Skeletal Shape Abstraction
Learning a class prototype from a set of exemplars is an
important challenge facing researchers in object categorization.
Although the problem is receiving growing interest, most approaches
assume a one-to-one correspondence among local features, restricting
their ability to learn true abstractions of a shape. We present a
new technique for learning an abstract shape prototype from a set of
exemplars whose features are in many-to-many correspondence.
Focusing on the domain of silhouettes, we represent a silhouette as
a medial axis graph, whose nodes correspond to ``parts'' defined by
medial branches and whose edges connect adjacent parts. Given a pair
of medial axis graphs, we establish a
many-to-many correspondence between their nodes to find
correspondences among articulating parts. Based on these
correspondences, we recover the abstracted medial axis graph along
with the positional and radial attributes associated with its nodes.
Primary Reference
TBA |