Synthesis of Automatic Recognition Systems Based on Properties Commonality

Abstract

The paper explores an actual applied problem related to the synthesis of automatic recognition systems. The conceptual base of synthesis is determined by the methods of describing and separating classes. Three basic principles are known: enumeration of class members, commonality of properties, and clustering. The report proposes an original method for implementing the principle of commonality of properties, based on the search for combinations of features that provide classes distinguishing. The efficiency of the approach is confirmed by the results of a numerical experiment