Vision Based Real Time Gesture Recognition

Abstract

With the advent of image processing and computer vision techniques there is a huge advancement going on in the field of bio-metric analysis. Bio-metric analysis is the measurement and statistical analysis of people’s unique physical and behavioral characteristics. A wide range of applications ranging from face recognition to finger print scanning are being developed. One of the applications of bio-metrics is in gesture recognition for human-machine communication, since it leads to a more intuitive interaction and control. This paper describes a vision based real-time gesture recognition system, designed for operating in an automotive environment. We have implemented a system in which the user can change the direction of movement of a bot using gestures. These gesture are converted to commands using image processing algorithms. Commands are transmitted wireless to a robot to move it in a specific direction.