Due to the large population of motorway users in the country of Iraq, various approaches have been adopted to manage queues such as implementation of traffic lights, avoidance of illegal parking, amongst others. However, defaulters are recorded daily, hence the need to develop a mean of identifying these defaulters and bring them to book. This article discusses the development of an approach of recognizing Iraqi licence plates such that defaulters of queue management systems are identified. Multiple agencies worldwide have quickly and widely adopted the recognition of a vehicle license plate technology to expand their ability in investigative and security matters. License plate helps detect the vehicle's information automatically rather than a long time consuming manually gathering for the information. In this article, transfer learning is employed to train two distinct YOLOv8 models for enhanced automatic number plate recognition (ANPR). This approach leverages the strengths of YOLOv8 in handling complex patterns and variations in license plate designs, showcasing significant promise for real-world applications in vehicle identification and law enforcement.
