计算机应用 ›› 2012, Vol. 32 ›› Issue (07): 1906-1909.DOI: 10.3724/SP.J.1087.2012.01906

• 图形图像技术 • 上一篇    下一篇

基于游程特征的选票符号识别方法

张晶晶,肖刚,张元鸣,陆佳炜,徐俊   

  1. 浙江工业大学 计算机科学与技术学院,杭州310023
  • 收稿日期:2012-01-03 修回日期:2012-02-27 发布日期:2012-07-05 出版日期:2012-07-01
  • 通讯作者: 张晶晶
  • 作者简介:张晶晶(1987-),男,河南周口人,硕士研究生,主要研究方向:图形图像处理;肖刚(1965-),男,浙江上虞人,教授,博士,主要研究方向:图形图像处理、智能信息系统;张元鸣(1977-),男,河南濮阳人,副教授,博士,主要研究方向:软件体系结构。
  • 基金资助:

    浙江省科技厅公益项目(2010C31002)

Recognition approach for ballot symbol based on run features

ZHANG Jing-jin,XIAO Gang,ZHANG Yuan-ming,LU Jia-wei,XU Jun   

  1. College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou Zhejiang 310023, China
  • Received:2012-01-03 Revised:2012-02-27 Online:2012-07-05 Published:2012-07-01
  • Contact: ZHANG Jing-jin

摘要: 选票符号识别是基于图像理解的计票系统的关键技术,为提高选票符号识别的正确率,提出了一种基于游程特征的选票符号识别方法。首先给出了选票符号游程特征的定义,构建了选票符号的游程判定模型;然后利用三叉树结构描述了游程区域之间的相对位置关系;此外,通过游程区域的合并实现了噪声环境下主游程区域的提取,并对歧义符号的处理方法进行了研究;最后,实验结果表明,游程特征能够准确描述选票符号的几何特征,所给出的算法细分能力强,识别正确率高,比基于模板匹配的算法的正确率提高了6.07%。

关键词: 选举计票, 选票符号识别, 游程特征

Abstract: Recognition of hand-written ballot symbols is crucial in vote-counting system based on image understanding. To improve the accuracy of ballot symbol recognition, a symbol recognition approach based on run feature was proposed. Firstly, the concept of run was presented and a discriminant model was established based on run features of ballot symbols. Secondly, the relative positions of runs were described with a ternary tree. In addition, the main run regions were extracted in noisy environment by merging run regions, and an approach of recognizing ambiguous symbols was also given. Finally, the experimental results show that the run features can accurately reflect the geometrical features of ballot symbols. The proposed approach achieves high accuracy, and its accuracy is 6.07% higher than that of template matching algorithm.

Key words: vote-counting, ballot symbol recognition, run feature

中图分类号: