<![CDATA[The Kinect camera is widely used for capturing human body images and human motion recognition in video game playing, and there are already some research works on gesture recognition. However, to achieve the anti-interference performance, the current recognition algorithms are often complex and tardiness, and most of the applications are based on the incomplete gesture library and not all hand gestures can be recognized. This paper explores a new method and algorithm which can describe all five fingertips for each hand in any time for hand gesture recognition with the Kinect system. The hand images are processed to build the hand models which are then compared with the gesture library for gesture recognition. After hand gestures are recognized with high accuracy and less computing, control commands corresponding to hand gestures are sent from the hand gesture recognition system to a hexagon robot controller wirelessly, the hexagon robot can then be controlled wirelessly and change its shape according to the hand gesture command. Thus the robot can interact with humans promptly through the gesture recognition system. DOI: http://dx.doi.org/10.11591/telkomnika.v11i5.2493]]>
