大数据时代的车牌汉字识别

doi:10.3969/j.issn.1007-2861.2015.04.019

上海大学学报(自然科学版) ›› 2016, Vol. 22 ›› Issue (1): 88-96.doi: 10.3969/j.issn.1007-2861.2015.04.019

大数据时代的车牌汉字识别

沈文枫, 张建蕾, 周丁倩, 陈圣波, 邱峰

上海大学计算机工程与科学学院, 上海 200444

收稿日期:2015-11-30 出版日期:2016-02-29 发布日期:2016-02-29
通讯作者: 沈文枫(1968—), 男, 副研究员, 博士, 研究方向为并行计算、高性能计算、心电仿真计算. E-mail: wfshen@mail.shu.edu.cn
基金资助:
上海市科委资助项目(14DZ2261200)

Recognition of Chinese characters on license plates based on big data

SHEN Wenfeng, ZHANG Jianlei, ZHOU Dingqian, CHEN Shengbo, QIU Feng

School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China

Received:2015-11-30 Online:2016-02-29 Published:2016-02-29

摘要/Abstract

摘要：

在大数据时代, 交通信息成为网络数据量最大的数据来源之一, 智能交通成为必然需求. 车牌识别是智能交通的基础, 可广泛应用于车库管理、交通监控等工程中, 然而识别的准确率还有待加强, 已有算法对于字母、数字的识别准确率都非常高, 而对于中国特有的汉字识别却效果不佳. 提出用受限玻尔兹曼机组成的深信度网络算法来识别车牌字符, 大大提升了汉字识别的准确率, 使准确率达到99.44%.

关键词: 车牌汉字识别, 深度学习, 深信度网络, 受限玻尔兹曼机

Abstract:

Today, traffic provides sources of huge scale data sets on the network, calling for the development of intelligent traffic. The license plate recognition (LPR) techniques are an important basis of intelligent traffic, and widely applied in applications such as garage management and traffic monitoring. However, the current LPR algorithms are imperfect in terms of recognition accuracy. Although working well in recognizing English letters and digits, they are unsatisfactory in recognizing Chinese characters. This paper proposes a license plate recognition algorithm using a deep belief network (DBN) algorithm consisting of restricted Boltzmann machines (RBM). It greatly improves the quality of Chinese character recognition with accuracy rate up to 99.44%.

Key words: deep belief network, deep learning, license plate of Chinese character recognition, restricted Boltzmann machine

沈文枫, 张建蕾, 周丁倩, 陈圣波, 邱峰. 大数据时代的车牌汉字识别[J]. 上海大学学报(自然科学版), 2016, 22(1): 88-96.

SHEN Wenfeng, ZHANG Jianlei, ZHOU Dingqian, CHEN Shengbo, QIU Feng. Recognition of Chinese characters on license plates based on big data[J]. Journal of Shanghai University（Natural Science Edition）, 2016, 22(1): 88-96.

参考文献

[1] 王笑京, 沈鸿飞, 汪林. 中国智能交通系统发展战略研究[J]. 交通运输系统工程与信息, 2006(4): 9-12.
[2] 吴佳. 车辆牌照识别系统的设计与实现[D]. 北京: 北京交通大学, 2015.
[3] 中华人民共和国公安部. GA36—2014 中华人民共和国公共安全行业标准: 中华人民共和国机动车号牌[S]. 北京: 中国标准出版社, 2014.
[4] Wu F, Wang Y G, Hou X W. License plate character recognition based on framelet [C]// International Conference on Wavelet Analysis and Pattern Recognition. 2007: 673-676.
[5] Cheng R, Bai Y P. A novel approach for license plate slant correction, character segmentation and Chinese character recognition [J]. International Journal of Signal Processing Image Processing and Pattern Recognition, 2014, 7(1): 353-364.
[6] 汪启伟. 图像直方图特征及其应用研究[D]. 合肥: 中国科学技术大学, 2014.
[7] 蔺海峰, 马宇峰, 宋涛. 基于SIFT特征目标跟踪算法研究[J]. 自动化学报, 2010, 36(8): 1204-1208.
[8] Ciresan D, Meier U, Masci J, et al. A committee of neural networks for traffic sign classification [C]//International Joint Conference on Neural Networks. 2011: 1918-1921.
[9] Google Tessact [EB/OL]. [2015-10-19]. http://sourceforge.net/projects/tesseract-ocr/.
[10] Bengio Y, Courville A, Vincent P. Representation learning: a review and new perspectives [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 1798-1828.
[11] Bengio Y. Learning deep architectures for AI [M]//Jordan M. Foundations and trends in machine learning. Boston: Now Publishers Inc, 2009: 1-127.
[12] Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets [J]. Neural Computation, 2006, 18(7): 1527-1554.
[13] Hinton G E. Deep belief networks [J]. Scholarpedia, 2009, 4(5): 5947.
[14] Fischer A, Igel C. Training restricted Boltzmann machines: an introduction [J]. Pattern Recognition, 2014, 47(1): 25-39.
[15] Le R N, Bengio Y. Representational power of restricted Boltzmann machines and deep belief networks [J]. Neural Computation, 2008, 20(6): 1631-1649.
[16] 刘忠, 茆诗松. 分组数据的Bayes分析——Gibbs抽样方法[J]. 应用概率统计, 1997(2): 211-216.

大数据时代的车牌汉字识别

Recognition of Chinese characters on license plates based on big data

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	胡嘉成, 王向阳, 刘晗. 基于深度学习的连铸坯表面缺陷检测[J]. 上海大学学报(自然科学版), 2019, 25(4): 445-452.
[2]	谢志峰, 叶冠桦, 闫淑萁, 何绍荣, 丁友东. 基于生成对抗网络的HDR图像风格迁移技术[J]. 上海大学学报(自然科学版), 2018, 24(4): 524-534.
[3]	郎玥1, 周霁婷1, 梁小龙2, 张文俊1. 基于人脸识别的影视剧镜头自动标注及重剪系统[J]. 上海大学学报(自然科学版), 2017, 23(3): 353-363.