Handwritten zip code recognition with multilayer networks

Yann LeCun, O. Matan, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, L. D. Jackel, H. S. Baird

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

Abstract

An application of back-propagation networks to handwritten zip-code recognition is presented. Minimal preprocessing of the data is required, but the architecture of the network is highly constrained and specifically designed for the task. The input of the network consists of size-normalized images of isolated digits. The performance on zip-code digits provided by the US Postal Service is 92% recognition, 1% substitution, and 7% rejects. Structured neural networks can be viewed as statistical methods with structure which bridge the gap between purely statistical and purely structural methods.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Pattern Recognition
PublisherPubl by IEEE
Pages35-40
Number of pages6
Volume2
StatePublished - 1990
EventProceedings of the 10th International Conference on Pattern Recognition - Atlantic City, NJ, USA
Duration: Jun 16 1990Jun 21 1990

Other

OtherProceedings of the 10th International Conference on Pattern Recognition
CityAtlantic City, NJ, USA
Period6/16/906/21/90

Fingerprint

Postal services
Backpropagation
Statistical methods
Multilayers
Substitution reactions
Neural networks

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

LeCun, Y., Matan, O., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., ... Baird, H. S. (1990). Handwritten zip code recognition with multilayer networks. In Proceedings - International Conference on Pattern Recognition (Vol. 2, pp. 35-40). Publ by IEEE.

Handwritten zip code recognition with multilayer networks. / LeCun, Yann; Matan, O.; Boser, B.; Denker, J. S.; Henderson, D.; Howard, R. E.; Hubbard, W.; Jackel, L. D.; Baird, H. S.

Proceedings - International Conference on Pattern Recognition. Vol. 2 Publ by IEEE, 1990. p. 35-40.

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

LeCun, Y, Matan, O, Boser, B, Denker, JS, Henderson, D, Howard, RE, Hubbard, W, Jackel, LD & Baird, HS 1990, Handwritten zip code recognition with multilayer networks. in Proceedings - International Conference on Pattern Recognition. vol. 2, Publ by IEEE, pp. 35-40, Proceedings of the 10th International Conference on Pattern Recognition, Atlantic City, NJ, USA, 6/16/90.
LeCun Y, Matan O, Boser B, Denker JS, Henderson D, Howard RE et al. Handwritten zip code recognition with multilayer networks. In Proceedings - International Conference on Pattern Recognition. Vol. 2. Publ by IEEE. 1990. p. 35-40
LeCun, Yann ; Matan, O. ; Boser, B. ; Denker, J. S. ; Henderson, D. ; Howard, R. E. ; Hubbard, W. ; Jackel, L. D. ; Baird, H. S. / Handwritten zip code recognition with multilayer networks. Proceedings - International Conference on Pattern Recognition. Vol. 2 Publ by IEEE, 1990. pp. 35-40
@inproceedings{115c1d8536ae41f58117f57689709ed8,
title = "Handwritten zip code recognition with multilayer networks",
abstract = "An application of back-propagation networks to handwritten zip-code recognition is presented. Minimal preprocessing of the data is required, but the architecture of the network is highly constrained and specifically designed for the task. The input of the network consists of size-normalized images of isolated digits. The performance on zip-code digits provided by the US Postal Service is 92{\%} recognition, 1{\%} substitution, and 7{\%} rejects. Structured neural networks can be viewed as statistical methods with structure which bridge the gap between purely statistical and purely structural methods.",
author = "Yann LeCun and O. Matan and B. Boser and Denker, {J. S.} and D. Henderson and Howard, {R. E.} and W. Hubbard and Jackel, {L. D.} and Baird, {H. S.}",
year = "1990",
language = "English (US)",
volume = "2",
pages = "35--40",
booktitle = "Proceedings - International Conference on Pattern Recognition",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Handwritten zip code recognition with multilayer networks

AU - LeCun, Yann

AU - Matan, O.

AU - Boser, B.

AU - Denker, J. S.

AU - Henderson, D.

AU - Howard, R. E.

AU - Hubbard, W.

AU - Jackel, L. D.

AU - Baird, H. S.

PY - 1990

Y1 - 1990

N2 - An application of back-propagation networks to handwritten zip-code recognition is presented. Minimal preprocessing of the data is required, but the architecture of the network is highly constrained and specifically designed for the task. The input of the network consists of size-normalized images of isolated digits. The performance on zip-code digits provided by the US Postal Service is 92% recognition, 1% substitution, and 7% rejects. Structured neural networks can be viewed as statistical methods with structure which bridge the gap between purely statistical and purely structural methods.

AB - An application of back-propagation networks to handwritten zip-code recognition is presented. Minimal preprocessing of the data is required, but the architecture of the network is highly constrained and specifically designed for the task. The input of the network consists of size-normalized images of isolated digits. The performance on zip-code digits provided by the US Postal Service is 92% recognition, 1% substitution, and 7% rejects. Structured neural networks can be viewed as statistical methods with structure which bridge the gap between purely statistical and purely structural methods.

UR - http://www.scopus.com/inward/record.url?scp=0025556967&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025556967&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 35

EP - 40

BT - Proceedings - International Conference on Pattern Recognition

PB - Publ by IEEE

ER -