Real-time visual static hand gesture recognition system and its FPGA-based hardware implementation

Abstract

Gesture recognition has been paid more and more attention as a new generation of human-computer interaction and visual input mode. In motion sensing games and other applications, gesture recognition is used as the input interface. However, because of its inherent features such as diversity, ambiguity, space-time difference and large computational burden, it is difficult to achieve the real-time application with software, especially in embedded system. Therefore, in this paper we propose a real-time hardware-based gesture recognition system as well as innovative algorithm architecture, which is easy to implement by hardware. Moreover, the operating speed is improved significantly. This paper optimizes the existing fingertip detection algorithms with the proposed essential constraints, which improves the recognition rate to 90.3%. Using parallel and pipeline structure, the gesture recognition system based on FPGA achieves 60 frames per second. The good real-time performance of this gesture recognition system is also attributed to the overall use of synchronous clock design.