Vision-based tracking technique provides intuitive experience for users to interact with their computers. However, such technique seldom appears on web applications that can be widely accessed by average users. The purpose of this paper is to suggest a technique that will enable more users to engage in the intuitive interaction on the Web. In order to achieve this, a vision based tracking system is built. The tracking system can be used by different types of web applications, so that a wide range of users can access this technique.