Recognition by Functional Parts

View/ Open
Date
1998-10-15Author
Rivlin, Ehud
Dickinson, Sven J.
Rosenfeld, Azriel
Metadata
Show full item recordAbstract
(Also cross-referenced as CAR-TR-703)
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 by parts" shape recognition framework to support
"recognition by functional parts", by com bining a set of functional
primitives and their relations with a set 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 themselves to range images of unoccluded scenes.
We show how these shape primitives and relations can be easily 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) object
recognition and expected (top-down) object recognition. We demonstrate
the approach on a simple domain by recognizing a restricted class of
hand-tools from 2-D images.