AI Automated Attendance System Using Face Recognition And RFID

Traditional attendance tracking in educational and corporate environments remains largely manual, a process that is time-consuming, prone to human error, and vulnerable to fraudulent proxy attendance. While RFID-based systems offer automation, they lack biometric verification, and standalone face recognition systems can be hampered by environmental factors like lighting. To address these limitations, this work presents a hybrid, AI-powered attendance system that integrates face recognition with RFID technology for robust, dual-factor authentication. The system utilizes an ESP32-CAM module to capture facial images and an RFID reader for identity verification, ensuring that only the authorized individual is marked present. Attendance records are securely stored in a cloud-based Firebase database, enabling real-time monitoring and report generation through a cross-platform mobile application developed in Flutter. The face recognition model, built using TensorFlow and OpenCV, is fine-tuned on a custom dataset to accurately identify users. The proposed solution is designed to be cost-effective, scalable, and easily deployable, significantly reducing administrative workload and enhancing security over conventional systems. Through this integrated approach of IoT hardware and AI software, the project demonstrates a significant advancement in automated attendance management.