Smart PPE Detection and Compliance Verification System Using Faster R-CNN for Medical Laboratories

This paper presents an automated and smart system for real-time checking and Detection of Personal Protective Equipment (PPE) Compliance in Medical Laboratory Environments. This solution uses an IoT-enabled camera network and a deep learning-based computer vision system for real-time monitoring to overcome the difficulties associated with manual safety verification. A Fast Region-based Convolutional Neural Network (Fast R-CNN), the main deep learning architecture for object detection and compliance verification, is at the heart of the suggested framework, which is trained on a custom dataset of medical lab situations to accurately identify and locate various types of PPE, including lab coats, safety goggles, face masks, and gloves. When the system spots any non-compliance, it is designed to send an immediate alert. Ensuring safety in medical laboratories is crucial. Improper use or the lack of Personal Protective Equipment (PPE) can cause serious health risks and contamination. This paper describes the design and development of a Smart PPE Detection and Compliance Verification System that uses deep learning to monitor PPE usage in real time. In order to identify essential PPE components like face masks, gloves, and lab coats, the suggested system uses a specially trained Faster Region-Based Convolutional Neural Network (Faster R-CNN) that was trained on a dataset of almost 3,000 annotated photos. The trained model was deployed on a Raspberry Pi 4 with a Camera Module 3 for real-time processing at the edge. Early testing of the prototype showed it could reliably detect face masks and lab coats with high accuracy. Experimental results confirm that the approach works well and provide a solid base for applying it in healthcare and research settings. Standard performance metrics - mean average precision (mAP), precision, and recall - are used to quantitatively assess the suggested model's efficacy.