Logo image
Automatic extraction of strokes by quadratic neural nets
Conference paper   Open access

Automatic extraction of strokes by quadratic neural nets

M.D. Alder and Y. Attikiouzel
[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
pdf
automatic_extraction_of_strokes.pdfDownloadView
Published (Version of Record) Open Access
url
Link to Published Version *Subscription may be requiredView

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

Metrics

123 File views/ downloads
39 Record Views
Logo image