liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
When patches match - a statistical view on matching under illumination variation
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Goethe University of Frankfurt, Germany.
Goethe University of Frankfurt, Germany.
2014 (English)In: 2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), IEEE COMPUTER SOC , 2014, 4364-4369 p.Conference paper (Refereed)
Abstract [en]

We discuss matching measures (scores and residuals) for comparing image patches under unknown affine photometric (=intensity) transformations. In contrast to existing methods, we derive a fully symmetric matching measure which reflects the fact that both copies of the signal are affected by measurement errors (noise), not only one. As it turns out, this evolves into an eigensystem problem; however a simple direct solution for all entities of interest can be given. We strongly advocate for constraining the estimated gain ratio and the estimated mean value offset to realistic ranges, thus preventing the matching scheme from locking into unrealistic correspondences.

Place, publisher, year, edition, pages
IEEE COMPUTER SOC , 2014. 4364-4369 p.
Series
, International Conference on Pattern Recognition, ISSN 1051-4651
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:liu:diva-121335DOI: 10.1109/ICPR.2014.747ISI: 000359818004084ISBN: 978-1-4799-5208-3OAI: oai:DiVA.org:liu-121335DiVA: diva2:853439
Conference
22nd International Conference on Pattern Recognition (ICPR)
Available from: 2015-09-14 Created: 2015-09-14 Last updated: 2015-09-14

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Mester, Rudolf
By organisation
Computer VisionFaculty of Science & Engineering
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 99 hits
ReferencesLink to record
Permanent link

Direct link