Conference item icon

Conference item

Obj cut

Abstract:
In this paper we present a principled Bayesian method for detecting and segmenting instances of a particular object category within an image, providing a coherent methodology for combining top down and bottom up cues. The work draws together two powerful formulations: pictorial structures ( PS ) and Markov random fields (MRFs) both of which have efficient algorithms for their solution. The resulting combination, which we call the Object Category Specific MRF, suggests a solution to the problem that has long dogged MRFs namely that they provide a poor prior for specific shapes. In contrast, our model provides a prior that is global across the image plane using the PS. We develop an efficient method, OBJ CUT, to obtain segmentations using this model. Novel aspects of this method include an efficient algorithm for sampling the PS model, and the observation that the expected log likelihood of the model can be increased by a single graph cut. Results are presented on two object categories, cows and horses. We compare our methods to the state of the art in object category specific image segmentation and demonstrate significant improvements.
Publication status:
Published
Peer review status:
Reviewed (other)

Actions

Access Document

Files:
Publisher copy:
10.1109/cvpr.2005.249

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Lady Margaret Hall
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Brasenose College
Role:
Author
ORCID:
0000-0002-8945-8573


More from this funder
Funder identifier:
https://ror.org/00k4n6c32


Publisher:
IEEE Computer Society
Host title:
Proceedings : 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition : CVPR 2005
Place of publication:
Los Alamitos, California, US
Publication date:
2005-07-25
Event title:
2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
Event series:
Conference on Computer Vision and Pattern Recognition (CVPR)
Event location:
San Diego, CA, USA
Event start date:
2005-06-20
Event end date:
2005-06-25
DOI:
ISSN:
1063-6919
ISBN-10:
0769523722
ISBN-13:
9780769523729


Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP