基于二维空间遍历长短时记忆网络的端到端车牌识别方法  

End-to-end license plate recognition method based on 2D space traversal LSTM network

作　　者：王骥 黄远甲 方炜 谢文武 熊文昌 李兴旺 WANG Ji;HUANG Yuanjia;FANG Wei;XIE Wenwu;XIONG Wenchang;LI Xingwang(College of Physical Science and Technology,Central China Normal University,Wuhan Hubei 430079,China;School of Information Science and Engineering,Hunan University of Science and Technology,Yueyang Hunan 414000,China;Shanghai Pulspread Artificial Intelligence Technology Company Limited,Shanghai 200032,China;School of Physics and Electronic Information Engineering,Henan Polytechnic University,Jiaozuo Henan 454000,China)

机构地区：[1]华中师范大学物理科学与技术学院,武汉430079 [2]湖南理工学院信息科学与工程学院,湖南岳阳414000 [3]上海脉衍人工智能科技有限公司,上海200032 [4]河南理工大学物理与电子信息学院,河南焦作454000

出　　处：《计算机应用》2024年第S2期257-261,共5页journal of Computer Applications

基　　金：国家自然科学基金资助项目(62101205);湖北省重点研发计划项目(2023BAB061)。

摘　　要：车牌识别方法是现代智能交通管理系统的重要组成部分,在许多领域得到了广泛的应用。然而,在实际应用场景中,存在多行牌照,传统方法在处理多行车牌时灵活性不够,无法实现高精度端到端识别。为此,提出一种基于二维空间遍历长短时记忆(2DST-LSTM)网络的端到端识别方法识别单行车牌和双行车牌。所提方法摒弃了以往的图像分割步骤,而以端到端的方式识别车牌,使车牌识别的效能和精度更高。2DST-LSTM可以提高车牌,尤其是双行车牌,在复杂环境下的识别效果。在多个数据集上的实验结果表明,所提方法对双行车牌的识别率最高达到了98.6%,证明了所提方法的有效性。License plate recognition method is an important part of modern intelligent traffic management system and has been widely used in many fields.However,in practical application scenarios,there are multi-row license plates,and the traditional methods are not flexible enough to deal with multi-row license plates,and cannot achieve high-precision end-to-end recognition.Therefore,an end-to-end recognition method based on 2D Space Traversal Long Short-Term Memory(2DST-LSTM)network was proposed to recognize single-row and double-row license plates.The proposed method abandons the previous image segmentation step,and carries out license plate recognition in an end-to-end way,which makes the license plate recognition more efficient and accurate.2DST-LSTM can improve the recognition effect of license plates,especially double-row license plates,in complex environment.Experimental results on multiple datasets show that the proposed method achieves the highest recognition rate up to 98.6%for double-row license plates,which verified its effectiveness.

关 键 词：车牌识别 双行车牌 端到端网络 深度学习 卷积神经网络 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]