信函上英文地址的自动识别和翻译

华东师范大学学报(自然科学版) ›› 2008, Vol. 2008 ›› Issue (3): 83-91.

信函上英文地址的自动识别和翻译

屠晓¹, 陈国跃², 吕岳¹

1. 华东师范大学计算机科学与技术系, 上海 200062; 2. 秋田县立大学电子与信息系统系,日本秋田 015-0055

收稿日期:2007-09-13 修回日期:2008-02-03 出版日期:2008-05-25 发布日期:2008-05-25
通讯作者: 吕岳

Automatic recognition and translation of english address on postal mails(Chinese)

TU Xiao¹, CHEN Guo-yue², LU Yue¹

1. Department of Computer Science and Technology, East China Normal University, Shanghai 200062, China; 2. Department of Electronics and Information Systems, Akita Prefectural University, Akita 015-0055, Japan

Received:2007-09-13 Revised:2008-02-03 Online:2008-05-25 Published:2008-05-25
Contact: LU Yue

摘要/Abstract

摘要：

根据地址的语言特性，定义和归纳了适用于邮政信函英文地址自动识别和翻译的用语规则.针对由字符识别技术获得的信函地址，提出了一种基于非精确字符串匹配技术的地址翻译方法，自动识别出英文地址并翻译成中文.实验结果验证了该方法的有效性，能较好地减少识别错误带来的影响，提高系统的翻译性能.

关键词: 非精确匹配, 基于规则, 地址识别, 地址翻译, OCR, 非精确匹配, 基于规则, 地址识别, 地址翻译, OCR

Abstract:

According to the characteristics of the language used in address, rules different from those of natural languages were defined and applied to automatically recognize and translate English address on postal mails. To deal with the address got from Optical Character Recognition, an English-to-Chinese address translation method based on inexact string matching technology was proposed to recognize English address and translate it into Chinese. The experimental results showed that the present method is capable of reducing the influence of OCR error, and improving the translation performance.

Key words: rule-based, address recognition, address translation, OCR, inexact matching, rule-based, address recognition, address translation, OCR

中图分类号:

TP391.2

屠晓;陈国跃;吕岳. 信函上英文地址的自动识别和翻译[J]. 华东师范大学学报(自然科学版), 2008, 2008(3): 83-91.

TU Xiao;CHEN Guo-yue;LU Yue. Automatic recognition and translation of english address on postal mails(Chinese)[J]. Journal of East China Normal University(Natural Sc, 2008, 2008(3): 83-91.