The Robotics Institute

Carnegie Mellon Robotics Institute

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.

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.

Keywords

image segmentation, graph partitioning, repulsion, dual graphs, object segmentation, shape selection, cue integration

Notes

Sponsor: DARPA

Grant ID: ONR N00014-00-1-0915 and NSF IRI-9817496

Text Reference

Stella Yu and Jianbo Shi, "Perceiving Shapes through Region and Boundary Interaction," tech. report CMU-RI-TR-01-21, Robotics Institute, Carnegie Mellon University, July, 2001

BibTeX Reference

@techreport{Yu_2001_3764,
   author = "Stella Yu and Jianbo Shi",
   title = "Perceiving Shapes through Region and Boundary Interaction",
   booktitle = "",
   institution = "Robotics Institute",
   month = "July",
   year = "2001",
   number= "CMU-RI-TR-01-21",
   address= "Pittsburgh, PA",
}

The Robotics Institute

Menu