A neural network approach to handprint character recognition

Author

Jackel, L.D. ; Stenard, C.E. ; Baird, H.S. ; Boser, B. ; Bromley, J. ; Burges, C.J.C. ; Denker, J.S. ; Graf, H.P. ; Henderson, D. ; Howard, R.E. ; Hubbard, W. ; LeCun, Y. ; Matan, O. ; Pednault, E. ; Satterfield, W. ; Sackinger, E. ; Thompson, T.

Author_Institution

AT&T Bell Lab., Holmdel, NJ, USA

fYear

1991

fDate

Feb. 25 1991-March 1 1991

Firstpage

472

Lastpage

475

Abstract

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.<>

Keywords

VLSI; computerised picture processing; neural nets; optical character recognition; custom VLSI chip; digital signal processors; feature extraction kernels; handprint character recognition; neural network approach; neural-net image processing; optical character recognition; recognition-based segmentation; special purpose neural net chips; Character recognition; Feature extraction; High speed optical techniques; Image recognition; Kernel; Neural networks; Optical character recognition software; Optical computing; Optical fiber networks; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Compcon Spring '91. Digest of Papers

Conference_Location

San Francisco, CA, USA

Print_ISBN

0-8186-2134-6

Type

conf

DOI

10.1109/CMPCON.1991.128851

Filename

128851