3D arm movement recognition using syntactic pattern recognition

Gesture-based applications widely range from direct manipulation interfaces to speaking aids for the deaf. The crucial point in recognizing gestures i s that it requires great computational power to deal with spatio-temporal p atterns. In this paper, a syntactic approach is proposed to provide a simpl e recognition algorithm. In order to verify the proposed method, we apply i t to recognize 3D arm movements involved in the Taiwanese Sign Language. We extract prime patterns from the input patterns. The classification is then accomplished by deciding which one of possible arm movements can produce t he sequence of primary patterns. Experiments were conducted to confirm the effectiveness of the method. (C) 2000 Elsevier Science Ltd. All rights rese rved.