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

Direct link
Spatio-featural scale-space
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
2009 (English)In: Scale Space and Variational Methods in Computer Vision: Second International Conference, SSVM 2009, Voss, Norway, June 1-5, 2009. Proceedings / [ed] Xue-Cheng Tai, Knut Mørken, Marius Lysaker, Knut-Andreas Lie, Springer Berlin/Heidelberg, 2009, 808-819 p.Conference paper (Refereed)
Abstract [en]

Linear scale-space theory is the fundamental building block for many approaches to image processing like pyramids or scale-selection. However, linear smoothing does not preserve image structures very well and thus non-linear techniques are mostly applied for image enhancement. A different perspective is given in the framework of channel-smoothing, where the feature domain is not considered as a linear space, but it is decomposed into local basis functions. One major drawback is the larger memory requirement for this type of representation, which is avoided if the channel representation is subsampled in the spatial domain. This general type of feature representation is called channel-coded feature map (CCFM) in the literature and a special case using linear channels is the SIFT descriptor. For computing CCFMs the spatial resolution and the feature resolution need to be selected. In this paper, we focus on the spatio-featural scale-space from a scale-selection perspective. We propose a coupled scheme for selecting the spatial and the featural scales. The scheme is based on an analysis of lower bounds for the product of uncertainties, which is summarized in a theorem about a spatio-featural uncertainty relation. As a practical application of the derived theory, we reconstruct images from CCFMs with resolutions according to our theory. The results are very similar to the results of non-linear evolution schemes, but our algorithm has the fundamental advantage of being non-iterative. Any level of smoothing can be achieved with about the same computational effort.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2009. 808-819 p.
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 5567
National Category
Computer Science
URN: urn:nbn:se:liu:diva-18206DOI: 10.1007/978-3-642-02256-2_67ISI: 000270543900067ISBN: 978-3-642-02255-5 (Print)ISBN: 978-3-642-02256-2 (Online)OAI: diva2:216715
Second International Conference, SSVM 2009, Voss, Norway, June 1-5, 2009
Available from: 2009-10-05 Created: 2009-05-11 Last updated: 2015-01-23Bibliographically approved

Open Access in DiVA

fulltext(852 kB)259 downloads
File information
File name FULLTEXT02.pdfFile size 852 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textfind book at a swedish library/hitta boken i ett svenskt bibliotek

Search in DiVA

By author/editor
Felsberg, Michael
By organisation
Computer VisionThe Institute of Technology
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 259 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

Altmetric score

Total: 347 hits
ReferencesLink to record
Permanent link

Direct link