Face detection and pose alignment using colour, shape and texture information

This paper presents an automatic method for sim simultaneous varying pose face detection and pose alignment from colour video images by using colour, shape, and texture information. At Me first stage, we use a skin colour Gaussian model to identify possible face locations under varying pose. Secondly, we compare image patterns with a varying pose face model in terms of shape and texture differences, using a combined feature-texture similarity measure (FTSM). False detections from the first stage are eliminated by setting an appropriate FTSM threshold. Moreover, one can also register the facial features (eyes, nose and mouth) by aligning a prototype face with the unknown pose faces. Experimental results show that the proposed method can achieve reliable face detection and pose alignment under various conditions, including different poses, face appearances, and lighting conditions.