• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2015, Vol. 37 ›› Issue (06): 1148-1153.

• 论文 • 上一篇    下一篇

人民币冠字号码识别预处理算法研究

冯博远1,任明武1,张煦尧2,杨静宇1   

  1. (1.南京理工大学计算机科学与工程学院,江苏 南京 210094;2.中国科学院自动化研究所,北京100190)
  • 收稿日期:2014-04-10 修回日期:2014-07-02 出版日期:2015-06-25 发布日期:2015-06-25
  • 基金资助:

     国家自然科学基金资助项目(60875010)

Image preprocessing for RMB serial number recognition  

FENG Boyuan1,REN Mingwu1,ZHANG Xuyao2,YANG Jingyu1   

  1. (1.School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094;
    2.Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China)
  • Received:2014-04-10 Revised:2014-07-02 Online:2015-06-25 Published:2015-06-25

摘要:

近年来,人民币冠字号码的识别受到越来越广泛的关注,其在打击经济犯罪,维持市场稳定和社会和谐等方面都具有很强的实用性和广阔的应用前景。一个稳定高效的人民币冠字码识别系统在很大程度上依赖于图像预处理的结果。提出了一套完整的人民币冠字码识别预处理方案,其中包括图像采集、倾斜校正、采集方向识别、冠字号码区域定位和二值化、字符提取等算法,并对三种冠字码区域二值化方法进行了比较和分析。实验结果表明,所提出的预处理方法精度很高,为后续的冠字码字符识别工作提供了可靠的技术保障。

关键词: 人民币冠字号码识别, 预处理, 二值化, 字符提取

Abstract:

In recent years, the research on RMB (renminbi bank note, the paper currency used in China) serial number recognition has drawn more and more attentions. It has promising applications in financial crime reduction, financial market and social stabilization. The accuracy of RMB recognition relies heavily on the image preprocessing results. In this paper, we propose an entire preprocessing system, including the steps of RMB image sampling, skew correction, identification of RMB orientation, serial number region detection and binarization, and character extraction. Experimental results demonstrate that the proposed method achieves high precision and facilitates the subsequent character recognition task.

Key words: RMB serial number recognition;preprocessing;binarizaiton;character extraction