DEVELOPMENT OF A YOLOv11-BASED VEHICLE LICENSE PLATE DETECTION AND RECOGNITION SYSTEM

GEORGE, DAVID NSEABASI (2025) DEVELOPMENT OF A YOLOv11-BASED VEHICLE LICENSE PLATE DETECTION AND RECOGNITION SYSTEM. Other thesis, GODFREY OKOYE UNIVERSITY, ENUGU.

Text REPO179(1).docx Download (5MB)

Abstract

This study seeks to address several challenges affecting Nigerian roads, especially for travelers who encounter unnecessary queues in different checking points and toll booths as a result of the use of the manual method of vehicle inspection. It also identifies the problems affecting the use of ML and DL techniques in automating vehicle license plate recognition systems. The study employed a public dataset to train and developed a YOLOv11-based vehicle license plate detection and recognition system that solves the identified problems. Additionally, OCR was employed to recognize and extract the characters. The performance was evaluated considering some metrics such as F1-score and accuracy. The model achieved a high accuracy of 97.4%, an F1-score of 96%, and demonstrated fast computational capabilities. Python’s tkinter to design a user-friendly software application to test how efficient the model is on live capture image and video data. The study encountered some limitations that hindered the achievement of some of the original goals. This led to a 5% misclassification rate, caused by lighting issues and broken or faded plates. However, the results offer a way forward for practical applications in Nigeria, with the model proving reliable for traffic monitoring and enforcement, thereby addressing the initial challenge of manual recognition inefficiencies.

Item Type:	Thesis (Other)
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Faculty of Natural and Applied Sciences
Depositing User:	Uchenna Eneogwe
Date Deposited:	19 Jun 2026 15:08
Last Modified:	19 Jun 2026 15:08
URI:	http://eprints.gouni.edu.ng/id/eprint/5853

Actions (login required)

View Item