Robust face detection and recognition for computer-based security surveillance

The research aims at improving the existing and creating new automated face detection and recognition methods by making them invariant, firstly to head pose, orientation, scale and rotation, and then to occulsion, lighting conditions and facial expressions. A robust face detector will be developed first and then a new face recognition algorithim that continues to learn identify-specific discriminants on-line by collecting incremental face exemplars. The result of the research will be an algorithim that can improve its performance on-line adapting in a stable learning process each identity model to the correct facial examples. The research has significant practical implication in visual surveillance increaasing the robustness of identification of person identity, state and intent.