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

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Magnitude Representation of Features in Image Analysis
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
1989 (English)In: Proceedings of the 6th Scandinavian Conference on Image Analysis : Oulu, June 19-22, 1989 / [ed] Matti Pietikainen and Juha Röning, Pattern Recognition Society of Finland , 1989, 212-219 p.Conference paper, Published paper (Refereed)
Abstract [en]

We have in the preceding sections studlied the use of magnitude representation for feature variables. There are several indications that such a representation may be used in biological visual systerms.

The natural introduction of a nonlinearity may be most useful for many purposes. This has been studied for the implementation of penalty function operations. Such operations show great promise as they can be made very specific based on their zero-crossing property.

There is a great deal of indication that inhibition or penalty mechanisms are very important in neural systems. It has e.g. been found that in the cerebellar structure almost all synapses are inhibitory. This could indicate that inhibitory or penalty matching is a primary mechanism in biological vision systems.

Place, publisher, year, edition, pages
Pattern Recognition Society of Finland , 1989. 212-219 p.
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:liu:diva-51313ISBN: 9789529008902 (print)OAI: oai:DiVA.org:liu-51313DiVA: diva2:274022
Conference
The 6th Scandinavian Conference on Image Analysis, June 19-22, Oulu, Finland
Available from: 2009-10-26 Created: 2009-10-26 Last updated: 2016-12-29Bibliographically approved

Open Access in DiVA

Magnitude Representation of Features in Image Analysis(2710 kB)24 downloads
File information
File name FULLTEXT01.pdfFile size 2710 kBChecksum SHA-512
d3eed5911eb59b785e9c7386a9e5c85fca134c690fe2542bc58050a5f4a85036c623ba16ebd36676e0c368bdb319f00517b143eef723a54d620916ff4bc4b2db
Type fulltextMimetype application/pdf

Authority records BETA

Granlund, Gösta H.

Search in DiVA

By author/editor
Granlund, Gösta H.
By organisation
Computer VisionThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 24 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

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 161 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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