Abstract :

An Essential Part Of Intelligent Transportation Systems Is Vehicle License Plate Number Recognition (VLPR), Which Makes Automated Vehicle Identification Possible For Uses Including Law Enforcement, Toll Collecting, And Traffic Monitoring. Tasks Involving Object Identification And Recognition Have Improved Due To Recent Developments In Deep Learning. The Performance Of More Recent Iterations, Such As YOLOv11, YOLOv12, And YOLOv10, Has Not Been Thoroughly Assessed For This Particular Task, Even Though YOLObased Models Have Shown Excellent Accuracy And Efficiency In VLPR. These Cutting-edge YOLO Models For Real-time License Plate Detection And Recognition Are Compared In This Study. The Evaluation Was Conducted Using A Unique Dataset That Included A Variety Of Environmental Conditions, Such As Low Light, Occlusions, And Distinct Plate Sizes. To Evaluate Inference Time, Accuracy, And Computational Efficiency, The Models Were Evaluated On Edge And Cloud-based Systems. According To Experimental Data, YOLOv10 Provides The Optimum Trade-off Between Speed And Precision For Edge Deployment, While YOLOv12 Achieves The Greatest Recognition Accuracy Of 98.6%. The Results Of This Study Demonstrate The Improvements In License Plate Identification With The Most Recent YOLO Architectures And Offer Information On How They Might Be Used In Real-world Intelligent Transportation Systems. KEYWORDS: VLPR, Computer Vision, YOLOv11, YOLOv12, Deep Learning, EasyOcr, CNN

Published:

25-9-2025

Issue:

Vol. 25 No. 9 (2025)

Page Nos:

217-223

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite