Defining bidimensional fuzzy sets for visual coarseness modelling

In this paper, the texture feature "coarseness" is modelled by means of fuzzy sets, relating representative coarseness measures (our reference set) with the human perception of this type of feature. In our study, a wide variety of measures have been analyzed, defining unidemsional and bidimensional fuzzy set for different combination of measures. The fineness human perception has been collected from polls filled by human subjects, performing an aggregation of their assessments by means of OWA operators. Using as reference set a combination of some measures, the membership function corresponding to the fuzzy set is modelled as the function which provides the best fit of the collected data.