Contextual post-processing based on the confusion matrix in offline handwritten Chinese script recognition

被引：32

作者：

Li, YX

Tan, CL ^{[1
]}

Ding, XQ

Liu, CS

机构：

[1] Natl Univ Singapore, Dept Comp Sci, Sch Comp, Singapore 117543, Singapore

[2] Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China

来源：

PATTERN RECOGNITION | 2004年 / 37卷 / 09期

基金：

美国国家科学基金会;

关键词：

Chinese character recognition; contextual post-processing; statistical language model; confusion matrix; candidate expansion; combination; approximate word-matching;

D O I：

10.1016/j.patcog.2004.03.002

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The inclusion of potentially correct characters in candidate sets is key to improving accuracy in the recognition of Chinese scripts in the aspect of contextual post-processing. This paper presents two methods based on a confusion matrix to recall the correct characters. The first method uses original candidates to conjecture the most likely correct characters, and then combines the conjectured set with the original candidates to produce a new candidate set. The second method performs an approximate matching of adjoining characters in a sentence with Chinese words so as to recall the most likely correct character. Experimental results demonstrate the effectiveness of our proposed methods. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：1901 / 1912

页数：12