SecureNest: Smart Home Security System

This paper introduces SecureNest, a smart home security system that leverages computer vision to monitor CCTV footage and categorize activities based on threat levels. The system employs MTCNN (Multi-Task Cascaded Convolutional Networks) for face detection, InceptionResNetV1 for face recognition, YOLOv8 for real-time object detection, and a combination of EasyOCR and Tesseract for license plate recognition. SecureNest dynamically updates its database of authorized individuals and vehicles while filtering out non-essential movements. Performance evaluation demonstrates high accuracy, achieving 0.95 for face recognition, 0.964 for object detection, and 0.767 for license plate recognition. By integrating these modules, SecureNest minimizes false positives and enhances threat assessment. A user-friendly interface ensures efficient alert management, making SecureNest a streamlined and reliable home security solution.