Handwritten zip code recognition with multilayer networks

Y. Le Cun; O. Matan; B. Boser; J. S. Denker; D. Henderson; R. E. Howard; W. Hubbard; L. D. Jackel; H. S. Baird

Handwritten zip code recognition with multilayer networks

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

Computer Science

Research output: Contribution to journal › Conference article › peer-review

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 language	English (US)
Pages (from-to)	35-40
Number of pages	6
Journal	Proceedings - International Conference on Pattern Recognition
Volume	2
State	Published - 1990
Event	Proceedings of the 10th International Conference on Pattern Recognition - Atlantic City, NJ, USA Duration: Jun 16 1990 → Jun 21 1990

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Cite this

@article{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 = "{Le Cun}, Y. 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",

journal = "Proceedings - International Conference on Pattern Recognition",

issn = "1051-4651",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "Proceedings of the 10th International Conference on Pattern Recognition ; Conference date: 16-06-1990 Through 21-06-1990",

}

TY - JOUR

T1 - Handwritten zip code recognition with multilayer networks

AU - Le Cun, Y.

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 article

AN - SCOPUS:0025556967

SN - 1051-4651

VL - 2

SP - 35

EP - 40

JO - Proceedings - International Conference on Pattern Recognition

JF - Proceedings - International Conference on Pattern Recognition

T2 - Proceedings of the 10th International Conference on Pattern Recognition

Y2 - 16 June 1990 through 21 June 1990

ER -

Handwritten zip code recognition with multilayer networks

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this