Liveness Detection for Face Recognition System

Biometrics is a rapidly developing technology that is to identify a person based on his or her physiological or behavioral characteristics. Among many biometric methods, face recognition is one of the most widely used method. To increase reliability of face recognition system, the system must be able to distinguish real face from its copy such as a photograph. In this paper, we propose a fast and memory efficient method of live face detection. We detect eyes and nose in sequential input images and calculate variation of distance between each eye region and nose region when the face rotate around a axis passing through spinal cord to determine whether the input face is a real face or not.
Compared to existing methods, this algorithm is very simple to implement. Experimental results show that there is big difference in the output for a real face and a photograph. Thus using proposed algorithm, we can easily distinguish between real face and a photo.