Automatic License Plate Recognition (ALPR) systems are essential for modern intelligent transportation systems, smart city infrastructure, electronic toll collection, and law enforcement surveillance. However, traditional computer vision methods and conventional Convolutional Neural Network (CNN) classifiers often fail to achieve real-time accuracy under unconstrained environments characterized by varying lighting conditions, motion blur, steep viewing angles, and complex backgrounds. Moreover, standard two-stage object detection architectures present significant computational overhead and latency, making them unuitable for edge hardware deployment. To overcome these limitations, this study proposes an end-to-end real-time License Plate Detection and Recognition framework powered by the state-of-the-art YOLOv8 architecture. A comprehensive dataset consisting of diverse vehicle license plate images under varied environmental conditions was pre-processed using spatial scaling, pixel normalization, and Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance localized edge boundaries. The dataset was annotated using Label Studio to demarcate license plate regions and individual character bounding boxes. The YOLOv8 model was trained utilizing GPU acceleration to ensure rapid convergence and optimal feature representation across multi-scale feature maps. Experimental evaluations on test datasets demonstrate that the proposed system achieves an overall mean Average Precision (mAP@0.5) of 98.6% and an mAP@0.5:0.95 of 78.4% at real-time processing speeds exceeding 35 frames per second (FPS). The proposed system offers automated, low-latency, and high-accuracy license plate localization that can be directly deployed in smart parking management, automated toll booths, traffic enforcement agencies, and security checkpoints to significantly minimize manual monitoring and operational overhead.

S.Subhasree, S.Sai Mahalakshmi, P.Nakul, S.Sanjay, Ms. Dhanya.K.R,"YOLOv8 — License Plate Detection" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(4): Page(440-444) July - August 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.