›› 2015, Vol. 28 ›› Issue (10): 72-.

• 论文 • 上一篇    下一篇



  1. (上海理工大学 光电信息与计算机工程学院,上海 200093)
  • 出版日期:2015-10-15 发布日期:2015-10-29
  • 作者简介:魏赟(1976—),女,博士,副教授。研究方向:智能交通控制,分布式系统。方玉玲(1990—),女,硕士研究生。研究方向:计算机视觉,图像处理。E-mail:forwardfyl@163.com
  • 基金资助:

Character Image Feature Extraction Method Based on Secondary Grid

FANG Yuling,WEI Yun   

  1. (School of Opto-electronic Information and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)
  • Online:2015-10-15 Published:2015-10-29

摘要: 为了提高字符识别率,克服传统字符特征提取方法复杂、计算量大等问题。文中提出了一种基于二次网格化的字符特征提取方法。将字符二值图像划分为4个网格,提取出字符轮廓的曲率特征;并将字符图像划分为32个网格,依次提取出各自网格的占空比、质心、散度3组特征。该方法兼具结构特征与统计特征的优点,对笔画结构相近的字符较易于区分,该方法抗干扰能力强,且足够稳定。通过对1 500张字符二值图像进行实验,其结果表明,该方法对字母与数字的识别准确率达到了97%以上,相较于其他特征提取方法有大幅提高。

关键词: 字符识别, 特征提取, 网格化, 归一化

Abstract: Traditional character feature extraction methods have such shortcomings as complexity,large calculating and low degree of differentiation.In order to improve the rate of license plate character recognition and overcome the presented drawbacks,this paper introduces a grid-based secondary character feature extraction method.Firstly,the normalized character images of license plate are divided into four grids and the curvature feature is extracted;secondly,the normalized character images are divided into 32 grids,followed by the extraction of the duty ratio of character pixels,center of mass,divergence,three quantitative characteristics to describe each grid.This method combines the advantages of structural feature and statistical feature.It is easier to distinguish characters which are similar in structure of strokes.What's more,it has strong anti-interference ability and enough stability.Features from 1500 different types of normalized character binary images are extracted by different feature extraction methods.The results show that the recognition accuracy of letters and numbers can reach more than 97% by the proposed method,a significant improvement over that achieved by other methods.

Key words: character recognition;feature extraction;gridding;normalization


  • TP391.41