Threshold Finite State Machine for Vision Based Gesture Recognition

Abstract

Vision-based hand gesture recognition is a popular research topic for human-computer interaction (HCI). Gestures provide a rich and intuitive form of interaction for controlling robots. We have earlier developed a gesture model as a sequence of key frames each bearing information about its duration. These constitute a finite state machine (FSM). In this paper we propose a threshold based FSM by incorporating some additional features in the FSM. These additional features are in terms of different thresholds. These new features greatly enhance the gesture recognition accuracy. We get recognition rate of about 96%, which demonstrate that our proposed threshold FSM is ideal for Human Computer Interaction (HCI) platform.