- Author
- Year
- 2015
- Title
- Per-patch metric learning for robust image matching
- Event
- 2015 IEEE International Conference on Image Processing
- Book/source title
- 2015 IEEE International Conference on Image Processing: ICIP 2015: proceedings: 27-30 September 2015, Québec City, Canada
- Pages (from-to)
- 3846-3850
- Publisher
- Piscataway, NJ: IEEE
- ISBN
- 9781479983391
- Document type
- Conference contribution
- Faculty
- Faculty of Science (FNWI)
- Institute
- Informatics Institute (IVI)
- Abstract
-
We propose a patch-specific metric learning method to improve matching performance of local descriptors. Existing methodologies typically focus on invariance, by completely considering, or completely disregarding all variations. We propose a metric learning method that is robust to only a range of variations. The ability to choose the level of robustness allows us to fine-tune the trade-off between invariance and discriminative power. We learn a distance metric for each patch independently by sampling from a set of relevant image transformations. These transformations give a-priori knowledge about the behavior of the query patch under the applied transformation in feature space. We learn the robust metric by either fully generating only the relevant range of transformations, or by a novel direct metric. The matching between query patch and data is performed with this new metric. Results on the ALOI dataset show that the proposed method improves performance of SIFT by 6.22% for geometric and 4.43% for photometric transformations.
- URL
- go to publisher's site
- Language
- English
- Persistent Identifier
- https://hdl.handle.net/11245/1.510260
Disclaimer/Complaints regulations
If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library, or send a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible.