In the past few years, the need of detecting human faces plays an important role in many visual applications, and the amount of related technologies are growing rapidly. There are many technologies of human face location, and the method by using the skin color of face to segment the face scope is one of the most commonly used technologies. However, there are many problems about this method, so it is difficult to segment the human face correctly from the background when the background color is close to the skin color. In this paper, we propose an automatic system for locating human face and determining the best representative among face photos. We combine several methods, including moving detection, skin color detection, and feature detection, to locate the positions of human face. When all detections is finished, the system will select the best representative among face photos.