Accelerometer Based Static Gesture Recognition and Mobile Monitoring System Using Neural Networks

Abstract

Gesture recognition enables humans to communicate with the machine and interact naturally without any mechanical devices. A lot of research has been already done in the field of gesture recognition using different mechanism and algorithms. The majority of work in this field is done using Image processing techniques1 and methodologies. This paper aims to propose a cost effective low power wearable wrist band to control the locomotion of robot using static gesture from hand which leads to the advance concept of unmanned vehicle. An artificial neural network (ANN) trained with a Learning Vector Quantization (LVQ) algorithm was used to train and recognize arm gesture. The results show that the system allows the control of a robot in an intuitive way. However, the achieved recognition rate of postures has a lot of scope for improvement by compromising the system response time.