Part-based representations allow for recognition that is robust in the
presence of occlusion, movement, growth, and deletion of portions of
an object, and play an important role in theories of object categoriza
tion and classification. A partitioning theory for visual form is prop
osed that is based on two types of parts: Limb-based parts arise from
a pair of negative curvature minima with evidence for 'good continuati
on' of boundaries on one side; neck-based parts arise from narrowings
in shape. The motivation for this model is computational requirements
for recognition. The psychophysical relevance of this model is address
ed by measuring intrasubject and intersubject consistency in partition
ing tasks and comparing perceived and computed parts. A series of expe
riments were performed in which subjects were required to partition a
variety of biological and nonsense two-dimensional shapes into perceiv
ed components. Specifically, it was examined (1) whether a subject det
ermines components consistently across different trials of the same pa
rtitioning task, (2) whether there is evidence for consistency between
subjects for the same partitioning task, and (3) how the perceived pa
rts compare with limbs and necks resulting from the computational mode
l. The results are interpreted as suggesting that there are high level
s of both intrasubject and intersubject consistency and that a large m
ajority of the perceived parts do in fact correspond to the parts comp
uted on the basis of our model. The implications of our model are disc
ussed in relation to previous experimental results. Intuitive observat
ions concerning the relationship between parts of visual form and thei
r function are then presented. Finally, a role is envisioned for parts
in figure/ground segregation; the notion of a 'parts receptive field'
through which parts can serve as an intermediate representation betwe
en local image features, eg edges, and global object models, is sugges
ted.