Vision Based Analysis of Hand Gesture Recognition for Human Computer Interaction (HCI)

This paper presents a static hand gesture recognition based on function classification using Multi Class Support vector Machine (SVM). Gestures have long been studied as a communication technique that can possibly deliver more instinctive, a powerful tool supporting efficient and perceptive methods for interaction with our computers. The data acquisition was achieved using high resolution Logitech c270 web camera. The different hand gestures were mathematically processed individually using Discrete Cosine Transform (DCT) and singular Value Decomposition (SVD) and then classified using SVM. The accuracy rate of function classification for DCT and SVD were 94 % and 98%.