A Feature-Based Algorithm for Recognizing Gestures on Portable Computers

Pen gestures are a promising feature of pen-based user interface. Recently, as the supply of pen-based portable computers such as PDAs has increased, so has the usage of them. But they have not yet been fully exploited. In this paper we proposed a new gesture set which consists of eight gestures for editing electronic ink data and a feature-based recognition algorithm to identify gestures. We implemented GesEdit, the gesture-allowed ink editor on PDAs, to verify the proposed algorithm. A variety of experiments involving twenty users showed that the gesture recognition rate reached 99.6%. In addition, they showed that the algorithm was efficient as much portable devices as desktop computers.