"We do dishes, but we don't do windows": Function-based modeling and recognition of rigid objects

Generic recognition for computer vision is a goal that is still far from reality. Part of the problem rests in the inherent limitations of current "model-based" vision. Our approach moves away from specific geometric or structural models arid instead focuses on the functionality of the object as the property which drives the recognition process. This results in a representation that is generic in the sense of capturing an entire category of objects. One important assumption underlying the form and function approach is that a "small" number of "primitive" concepts about shape, physics and causation will suffice to define the functionality of a broad range of categories. If multiple new "primitives" were required to define each additional category, then much of the advantage of the function-based approach over the traditional model-based approach would be lost. This paper presents some initial experimental results from the GIUJFF-3 system, which uses function-based representation to recognize rigid objects in the superordinate category dishes. The performance of this system has been evaluated on a database of approximately 200 shapes.Conference ProceedingsPublished presentatio