Issue No. 03 - March (1995 vol. 17)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.368189
<p><it>Abstract</it>—Underlying recognition is an organization of objects and their parts into classes and hierarchies. A representation of parts for recognition requires that they be invariant to rigid transformations, robust in the presence of occlusions, stable with changes in viewing geometry, and be arranged in a hierarchy. These constraints are captured in a general framework using notions of a <scp><b>PART-LINE</b></scp> and a <scp><b>PARTITIONING SCHEME</b></scp>. A proposed general principle of “form from function” motivates a particular partitioning scheme involving two types of parts, <scp><b>NECK-BASED</b></scp> and <scp><b>LIMB-BASED</b></scp>, whose psychophysical relevance was demonstrated in [<ref rid="BIBP023939" type="bib">39</ref>]. Neck-based parts arise from narrowings in shape, or the local minima in distance between two points on the boundary, while limb-based parts arise from a <it>pair</it> of negative curvature minima which have “co-circular” tangents. In this paper, we present computational support for the limb-based and neck-based parts by showing that they are invariant, robust, stable and yield a hierarchy of parts. Examples illustrate that the resulting decompositions are robust in the presence of occlusion and clutter for a range of man-made and natural objects, and lead to natural and intuitive parts which can be used for recognition.</p>
Parts, recognition, invariance, robustness, stability, salience, scale.
B. B. Kimia and K. Siddiqi, "Parts of Visual Form: Computational Aspects," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 17, no. , pp. 239-251, 1995.