MDL Patch Correspondences on Unlabeled Images
Author
Summary, in English
Automatic construction of Shape and Appearance Models from examples
via establishing correspondences across the training set has been successful in the last decades.
One successful measure for establishing correspondences of high quality is minimum description length (MDL).
In other approaches it has been shown that parts+geometry models which model the appearance of parts of the object and the geometric relation between the parts
have been successful for automatic model building.
In this paper it is shown how to fuse the above approaches and use MDL to
fully automatically build optimal parts+geometry models from unlabeled
images.
via establishing correspondences across the training set has been successful in the last decades.
One successful measure for establishing correspondences of high quality is minimum description length (MDL).
In other approaches it has been shown that parts+geometry models which model the appearance of parts of the object and the geometric relation between the parts
have been successful for automatic model building.
In this paper it is shown how to fuse the above approaches and use MDL to
fully automatically build optimal parts+geometry models from unlabeled
images.
Department/s
Publishing year
2008
Language
English
Pages
3249-3253
Publication/Series
19th International Conference on Pattern Recognition, vols 1-6
Document type
Conference paper
Publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
Topic
- Mathematics
Conference name
19th International Conference on Pattern Recognition (ICPR 2008)
Conference date
2008-12-08 - 2008-12-11
Conference place
Tampa, FL
Status
Published
ISBN/ISSN/Other
- ISSN: 1051-4651
- ISBN: 978-1-4244-2174-9