Recognition by functional parts [function-based object recognition]

We present an approach to function-based object recognition that reasons about the functionality of an object’s intuitive parts. We extend the popular “recognition b y parts” shape recognition framework to support “recognition by functional parts”, b y combining a set of functional primitives and their relations with a sel of abstract volumetric shape primitives and their relations. Previous approaches have relied on more global object features, often ignoring the problem of object segmentation and thereby restricting theriiselves to range images of unoccluded scenes. We show how these shape primitives and relations can be easdy recovered from superquadric ellipsoids which, in turn, can be recovered from either range or intensity images of occluded scenes. Furthermore, the proposed framework supports both unexpected (bottom-up) obj ec t recognition and expected (top-down) object recognition. We demonstrate the approach on a simple domain b y recognizing a restricted class of hand-tools from 2D images.