A neural network approach to handprint character recognition

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationDigest of Papers - IEEE Computer Society International Conference
PublisherPubl by IEEE
Pages472-475
Number of pages4
ISBN (Print)0818621346
StatePublished - 1991
Event36th IEEE Computer Society International Conference - COMPCON Sping '91 - San Francisco, CA, USA
Duration: Feb 25 1991Mar 1 1991

Other

Other36th IEEE Computer Society International Conference - COMPCON Sping '91
CitySan Francisco, CA, USA
Period2/25/913/1/91

Fingerprint

Character recognition
Neural networks
Feature extraction
Optical character recognition
Digital signal processors
Image processing

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Jackel, L. D., Stenard, C. E., Baird, H. S., Boser, B., Bromley, J., Burges, C. J. C., ... Thompson, T. (1991). A neural network approach to handprint character recognition. In Digest of Papers - IEEE Computer Society International Conference (pp. 472-475). Publ by IEEE.

A neural network approach to handprint character recognition. / 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, Yann; Matan, O.; Pednault, E.; Satterfield, W.; Sackinger, E.; Thompson, T.

Digest of Papers - IEEE Computer Society International Conference. Publ by IEEE, 1991. p. 472-475.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Jackel, LD, Stenard, CE, Baird, HS, Boser, B, Bromley, J, Burges, CJC, Denker, JS, Graf, HP, Henderson, D, Howard, RE, Hubbard, W, LeCun, Y, Matan, O, Pednault, E, Satterfield, W, Sackinger, E & Thompson, T 1991, A neural network approach to handprint character recognition. in Digest of Papers - IEEE Computer Society International Conference. Publ by IEEE, pp. 472-475, 36th IEEE Computer Society International Conference - COMPCON Sping '91, San Francisco, CA, USA, 2/25/91.
Jackel LD, Stenard CE, Baird HS, Boser B, Bromley J, Burges CJC et al. A neural network approach to handprint character recognition. In Digest of Papers - IEEE Computer Society International Conference. Publ by IEEE. 1991. p. 472-475
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, Yann ; Matan, O. ; Pednault, E. ; Satterfield, W. ; Sackinger, E. ; Thompson, T. / A neural network approach to handprint character recognition. Digest of Papers - IEEE Computer Society International Conference. Publ by IEEE, 1991. pp. 472-475
@inproceedings{12b2f297888c456896ade685a3b6b05a,
title = "A neural network approach to handprint character recognition",
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.",
author = "Jackel, {L. D.} and Stenard, {C. E.} and Baird, {H. S.} and B. Boser and J. Bromley and Burges, {C. J C} and Denker, {J. S.} and Graf, {H. P.} and D. Henderson and Howard, {R. E.} and W. Hubbard and Yann LeCun and O. Matan and E. Pednault and W. Satterfield and E. Sackinger and T. Thompson",
year = "1991",
language = "English (US)",
isbn = "0818621346",
pages = "472--475",
booktitle = "Digest of Papers - IEEE Computer Society International Conference",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - A neural network approach to handprint character recognition

AU - Jackel, L. D.

AU - Stenard, C. E.

AU - Baird, H. S.

AU - Boser, B.

AU - Bromley, J.

AU - Burges, C. J C

AU - Denker, J. S.

AU - Graf, H. P.

AU - Henderson, D.

AU - Howard, R. E.

AU - Hubbard, W.

AU - LeCun, Yann

AU - Matan, O.

AU - Pednault, E.

AU - Satterfield, W.

AU - Sackinger, E.

AU - Thompson, T.

PY - 1991

Y1 - 1991

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0026368669&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026368669&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026368669

SN - 0818621346

SP - 472

EP - 475

BT - Digest of Papers - IEEE Computer Society International Conference

PB - Publ by IEEE

ER -