Invariant character recognition in dynamic link architecture

被引：11

作者：

Liu, JNK

Lee, RST

机构：

来源：

1997 IEEE KNOWLEDGE AND DATA ENGINEERING EXCHANGE WORKSHOP, PROCEEDINGS | 1997年

关键词：

Dynamic Link Architecture; Chinese character recognition; invariant recognition; long-term and short-term memory; Neural Networks; Temporary Links;

D O I：

10.1109/KDEX.1997.629865

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A model based on the application of Dynamic Link Architecture (DLA) is presented for the off-line recognition of (Chinese characters, It is a revised DLA model employing 4-vector dynamic link assignment instead of the original 3-vector links [8], A sample set of Chinese characters was used to test the performance of the model under various transformations including translation, reflection, rotation, dilation and distortion. Challenging results are obtained. An improvement of 40% in recognition rate was attained by using the revised DLA model for Chinese character recognition. On the other hand, for the testing of invariant properties, an overall correct recognition rate of 85% was obtained under various transformations.

引用

页码：188 / 195

页数：8