Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/99396
Title: Recognizing chinese characters through interactive activation and competition
Authors: Lua, K.T. 
Gan, K.W. 
Keywords: Hebbian learning
Interactive activation and competition model (IAC model)
Pattern recognition
Word context effects
Word-oriented Chinese character recognition
Issue Date: 1990
Source: Lua, K.T.,Gan, K.W. (1990). Recognizing chinese characters through interactive activation and competition. Pattern Recognition 23 (12) : 1311-1321. ScholarBank@NUS Repository.
Abstract: Most conventional approaches to Chinese character recognition attempt to recognize unknown Chinese characters per se. Hence the discriminative power of features employed play a crucial role in determining the ultimate recognition rate. However, high level linguistic knowledge such as the strong word context effects present in the Chinese language and the different frequencies of words in the daily use of the language, are not utilized in machine recognition of Chinese characters. In this paper, a word-oriented recognizer using the Interactive Activation and Competition model (IAC model) is proposed. Such a recognizer is tolerant to noise, size and font variations and it also possesses self-learning capability. © 1990.
Source Title: Pattern Recognition
URI: http://scholarbank.nus.edu.sg/handle/10635/99396
ISSN: 00313203
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

36
checked on Feb 15, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.