Perceiving Shapes through Region and Boundary Interaction

July 2001

Perceiving Shapes through Region and Boundary Interaction

Authors:

Stella Yu and Jianbo Shi
Technical Report
CMU-RI-TR-01-21

Abstract:

We present a computational algorithm for shape perception by studying the interaction between region and boundary cues. We formulate this problem in a graph partitioning framework, where region cues defined on a pixel graph and boundary cues defined on its dual edgel graph are coupled through edge-node incidence relationships. The consistency of simultaneous partitioning on such graphs can thus be guaranteed. We generalize normalized cuts criteria and algorithms to this model for globally optimal solutions. We demonstrate that by incorporating boundary smoothness, objects with heterogeneous region properties can stand out as one group and objects with weak contours can be segmented more readily without the suppression from objects of high contrast. This model can also encode higher-order shape information and preliminary results on shape selection are given.
@techreport{Yu-2001-8269,
author = {Stella Yu And Jianbo Shi},
title = {Perceiving Shapes through Region and Boundary Interaction},
year = {2001},
month = {July},
institute = {Carnegie Mellon University},
address = {Pittsburgh, PA},
number = {CMU-RI-TR-01-21},
keywords = {image segmentation, graph partitioning, repulsion, dual graphs, object segmentation, shape selection, cue integration},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.