AI-Based Automatic Vehicle Verification System for Restricted Area

Abstract

This paper presents an AI-based Automatic Number Plate Recognition (ANPR) system designed for vehicle verification in restricted areas. The system utilizes deep learning and computer vision techniques to detect and recognize vehicle license plates in real time. YOLO is employed for accurate number plate detection, while PaddleOCR is used for extracting alphanumeric characters from the detected plate region. The extracted vehicle number is then processed and compared with a predefined authorized database to determine access permission. A user-friendly dashboard provides real-time monitoring, displaying live camera feed along with instant access status indicators such as “Access Granted” or “Access Denied.” The system ensures high accuracy, fast processing, and efficient performance, making it suitable for applications such as smart parking systems, gated communities, and secure institutional environments. The proposed solution reduces manual effort and enhances security through automated decision-making.

Introduction

The text describes an AI-based Automatic Number Plate Recognition (ANPR) system designed to improve vehicle security and access control in restricted areas such as campuses, parking lots, and industrial zones. It addresses the limitations of traditional manual verification and earlier ANPR systems, which struggle with accuracy, lighting conditions, and real-time performance.

The proposed system uses a deep learning pipeline where YOLO is employed for fast and accurate number plate detection, and PaddleOCR is used to extract the text from the detected plates. The extracted number is then compared with an authorized database to decide whether to allow or deny access. A PyQt6-based interface displays the live camera feed and system status for easy monitoring.

The system follows a modular architecture consisting of input capture, detection, recognition, and verification modules, ensuring real-time processing and scalability. Overall, the approach improves accuracy, reduces manual effort, and provides a practical and automated solution for modern vehicle security management.

Conclusion

This paper presents an AI-based Automatic Number Plate Recognition (ANPR) system for efficient vehicle verification in restricted areas. The system integrates YOLOv8 for number plate detection and PaddleOCR for text recognition, enabling accurate and real-time performance. The extracted number plate is verified against an authorized database to automate access control decisions. The inclusion of a PyQt6-based interface enhances usability by providing real-time monitoring and status updates. The proposed system successfully reduces manual effort, improves accuracy, and ensures efficient vehicle verification. It provides a practical and scalable solution for modern security applications.

References

[1] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [2] PaddlePaddle Team, “PaddleOCR: Awesome multilingual OCR toolkits based on PaddlePaddle,” 2021. [3] OpenCV, “Open Source Computer Vision Library,” Available: https://opencv.org/ [4] I. Goodfellow, Y. Bengio, and A. Courville, “Deep Learning,” MIT Press, 2016. [5] A. Sharma, K. Jain, and S. Gupta, “Automatic Number Plate Recognition System using Machine Learning Techniques,” International Journal of Engineering Research and Applications, 2020. [6] S. Du, M. Ibrahim, M. Shehata, and W. Badawy, “Automatic License Plate Recognition (ALPR): A State- of-the-Art Review,” IEEE Transactions on Circuits and Systems for Video Technology, 2013. [7] Ultralytics, “YOLO Documentation,” Available: https://docs.ultralytics.com/ [8] R. Smith, “An Overview of the Tesseract OCR Engine,” Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2007. [9] W. Wang, Y. Chen, and X. Liu, “YOLOv10: Real-Time End-to-End Object Detection,” arXiv preprint arXiv:2405.14458, 2024. [10] Ultralytics, “YOLOv10 Documentation,” Available: https://docs.ultralytics.com/ [11] A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLO-Based Object Detection Models: Evolution and Performance Analysis,” 2024.

Copyright

Copyright © 2026 Shraddha Raut, Pallov Pramanik, Chetan Supare, Dhavarlal Jodh, Shriya Dahake, Harsh Mohod, Chaitanya Chambhare. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.