Vision & Cognition Laboratory

Department of Computer Science, Drexel University

 
home  |  projects  |  people  |  publications  |  facilities  |  sponsors

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