Conference item icon

Conference item

Cats and dogs

Abstract:
We investigate the fine grained object categorization problem of determining the breed of animal from an image. To this end we introduce a new annotated dataset of pets covering 37 different breeds of cats and dogs. The visual problem is very challenging as these animals, particularly cats, are very deformable and there can be quite subtle differences between the breeds. We make a number of contributions: first, we introduce a model to classify a pet breed automatically from an image. The model combines shape, captured by a deformable part model detecting the pet face, and appearance, captured by a bag-of-words model that describes the pet fur. Fitting the model involves automatically segmenting the animal in the image. Second, we compare two classification approaches: a hierarchical one, in which a pet is first assigned to the cat or dog family and then to a breed, and a flat one, in which the breed is obtained directly. We also investigate a number of animal and image orientated spatial layouts. These models are very good: they beat all previously published results on the challenging ASIRRA test (cat vs dog discrimination). When applied to the task of discriminating the 37 different breeds of pets, the models obtain an average accuracy of about 59%, a very encouraging result considering the difficulty of the problem.
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.1109/cvpr.2012.6248092

Authors

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:
New College
Role:
Author
ORCID:
0000-0003-1374-2858
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Brasenose College
Role:
Author
ORCID:
0000-0002-8945-8573


Publisher:
IEEE
Host title:
2012 IEEE Conference on Computer Vision and Pattern Recognition
Pages:
3498-3505
Publication date:
2012-07-26
Event title:
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012)
Event location:
Providence, RI, USA
Event website:
https://www.computer.org/csdl/proceedings/cvpr/2012/12OmNwdbV00
Event start date:
2012-06-16
Event end date:
2012-06-21
DOI:
ISSN:
1063-6919
EISBN:
978-1-4673-1228-8
ISBN:
978-1-4673-1226-4


Language:
English
Keywords:
Pubs id:
355067
Local pid:
pubs:355067
Deposit date:
2024-07-18
ARK identifier:

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