FACE FRAUD DETECTION IN ONLINE EXAM

Abstract: With the expansion of the Internet and technology over the past decade, Elearning has grown exponentially day by day. Online examination is an integral and vital component of E-learning. Face recognition is widely viewed a an alternative means of authentication to replace traditional password methods in different applications for access control. Despite significant improvements, this form of authentication remains plagued by several vulnerabilities ranging from the use of printed photographs, 3D masks, and video replay attacks.In face recognition systems, replay attacks where a pre-recorded video of the user is played and printed photograph is placed in front of the camera are the two most common ways to do the fraud while attending the examination.So there is a need for the robust face liveness detection method that can be used in detecting spoof attacks for differentiation between legitimate and illegitimate users using machine learning techniques. Using the observation that different materials reflect light differently, we propose a system that uses light reflection getting from the photo while recording a video or taking an image of examinee during an examination.

Keywords: 1. Face Fraud Detection 2. Online Examination 3. Face Recognition 4. Liveness Detection Light Reflection 6. Biometric Authentication 7. Machine Learning 8. Haar Cascade classifier, 9. Support Vector Machine