摘要
我国的公路交通事业迅速地发展并与智能交通系统相辅相成,车牌识别技术是智能交通系统中的较重要的一部分,也是国内外学者们研究图像识别的热门问题。论文建立在图像预处理、车牌定位、字符分割的基础上,采用改进的BP神经网络对字符识别,添加动量因子与自适应的学习率增强识别系统的稳定性与良好的速率。实验结果表明该算法具有良好的鲁棒性和有效性,对车牌识别的准确率达到96.15%。
With the rapid development of highway transportation and intelligent transportation system of our country, license plate recognition（LPR） system is an important part of intelligent transportation system, and it is also a hot sport of domestic and foreign scholars＇ research. This paper is based on image preprocessing, license plate location and character segmentation, and charac- ter recognition is used by improving BP neural network to enhance the stability and speed of recognition system by adding momen- tum factor and adaptive learning rate. The experimental results show that the algorithm has good robustness and effectiveness, and character recognition accuracy rate reaches 96.15%.
作者
张娜
韩美林
王园园
杨琳
ZHANG Na;HAN Meilin;WANG Yuanyuan;YANG Lin(College of Electronic information and Electrical Engineering,Shangluo University,Shangluo 72600)
出处
《计算机与数字工程》
2018年第10期2094-2097,2110,共5页
Computer & Digital Engineering
基金
2017年国家自然科学基金(编号:21703135)
陕西省商洛市科技局项目(编号:sk2017-42)
陕西省体育局科研常规课题(编号:17056)资助
关键词
BP神经网络
车牌定位
字符分割
字符识别
BP neural network
license plate location
character segmentation
character recognition
