Learning and recognising 3D models represented by multiple views by means of methods based on random graphs

The aim of this yticle is to describe and compare the methods based on random graphs (RGs) which are applied to learn and recognize 3D objects represented by multiple views. These methods me based on modelling the objects by means of probabilistic structures that keep 1'' and Zndorder probabilities. That is, multiple views of a 3D object are represented by few RGs. The most important probabilistic stmctures presented in the literature are First-Order Random Graphs (FORGs), FunctionDescribed Graphs (FDGs) and Second-Order Random Graphs(S0RGs). In the learning process, each one of the 3D-object views are represented by an attribute graph (AG), and a group of AGs are synthesized in a RG. In the recognizing process, the view of the object is represented by an AG and then it is compared with the RG that model each one of the 3D-object prototypes. In t h i s paper, it is explained the modelling of the 3D-objects and the methods of learning and recognition based on FORGs, FDGs and SORGs. We show some results of tbe methods for real 3D objects.