MDL Patch Correspondences on Unlabeled Images
(2008) 19th International Conference on Pattern Recognition (ICPR 2008) p.3249-3253- Abstract
- 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.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1275697
- author
- Karlsson, Johan
LU
and Åström, Karl
LU
- organization
- publishing date
- 2008
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 19th International Conference on Pattern Recognition, vols 1-6
- pages
- 3249 - 3253
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 19th International Conference on Pattern Recognition (ICPR 2008)
- conference location
- Tampa, FL
- conference dates
- 2008-12-08 - 2008-12-11
- external identifiers
-
- wos:000264729001314
- ISSN
- 1051-4651
- ISBN
- 978-1-4244-2174-9
- language
- English
- LU publication?
- yes
- id
- 341c0787-7aac-47d9-b8a4-37d2b2eef3d2 (old id 1275697)
- date added to LUP
- 2016-04-01 13:48:19
- date last changed
- 2020-12-22 02:16:17
@inproceedings{341c0787-7aac-47d9-b8a4-37d2b2eef3d2, abstract = {{Automatic construction of Shape and Appearance Models from examples <br/><br> via establishing correspondences across the training set has been successful in the last decades.<br/><br> One successful measure for establishing correspondences of high quality is minimum description length (MDL).<br/><br> 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<br/><br> have been successful for automatic model building.<br/><br> In this paper it is shown how to fuse the above approaches and use MDL to<br/><br> fully automatically build optimal parts+geometry models from unlabeled <br/><br> images.}}, author = {{Karlsson, Johan and Åström, Karl}}, booktitle = {{19th International Conference on Pattern Recognition, vols 1-6}}, isbn = {{978-1-4244-2174-9}}, issn = {{1051-4651}}, language = {{eng}}, pages = {{3249--3253}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{MDL Patch Correspondences on Unlabeled Images}}, year = {{2008}}, }