Abstract
This paper presents a model-based neural vision system. Scenes are described in terms of shape primitives (line segments derived from edges in the scenes) and their relational structure. The neural network matches the primitives in the scene to the primitives in a model base by finding the best agreement between primitives and their relational structure under the constraint that at most one primitive in the model base should be assigned to a primitive in the scene. The quality of the solutions and the convergence speed were both improved by using mean field approximations. This approach was tested in 2-D and in 3-D object recognition. In the 2-D problem, the recognition is independent of position, orientation, size and small perspective distortions of the objects. In the 3-D problem, stereo images are used to generate a 3-D description of the scene which is then matched against objects in a model base.
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
E. Bienenstock, C. von der Malsburg. A Neural Network for Invariant Pattern Recognition. Europhys. Lett., 4 (1), 121–126, 1987.
Eric Mjolsness, Gene Gindi, P. Anadan. Neural Optimization in Model Matching and Perceptual Organization. Neural Computation 1, 218–209, 1989.
Carsten Peterson, Bo Soederberg. A new method for mapping optimization problems onto neural networks. International Journal of Neural Systems, Vol. 1, No. 1, 1989.
Grant Shumaker, Gene Gindi, Eric Mjolsness, P. Anadan. Stickville: A Neural Net for Object Recognition via Graph Matching. Tech. Report No. 8908, Yale
Volker Tresp, Gene Gindi. Invariant Object Recognition by Inexact Subgraph Matching with Applications in Industrial Part Recognition. International Neural Network Conference, 1990, Paris, pages 95–98.
Volker Tresp. A Neural Network Approach for Three-Dimensional Object Recognition in D. S. Touretzky, R. Lippman, (eds.) Advances in Neural Information Processing Systems 3,San Mateo, CA: Morgan Kaufman.
Joachim Utans, Gene Gindi, Eric Mjolsness, P. Anadan. Neural Networks for Object Recognition within Compositional Hierarchies. Initial Experiments, Tech. Report No. 8903, Yale University, 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tresp, V. (1991). A Neural Architecture for 2-D and 3-D Vision. In: Radig, B. (eds) Mustererkennung 1991. Informatik-Fachberichte, vol 290. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-08896-8_58
Download citation
DOI: https://doi.org/10.1007/978-3-662-08896-8_58
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54597-2
Online ISBN: 978-3-662-08896-8
eBook Packages: Springer Book Archive