Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Appearance based qualitative image description for object class recognition
KTH, Tidigare Institutioner, Numerisk analys och datalogi, NADA.
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
2004 (engelsk)Inngår i: COMPUTER VISION - ECCV 2004, PT 2 / [ed] Pajdla, T; Matas, J, BERLIN: SPRINGER , 2004, Vol. 3022, s. 518-529Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

The problem of recognizing classes of objects as opposed to special instances requires methods of comparing images that capture the variation within the class while they discriminate against objects outside the class. We present a simple method for image description based on histograms of qualitative shape indexes computed from the combination of triplets of sampled locations and gradient directions in the image. We demonstrate that this method indeed is able to capture variation within classes of objects and we apply it to the problem of recognizing four different, categories from a large database. Using our descriptor on the whole image, containing varying degrees of background clutter, we obtain results for two of the objects that are superior to the best results published so far for this database. By cropping images manually we demonstrate that our method has a potential to handle also the other objects when supplied with an algorithm for searching the image. We argue that our method, based on qualitative image properties, capture the large range of variation that is typically encountered within an object class. This means that our method can be used on substantially larger patches of images than existing methods based on simpler criteria for evaluating image similarity.

sted, utgiver, år, opplag, sider
BERLIN: SPRINGER , 2004. Vol. 3022, s. 518-529
Serie
LECTURE NOTES IN COMPUTER SCIENCE, ISSN 0302-9743 ; 3022
Emneord [en]
object recognition, shape, appearance
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-43978ISI: 000221519200041Scopus ID: 2-s2.0-35048840352ISBN: 3-540-21983-8 (tryckt)OAI: oai:DiVA.org:kth-43978DiVA, id: diva2:450902
Konferanse
8th European Conference on Computer Vision. Prague, CZECH REPUBLIC. MAY 11-14, 2004
Merknad
QC 20111024Tilgjengelig fra: 2011-10-24 Laget: 2011-10-19 Sist oppdatert: 2018-01-12bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Scopus

Søk i DiVA

Av forfatter/redaktør
Thureson, JohanCarlsson, Stefan
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetric

isbn
urn-nbn
Totalt: 53 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf