Design of Vehicle License Plate Detection System Using YOLOv8 and PaddleOCR

The increasing number of vehicles-related incidents demands a more efficient and accurate method to detect and identify vehicle license plates. In answering this challenge, a prototype of a YOLOv8-based vehicle license plate detection system was developed. This system is designed to detect vehicle license plates automatically, by utilizing a Mini PC as a data processing center. This prototype is able to recognize vehicle license plates as the main method in various applications, such as managing access in and out of certain areas or traffic monitoring, in order to improve the accuracy and efficiency of vehicle data collection. Testing shows that the system can identify license plates with a high level of accuracy of 91.6 %, and the results of reading vehicle license plates using PaddleOCR also show quite satisfactory quality of 86 %. Overall, this YOLOv8-based vehicle license plate detection system is able to provide accurate and efficient results in detecting and identifying vehicle license plates.