Automated License Plate Recognition (ALPR) systems are vital for modern traffic management, law enforcement, and security applications, yet they face limitations in accurately identifying license plates under varied real-world conditions. This study aims to address these challenges by developing a scalable ALPR system that integrates efficient object detection and Optical Character Recognition (OCR) techniques. Leveraging the YOLO model for license plate detection and Pytesseract OCR for character recognition, the system employs pre-processing and data augmentation to enhance accuracy in diverse environments, including low-light and occluded settings. Unique features such as real-time processing capabilities and privacy-preserving Gaussian blur ensure compliance with privacy standards while maintaining cost-efficiency. Evaluation of the system on real-world datasets demonstrated a high detection rate and reliable OCR accuracy, even under challenging conditions. This research not only improves upon traditional ALPR methods but also offers a versatile solution with potential applications in smart city infrastructure and automated vehicle monitoring. The findings indicate that this ALPR system can be effectively deployed across a range of resource-constrained and dynamic environments.Code available on GitHub