基于Faster R-CNN与BRNN的车牌识别  

License Plate Recognition Based on Faster R-CNN and BRNN

作　　者：潘安琪 门玉英[2] PAN An-qi;MEN Yu-ying(College of International Culture and Education,Heilongjiang University,Harbin 150080,China;Office of Scientific Research Management and Innovation Development,Hubei Academy of Scientific and Technological Information,Wuhan 430071,China)

机构地区：[1]黑龙江大学国际文化教育学院,黑龙江哈尔滨150080 [2]湖北省科技信息研究院科研管理与创新发展办公室,湖北武汉430071

出　　处：《软件导刊》2020年第8期49-53,共5页Software Guide

摘　　要：针对传统车牌检测方法在复杂环境下识别准确率不高且过程繁复问题,提出一种基于Faster R-CNN和BRNN统一深度神经网络的车牌识别方法。首先,使用Faster R-CNN网络进行车牌定位:先通过RPN(区域提案网络)进行候选区域提取与输出,提供粗略搜索范围,再通过分类层结合提议目标层生成的边界框坐标和其回归系数,生成所需的最终边界框;然后,将车牌识别看作序列标记问题,使用具有CTC损耗的BRNN(双向循环神经网络)用于标记其顺序特征,实现车牌字符识别。试验结果表明,该技术识别准确率高达94.5%。Aiming at the problem of low recognition accuracy and complicated process in traditional license plate detection methods in complex environments,we propose a license plate recognition method based on Faster R-CNN and BRNN unified deep neural net⁃work.First,we use the Faster R-CNN network for license plate location.Candidate regions is extracted and output through RPN(re⁃gional proposal network)to provide a rough search range;then the classification layer is combined with the bounding box coordinates generated by the proposed target layer and its regression coefficient to generate the final bounding box required.Secondly,the license plate recognition is regarded as a sequence marking problem.A BRNN(Bidirectional Recurrent Neural Network)with CTC loss is used to label its sequential features to realize the character recognition of the license plates.According to the experimental results,the recognition accuracy rate is as high as 94.5%.

关 键 词：卷积神经网络 深度学习 车牌识别 图像识别 R-CNN 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]