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

Quen Zong Wu, Yann Le Cun, 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
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

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume4
ISSN (Print)0271-4310

Other

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

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'On-line recognition of limited-vocabulary Chinese character using multiple convolutional neural networks'. Together they form a unique fingerprint.

  • Cite this

    Wu, Q. Z., Cun, Y. L., 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 (pp. 2435-2438). (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 4). Publ by IEEE.