Automatic detection and tracking of faces and facial features in video sequences

This paper presents an algorithm for the detection and tracking of the face and facial features in video image sequences. In the first stage, the face is located in the image sequences by utilizing both color and scene background information. In the second stage, the eyes are detected within the face region. Face and eyes are then tracked constantly over time. The proposed techniques are integrated in an interactive computer system, where they serve as a pre-processing step for the determination of the 3D eye positions.