Realization of Facial Recognition Technology for Attendance Monitoring Through Biometric Modalities Employing MTCNN Integration

The use of facial recognition technology in attendance tracking has become increasingly popular in a variety of industries. Conventional techniques, including radio frequency identification devices, have proved to be expensive, time-consuming, and unreliable. Researchers have looked to facial recognition for more effective attendance tracking in order to overcome these drawbacks. This paper proposes a novel method that merges facial recognition using K-nearest neighbours (KNN) and multi-task cascaded convolutional networks (MTCNN) via a Flask-based web application. The system's goal is to increase accuracy, especially in situations where masks partially conceal faces. Importing the required libraries and configuring a Flask application are part of the implementation. To improve context, pictures containing dates are taken when a user registers. MTCNN is used to address localization issues and increase the accuracy of face detection. The system makes sure that directories are managed correctly, which includes making folders for daily attendance records. Tracking user registration, extracting facial features with HaarCascade, identifying faces using a trained KNN model, and training the KNN model with readily available facial data are some of the main features. MTCNN demonstrates a considerable improvement by significantly increasing recognition accuracy. This combined system exemplifies the collaboration capabilities of Flask, MTCNN, HaarCascade, and KNN models by showcasing the real-world implementation of sophisticated convolutional networks in an intuitive interface. Experimental findings validate the system's efficacy in well-lit, unobstructed surroundings, with a recognition accuracy of 92.59–97.36% under ideal conditions. The present study highlights the smooth integration of different technologies, providing an adaptable framework for effective attendance control.