In the digital information time, daily life is inseparable with human-computer interface (HCI). Human computer interaction has a long history to become more intuitive. For human being, hand gesture of different kind is one of the most intuitive and common communication. However, vision-based hand gesture recognition is still a challenging problem. In this paper, an embedded virtual mouse system by using hand gesture recognition is proposed. There are several techniques involved in the proposed system. Skin detection and motion detection method are used to capture the region-of-interest and distinguish the foreground/background area. Connected component labeling algorithm is used to identify the centroid of an object. The removal on arm and the convex hull algorithm are used to recognize hand area as well as the related gesture. The result shows that our system can operate well even in some harsh environment.