The method described in this paper recognizes previously learned gestures which the system was taught by performing them.
Any kind of 6DOF input device (e.g. data glove, visual systems, space mouse etc.) can be used to gather the motion data that carries out the gesture. The reliability of the recognition process can be improved by repeating the same gestures several times and correcting wrong recognition results. This extends the systemís knowledge. Once learned, the system translates the recognized gestures into (for a computer) identifiable objects (numbers, strings, events, etc.) that can be further processed.
The systemís advantages are its usability (e.g. with 2D or 3D input devices or in combination with finger status information, etc.), the minimum of information needed to recognize a gesture, and, consequently, the high speed of its scanning and comparison process.