Deep Learning-Based License Plate Recognition in Complex Environments

DOI

10.2991/978-94-6463-821-9_31How to use a DOI?

Keywords

Deep Learning; CNN; Transformers; YOLO

Abstract

The traditional method of license plate recognition has good recognition for objects in a relatively fixed position and objects with good lighting conditions, while it exhibits low robustness when dealing with varying light conditions and recognizing moving vehicles. In order to be able to accurately identify vehicles at high speeds and in complex environments, this review starts from the perspective of historical development. The deep learning algorithms represented by CNN, YOLO and Transformers and their combined application in the domain of license plate recognition are studied. By combining CNN with YOLO algorithms, the system achieves a 99.37% detection accuracy and a 98.43% overall recognition rate. The YOLO algorithm itself has an average accuracy of 98.56% for license plate detection, and Transformers can achieve an accuracy of 99% in SSIM under transformerRain100L.In conclusion, for CNN, it is recommended to develop towards optimizing their own parameters and combining them with other algorithms. High-accuracy YOLO and Transformer models can be integrated with other techniques to further enhance LPR performance.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Zechao Dai
PY  - 2025
DA  - 2025/08/31
TI  - Deep Learning-Based License Plate Recognition in Complex Environments
BT  - Proceedings of the 2025 2nd International Conference on Mechanics, Electronics Engineering and Automation (ICMEEA 2025)
PB  - Atlantis Press
SP  - 280
EP  - 291
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-821-9_31
DO  - 10.2991/978-94-6463-821-9_31
ID  - Dai2025
ER  -