Gesture Based Robot Control

Abstract

Vision based techniques provide a natural way for controlling robots. In this paper, we present a visual gesture recognition system for controlling robots by using fuzzy-C - means clustering algorithm. The proposed method is applied for recognizing both static and dynamic hand gestures. In dynamic hand gesture recognition, instead of processing all video frames, key frames are extracted by using Hausdorff' distance method. After key frame extraction, a sequence of static gesture recognition operations is done for recognizing these key frames. The proposed technique requires training prior to its operation. Once trained, the system is ready for recognizing new gestures. A gesture database, consisting of 10 static gesture classes and 500 gesture samples per class and 3 different dynamic gestures, is created. The proposed method is successfully tested for recognizing 5000 new static gestures and 9 dynamic gestures.