计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (24): 176-177.DOI: 10.3778/j.issn.1002-8331.2009.24.052

• 图形、图像、模式识别 • 上一篇    下一篇

最小海明距离分类器的字符识别方法研究

岳俊华1,2,3,李 岩1,2,郭永飞1   

  1. 1.中国科学院 长春光学精密机械与物理研究所,长春 130033
    2.中国科学院 研究生院,北京 100039
    3.吉林建筑工程学院,长春 130021
  • 收稿日期:2008-05-09 修回日期:2008-08-01 出版日期:2009-08-21 发布日期:2009-08-21
  • 通讯作者: 岳俊华

Research of character identifying method about least Hamming distance classifier

YUE Jun-hua 1,2,3,LI Yan 1,2,GUO Yong-fei1
  

  1. 1.Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033,China
    2.Graduate School of Chinese Academy of Sciences,Beijing 100039,China
    3.Jilin Architectural and Civil Engineering Institute,Changchun 130021,China
  • Received:2008-05-09 Revised:2008-08-01 Online:2009-08-21 Published:2009-08-21
  • Contact: YUE Jun-hua

摘要: 应用最小海明距离(Hamming Distance,缩写HD)分类器,研制了一种新型的基于最小海明分类器的字符识别方法。讨论了该字符识别方法实现的技术路线,较好解决了理论的工程化应用问题,对500帧连续图像的时间字符进行实验,时间字符识别准确率为99.8%,达到了字符比较准确识别的目的。

关键词: 字符识别, 海明距离分类器, 模板索引

Abstract: This paper develops a new character identifying method applying least Hamming distance classifier system.The implementation of this character recognition method is discussed.It provides a practical approach of academic project applying.This paper does time-character identifying experiment about 500 frame continuous image,character identifying accurate rate is 99.8%. This character identifying method can pick up character accurately.It meets the purpose of accurate recognition character.

Key words: character identification, Hamming Distence classifier system, templet index

中图分类号: