Face location from a single image

Abstract

Human face detection is important for the aspects of face recognition and video surveillance. We propose to detect face from image with varying lighting condition and complex background. The face detection algorithm is based on YCbCr color method with lighting compensation technique and nonlinear color transformation. We first detect the skin region from image, then finding face candidates from grouping skin region. Then we construct eye and mouth maps in order to work on the triangle relationship between them. The result works well on wide range of facial variation in color, position, scale and orientation with photo collection including both indoors and outdoors.