With the exponential growth in urbanization and industrialization, the volume of vehicles traversing road networks has surged, presenting multifaceted challenges for urban management and public safety. The escalating number of vehicles not only exacerbates traffic congestion and demands for traffic and parking management but also amplifies the incidence of traffic violations, accidents, and criminal activities. To address these issues there’s a growing interest in Automatic Number Plate Recognition (ANPR) systems. This research presents a comprehensive system leveraging convolutional neural networks for license plate detection, vehicle tracking, and optical character recognition. We employ state-of-the-art techniques including YOLOv9 for object detection, DeepSORT for tracking, and PaddleOCR for character reading. Our model achieves remarkable performance with a 98.6% mAP50 score for license plate detection, maintaining a precision of 98.3% and recall of 95.8%. Additionally, the proposed system demonstrates exceptional performance on test videos, accurately detecting 97.4% of characters. These findings highlight the promising potential for future ANPR technology utilizing YOLO.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Synergetic Integration of YOLOv9, DeepSORT, and PaddleOCR: Revolutionizing ANPR Technology


    Additional title:

    Lect. Notes in Networks, Syst.


    Contributors:

    Conference:

    International Conference on Data Analytics & Management ; 2024 ; London, United Kingdom June 14, 2024 - June 15, 2024



    Publication date :

    2025-07-09


    Size :

    9 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





    Parking Assistance System using ANPR

    Shukla, Abhishek Kumar / Kumar, Yash / Nagpal, Shourya et al. | IEEE | 2023




    Street enforcement applications for mobile ANPR systems

    Percival, M. E. / Sedgwick, A. / Ellis, T. et al. | British Library Conference Proceedings | 2004