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
Discrete approximations of affine Gaussian receptive fields
KTH, School of Computer Science and Communication (CSC), Computational Science and Technology (CST). (Computational Brain Science Lab)ORCID iD: 0000-0002-9081-2170
2017 (English)Report (Other academic)
Abstract [en]

This paper presents a theory for discretizing the affine Gaussian scale-space concept so that scale-space properties hold also for the discrete implementation.

Two ways of discretizing spatial smoothing with affine Gaussian kernels are presented: (i) by solving semi-discretized affine diffusion equation as derived by necessity from the requirement of a semi-group structure over a continuum of scale parameters as parameterized by a family of spatial covariance matrices and obeying non-creation of new structures from any finer to any coarser scale as formalized by the requirement of non-enhancement of local extrema and (ii) a set of parameterized 3x3-kernels as derived from an additional discretization of the above theory along the scale direction and with the parameters of the kernels having a direct interpretation in terms of the covariance matrix of the composed discrete smoothing operation.

We show how convolutions with the first family of kernels can be implemented in terms of a closed form expression for the Fourier transform and analyse how a remaining degree of freedom in the theory can be explored to ensure a positive discretization and optionally also achieve higher-order discrete approximation of the angular dependency of the shapes of the affine Gaussian kernels.

We do also show how discrete directional derivative approximations can be efficiently implemented to approximate affine Gaussian derivatives as constituting a canonical model for receptive fields over a purely spatial image domain and with close relations to receptive fields in biological vision.

Place, publisher, year, edition, pages
2017.
Keyword [en]
scale space, scale, affine, receptive field, Gaussian kernel, discrete, spatial, spatio-chromatic, double-opponent, feature detection, computer vision
National Category
Computer Vision and Robotics (Autonomous Systems) Mathematics
Identifiers
URN: urn:nbn:se:kth:diva-199589OAI: oai:DiVA.org:kth-199589DiVA: diva2:1063218
Projects
Scale-space theory for invariant and covariant visual receptive fields
Funder
Swedish Research Council, 2014-4083
Note

QC 20170110

Available from: 2017-01-09 Created: 2017-01-09 Last updated: 2017-01-10Bibliographically approved

Open Access in DiVA

fulltext(1442 kB)23 downloads
File information
File name FULLTEXT01.pdfFile size 1442 kBChecksum SHA-512
c2f020ef4c0379f3cd9b046eba6f14e7657974d9454efcceaef77ff788cbbfe37981cdb20da5071f8ff16a924d03c1b301c7cfc2e551f2bf9a164f3966d6423c
Type fulltextMimetype application/pdf

Other links

arXiv:1701.02127

Search in DiVA

By author/editor
Lindeberg, Tony
By organisation
Computational Science and Technology (CST)
Computer Vision and Robotics (Autonomous Systems)Mathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 23 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

Total: 389 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