View organization and matching of free-form objects

We address the problem of constructing view aspects of free-form objects for efficient matching during recognition. We introduce a novel view representation based on "shape spectrum" features, and propose a general and powerful technique for organizing multiple views of objects of complex shape and geometry into compact and homogeneous clusters. Our view-grouping technique obviates the need for surface segmentation and edge detection. We also demonstrate that when view-grouping is exploited to structure a large model base of views, even with a relatively flat (two-tiered) arrangement a small set of plausible correct matches can be determined quickly. Experimental results on a database of 3,200 views of 10 objects show that when tested with 1,000 independent views, our matching technique examined, on the average, only 23.5% of the database for correct classification.