Parts of visual form: computational aspects

Underlying recognition is an organization of ob jects and their parts into classes and hierarchies A rep resentation of parts for recognition requires that they be invariant to rigid transformations robust in the presence of occlusions stable with changes in viewing geometry and be arranged in a hierarchy These constraints are captured in a general framework using notions of a part line and a parti tioning scheme A proposed general principle of form from function motivates a particular partitioning scheme involv ing two types of parts neck based and limb based whose psychophysical relevance was demonstrated in Neck based parts arise from narrowings in shape or the local minima in distance between two points on the boundary while limb based parts arise from a pair of negative curva ture minima which have co circular tangents In this pa per we present computational support for the limb based and neck based parts by showing that they are invariant robust stable and yield a hierarchy of parts Examples il lustrate that the resulting decompositions are robust in the presense of occlusion and clutter for a range of man made and natural objects and lead to natural and intuitive parts which can be used for recognition