Hummel and Biederman have offerd a network theory dubbed the recognition by components model. The crucial innovation in this model, is an intermediate level of detecotrs, sensitive to geons. Geons serve as the basic building blocks of all the objects we recognize. Geons are simple shapes, such as cyliinders, cones, and blocks. We need three dozen different geons to describe every object in the world. These geons can then be combined in various ways. The RBC model, uses a hierarchy of detecotrs. The lowest-level detecotrs are feature detecotrs, which respond to edges, curves, vertices and so on. These detectors in turn activate the geon detectors. Higher levels of detecotrs are then sensitive to combinations of geons. These assemblies activate the object model , a representation of the complete, recognized object. The presence of the geon and geon-assembly levels, within this hierarchy, buys us several advantages. Geons can be identified from virtually any angle of view, and so recognition based on geons is viewpoint-independent. Several lines of evidence seem to confirm that geons do play a rol in recognition: recognition is more difficlut if the geons are hard to identify.