Conference paper
Automatic extraction of strokes by quadratic neural nets
[Proceedings 1992] IJCNN International Joint Conference on Neural Networks, Vol.1, pp.559-564
IEEE
International Joint Conference on Neural Networks, IJCNN 92 (Baltimore, MD, USA, 07/07/1992–11/07/1992)
1992
Abstract
The authors present a preliminary exploration of some ideas from syntactic pattern recognition theory and some insights of D.A. Marr (1970). The use of quadratic neural nets for the automatic extraction of strokes is examined. The concrete problem of optical character recognition (OCR) of handwritten characters is considered. That human OCR of cursive script entails both upwriting and downwriting into strokes and presumably other structures is eminently plausible, as an examination of the differences between human and machine OCR makes clear. That this is accomplished by arrays of neurons in the central nervous system is indisputable
Details
- Title
- Automatic extraction of strokes by quadratic neural nets
- Authors/Creators
- M.D. Alder (Author/Creator) - The University of Western AustraliaY. Attikiouzel (Author/Creator) - The University of Western Australia
- Publication Details
- [Proceedings 1992] IJCNN International Joint Conference on Neural Networks, Vol.1, pp.559-564
- Conference
- International Joint Conference on Neural Networks, IJCNN 92 (Baltimore, MD, USA, 07/07/1992–11/07/1992)
- Publisher
- IEEE
- Identifiers
- 991005543135007891
- Copyright
- © 1992 IEEE
- Murdoch Affiliation
- Murdoch University
- Language
- English
- Resource Type
- Conference paper
Metrics
123 File views/ downloads
39 Record Views