Connectionist object recognition: methods and methodologies

Abstract

An overview of different connectionist approaches for object recognition is presented. These approaches are first of all classified on the basis of functional characteristics and structural characteristics of the networks. Atthe nextlevel, these are partitioned on the basis of their underlying assumptions and the types of recognition problem that they handle. Their principles and key features are highlighted. The issue of mixed category perception (in thecontextof multipleobject recognition) is addressed. A comparison of the characteristics of various application-specific systems is provided in a tabular form. Some of the basic issues to be considered while building a connectionist system for object recognition are finally listed.