Automatic location and tracking of the facial region in color video sequences

A novel technique is introduced to locate and track the facial area in videophone-type sequences. The proposed method essentially consists of two components: (i) a color processing unit, and (ii) a knowledge-based shape and color analysis module. The color processing component utilizes the distribution of skin-tones in the HSV color space to obtain an initial set of candidate regions or objects. The second component in the segmentation scheme, that is, the shape and color analysis module is used to correctly identify and select the facial region in the case where more than one object has been extracted. A number of fuzzy membership functions are devised to provide information about each object’s shape, orientation, location and average hue. An aggregation operator finally combines these measures and correctly selects the facial area. The suggested approach is robust with regard to different skin types, and various types of object or background motion within the scene. Furthermore, the algorithm can be implemented at a low computational complexity due to the binary nature of the operations involved. Experimental results are presented for a series of CIF and QCIF video sequences.