Incomplete classifications of a finite set of objects using monotone systems (Q920517)

The paper is dedicated to incomplete classifications. An incomplete classification is a method which identifies a special class of objects (e.g. background) and then assigns the rest of objects to disjoint classes. The authors introduce an incomplete classification method based on the identification of the minimal cores of a monotone system. The proposed algorithm does not depend neither on the number of classes nor on the number of objects involved in the process of classification.