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
Provably scale-covariant networks from oriented quasi quadrature measures in cascade
KTH, Skolan för elektroteknik och datavetenskap (EECS), Beräkningsvetenskap och beräkningsteknik (CST). (Computational Brain Science Lab)ORCID-id: 0000-0002-9081-2170
2019 (engelsk)Inngår i: Scale Space and Variational Methods in Computer Vision / [ed] M. Burger, J. Lellmann and J. Modersitzki, Springer Berlin/Heidelberg, 2019, Vol. 11603, s. 328-340Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

This article presents a continuous model for hierarchical networks based on a combination of mathematically derived models of receptive fields and biologically inspired computations.

Based on a functional model of complex cells in terms of an oriented quasi quadrature combination of first- and second-order directional Gaussian derivatives, we couple such primitive computations in cascade over combinatorial expansions over image orientations. Scale-space properties of the computational primitives are analysed and it is shown that the resulting representation allows for provable scale and rotation covariance.

A prototype application to texture analysis is developed and it is demonstrated that a simplified mean-reduced representation of the resulting QuasiQuadNet leads to promising experimental results on three texture datasets.

sted, utgiver, år, opplag, sider
Springer Berlin/Heidelberg, 2019. Vol. 11603, s. 328-340
Serie
Lecture Notes in Computer Science, ISSN 0302-9743 ; 11603
HSV kategori
Forskningsprogram
Datalogi
Identifikatorer
URN: urn:nbn:se:kth:diva-244788DOI: 10.1007/978-3-030-22368-7_26Scopus ID: 2-s2.0-85068440199ISBN: 9783030223670 (tryckt)OAI: oai:DiVA.org:kth-244788DiVA, id: diva2:1291606
Konferanse
7th International Conference on Scale Space and Variational Methods in Computer Vision, SSVM 2019; Hofgeismar; Germany; 30 June 2019 through 4 July 2019
Prosjekter
Scale-space theory for covariant and invariant visual perception
Forskningsfinansiär
Swedish Research Council, 2018-03586
Merknad

QC 20190305

Tilgjengelig fra: 2019-02-25 Laget: 2019-02-25 Sist oppdatert: 2019-08-08bibliografisk kontrollert

Open Access i DiVA

fulltext(1179 kB)83 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 1179 kBChecksum SHA-512
5d2472c9f90626a3732e45d4201f10691587a2edc55262fa4c463d3acbdf8be4e04d0ae1933166d8c538b80cd0d955be3c7cc1a273bf063ebd63fd8b336172a8
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopuspreprint at arXiv:1903.00289Conference webpage

Søk i DiVA

Av forfatter/redaktør
Lindeberg, Tony
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 83 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 968 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