Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
Shape from Texture from a Multi-Scale Perspective
KTH, School of Computer Science and Communication (CSC), Computational Biology, CB.ORCID iD: 0000-0002-9081-2170
1993 (English)In: Fourth International Conference on Computer Vision, 1993. Proceedings: ICCV'93 / [ed] H.-H. Nagel, IEEE conference proceedings, 1993, 683-691 p.Conference paper, Published paper (Refereed)
Abstract [en]

The problem of scale in shape from texture is addressed. The need for (at least) two scale parameters is emphasized; a local scale describing the amount of smoothing used for suppressing noise and irrelevant details when computing primitive texture descriptors from image data, and an integration scale describing the size of the region in space over which the statistics of the local descriptors is accumulated.

A novel mechanism for automatic scale selection is used, based on normalized derivatives. It is used for adaptive determination of the two scale parameters in a multi-scale texture descriptor, thewindowed second moment matrix, which is defined in terms of Gaussian smoothing, first order derivatives, and non-linear pointwise combinations of these. The same scale-selection method can be used for multi-scale blob detection without any tuning parameters or thresholding.

The resulting texture description can be combined with various assumptions about surface texture in order to estimate local surface orientation. Two specific assumptions, ``weak isotropy'' and ``constant area'', are explored in more detail. Experiments on real and synthetic reference data with known geometry demonstrate the viability of the approach.

Place, publisher, year, edition, pages
IEEE conference proceedings, 1993. 683-691 p.
Keyword [en]
Computer vision, Data mining, Geometry, Image analysis, Laboratories, Noise shaping, Shape, Smoothing methods, Statistics, Surface texture
National Category
Computer Science Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:kth:diva-58571DOI: 10.1109/ICCV.1993.378146ISBN: 0-8186-3870-2 (print)OAI: oai:DiVA.org:kth-58571DiVA: diva2:473366
Conference
4th International Conference on Computer Vision (Berlin, Germany), 11-14 May 1993
Note

QC 20130422

Available from: 2012-01-05 Created: 2012-01-05 Last updated: 2013-04-23Bibliographically approved

Open Access in DiVA

fulltext(456 kB)444 downloads
File information
File name FULLTEXT01.pdfFile size 456 kBChecksum SHA-512
628cf5a31c58daa5fcb371f55f0ec66a6d8bec42a70a35e2be062a09a3d214bcf823170306fc4633711b73d8bdd0573c338dec3db99c474d80e0d0f6be7caf9d
Type fulltextMimetype application/pdf

Other links

Publisher's full textAt author's home pageIEEEXplore

Authority records BETA

Lindeberg, Tony

Search in DiVA

By author/editor
Lindeberg, TonyGårding, Jonas
By organisation
Computational Biology, CB
Computer ScienceComputer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 444 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: 125 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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