Secure Face Track: A Deep Learning-Powered Attendance Automation

A Deep Learning-Powered Attendance Automation addresses a pressing challenge in the realm of smart attendance systems: spoofing or deception attempts by individuals seeking to manipulate the system with fake or altered facial images or videos. This project presents an intelligent anti-spoofing system, named Deep Learning-Powered Attendance Automation, designed to accurately distinguish between genuine and fraudulent faces within a smart attendance context. The system's development encompasses the creation of a comprehensive dataset comprising real and fake facial images and videos. Leveraging deep learning, the project employs a robust feature extraction and classification pipeline, including the utilization of the Facenet model for facial recognition. Facenet operates across three phases: registration, training, and testing, integral to the functioning of the face recognition model. Furthermore, various data augmentation techniques, including rotation, scaling, and translation, are incorporated to enhance the system's resilience against diverse spoofing attacks. Performance metrics such as accuracy, precision, and recall are used to evaluate the system's effectiveness in detecting and preventing spoofing attempts.