Attendance Management System using Haar Cascades and MTCNN Algorithm

A cloud-based attendance management system utilizing advanced facial recognition algorithms to enhance efficiency and accuracy in educational environments. By employing the CASIA WebFace dataset, which features a diverse collection of facial images, the system leverages deep learning techniques to extract meaningful features and identify individuals effectively. The process begins with image acquisition via webcams or mobile devices, followed by preprocessing to improve image quality. Face detection is accomplished using Haar Cascades, a swift method for identifying facial regions in real-time. Once detected, facial features are extracted using Convolutional Neural Networks (CNNs), which are designed to learn and classify complex patterns inherent in facial data. These extracted features are then compared against a centralized database, allowing for real-time updates to attendance records. The cloud infrastructure supports the processing of large datasets efficiently, ensuring rapid and accurate attendance tracking. This architecture enhances scalability, making it adaptable to various classroom sizes and environments. The findings demonstrate notable improvements in both accuracy and processing speed for attendance monitoring, highlighting the transformative potential of automated facial recognition systems in modern educational settings. This research contributes to the ongoing evolution of intelligent solutions, paving the way for streamlined attendance management practices.