Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (29): 207-210.DOI: 10.3778/j.issn.1002-8331.2010.29.060

• 工程与应用 • Previous Articles     Next Articles

Classification for white license plate based on SVM and align modes

ZHANG Xu-guang1,2,LUO Yi-ning1,AI Bi-gang1,JIANG Tao1   

  1. 1.College of Computer Science,Sichuan University,Chengdu 610064,China
    2.Command and Engineering College of Chemical Defense of PLA,Beijing 102205,China
  • Received:2009-03-05 Revised:2009-06-02 Online:2010-10-11 Published:2010-10-11
  • Contact: ZHANG Xu-guang

基于SVM和排列模型的白色车牌分类

张旭光1,2,罗以宁1,艾必刚1,蒋 涛1   

  1. 1.四川大学 计算机学院,成都 610064
    2.防化指挥工程学院,北京 102205
  • 通讯作者: 张旭光

Abstract: Compared to the character of the blue license plate,the white license plate has own specification.The align modes of the white license plate’s ID codes are varied,so that they need to be classified alone.The white plate is classified correctly in favor of improving the accuracy of the whole system.Support Vector Machine is used to classification according to the align modes of the vehicle identity codes.Then,the extraction of ID codes is realized according to the standard align modes of the ID.Experiment results show that the proposed method has good performance.

Key words: Support Vector Machine(SVM), align modes, classification of vehicle plate

摘要: 与蓝色牌照的固定格式相比,白色牌照的字符排列方式呈现多变的特点。如果能够对白色车牌的字符进行准确分割及分类,就可以提高整个系统的识别正确率。首先根据车牌内字符间的排列方式使用支持向量机进行分类,然后根据该类车牌的标准排列模型,即可实现对车牌字符的准确分割及分类。实验结果表明,该方法正确率较高,稳定性好。

关键词: 支持向量机, 排列模型, 车牌分类

CLC Number: