Features Fitting using Multivariate Gaussian Distribution for Hand Gesture Recognition

Abstract

Gesturing and posturing are two common tools that used by the human to support his oral language during ommunication with other people which helped and proved to deliver the message easily and correctly especially when those two persons were on some sight distance, in this paper we have implemented a novel approach for providing such intuitive interface but this time will be used between human and human-made machine for human computer interaction purposes which helps the hearing impaired people as well, our approach based on feature distribution using bivariate Gaussian distribution function for finding a permanent remedy for translation, scaling, as well as rotation as one pack, these features are controlled by the direction of hand object which is extracted using our direction analysis algorithm, central moments are used herein for feature vector representation and static gesture recognition which proves its robustness, we have achieved a remarkable recognition rates especially with few number of training samples which is our aim of this study with a recognition time of 0.794 second.