NIGERIAN VEHICLE PLATE NUMBER RECOGNITION USING DEEP LEARNING
Abstract
ABSTRACT
The development of an Android application for Nigerian vehicle plate number recognition addresses the need for efficient and portable vehicle identification solutions. Leveraging Optical Character Recognition (OCR) technology, the application extracts and interprets alphanumeric details from Nigerian license plates. The project employs advanced machine learning techniques, integrating Google’s ML Kit for text recognition to enhance accuracy and reliability. A user-friendly interface allows users to upload images for processing, while the backend seamlessly detects, segments, and interprets plate information. Extensive testing revealed the application's capability to handle diverse plate designs under varying conditions, though minor inconsistencies were noted in text recognition due to plate degradation or obstructions. The implementation process involved detailed system design, including flowcharts that outlined the data preprocessing, plate detection, and OCR recognition stages. The application demonstrates significant potential for real-world applications, such as traffic monitoring and automated toll systems, with further refinements recommended for handling noisy or obscured images. This project represents a step toward practical, mobile-based solutions for license plate recognition in Nigeria.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.