Automatic color face tracking using gray information

In this paper we propose a new automatic face tracking method using the gray information. The method uses the gray information for extracting online the color skin of the main person. Therefore the proposed method is more robust than other approaches that uses a given database of skin, and more practical than methods witch uses manual initialization. The proposed framework combines face detection, on line skin color extraction, Kalman filter, and Gaussian skin color model for robust face tracking. The system is relatively insensitive to illumination conditions. In fact the system is able to track the face in the presence of blue light for example.