A rotation invariant approach on static-gesture recognition using boundary histograms and neural networks

The appropriate selection of feature extraction method plays an important role in designing a pattern recognition system. The proper representation of features contributes to a significant improvement of the classifier performance and also to the reduction of time processing. The purpose of this study is to present a description of hand's posture features based on boundary histograms. The use of histograms aims to deal with two problems: the chain small magnitude circular-shift problem caused by posture rotation and, to attenuate the non-linearity caused by shape differences when performing gesture postures. We also present a fast search start point algorithm for the boundary chain that gives a rotation invariance property to the system. The performance was evaluated using 26 postures of American Sign Language, and a comparison with other algorithms is presented. As result we obtained a robust method to be used in largescale applications using neural networks.