Virtual Booth

In the modern healthcare sector, the reliance on manual patient identification methods, such as physical ID cards and verbal confirmation presents significant challenges, including administrative bottlenecks, human error, and hygiene risks associated with physical contact. To address these inefficiencies and enhance patient safety, particularly for unresponsive individuals in emergency settings, this project develops an automated patient record access system utilizing advanced Artificial Intelligence and Deep Learning technologies. The proposed solution employs a robust facial recognition architecture powered by Convolutional Neural Networks (CNNs), leveraging the DeepFace framework and OpenCV for real-time face detection and feature extraction to accurately authenticate individuals under varying conditions. Integrated with a responsive React.js frontend and a secure MySQL and Node.js backend, the system allows medical personnel to instantly retrieve and view Electronic Health Records (EHR), including critical data like allergies and diagnosis history immediately upon positive identification. By eliminating the need for physical touchpoints and manual database searches, this research demonstrates that Al-driven biometric integration significantly reduces registration time, mitigates the risk of identity theft, and ensures rapid, contactless access to vital medical information, thereby optimizing hospital workflows and improving clinical outcomes.