摘要
近年,随着家用车辆的不断增多,交通管制已成为当前国家亟待解决的一个重要问题.考虑到传统车牌识别系统识别率低的缺陷,本文针对车牌图像识别方面提出了一种基于深度学习卷积神经网络的车牌识别技术.实验表明,通过该方案进行的车牌识别在识别率和实用方面都具有较高的价值.
In recent years,with the increase of domestic automobile,traffic control has become an urgent problem to be solved.In view of some problems in the existing license plate recognition system,this paper proposes a license plate recognition technology based on deep learning neural network.The experiment shows that the license plate recognition is of high value in recognition rate and practical aspect.
作者
白璐
衣姝颖
李天平
Bai lu;Yi Shuying;Li Tianping(School of Physics and Electronics,Shandong Normal University,250358,Jinan,China)
出处
《山东师范大学学报（自然科学版）》
CAS
2018年第4期438-442,共5页
Journal of Shandong Normal University(Natural Science)
基金
山东省科技发展计划资助项目(2018GGX106008)
关键词
图像预处理
车牌定位
车牌字符识别
卷积神经网络
mage preprocessing
license plate location
license plate character recognition
convolutional neural network
