Hand Posture Recognition with Application to Robot Control

In recent years, several researches are being done to improve the means by which humans interact with machines. Having developed a variety of input devices, we still are not completely comfortable with the present human–machine interaction processes. This stirred up the efforts undertaken to make the machines adapt to the human’s natural means of communication which are speech and body language. The objective of this paper is to implement a real-time vision system which offers better comfort to humans while interacting with machines. In our paper, we showed a simple but efficient method to implement a hand posture recognition system and by means of which we control a bot wirelessly through Bluetooth. The simplicity of our method enables fast recognition of the hand postures shown and therefore achieves the real-time continuous control over the bot. Keyword – machine interaction, real-time vision system, hand posture, Bluetooth.