Classification of hand movements using motion templates and geometrical based moments

This paper presents a method for hand gesture classification using a view-based approach for representation and artificial neural network for classification. This approach uses a cumulative image difference technique in which time between the sequences of images is implicitly captured in the representation of action. This results in the construction of motion history images. These images are used to compute the geometrical image moments, which are invariant to scale, rotation and translation. The classification is then performed using back propagation based multilayer perceptron (MLP) artificial neural network (ANN). The preliminary experiments show that such a system can classify human hand gestures with a classification accuracy of 96%.