We present an aspect-graph approach to 3D object recognition where the
definition of an aspect is motivated by its role in the subsequent recognition
step. Specifically, we measure the similarity between two views by
a 2D shape metric of similarity measuring the distance between the projected,
segmented shapes of the 3D object. This endows the viewing sphere
with a metric which is used to group similar views into aspects, and to
represent each aspect by a prototype. The same shape similarity
metric is then used to rate the similarity between unknown views of unknown
objects and stored prototypes to identify the object and its pose.
The performance of this approach on a database of 18 objects each viewed
in five degree increments along the ground viewing plane is demonstrated.