Object Recognition by a Cascade of Edge Probes

Owen Carmichael and Martial Hebert
British Machine Vision Conference 2002, October, 2002, pp. 103-112.


Download
  • Adobe portable document format (pdf) (481KB)
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 frame the problem of object recognition from edge cues in terms of determining whether individual edge pixels belong to the target object or to clutter, based on the configuration of edges in their vicinity. A classifier solves this problem by computing sparse, localized edge features at image locations determined at training time. In order to save computation and solve the aperture problem, we apply a cascade of these classifiers to the image, each of which computes edge features over larger image regions than its predecessors. Experiments apply this approach to the recognition of real objects with holes and wiry components in cluttered scenes under arbitrary out-of-image-plane rotation.

Keywords
object recognition, computer vision

Notes
Associated Center(s) / Consortia: Vision and Autonomous Systems Center
Associated Lab(s) / Group(s): 3D Computer Vision Group
Number of pages: 10

Text Reference
Owen Carmichael and Martial Hebert, "Object Recognition by a Cascade of Edge Probes," British Machine Vision Conference 2002, October, 2002, pp. 103-112.

BibTeX Reference
@inproceedings{Carmichael_2002_4061,
   author = "Owen Carmichael and Martial Hebert",
   editor = "Paul Rosin, David Marshall",
   title = "Object Recognition by a Cascade of Edge Probes",
   booktitle = "British Machine Vision Conference 2002",
   pages = "103-112",
   publisher = "British Machine Vision Association",
   month = "October",
   year = "2002",
   volume = "1",
}