Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Gradient sample argument weighting for robust image region description
KTH, School of Electrical Engineering (EES), Signal Processing. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre. KTH, School of Electrical Engineering (EES), Signal Processing.ORCID iD: 0000-0002-2718-0262
2013 (English)In: Proceedings of the 2013 IEEE International Conference on Electronics, Computing and Communication Technologies (IEEE CONECCT), IEEE conference proceedings, 2013, 1-4 p.Conference paper, Published paper (Refereed)
Abstract [en]

The weighting of gradient sample arguments for the creation of descriptors of image regions is studied. The descriptors are interpreted as binned and weighted argument kernel density estimates and thereby their defining attributes are identified as the binning rules and the weighting. The weighting is further studied and four different weighting strategies are analyzed. The naive constant weighting is argued to have a poor robustness to image perturbations. As an answer to this, the customary gradient magnitude weighting is motivated. However, the short-comings of this approach are pointed out and two novel weighting strategies are suggested. The first suggested weighting gives a system parameter determining a distinctiveness to robustness trade-off with the customary magnitude weighting being a special case of it. The second suggested weighting gives a similar robustness as the first one, but at a lower computational cost. Finally, the effects of the different weighting strategies are demonstrated with real imagery data and synthetic perturbations.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2013. 1-4 p.
Keyword [en]
Computational efficiency, Estimation, Histograms, Kernel, Lighting, Noise, Robustness
National Category
Signal Processing Telecommunications
Identifiers
URN: urn:nbn:se:kth:diva-116472DOI: 10.1109/CONECCT.2013.6469287ISI: 000319415800007Scopus ID: 2-s2.0-84875486765ISBN: 978-1-4673-4609-2 (print)OAI: oai:DiVA.org:kth-116472DiVA: diva2:589712
Conference
2013 IEEE International Conference on Electronics, Computing and Communication Technologies (IEEE CONECCT),17 Jan - 19 Jan 2013,Bangalore
Note

QC 20130422

Available from: 2013-05-07 Created: 2013-01-18 Last updated: 2013-07-09Bibliographically approved

Open Access in DiVA

fulltext(110 kB)188 downloads
File information
File name FULLTEXT01.pdfFile size 110 kBChecksum SHA-512
4b322b97a3b189bdb5834c75754b160f292025d16b0c06b3770c8eb6fa9e6783447d878aea8730bd7a71c64832fbdf80e692ae6943b73a4ddff8769c1f310cc4
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopusIEEEXplore

Search in DiVA

By author/editor
Nilsson, John-OlofHändel, Peter
By organisation
Signal ProcessingACCESS Linnaeus Centre
Signal ProcessingTelecommunications

Search outside of DiVA

GoogleGoogle Scholar
Total: 188 downloads
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

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 83 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf