A Comparative Study on Thai License Plate Recognition: Object Detection and Transformer Learning Approaches

Car theft remains a significant issue in Thailand, necessitating advanced security solutions. This research investigates the application of license plate recognition (LPR) technology using deep learning models for vehicle and license plate detection, as well as both YOLO and Transformer models for c...

Full description

Saved in:
Bibliographic Details
Main Authors: Kwankamon Dittakan, Jirawat Thaenthong, Thanakorn Prasomkit
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11021500/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849320421132861440
author Kwankamon Dittakan
Jirawat Thaenthong
Thanakorn Prasomkit
author_facet Kwankamon Dittakan
Jirawat Thaenthong
Thanakorn Prasomkit
author_sort Kwankamon Dittakan
collection DOAJ
description Car theft remains a significant issue in Thailand, necessitating advanced security solutions. This research investigates the application of license plate recognition (LPR) technology using deep learning models for vehicle and license plate detection, as well as both YOLO and Transformer models for character recognition. Experimental results demonstrate that YOLOv5nu achieved a high Mean Average Precision (mAP) of 0.995 for license plate detection, while the Transformer model excelled in character recognition with an accuracy of 0.9108 and a loss of 0.0326. Despite these promising results, the models faced limitations in low-light conditions and complex plate layouts, affecting detection accuracy. Future work should focus on enhancing the models’ adaptability to real-world environments, expanding datasets to include diverse scenarios, and improving robustness against environmental variations. These findings underscore the potential of AI-driven LPR systems in advancing vehicle security technology.
format Article
id doaj-art-91e664a37a1d423386aa094e7146b79e
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-91e664a37a1d423386aa094e7146b79e2025-08-20T03:50:06ZengIEEEIEEE Access2169-35362025-01-0113998029981510.1109/ACCESS.2025.357581111021500A Comparative Study on Thai License Plate Recognition: Object Detection and Transformer Learning ApproachesKwankamon Dittakan0https://orcid.org/0000-0002-0097-8610Jirawat Thaenthong1https://orcid.org/0000-0001-9341-0524Thanakorn Prasomkit2College of Computing, Prince of Songkla University, Phuket, ThailandCollege of Computing, Prince of Songkla University, Phuket, ThailandCollege of Computing, Prince of Songkla University, Phuket, ThailandCar theft remains a significant issue in Thailand, necessitating advanced security solutions. This research investigates the application of license plate recognition (LPR) technology using deep learning models for vehicle and license plate detection, as well as both YOLO and Transformer models for character recognition. Experimental results demonstrate that YOLOv5nu achieved a high Mean Average Precision (mAP) of 0.995 for license plate detection, while the Transformer model excelled in character recognition with an accuracy of 0.9108 and a loss of 0.0326. Despite these promising results, the models faced limitations in low-light conditions and complex plate layouts, affecting detection accuracy. Future work should focus on enhancing the models’ adaptability to real-world environments, expanding datasets to include diverse scenarios, and improving robustness against environmental variations. These findings underscore the potential of AI-driven LPR systems in advancing vehicle security technology.https://ieeexplore.ieee.org/document/11021500/Object detectiondeep learningimage analysistransformer learninglicense plate
spellingShingle Kwankamon Dittakan
Jirawat Thaenthong
Thanakorn Prasomkit
A Comparative Study on Thai License Plate Recognition: Object Detection and Transformer Learning Approaches
IEEE Access
Object detection
deep learning
image analysis
transformer learning
license plate
title A Comparative Study on Thai License Plate Recognition: Object Detection and Transformer Learning Approaches
title_full A Comparative Study on Thai License Plate Recognition: Object Detection and Transformer Learning Approaches
title_fullStr A Comparative Study on Thai License Plate Recognition: Object Detection and Transformer Learning Approaches
title_full_unstemmed A Comparative Study on Thai License Plate Recognition: Object Detection and Transformer Learning Approaches
title_short A Comparative Study on Thai License Plate Recognition: Object Detection and Transformer Learning Approaches
title_sort comparative study on thai license plate recognition object detection and transformer learning approaches
topic Object detection
deep learning
image analysis
transformer learning
license plate
url https://ieeexplore.ieee.org/document/11021500/
work_keys_str_mv AT kwankamondittakan acomparativestudyonthailicenseplaterecognitionobjectdetectionandtransformerlearningapproaches
AT jirawatthaenthong acomparativestudyonthailicenseplaterecognitionobjectdetectionandtransformerlearningapproaches
AT thanakornprasomkit acomparativestudyonthailicenseplaterecognitionobjectdetectionandtransformerlearningapproaches
AT kwankamondittakan comparativestudyonthailicenseplaterecognitionobjectdetectionandtransformerlearningapproaches
AT jirawatthaenthong comparativestudyonthailicenseplaterecognitionobjectdetectionandtransformerlearningapproaches
AT thanakornprasomkit comparativestudyonthailicenseplaterecognitionobjectdetectionandtransformerlearningapproaches