Document Details

Document Type : Thesis 
Document Title :
Video Analysis for Abnormal Human Behavior in The examination Room
تحليل تصرف الانسان باستخدام الفيديو في غرفة الاختبارات
 
Subject : Faculty of Computing and Information Technology 
Document Language : Arabic 
Abstract : The anomalous behavior is hard to be detected simultaneously in a complex scene such as detecting abnormal movements of examinees in examination rooms. Modeling activities of moving objects and classifying them as normal or anomalous is a major research problem in video analysis. In this thesis, we make use of the Neural Networks and Gaussian distribution to help solve this problem by building a prototype of a monitoring system that consists of three stages; face detection using Haar cascade detector, suspicious state detection using a neural network and lastly anomaly detection based on the Gaussian distribution. The main idea is to decide on whether the student is in a suspicious state or not using a trained neural network and then decide that a student performs an anomalous behavior based on how many times he was found in a suspicious state in a defined time duration. The type of cheating that we will detect in our systems will include looking at other students’ papers or if the student moved his/her head to look right, left, up or down. The complete system has been tested on a proprietary data set achieving 97% accuracy with 3% false negative rate. 
Supervisor : Dr. Mohamed Dahab 
Thesis Type : Master Thesis 
Publishing Year : 1440 AH
2018 AD 
Co-Supervisor : Dr. Gabriel Abu Samra 
Added Date : Sunday, December 9, 2018 

Researchers

Researcher Name (Arabic)Researcher Name (English)Researcher TypeDr GradeEmail
أسماء إبراهيم آل إبراهيمAl Ibrahim, Asma IbrahimResearcherMaster 

Files

File NameTypeDescription
 43846.pdf pdf 

Back To Researches Page