A Multifarious Faces and Facial Features Detection Algorithm for Color Images Based on Grey-scale Information and Facial Geometry

The requirements for human face and facial features detection are motivated by various applications: face recognition, videoconferencing, and human computer interaction and security control are only a few examples. In this paper a novel face detection algorithm for color images is proposed in presence of varying lighting condition as well as complex background. Our algorithm detects eyes over the entire image, then generates facial features (mouth, nose) based on facial geometry and at last, generates face boundaries based on information collected from facial features. Experimental results demonstrate successful detection over a wide variety of facial variations in color, position, scale, rotation and pose from various photo collections.