| 基于Faster R-CNN的车牌识别算法 |
| |
| 引用本文： | 王燕,张继凯,尹乾.基于Faster R-CNN的车牌识别算法[J].北京师范大学学报(自然科学版),2020,56(5):647-653. |
| |
| 作者姓名： | 王燕 张继凯 尹乾 |
| |
| 作者单位： | 1.北京师范大学人工智能学院，100875，北京 |
| |
| 基金项目： | 国家重点研发计划资助项目（2018AAA0100203）；内蒙古科技大学创新基金资助项目（2017QDL-B19）；内蒙古自治区自然科学基金资助项目（2018MS06019，2019BS06005） |
| |
| 摘 要： | 针对传统车牌检测方法定位不准确、检测结果易受环境影响的问题，提出一种基于Faster R-CNN和Inception ResNet_v2的车牌检测算法:通过迁移学习的方式实现精确的车牌定位，用像素点统计法处理车牌图像，实现单个字符的有效提取；mLeNet5卷积神经网络模型用于对单字符进行识别。结果表明，算法对有遮挡及角度倾斜的车牌字符能实现高效、高精确度的识别.
|
| 关 键 词： | 卷积神经网络 车牌检测 字符识别 |
| 收稿时间： | 2019-09-10 |
License plate recognition algorithm based on Faster R-CNN |
| |
| Affiliation: | 1.School of Artificial Intelligence, Beijing Normal University, 100875, Beijing, China2.School of Information Engineering, Inner Mongolia University of Science&Technology, 014010, Baotou,Inner Mongolia, China |
| |
| Abstract: | Problems such as inaccurate positioning,and location uncertainty in traditional license plate detection were alleviated by license plate detection algorithms Faster R-CNN and Inception ResNet v2. Accurate location of license plate is now achieved with transfer learning. License plate processing entails pixel counting to effectively extract single character. Single character recognition is then done by mLeNet5 convolutional neural network. Character images are collected under complex conditions including partial occlusion or tilt. Experiments show that this algorithm is effective and accurate. |
| |
| Keywords: | |
|
| 点击此处可从《北京师范大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《北京师范大学学报(自然科学版)》下载全文 |
