A neural network approach to handprint character recognition
L. D. Jackel, C.E. Stenard, Henry S. Baird, Bernhard E. Boser, Jane M. Bromley, Christopher J. C. Burges, John S. Denker, Hans Peter Graf, D. Henderson, Richard E. Howard, W. Hubbard, Yann LeCun, O. Matan, Edwin Pednault, W.D. Satterfield, Eduard Säckinger, T. Thompson · 2002
The authors outline OCR (optical character recognition) technology developed at AT&T Bell Laboratories, including a recognition network that learns feature extraction kernels and a custom VLSI chip that is designed for neural-net image processing. It is concluded that both high speed and high accuracy can be obtained using neural-net methods for character recognition. Networks can be designed that learn their own feature extraction kernels. Special-purpose neural-net chips combined with digital signal processors can quickly evaluate character-recognition neural nets. This high speed is particularly useful for recognition-based segmentation of character strings.>