtz, and Wolfgang Konen. Distortion invariant object recognition in the dynamic link architecture. IEEE Transactions on Computers, 42 (3): 300–311, 1993.
Tino Lourens. A Biologically Plausible Model for Corner-based Object Recognition from Color Images. Shaker, Maastricht, 1998.
Tino Lourens and Rolf P. Würtz. Object recognition by matching symbolic edge graphs. In Roland Chin and Ting-Chuen Pong, editors, Computer Vision — ACCV’98, volume 1352 of Lecture Notes in Computer Science, pages II-193–II-200. Springer Verlag, 1998.
Stephen J. McKenna, Shaogang Gong, Rolf P. Würtz, Jonathan Tanner, and Daniel Banin. Tracking facial feature points with Gabor wavelets and shape models. In Josef Bigün, Gerard Chollet, and Gunilla Borgefors, editors, Proceedings of the First International Conference on Audio- and Video-based Biometrie Person Authentication Crans-Montana, Switzerland, March 1997, volume 1206 of LNCS, pages 35–42. Springer Verlag, 1997.
Paul L. Rosin. Augmenting corner descriptors. Graphical Models and Image Pro-cessing, 58 (3): 286–294, May 1996.
J. Triesch and C. von der Malsburg. A gesture interface for robotics. In FG’98, The IEEE Third International Conference on Automatic Face and Gesture Recognition, 1998. In press.
Jochen Triesch and Christoph von der Malsburg. Robust classification of hand postures against complex backgrounds. In Proceedings of the Second International Conference on Automatic Face and Gesture Recognition 1996, Killington, Vermont, USA, October 14-16, pages 170-175. IEEE Computer Society Press, 1996.
J. R. Ullman. An algorithm for subgraph isomorphism. Journal of the Association for Computing Machinery, 23 (l): 31 - 42, 1976.
Laurenz Wiskott, Jean-Marc Fellous, Norbert Krüger, and Christoph von der Malsburg. Face recognition and gender determination. In Martin Bichsei, editor, Proceedings of IWAFGR95, Zürich, June 1995, pages 92 - 97, 1995.
Laurenz Wiskott, Jean-Marc Fellous, Norbert Krüger, and Christoph von der Mals¬burg. Face recognition by elastic bunch graph matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19 (7), 1997.
Laurenz Wiskott and Christoph von der Malsburg. Face recognition by dynamic link matching. In Joseph Sirosh, Risto Miikkulainen, and Yoonsuck Choe, edi¬tors, Lateral Interactions in the Cortex: Structure and Function. The UTCS Neu¬ral Networks Research Group, Austin, TX, Electronic book, ISBN 0-9647060-0-8, http://www.cs.utexas.edu/users/nn/web-pubs/htmlbook96, 1996.
Rolf P. Würtz. Multilayer Dynamic Link Networks for Establishing Image Point Correspondences and Visual Object Recognition, volume 41 of Reihe Physik. Verlag Harri Deutsch, Thun, Frankfurt am Main, 1995.
Rolf P. Würtz. Object recognition robust under translations, deformations and changes in background. IEEE Transactions on Pattern Recognition and Machine Intelligence, 19 (7): 769–775, 1997.
Rolf P. Würtz and Tino Lourens. Corner detection in color images by multi- scale combination of end-stopped cortical cells. In Wulfram Gerstner, Alain Germond, Martin Hasler, and Jean-Daniel Nicoud, editors, Artificial Neural Networks - ICANN ’91, volume 1327 of Lecture Notes in Computer Science, pages 901–906, Berlin, Heidelberg, New York, 1997. Springer Verlag.
Rolf P. Würtz and Christoph von der Malsburg. A hierarchical dynamic link network for correspondence maps between image points. 1997. In preparation.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Würtz, R.P. (1998). Extracting Symbols from the Environment — The Concept of Correspondence-Based Object Recognition. In: Dassow, J., Kruse, R. (eds) Informatik ’98. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-72283-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-72283-7_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64938-0
Online ISBN: 978-3-642-72283-7
eBook Packages: Springer Book Archive