摘要
车牌识别(LPR)是智能交通中关键技术之一。针对目前车牌识别技术存在的一些问题,详细分析基于BP神经网络的车牌字符识别方法,对BP神经网络收敛速度慢且容易陷入局部极小点的缺陷进行改进。经仿真实验结果表明效果良好。
License plate recognition(LPR) is one of the critical techniques for the intelligent transportation system.Focusing on the difficulties of LPR,the paper analyzes the way of character recognition algorithm based on BP neural network.Some methods are proposed to improve the convergent speed and precision of BP neural network.
出处
《山西电子技术》
2010年第5期88-90,共3页
Shanxi Electronic Technology
关键词
车牌识别
BP神经网络
字符识别
license plate recognition
BP neural network
character recognition