Milad, Ali Ali Alhadar <br/><br/>
AUTOMATIC CLASS ATTENDANCE MANAGEMENT SYSTEM USING FACIAL SYNTHESIS AND RECOGNITION /  
ALI ASLI ALHADAR MILAD; SUPERVISOR: ASSOC. PROF. DR. KAMIL YURTKAN 
 - 135 sheets;  31 cm.  Includes CD 
<br/><br/>Thesis (PhD) - Cyprus International University. Institute of Graduate Studies and Research Management Information Systems Department 
<br/><br/>Includes bibliography (sheets 124-135) 
<br/><br/> ABSTRACT<br/>Classroom attendance systems have been a principal part of the learning process of<br/>conventional classroom institutions. Many processes have been devised over the<br/>years for the adequate recording of student attendance in classrooms to ensure<br/>students attend their classes which is synonymous to good academic performance in<br/>students. The rise of the digital age in the 21st century has enabled the introduction<br/>of several electronic technological platforms for classroom attendance purposes, one<br/>of such technologies is the use of human face recognition for classroom attendance.<br/>Unfortunately classroom attendance has been faced by several challenges which<br/>many studies have tried to mitigate and proffer solutions to. This study proposed a<br/>methodology to mitigate the challenges of varying face poses and facial expressions<br/>which both face recognition-based classroom attendance systems have been reported<br/>to face over the years. This research leverages the use of 3D analysis of facial<br/>expressions to synthesize face image poses and facial expressions from a single input<br/>image of a subject. The study uses six basic facial expressions which it implements<br/>using a 3D model of set of points triangle mesh points connected in 3D space of 20<br/>geometric feature points on human faces. The synthesized facial images are applied<br/>Local Binary Pattern Histogram (LBPH) texture operator on, to enable the extraction<br/>of histograms which are used to train a Support Vector Machine (SVM) classifier.<br/>The study uses two different human face databases; FEI and BU-3DFE, the two<br/>databases are used to evaluate the proposed methodology separately, with the FEI<br/>database images yielding an average of 71.78% performance accuracy and the BU-<br/>3DFE database yielding an average of 78.57% performance accuracy. This designed<br/>methodology is further developed and applied as a recognition system for classroom<br/>attendance scenarios which led to the achievement of a satisfactory performance<br/>accuracy for individual subjects tested on it.<br/>Keywords: Classroom Attendance System, 3D Face Analysis, Face Recognition,<br/>Support Vector Machine, Local Binary Pattern Histogram 
<br/><br/><label>Subjects--Topical Terms: </label><br/>Human face recognition (Computer science)--Dissertations, Academic<br/>Support vector machines--Dissertations, Academic