Classifying pixels by means of fuzzy relations

Most of the classification models assume, in a direct or indirect way, the possibility of a representation of the object to be classified within a goo d properties space, in which one is able to define some distances. Quite of ten this representation, which usually is the base of intuitive arguments m ade by the decision maker, is elaborated from a systematic comparison betwe en different available options. The target of this article is to model a cl assification problem in the case that a comparative analysis is an essentia l part of the available information. This will be accomplished by using a d escription of the option set quality.