From geons to structure. A note on object representation.

Abstract

Two models of object perception are compared: recognition by components (RBC), proposed by Biederman, and structural information theory (SIT), initially proposed by Leeuwenberg. According to RBC a complex object is decomposed into predefined elementary objects, called geons. According to SIT, the decomposition is guided by regularities in the object. It is assumed that the simplest of all possible interpretations of any object is perceptually preferred. The comparison deals with two aspects of the models. One is the representation of simple objects--various definitions of object axes are considered. It is shown that the more these definitions account for object regularity and thus the more they agree with SIT, the better the object representations predict object classification. Another topic concerns assumptions underlying the models: the identification of geons is mediated by cues which are supposed to be invariant under varying viewpoints of objects. It is argued that such cues are not based on this invariance but on the regularity of actual objects. The latter conclusion is in line with SIT. An advantage of RBC, however, is that it deals with the perceptual process from stimulus to interpretation, whereas SIT merely concerns the outcome of the process, not the process itself.