Design of Gesture Recognition System for Real Time Applications

Abstract

Goal of gesture recognition system is to create a system which can identify specific human gestures and use them to convey information for device control. Hand gesture recognition system can be used for interfacing between computer and human using hand gesture. They are efficient for natural and intuitive human-computer interaction. To achieve this goal, computers should be able to visually recognize hand gestures from video input. We propose a new architecture to solve the problem of real-time gesture recognition. The fundamental idea is to use a combination of hand gestures to control various functionalities. This will include two parts, first is to track the movement of the hand and secondly is to track the orientation of the hand. This paper presents a robust and efficient technique for gesture recognition. The OpenCV library provides us a greatly interesting demonstration for object detection. Furthermore, it provides programs (or functions) that they used to train classifiers for their gesture detection system, called HaarTraining, so that we can create our own object classifiers using these functions. Our working environment is Visual Studio on Windows 7. The objective of this project is to develop an application for recognition of hand gestures with reasonable accuracy and thus creating windows media player compatible remote control.