On Chinese Character Structure(CCS) Recognition Based On Bayesian learning

DOI

10.2991/iske.2007.209How to use a DOI?

Keywords

Chinese character structure representation; Feature exaction; Simple grid; Naive Bayesian; Recognition

Abstract

Chinese character structure(CCS) is too complex to be represented or recognized by computer. In literature [6], simple grid was proposed to be representation tools for CCS. In order to check effectiveness of CCS representation based on simple grid, the method of CCS recognition based on Bayesian learning is proposed by this paper. In the method, after acquiring candidate separate location between radicals under the guidance of simple gird, the optimal separate location is determined by Naive Bayesian classifier. The method proposed is simple and easy-to-use, and has good extension. The effectiveness of method proposed is proved by experimental results.

Copyright

© 2007, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Tiancai Liang
AU  - Youguo Pi
PY  - 2007/10
DA  - 2007/10
TI  - On Chinese Character Structure(CCS) Recognition Based On Bayesian learning
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 1230
EP  - 1235
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.209
DO  - 10.2991/iske.2007.209
ID  - Liang2007/10
ER  -