Automatic extraction of strokes by quadratic neural nets

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.<>