Object Classification based on Visual Classes

Abstract

This article introduces the concept of visual classes as a general framework for object classification. Based on a statistical object representation, visual classes associate similar appearances of objects. Such visual classes are implicit in many object representation schemes (geometric as well as appearance based models). We argue that the identification of visual classes provides a powerful tool for object classification as a first step to object classification which depends on information provided for recognition, including context dependency and relations in space and time between objects. Based on a general statistical object representation, the article introduces an extraction and representation of visual classes. First experimental results are given in order to motivate the validity of the concept.