Pattern Classification through Fuzzy Likelihood

This paper introduces a novel way to compute the membership functionof a fuzzy set approximating the distribution of some observed datastarting with their histogram. This membership function is in turn used toobtain a posteriori probability through a suitable version of the Bayesianformula. The ordering imposed by an overtaking relation between fuzzynumbers translates immediately into a dominance of the a posteriori probabilityof a class over another for a given observed value. In this way acrisp classification is eventually obtained.