Accurate systems for person detection and recognition are critical across domains. This paper introduces a novel approach integrating YOLO11, a cutting-edge object detection model, with FaceNet, a high-accuracy face recognition model, to achieve real-time person detection and identification. YOLO11 delivers swift localization with a mean Average Precision of 51.5% on the MS COCO dataset, while FaceNet achieves 100% accuracy on several benchmarks. Unlike traditional methods, this system employs a one-shot learning framework, enabling recognition with minimal data per individual. It effectively tracks individuals by logging their entries and exits, addressing challenges like real-time performance and scalability. A custom student dataset further validates the approach, achieving 97.14% recognition accuracy. This integration ensures rapid detection, precise identification, and practical applicability in diverse monitoring scenarios, overcoming limitations of prior systems by blending speed, accuracy, and adaptability.