AI based College Surveillance System for Class Skipper

Abstract

In many of the educational institutions, managing attendance of students/candidates is tedious, as there would be large number of students in the class and keeping track of all is onerous. There are situations where student act as proxies for their friends even though they are not present. The presence of students repeatedly skipping classes and spending considerable time wandering on campus signals potential underlying issues, such as disengagement, personal challenges, or dissatisfaction with the educational experience. Traditional methods of monitoring attendance are often inadequate in addressing these nuanced challenges. Therefore, there is a need for an AI-based College Surveillance System using Faster R-CNN to accurately detect class skippers and provide insights into their behavioural patterns. In this system, a database containing the trained student’s face. A camera installed in the college campus captures the face of all the student in the classroom and other places too. This face image is processed using FRCNN algorithms to detect faces and to mark the attendance automatically in an excel sheet. The system records the entire class session and identifies when the students pay attention in the classroom, and then reports to the facilities and also this system can record violations of classroom, that is absence, roaming around the college campus during the class hours and send alert message to the H.O.D.This dynamic attendance system uses face recognition as an important aspect of taking attendance which saves time and proxy attendance and is avoided. The system identifies faces very fast needing only 100 milliseconds to one frame and obtaining a high accuracy. Our face recognition model has an accuracy rate of 98.87%..