In recent years, face recognition has often been proposed for personal identification. However, there are many difficulties with face recognition systems. For example, an imposter could login the face recognition system by stealing the facial photograph of a person registered on the facial recognition system. The security of the face recognition system requires a live detection system to prevent system login using photographs of a human face. This paper describes an effective, efficient face live detection method which uses physiological motion detected by estimating the eye blinks from a captured video sequence and an eye contour extraction algorithm. This technique uses the conventional active shape model with a random forest classifier trained to recognize the local appearance around each landmark. This local match provides more robustness for optimizing the fitting procedure. Tests show that this face live detection approach successfully discriminates a live human face from a photograph of the registered person's face to increase the face recognition system reliability.

Locating multi-view faces in images with a complex background remains a challenging problem. In this paper, an integrated method for real-time multi-view face detection and pose estimation is presented. A simple-to-complex and coarse-to-fine view-based detector architecture has been designed to detect multi-view faces and estimate their poses efficiently. Both the pose estimators and the view-based face/nonface detectors are trained by a cost-sensitive AdaBoost algorithm to improve the generalization ability. Experimental results show that the proposed multi-view face detector, which can be constructed easily, gives more robust face detection and pose estimation and has a faster real-time detection speed compared with other conventional methods.