Development of a hand pose recognition system on an embedded computer using Artificial Intelligence

The recognition of hand gestures is a very interesting research topic due to the growing demand in recent years in robotics, virtual reality, autonomous driving systems, human-machine interfaces and in other new technologies. Despite several approaches for a robust recognition system, gesture recognition based on visual perception has many advantages over devices such as sensors, or electronic gloves. This paper describes the implementation of a visual-based recognition system on a embedded computer for 10 hand poses recognition. Hand detection is achieved using a tracking algorithm and classification by a light convolutional neural network. Results show an accuracy of 94.50%, a low power consumption and a near real-time response. Thereby, the proposed system could be applied in a large range of applications, from robotics to entertainment.

I. Introduction

Hand gesture recognition is one obvious strategy to build user-friendly interfaces between machines and users. In the near future, hand posture recognition technology would allow for the operation of complex machines and smart devices through only series of hand postures, finger and hand movements, eliminating the need for physical contact between man and machine. Hand gesture recognition on images from common single camera is a difficult problem because occlusions, variations of posture appearance, differences in hand anatomy, etc. Despite these difficulties, several approaches to gesture recognition on color images has been proposed during the last decade [1] .