Hand gesture recognition using fourier descriptors

Accurate, real-time hand gesture recognition is a challenging and crucial task due to the need of more natural human-computer interaction methods. The major problem lies in fining a good compromise between the accuracy of recognition and the computational load for the algorithm to run in real-time. In this paper we propose a method for static hand gesture recognition using Fourier descriptors for feature extraction with different classifiers. Fourier descriptors have the advantage of giving a set of features that are invariant to rotation, translation and scaling. They are also efficient in terms of speed as they only use a small number of points from the entire image. The proposed method is evaluated using images from the Cambridge Hand Gesture Dataset at different number of features and different classifiers. The effectiveness of the method is shown through simulation results.