GESTURE RECOGNITION SYSTEM

Satish Kumar Kotha, Jahnavi Pinjala, Kavya Kasoju, Manvitha Pothineni

Abstract: This paper presents a novel approach for the gesture recognition system using software. In this paper the real time image is taken and is compared with a training set of images and displays a matched training image. In this approach we have used skin detection techniques for detecting the skin threshold regions, Principle Component Analysis (PCA) algorithm and Linear Discriminant Analysis (LDA) for data compressing and analyzing and K-Nearest Neighbor (KNN), Support Vector Machine (SVM) classification for matching the appropriate training image to the real-time image. The software used is MATLAB. The hand gestures used are taken from the American Sign Language

Keywords: PCA algorithm, LDA algorithm, skin detection, KNN and SVM classification

DOI: https://doi.org/10.15623/ijret.2015.0405019