LPRNet Improvement for License Plate Recognition in Complex Environments
Authors: 
Haoran Yang, Yunyu Wang, Zongqiang Xia, Xiu Guo, Yuxuan Li, Ange Lucrecia Malamba Onanga, Mingtao Liu, Xin ZhangAuthors Info & Claims
Haoran Yang, Yunyu Wang, Zongqiang Xia, Xiu Guo, Yuxuan Li, Ange Lucrecia Malamba Onanga, Mingtao Liu, Xin ZhangAuthors Info & ClaimsPages 29 - 33
Abstract
LPRNet is a widely used lightweight license plate recognition model, but its recognition effect is poor when facing license plate images in complex environments. This paper finds that it can only achieve 79.0% recognition accuracy by confirming it on the CCPD2019 complex environment dataset. In this paper, an improvement scheme is proposed to enhance the recognition effect of LPRNet when facing complex environments, which firstly incorporates a multi-scale feature extraction module to increase the network sensory field and extract features at different scales. After that, the attention mechanism is integrated so that the model in this paper can focus more on the most informative and discriminative part of the license plate image. The proposed network in this paper is verified using the CCPD2019 complex environment dataset, and the recognition accuracy reaches 86.0%, which is an improvement of about 7.0% compared with the original LPRNet, while the model size is only 2.4MB, which can satisfy the requirements of embedded devices. Through comparative experiments, this paper verifies the excellent performance of the proposed network in the face of complex recognition environments.
References
[1]
Alex Graves, Santiago Fernández, Faustino Gomez, and Jürgen Schmidhuber. 2006. Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In Proceedings of the 23rd International Conference on Machine Learning (Pittsburgh, Pennsylvania, USA) (ICML ’06). Association for Computing Machinery, New York, NY, USA, 369–376.
[2]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 37, 9 (2015), 1904–1916.
[3]
Hui Li, Peng Wang, and Chunhua Shen. 2019. Toward End-to-End Car License Plate Detection and Recognition With Deep Neural Networks. IEEE Transactions on Intelligent Transportation Systems 20, 3 (2019), 1126–1136.
[4]
Longjuan Wang, Chunjie Cao, Binghui Zou, Jun Ye, and Jin Zhang. 2023. License Plate Recognition via Attention Mechanism. Computers, Materials and Continua 75, 1 (2023), 1801–1814.
[5]
Zhichao Wang, Yu Jiang, Jiaxin Liu, Siyu Gong, Jian Yao, and Feng Jiang. 2021. Research and Implementation of Fast-LPRNet Algorithm for License Plate Recognition. Journal of Electrical and Computer Engineering 2021, 1 (2021), 8592216. arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1155/2021/8592216
[6]
Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In So Kweon. 2018. CBAM: Convolutional Block Attention Module. In Computer Vision – ECCV 2018, Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer International Publishing, Cham, 3–19.
[7]
Zhenbo Xu, Wei Yang, Ajin Meng, Nanxue Lu, Huan Huang, Changchun Ying, and Liusheng Huang. 2018. Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline. In Computer Vision – ECCV 2018, Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer International Publishing, Cham, 261–277.
[8]
Yesheng Zhang, Zilei Wang, and Jiafan Zhuang. 2021. Efficient License Plate Recognition via Holistic Position Attention. Proceedings of the AAAI Conference on Artificial Intelligence 35, 4 (May 2021), 3438–3446.
[9]
Yujie Zheng, Lei Guan, and Haohong Li. 2023. The Low-light License Plate Recognition via CNN. Journal of Physics: Conference Series 2424, 1 (jan 2023), 012028.
[10]
Sergey Zherzdev and Alexey S. Gruzdev. 2018. LPRNet: License Plate Recognition via Deep Neural Networks. CoRR abs/1806.10447 (2018). arXiv:https://arXiv.org/abs/1806.10447http://arxiv.org/abs/1806.10447
Index Terms
- LPRNet Improvement for License Plate Recognition in Complex Environments
Recommendations
Research and Implementation of Fast-LPRNet Algorithm for License Plate Recognition
The license plate recognition is an important part of the intelligent traffic management system, and the application of deep learning to the license plate recognition system can effectively improve the speed and accuracy of recognition. Aiming at the ...
Research on license plate location and recognition in complex environment
AbstractAiming at the problems of license plate location difficulty and low character recognition accuracy in complex environments, such as a small number of license plate samples, illumination transformation, changeable weather and motion blur, this ...
Graph Grammar Based License Plate Recognition
ICINIS '12: Proceedings of the 2012 Fifth International Conference on Intelligent Networks and Intelligent SystemsAutomatic license plate recognition is still a challenging problem where severe imaging conditions must be handled. As compared with other formal tools, the graph grammar model is more suitable when dealing with the severe imaging conditions. In this ...
Comments
Information & Contributors
Information
Published In
July 2024
76 pages
ISBN:9798400716867
DOI:10.1145/3695719
Copyright © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 13 November 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Innovation and Business Training, Program for College Students of Linyi University, China
Conference
ICDLT 2024
ICDLT 2024: 2024 8th International Conference on Deep Learning Technologies (ICDLT)
July 15 - 17, 2024
Suzhou, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 25Total Downloads
- Downloads (Last 12 months)25
- Downloads (Last 6 weeks)8
Reflects downloads up to 27 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderFull Text
View this article in Full Text.
Full TextHTML Format
View this article in HTML Format.
HTML Format