Change search
ReferencesLink to record
Permanent link

Direct link
Scale Selection Properties of Generalized Scale-Space Interest Point Detectors
KTH, School of Computer Science and Communication (CSC), Computational Biology, CB.ORCID iD: 0000-0002-9081-2170
2013 (English)In: Journal of Mathematical Imaging and Vision, ISSN 0924-9907, E-ISSN 1573-7683, Vol. 46, no 2, 177-210 p.Article in journal (Refereed) Published
Abstract [en]

Scale-invariant interest points have found several highly successful applications in computer vision, in particular for image-based matching and recognition. This paper presents a theoretical analysis of the scale selection properties of a generalized framework for detecting interest points from scale-space features presented in Lindeberg (Int. J. Comput. Vis. 2010, under revision) and comprising: an enriched set of differential interest operators at a fixed scale including the Laplacian operator, the determinant of the Hessian, the new Hessian feature strength measures I and II and the rescaled level curve curvature operator, as well as an enriched set of scale selection mechanisms including scale selection based on local extrema over scale, complementary post-smoothing after the computation of non-linear differential invariants and scale selection based on weighted averaging of scale values along feature trajectories over scale. A theoretical analysis of the sensitivity to affine image deformations is presented, and it is shown that the scale estimates obtained from the determinant of the Hessian operator are affine covariant for an anisotropic Gaussian blob model. Among the other purely second-order operators, the Hessian feature strength measure I has the lowest sensitivity to non-uniform scaling transformations, followed by the Laplacian operator and the Hessian feature strength measure II. The predictions from this theoretical analysis agree with experimental results of the repeatability properties of the different interest point detectors under affine and perspective transformations of real image data. A number of less complete results are derived for the level curve curvature operator.

Place, publisher, year, edition, pages
2013. Vol. 46, no 2, 177-210 p.
Keyword [en]
feature detection, interest point, blob detection, corner detection, scale, scale-space, scale selection, scale invariance, scale calibration, scale linking, feature trajectory, deep structure, affine transformation, differential invariant, Gaussian derivative, multi-scale representation, computer vision
National Category
Computer Science Computer Vision and Robotics (Autonomous Systems) Mathematics
URN: urn:nbn:se:kth:diva-101220DOI: 10.1007/s10851-012-0378-3ISI: 000318795800002ScopusID: 2-s2.0-84877740576OAI: diva2:546842
Image descriptors and scale-space theory for spatial and spatio-temporal recognition
Swedish Research Council, 2010-4766Swedish Research Council, 2004-4680Knut and Alice Wallenberg Foundation

QC 20121003

Available from: 2012-08-24 Created: 2012-08-24 Last updated: 2013-06-18Bibliographically approved

Open Access in DiVA

fulltext(2639 kB)45 downloads
File information
File name FULLTEXT01.pdfFile size 2639 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Lindeberg, Tony
By organisation
Computational Biology, CB
In the same journal
Journal of Mathematical Imaging and Vision
Computer ScienceComputer Vision and Robotics (Autonomous Systems)Mathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 45 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: 1437 hits
ReferencesLink to record
Permanent link

Direct link