Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318) (1999)
Sept. 20, 1999 to Sept. 22, 1999
Masahiro Takatsuka , Ohio State University
Terry M. Caelli , Curtin University of Technology
Geoff A.W. West , Curtin University of Technology
Svetha Venkatesh , Penn State University
This paper describes object-centered symbolic representation and distributed matching strategies of 3-D objects in a schematic form which occur in engineering drawings and maps. The object-centered representation has a hierarchical structure and is constructed from symbolic representations of schematics. With this representation, two independent schematics representing the same object can be matched. We also consider matching strategies using distributed algorithms. The object recognition is carried out with two matching methods: (1)matching between an object model and observed data at the lowest level of the hierarchy, and (2) constraints propagation.The first is carried out with symbolic Hopfield-type neural networks and the second is achieved via hierarchical Winner-Takes-All algorithms.
S. Venkatesh, G. A. West, M. Takatsuka and T. M. Caelli, "Symbolic Representation and Distributed Matching Strategies for Schematics," Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318)(ICDAR), Bangalore, India, 1999, pp. 693.