Attendance Management System

This project introduces a Time-Based Attendance Management System that aims to streamline and modernize the traditional manual attendance tracking method, which is both time-consuming and challenging to maintain. The proposed system leverages advanced biometric technology, particularly Deep Learning (DL) based Face Recognition algorithms. Human faces serve as the primary dataset for training, employing the LBPH Face Recognizer. The user interface is developed through the Flask framework, providing a user-friendly web page. Notably, as an enhancement to this system, it offers the capability to store attendance data in a database, including timestamps.

 

The system is designed with two key modules:

Admin Module: The Admin has the ability to upload student data, view individual student profiles, and train the face recognition model on the student data. The Admin can also add marks details and view attendance statistics, such as total students, present students, and absent students. Additionally, the Admin can filter the attendance data by student name. An innovative feature automatically sends an email to parents regarding attendance condonation, based on the student’s attendance percentage.

Student Module: Students can mark their attendance using facial recognition, view their profile, and download their marks. The student dashboard provides easy access to attendance details and academic performance, enhancing the user experience.

In addition, the system includes a feature to notify parents about their children’s attendance, marks, and behavior through the Fast to SMS website, strengthening the communication between educational institutions and parents. This enhancement not only boosts the efficiency of attendance management but also fosters a more informed and engaged educational environment

Keywords: Attendance Management, Computer Vision, Deep Learning, Human Face Images, sending SMS