Vision-based user interfaces: methods and applications

Within the class of perceptive user interfaces (i.e. interfaces providing the computer with perceptive capabilities), artificial vision is being exploited more and more as a new input modality, in addition to or in replacement of standard interaction paradigms. The aim of this paper is to provide a global view on the field of vision-based interfaces (VBIs), through the analysis of the methods used for their implementation and the exploration of the practical systems in which they have been em-ployed. The focus will mostly be on techniques and prototypes intended for office and home PC-based use, as we are mainly interested in vision technology applied to ordinary computing environ-ments. After a brief introduction to basic concepts about interfaces and image processing, the attention will be shifted to the four main areas in which VBIs find their maximum expression, namely head tracking, face/facial expression recognition, eye tracking and gesture recognition.