A Survey on Deep Learning-Based Number Plate Recognition Systems in Vehicles for Real-Time Applications

Abstract

Innovation is integral to human existence, and research on modernisation aimed at enhancing daily life has proliferated in recent decades. One notable advancement is the evolution of AI, and we are in the era of machine intelligence. These developments are essential for society, as access to these amenities is not restricted to any specific group. A prevalent application of intelligent technology is traffic monitoring. A paramount application is Automatic Number Plate Recognition (ANPR) systems; various technologies are being developed to enhance performance. Research into innovative technologies, their enhancement, and the advancement of existing methods commenced several years ago and remains essential. Real-time video-based ANPR systems are complex and essential for modern intelligent transportation applications. This study presents a systematic review of real-time video-based automatic number plate recognition systems, tracing the evolution from traditional image processing to deep learning, end-to-end methods, and Transformer-based methods. We compare detection and recognition techniques and identify the limitations of current ANPR systems. The review concludes with proposed directions for developing more robust and efficient ANPR systems for real-time traffic analysis in intelligent transportation systems.