Video based classroom monitoring

Abstract

In traditional classroom environments,
the demand for tools to automate attendance tracking
and analyze student emotions has become
increasingly important. This project develops a videobased
classroom monitoring system that performs
automated attendance and emotion analysis to
evaluate student engagement. The system uses facial
recognition to identify students and records
attendance data into a well-organized Excel file for
each session. Additionally, emotion recognition
algorithms are implemented to analyze students'
emotional states. While the system operates in real
time, it suffers from slow processing speed and
moderate accuracy. Built using Python and OpenCV,
the system was tested in a simulated classroom
environment, achieving basic project objectives.
However, improvements in performance and accuracy
are necessary for broader applications. This
innovation supports educators in managing
classrooms more effectively while providing valuable
insights into student engagement