On-line recognition of limited-vocabulary Chinese character using multiple convolutional neural networks

Quen Zong Wu, Yann LeCun, Larry D. Jackel, Bor Shenn Jeng

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

Abstract

This paper presents a new feature extraction method together with neural network recognition for on-line Chinese characters. A Chinese character can be represented by a three-dimensional 12×12×4 array of numbers. Multiple convolutional neural networks are used for on-line small vocabulary Chinese character recognition based on this feature extraction method. We choose one hundred character classes as an example for recognition. Simulation result shows that 98.8% and 94.2% of training examples and test examples are correctly recognized respectively.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Symposium on Circuits and Systems
PublisherPubl by IEEE
Pages2435-2438
Number of pages4
Volume4
ISBN (Print)0780312813
StatePublished - 1993
EventProceedings of the 1993 IEEE International Symposium on Circuits and Systems - Chicago, IL, USA
Duration: May 3 1993May 6 1993

Other

OtherProceedings of the 1993 IEEE International Symposium on Circuits and Systems
CityChicago, IL, USA
Period5/3/935/6/93

Fingerprint

Feature extraction
Neural networks
Character recognition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

Wu, Q. Z., LeCun, Y., Jackel, L. D., & Jeng, B. S. (1993). On-line recognition of limited-vocabulary Chinese character using multiple convolutional neural networks. In Proceedings - IEEE International Symposium on Circuits and Systems (Vol. 4, pp. 2435-2438). Publ by IEEE.

On-line recognition of limited-vocabulary Chinese character using multiple convolutional neural networks. / Wu, Quen Zong; LeCun, Yann; Jackel, Larry D.; Jeng, Bor Shenn.

Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 4 Publ by IEEE, 1993. p. 2435-2438.

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

Wu, QZ, LeCun, Y, Jackel, LD & Jeng, BS 1993, On-line recognition of limited-vocabulary Chinese character using multiple convolutional neural networks. in Proceedings - IEEE International Symposium on Circuits and Systems. vol. 4, Publ by IEEE, pp. 2435-2438, Proceedings of the 1993 IEEE International Symposium on Circuits and Systems, Chicago, IL, USA, 5/3/93.
Wu QZ, LeCun Y, Jackel LD, Jeng BS. On-line recognition of limited-vocabulary Chinese character using multiple convolutional neural networks. In Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 4. Publ by IEEE. 1993. p. 2435-2438
Wu, Quen Zong ; LeCun, Yann ; Jackel, Larry D. ; Jeng, Bor Shenn. / On-line recognition of limited-vocabulary Chinese character using multiple convolutional neural networks. Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 4 Publ by IEEE, 1993. pp. 2435-2438
@inproceedings{c2286ddc51914371b97b756d6d257d1e,
title = "On-line recognition of limited-vocabulary Chinese character using multiple convolutional neural networks",
abstract = "This paper presents a new feature extraction method together with neural network recognition for on-line Chinese characters. A Chinese character can be represented by a three-dimensional 12×12×4 array of numbers. Multiple convolutional neural networks are used for on-line small vocabulary Chinese character recognition based on this feature extraction method. We choose one hundred character classes as an example for recognition. Simulation result shows that 98.8{\%} and 94.2{\%} of training examples and test examples are correctly recognized respectively.",
author = "Wu, {Quen Zong} and Yann LeCun and Jackel, {Larry D.} and Jeng, {Bor Shenn}",
year = "1993",
language = "English (US)",
isbn = "0780312813",
volume = "4",
pages = "2435--2438",
booktitle = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - On-line recognition of limited-vocabulary Chinese character using multiple convolutional neural networks

AU - Wu, Quen Zong

AU - LeCun, Yann

AU - Jackel, Larry D.

AU - Jeng, Bor Shenn

PY - 1993

Y1 - 1993

N2 - This paper presents a new feature extraction method together with neural network recognition for on-line Chinese characters. A Chinese character can be represented by a three-dimensional 12×12×4 array of numbers. Multiple convolutional neural networks are used for on-line small vocabulary Chinese character recognition based on this feature extraction method. We choose one hundred character classes as an example for recognition. Simulation result shows that 98.8% and 94.2% of training examples and test examples are correctly recognized respectively.

AB - This paper presents a new feature extraction method together with neural network recognition for on-line Chinese characters. A Chinese character can be represented by a three-dimensional 12×12×4 array of numbers. Multiple convolutional neural networks are used for on-line small vocabulary Chinese character recognition based on this feature extraction method. We choose one hundred character classes as an example for recognition. Simulation result shows that 98.8% and 94.2% of training examples and test examples are correctly recognized respectively.

UR - http://www.scopus.com/inward/record.url?scp=0027308368&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027308368&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027308368

SN - 0780312813

VL - 4

SP - 2435

EP - 2438

BT - Proceedings - IEEE International Symposium on Circuits and Systems

PB - Publ by IEEE

ER -