| 摘 要: 研究车牌识别技术时，存在着识别准确率波动较大，准确率较低等问题。为提高车牌识别准确率，提 出了一种改进的卷积神经网络算法，在卷积神经网络模型的基础上对其层次、参数进行改进，通过设置对照实验获得 较好的训练参数数值，使改进的卷积神经网络对车牌识别的准确率有一定提升。根据实验方案，对全连接神经网络、 LeNet-5，以及改进的卷积神经网络在识别准确率方面进行对比实验，实验数据表明，改进的卷积神经网络在识别准确 率方面高于全连接神经网络和LeNet-5。 |
| 关键词: 机器学习；车牌识别；卷积神经网络 |
|
中图分类号: TP183
文献标识码: A
|
| 基金项目: 国家级大学生创新创业训练项目(xcx2018001)；徐州市科技计划项目(KC16SQ178)；江苏省高等学校自然科学研究重大项目(18KJA520012). |
|
| A License Plate Recognition Method Based on Improved Convolutional Neural Network |
|
XU Shaokai,CHEN Yin,ZHAO Linjuan,JIANG Daihong
|
( Xuzhou Institute of Technology, Institute of Electrical Engineering, Xuzhou 221000, China)
|
| Abstract: In the study of license plate recognition technology,there are some problems,such as large fluctuation of recognition accuracy,low accuracy and so on.In order to improve the accuracy of license plate recognition,an improved convolutional neural network algorithm is proposed.On the basis of the convolutional neural network model,the hierarchy and parameters are optimized.Better training parameters are obtained by setting the control experiment,which enables the improved convolutional neural network to improve the accuracy of license plate recognition to a certain extent.According to the experimental scheme,a comparison experiment is carried out on the recognition accuracy of fully connected neural network,LeNet-5 and improved convolutional neural network.The experimental data shows that the improved onvolutional neural network is better than the other two neural networks in recognition accuracy |
| Keywords: machine learning;license plate recognition;convolutional neural network |
