Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (7): 2014-2018.DOI: 10.11772/j.issn.1001-9081.2017.07.2014

Previous Articles     Next Articles

Character recognition of license plate based on convolution neural network

DONG Junfei, ZHENG Bochuan, YANG Zejing   

  1. College of Mathematics and Information, China West Normal University, Nanchong Sichuan 637009, China
  • Received:2017-01-13 Revised:2017-03-03 Online:2017-07-10 Published:2017-07-18
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (11401480), the Innovation Team of China West Normal University (CXTD2014-4), the Technological Innovation Miaozi Cultivate Project of Sichuan Province (2016033), the University Student Innovation and Entrepreneurship Project of Sichuan Province (201710638022), the University Student Innovation and Entrepreneurship Project of China West Normal University (CXCY2016004)

基于卷积神经网络的车牌字符识别

董峻妃, 郑伯川, 杨泽静   

  1. 西华师范大学 数学与信息学院, 四川 南充 637009
  • 通讯作者: 郑伯川
  • 作者简介:董峻妃(1993-),女,四川南充人,硕士研究生,CCF会员,主要研究方向:机器学习;郑伯川(1974-),男,四川自贡人,教授,博士,CCF会员,主要研究方向:人工神经网络、深度学习、计算机视觉;杨泽静(1993-),女,四川南充人,硕士研究生,主要研究方向:机器学习。
  • 基金资助:
    国家自然科学基金资助项目(11401480);西华师范大学校级创新团队项目(CXTD2014-4);四川省科技创新苗子培育项目(2016033);四川省大学生创新创业项目(201710638022);西华师范大学大学生创新创业项目(CXCY2016004)。

Abstract: Character recognition of license plate is an important component of an intelligent license plate recognition system. Both the number of categories and the complexity of background of license plate character affected the correct recognition rate. A character recognition method of license plate based on Convolution Neural Network (CNN) was proposed for improving the correct recognition rate. Firstly, the simple shape structures of license plate characters were obtained through image preprocessing which included image size normalization, image denoising, image binarization, image thinning, and character centering. Secondly, the preprocessed character images were trained and recognized by the proposed CNN model. The experimental results show that the correct recognition rate of the proposed method can reach 99.96%, which is better than the other three compared methods. It is demonstrated that the proposed CNN method has good recognition performance for the license plate character, and can meet the practical application requirements.

Key words: deep learning, license plate character recognition, Convolutional Neural Network (CNN), intelligent transportation, image preprocessing

摘要: 车牌字符识别是智能车牌识别系统中的重要组成部分。针对车牌字符类别多、背景复杂影响正确识别率的问题,提出了一种基于卷积神经网络(CNN)的车牌字符识别方法。首先对车牌字符图像进行大小归一化、去噪、二值化、细化、字符区域居中等预处理,去除复杂背景,得到简单的字符形状结构;然后,利用所提出的CNN模型对预处理后的车牌字符集进行训练、识别。实验结果表明,所提方法能够达到99.96%的正确识别率,优于其他三种对比方法。说明所提出的CNN方法对车牌字符具有很好的识别性能,能满足实际应用需求。

关键词: 深度学习, 车牌字符识别, 卷积神经网络, 智能交通, 图像预处理

CLC Number: