Static Hand Gesture Recognition and its Application based on Support Vector Machines

Abstract

Hand gesture recognition plays an important role in applications such as human computer interface, remote controlling, and virtual environments (VEs). A novel hand gesture recognition algorithm is proposed to identify whether the hand can meet the requirements of driving license test or not. The algorithm is mainly based on Hu moments and support vector machines (SVMs). Firstly, Hu invariant moments are extracted into a vector of 7 dimensions. Then, a support vector machine is used to find a decision border between the integrated hand and the defected hand. At testing time, a decision is taken using the previously learned SVMs. This algorithm brings a 3.5% error rate of identifying the hand.