Classifying gestures by using a self-organizing neural network

One way to improve information technology systems is to allow the computer user to communicate in a more natural way than through the use of the keyboard. One approach to developing such novel input devices is the recognition of gestures. In this sense, the main goal of this paper is to develop an adaptive interface to make the communication easier for people with psychomotive disabilities. The developed prototype uses gestural input. Animation software has been used for obtaining a wide range of gestures. To use these gestures both as input patterns and to associate them with their appropriate output, we use the generalisation properties of self-organising neural networks. This type of neural network learns to recognise features from the gestures obtained by the animation software; in addition it can generalise from this information to classify other inaccurate or ill-formed gestures