Deep Learning Approaches for License Plate Detection in Saudi Arabia

The most important and challenging tasks in an intelligent traffic monitoring system are vehicle detection and classification. Conventional approaches are significantly computationally intensive and create limitations when the data-collecting modality alters. This study evaluates the effectiveness of deep learning models in extracting and classifying key vehicle attributes, such as license plates, models, and colors, through four AI-driven components for vehicle analysis. The YOLOv8m model was used for detecting the vehicle license plate and character recognition, achieving accuracy ranging from 95.10% to 99.24%. For vehicle model recognition, the Xception model also showed high performance with a precision of 96.79%. The EfficientNetB3 model used for vehicle color recognition achieved an accuracy of 96.30%. The findings demonstrate the practical value of deep learning models in improving the vehicle identification process tailored to Saudi Arabia’s transportation needs. Therefore, this study contributes a unified deep learning framework that integrates license plate detection, character recognition, vehicle model and color classification, offering a practical and robust solution for real-world traffic monitoring in Saudi Arabia.