A Situation-Bayes View of Object Recognition Based on SymGeons
Fiora Pirri, Massimo Romanò · 2002
We describe in this paper a high level recognition system. The system implements a new approach to model-based object recognition, fully exploiting compositionality of representa-tions: from the analysis of the elementary signs in the im-age to the analysis and description of an object structure and, finally, to the interpretation of the scene. Perceptual reason-ing, likewise the symbolic description of the scene are stated in the Situation Calculus. A description is a specification of an object in terms of its single components which, in turn, are specified using SymGeons, a generalization of parametric Geons. The cognitive process of recognition relies on Sym-Geons recognition. Here we extend the concepts of aspect graphs and hierarchical aspect graph to obtain a Bayes net-work integrating composition of aspects together with com-position of features.