Monitoring Students Actions During Examination using Neural Networks

Potla, Bharath (2024) Monitoring Students Actions During Examination using Neural Networks. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (961kB) | Preview
Preview	PDF (Configuration Manual) Download (72kB) | Preview

Abstract

In the event where the number of students enrolling into the education institutions increases, cases of academic violation also a case in point is the examinations. The research we introduce a computer vision system for observing student exam behavior by analyzing live video feeds for suspicious activity. The system tracks key facial movements such as eye shifts, lip movements, and head posture with the intent of identifying warning signs of cheating. In order to achieve this goal, this study extends the utility of Python's segmentation and recognition libraries such as OpenCV and TensorFlow by applying it to face recognition to detect subtle facial movements associated with suspicious behavior. Moreover, an object detection module, YOLO (You Only Look Once), is also added into the research to detect banned objects including mobile phones inside examination environment. The system combines facial analysis with object detection and produces a complete solution for surveillance during exams to aid in the detection of dishonest practices in real time. The findings show that the proposed system can accurately capture and analyze pupil behaviors for use as a reliable and automated application to support academic integrity during examine situations.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Nolan, Eamon UNSPECIFIED
Subjects:	L Education > L Education (General) Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science L Education > LB Theory and practice of education > LB2300 Higher Education > Assessment
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	04 Sep 2025 10:14
Last Modified:	04 Sep 2025 10:14
URI:	https://norma.ncirl.ie/id/eprint/8774

Actions (login required)

View Item