Human face detection and location in complex background

In this paper a new method to detect and locate human faces in complex background is proposed. First, an evolutionary computation algorithm is used to search the skin like pixels and segment the face like regions in a color image. Then, the shape and the gray intensity distribution information of each face like region are examined and those regions that satisfy with the knowledge of a human face are located and marked. The experimental results show that the proposed approach not only has the features of high speed and high efficiency, but also has the ability to detect human faces of any number with any poses in any background.