Aspects of high level computer vision using fuzzy sets

Fuzzy set theory is making many inroads into the handling of uncertainty in various aspects of image processing and computer vision. High level computer vision is a place that holds great potential for fuzzy sets because of its natural linguistic capabilities. Scene description, i.e., the language-based representation of regions and their relationships, for either humans or higher automated reasoning provides an excellent opportunity. In this paper we discuss aspects of scene interpretation involving linguistic descriptions of spatial relations between image objects.