A Hierarchical Neural Object Classifier for Subsymbolic-Symbolic Coupling

Abstract

A prototype based hierarchical classifier is established as a link between subsymbolic and symbolic data processing. During learning the classifier generates a hierarchy of prototypes. These prototypes constitute a taxonomy of objects. By assigning confidence values to the prototypes a classification request may also return symbols with confidence values.

For performance evaluation the classifier was applied to the task of visual object categorization on two data sets, one real-world and one artificial. Orientation histograms on subimages were utilized as features. The hierarchy generated proved to be very stable across the different cross-validation runs. With the currently very simple feature extraction method, classification accuracies of about 80% to 90% were attained.