Tractable and Reliable Registration of 2D Point Sets
(2014) 13th European Conference on Computer Vision - ECCV 2014 8689. p.393-406- Abstract
- This paper introduces two new methods of registering 2D point sets over rigid transformations when the registration error is based on a robust loss function. In contrast to previous work, our methods are guaranteed to compute the optimal transformation, and at the same time, the worst-case running times are bounded by a low-degree polynomial in the number of correspondences. In practical terms, this means that there is no need to resort to ad-hoc procedures such as random sampling or local descent methods that cannot guarantee the quality of their solutions.
We have tested the methods in several different settings, in particular, a thorough evaluation on two benchmarks of microscopic images used for histologic analysis... (More) - This paper introduces two new methods of registering 2D point sets over rigid transformations when the registration error is based on a robust loss function. In contrast to previous work, our methods are guaranteed to compute the optimal transformation, and at the same time, the worst-case running times are bounded by a low-degree polynomial in the number of correspondences. In practical terms, this means that there is no need to resort to ad-hoc procedures such as random sampling or local descent methods that cannot guarantee the quality of their solutions.
We have tested the methods in several different settings, in particular, a thorough evaluation on two benchmarks of microscopic images used for histologic analysis of prostate cancer has been performed. Compared to the state-of-the-art, our results show that the methods are both tractable and reliable despite the presence of a significant amount of outliers. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/4644690
- author
- Ask, Erik LU ; Enqvist, Olof LU ; Svärm, Linus LU ; Kahl, Fredrik LU and Lippolis, Giuseppe LU
- organization
- publishing date
- 2014
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Optimization, 2D Registration, L1 norm
- host publication
- Lecture Notes in Computer Science (Computer Vision - ECCV 2014, 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I)
- editor
- Fleet, David ; Pajdla, Tomas ; Schiele, Bernt and Tuytelaars, Tinne
- volume
- 8689
- pages
- 14 pages
- publisher
- Springer
- conference name
- 13th European Conference on Computer Vision - ECCV 2014
- conference dates
- 2014-09-06 - 2014-09-12
- external identifiers
-
- wos:000345524200026
- scopus:84906495656
- ISSN
- 1611-3349
- 0302-9743
- ISBN
- 978-3-319-10589-5 (Print)
- 978-3-319-10590-1 (Online)
- DOI
- 10.1007/978-3-319-10590-1_26
- language
- English
- LU publication?
- yes
- id
- 9edeafb0-fa89-42c4-9f8c-a96f38b6b333 (old id 4644690)
- date added to LUP
- 2016-04-01 09:58:13
- date last changed
- 2025-01-14 02:45:26
@inproceedings{9edeafb0-fa89-42c4-9f8c-a96f38b6b333,
abstract = {{This paper introduces two new methods of registering 2D point sets over rigid transformations when the registration error is based on a robust loss function. In contrast to previous work, our methods are guaranteed to compute the optimal transformation, and at the same time, the worst-case running times are bounded by a low-degree polynomial in the number of correspondences. In practical terms, this means that there is no need to resort to ad-hoc procedures such as random sampling or local descent methods that cannot guarantee the quality of their solutions. <br/><br>
<br/><br>
We have tested the methods in several different settings, in particular, a thorough evaluation on two benchmarks of microscopic images used for histologic analysis of prostate cancer has been performed. Compared to the state-of-the-art, our results show that the methods are both tractable and reliable despite the presence of a significant amount of outliers.}},
author = {{Ask, Erik and Enqvist, Olof and Svärm, Linus and Kahl, Fredrik and Lippolis, Giuseppe}},
booktitle = {{Lecture Notes in Computer Science (Computer Vision - ECCV 2014, 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I)}},
editor = {{Fleet, David and Pajdla, Tomas and Schiele, Bernt and Tuytelaars, Tinne}},
isbn = {{978-3-319-10589-5 (Print)}},
issn = {{1611-3349}},
keywords = {{Optimization; 2D Registration; L1 norm}},
language = {{eng}},
pages = {{393--406}},
publisher = {{Springer}},
title = {{Tractable and Reliable Registration of 2D Point Sets}},
url = {{https://lup.lub.lu.se/search/files/1434748/4644715.pdf}},
doi = {{10.1007/978-3-319-10590-1_26}},
volume = {{8689}},
year = {{2014}},
}