Scale-space theory with applications: Selected publications sorted by subject
General
-
Lindeberg (2014)
``Scale selection'',
Computer Vision: A Reference Guide, (K. Ikeuchi, ed.), Springer, pages 701-713.
(PDF 2.3 Mb)
-
Lindeberg (2013)
``Generalized axiomatic scale-space theory'',
Advances in Imaging and Electron Physics,
(P. Hawkes, ed.), Elsevier, volume 178, pages 1-96.
(PDF 20.1 Mb)
-
Lindeberg (2008)
``Scale-space'',
Encyclopedia of Computer Science and Engineering, (B. Wah, ed), John Wiley and Sons, Volume IV, pages 2495--2504, Hoboken, New Jersey, Jan 2009.
dx.doi.org/10.1002/9780470050118.ecse609 (Sep 2008)
(PDF 1.2 Mb)
-
Lindeberg (1993)
Scale-Space Theory in Computer Vision,
Kluwer Academic Publishers/Springer, Dordrecht, Netherlands, 1994.
(Online edition at SpringerLink)
-
Lindeberg (1991)
Discrete Scale-Space Theory and the Scale-Space Primal Sketch,
PhD thesis, Department of Numerical Analysis and Computer Science, KTH Royal Institute of Technology, 1991.
(Contains some details not included in the book.)
-
A concise one-page illustration of some of the most basic ideas with a scale-space representation,
Review articles
-
Lindeberg (2012)
``
Scale invariant feature transform'',
Scholarpedia, 7(5):10491,
2012.
(Online version)
(SIFT)
-
Lindeberg (1999)
``
Principles for automatic scale selection'',
Handbook on Computer Vision and Applications,
(B. J"ahne et al., eds.),
volume 2, pages 239--274, Academic Press, Boston, USA, 1999.
(PDF 2.3 Mb)
-
Lindeberg (1999)
"Automatic scale selection as a pre-processing stage for
interpreting the visual world",
Proc. Fundamental Structural Properties in Image and
Pattern Analysis FSPIPA'99,
Budapest, Hungary, September 6-7, 1999.
Schriftenreihen der "Osterreichischen Computer Gesellschaft, volume 130,
pages 9--23.
(PDF 2.9 Mb)
-
Lindeberg (1996)
``Scale-space:
A framework for handling image structures at multiple scales'',
Proc. CERN School of Computing,
Egmond aan Zee, The Netherlands, Sep. 8--21, 1996.
(An introductory overview on 12 pages PostScript 1.4Mb).
(PDF 2.0 Mb)
-
Lindeberg (1994)
``Scale-space theory: A basic tool for
analysing structures at different scales'',
J. of Applied Statistics,
21(2), pages 224--270, 1994.
(Supplement on
Advances in Applied Statistics: Statistics and Images: 2).
(PostScript 49 pages/1.4Mb)
(PDF 933 kb)
-
Lindeberg and ter Haar Romeny (1994)
``Linear scale-space: (I) Basic theory and (II) Early visual operations.''
Geometry-Driven Diffusion, (ter Haar Romeny, ed.), pages 1--77,
Kluwer Academic Publishers/Springer, Dordrecht, Netherlands, 1994.
(PostScript 83 pages/1.7Mb)
(PDF 1.1Mb)
Basic theory of scale-space representation
Axiomatic theories for continuous and discrete scale-space as well as foveal scale-space. General theoretical framework for modelling the deep structure of how image features are related over scales and for how to measure the lifelength of image structures over scales with general validity for both continuous and discrete signals.
-
Lindeberg (2016)
"Time-causal and time-recursive spatio-temporal receptive fields",
Journal of Mathematical Imaging and Vision,
volume 55, number 1, pages 50-88, March 2016.
Digitally published with
DOI:10.1007/s10851-015-0613-9 in December 2015.
Preprint at arXiv:1504.02648.
(PDF 4.7 Mb)
-
Lindeberg (2015)
"Separable time-causal and time-recursive spatio-temporal receptive fields",
Proc. SSVM2015: Scale-Space and Variational Methods in Computer Vision,
Springer LNCS vol 9087, pages 90-102, preprint at arXiv:1504.01502.
(PDF 6.1 Mb)
-
Lindeberg (2011)
``Generalized Gaussian scale-space axiomatics comprising linear scale-space,
affine scale-space and spatio-temporal scale-space''.
Journal of Mathematical Imaging and Vision,
volume 40, number 1, pages 36-81, May 2011.
Digitally published with
DOI:10.1007/s10851-010-0242-2 in December 2010.
Extended version available in
Technical report ISRN KTH/CSC/CV--2010/3--SE, ISSN 1653-7092, November 2010
.
(Shorter journal version 47 pages 17.3 Mb)
(Longer technical report version 76 pages 17.4 Mb).
-
Lindeberg (1997)
``On the axiomatic foundations of linear scale-space: Combining semi-group structure with causality vs. scale invariance''.
Technical report ISRN KTH NA/P--93/18--SE.
Revised version published as
Chapter 6 in J. Sporring, M. Nielsen, L. Florack, and P. Johansen (eds.)
Gaussian Scale-Space Theory: Proc. PhD School on Scale-Space Theory
,
(Copenhagen, Denmark, May 1996), pages 75--98,
Kluwer Academic Publishers/Springer, 1997.
(PostScript 132 kb)
(PDF 394 kb)
-
Lindeberg and Florack (1994)
``Foveal scale-space and the linear increase of receptive field size as a function of eccentricity'',
Technical report ISRN KTH NA/P--94/27--SE,
(PostScript 342 kb)
(PDF 378 kb)
-
Lindeberg (1993)
``Discrete derivative approximations with scale-space properties:
A basis for low-level feature detection'',
J. of Mathematical Imaging and Vision,
3(4), pp. 349--376, 1993.
(PostScript 1.3Mb)
(PDF 203 kb)
-
Lindeberg (1993)
``Effective scale: A natural unit for measuring scale-space lifetime'',
IEEE Transactions on Pattern Analysis and Machine Intelligence,
15(10), pp. 1068--1074, 1993.
(PDF 272kb)
(figures in PDF 182kb)
(PostScript 1.3Mb)
(figures in PostScript 0.1Mb)
-
Lindeberg (1992)
``Scale-space for N-dimensional discrete signals'',
Proc. Workshop on Shape in Picture,
Driebergen, Netherlands, Sep. 1992.
Also in: Y. O. Ying (ed.)
Shape in Picture,
NATO ASI Series F, pp. 571--590, Springer-Verlag, 1994.
(PDF 256kb)
(PostScript 221kb)
-
Lindeberg (1992)
``Scale-space behaviour and invariance properties of differential
singularities'',
Proc. Workshop on Shape in Picture,
Driebergen, Netherlands, Sep. 1992.
Also in: Y. O. Ying (ed.)
Shape in Picture,
NATO ASI Series F, pp. 591--6000, Springer-Verlag, 1994.
(PostScript 0.1Mb)
(PDF 0.2Mb)
-
Lindeberg (1992)
``Scale-space behaviour of local extrema and blobs'',
J. of Mathematical Imaging and Vision,
1(1), pp. 65--99, 1992.
Only a condensed, subststantially shortened, version available here
(PDF 407kb)
(PostScript 206kb)
-
Lindeberg (1990)
``Scale-space for discrete signals'',
IEEE Transactions of Pattern Analysis and Machine Intelligence,
12(3), 234--254, 1990.
(PostScript 149 kb)
(PDF 421 kb)
Computational modelling of visual receptive fields
Cell recordings of neurons in the primary visual cortex (V1) have shown that mammalian vision has developed receptive fields tuned to different sizes and orientations in the image domain as well as to different image velocities in space-time.
We show how such families of idealized receptive field profiles can be derived mathematically from a small set of basic assumptions that correspond to structural properties of the environment.
We also show how basic invariance properties of a visual system can be obtained already at the level of receptive fields, and that we can explain the different shapes of receptive field profiles found in biological vision from a requirement that the visual system should be able to be invariant to the natural types of image transformations that occur in the environment.
Computational modelling of auditory receptive fields
A scale-space theory is developed for auditory signals, showing how temporal and spectro-tempioral receptive fields can be derived by necessity and with good qualitative similarity to biological receptive fields in the inferior colliculus (ICC) and primary auditory cortex (A1).
Feature detection, automatic scale selection and scale-invariant image features
Feature detection methods based on the combination of Gaussian derivative
operators at multiple scales. Special focus is given to the problem of
scale selection, in order to adapt the local scales of processing
to the local image structure.
Specifically, the notion of automatic scale selection based on local extrema over scales of gamma-normalized derivatives makes it possible
to define scale-invariant image features.
The use of such scale-invariant image features allows the vision system to
automatically handle the unknown scale variations that may occur in real-world
image data, due to objects of different physical size as well as objects with
different distances to the camera.
This theory, which includes the definition of scale-invariant feature detectors from scale-space extrema of the scale normalized Laplacian and the scale normalized determinant of the Hessian, constitutes the theoretical basis for the scale-invariant properties of the SIFT and SURF descriptors. The differences-of-Gaussians operator in the SIFT descriptor can be seen as an approximation of the scale normalized Laplacian and the blob detector in the SURF descriptor can be seen as an approximation of the scale-normalized determinant of the Hessian, with the underlying second-order Gaussian derivative operators replaced by Haar wavelets. In addition, we have proposed a scale-invariant corner detector based on the scale-normalized rescaled level curve curvature of level curves.
-
Lindeberg (2015)
``Image matching using generalized scale-space interest points",
Proc. SSVM 2013: Fourth International Conference on Scale Space and Variational Methods in Computer Vision,
Schloss Seggau, Graz region, Austria, June 2-6, 2013,
Springer Lecture Notes in Computer Science volume 7893,
pages 355-367.
(PDF 8.3 Mb).
Journal of Mathematical Imaging and Vision, volume 52,
number 1, pages 3-36, 2015. Special issue with selected papers from SSVM 2013.
(PDF 11.9 Mb).
-
Lindeberg (2013)
``Scale selection properties of generalized scale-space interest point detectors",
Journal of Mathematical Imaging and Vision, volume 46, number 2, pages 177-210.
(PDF 2.7 Mb)
-
Lindeberg and Bretzner (2003)
``Real-time scale selection in hybrid multi-scale representations'',
Proc. Scale-Space'03,
Isle of Skye, Scotland,
Springer Lecture Notes in Computer Science, volume 2695, pages 148--163.
(PDF 220 kb)
(PostScript 393 kb)
-
Laptev and Lindeberg (2003)
``A distance measure and a feature likelihood map concept for scale-invariant model matching'',
International Journal of Computer Vision, vol. 52, number 2/3, pages 97--120, 2003.
(PDF 1.5Mb)
-
Lindeberg (1998)
``Feature detection with automatic scale selection''.
International Journal of Computer Vision, vol 30, number 2, pp. 77--116, 1998.
(PostScript 2.8Mb)
(PDF 3.5Mb) (Comprises the basic theory for scale-invariant interest points and image descriptors.)
-
Lindeberg (1998)
``Edge detection and ridge detection with automatic scale selection'',
Proc. CVPR'96,
San Francisco, California,
pages 465--470, june 1996.
(PostScript 1.3Mb)
(PDF 1.6Mb)
International Journal of Computer Vision, vol 30, number 2, pp. 117--154, 1998.
(PostScript 5.1Mb)
(PDF 10.3Mb)
-
Lindeberg (1994)
``Junction detection with automatic selection of
detection scales and localization scales'',
Proc. 1st International Conference on Image Processing,
(Austin, Texas), pp. 924--928, vol I, Nov. 1994.
(PostScript 307 kb)
(PDF 290 kb)
-
Lindeberg (1993)
``Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention'',
International Journal of Computer Vision,
vol. 11, pp. 283--318, Dec. 1993.
(PostScript 1.6Mb)
(PDF 787kb).
(The underlying algorithm for linking blobs and local extrema over scales is described in chapter 9 in Scale-Space Theory in Computer Vision as well as in chapter 7 in Discrete Scale-Space Theory and the Scale-Space Primal Sketch.)
-
Lindeberg (1993)
``On scale selection for differential operators'',
Technical report ISRN KTH NA/P--94/05--SE.
Shortened version
in
Proc. 8th Scandinavian Conference on Image Analysis,
(Tromso, Norway), pp. 857--866, May 1993.
(PostScript 0.8Mb)
(PDF 0.5Mb)
-
Brunnstrom, Lindeberg and Eklundh (1992)
``Active detection and classification of junctions by foveation with a
head-eye system guided by the scale-space primal sketch''.
In: Sandini (ed.),
Proc. 2nd European Conf. on Computer Vision,
(Santa Margeritha Ligure, Italy),
vol. 588 of Lecture Notes in Computer Science,
pp. 701--709, Springer-Verlag, May 1992.
(PDF 0.5Mb)
(PostScript 0.8Mb)
-
Brunnstrom, Eklundh and Lindeberg (1990)
``On scale and resolution in active analysis of local image structure''.
Image and Vision Computing,
8, 289--296, 1990.
Object recognition
-
Linde and Lindeberg (2012)
``Composed complex-cue histograms: An investigation of the information content in receptive field based image descriptors for object recognition'',
Computer Vision and Image Understanding, volume 116, number 4, pages 538-560.
Digitally published with
DOI: 10.1016/j.cviu.2011.12.003 in December 2011.
(PDF 4.2 Mb)
-
Linde and Lindeberg (2004)
``Object recognition using composed receptive field histograms of higher dimensionality'',
Proc 17th International Conference on Pattern Recognition ICPR 2004,
(Cambridge, U.K), volume: 2, pages 1-6, August 2004.
(PDF 108 kb)
Multi-scale processing of temporal data including temporal and spatio-temporal scale-space as well as temporal scale selection
-
Lindeberg (1997)
``Linear spatio-temporal scale-space'',
Proc. 1st International Conference on
Scale-Space Theory in Computer Vision,
(Utrecht, Netherlands), July 2-4, 1997.
Springer-Verlag Lecture Notes in Computer Science, volume 1252, pages 113--127.
(PostScript 191 kb)
(PDF 258 kb)
-
Lindeberg (1997)
``On automatic selection of temporal scales in time-causal scale-space'',
Proc AFPAC'97: Algebraic Frames for the Perception-Action Cycle
(G. Sommer and J. J. Koenderink, eds),
vol 1315 of Springer Lecture Notes in Computer Science, (Kiel, Germany),
1997, pages 94-113.
(PDF 415 kb)
-
Bretzner and
Lindeberg (1997)
``On the handling of spatial and temporal scales in feature tracking'',
Proc. 1st International Conference on
Scale-Space Theory in Computer Vision,
(Utrecht, Netherlands), July 2-4, 1997.
Springer-Verlag Lecture Notes in Computer Science,
volume 1252.
(PostScript 933 kb)
(PDF 195 kb)
-
Lindeberg and
Fagerstrom (1996)
``Scale-space with causal time direction'',
Proc. 4th European Conference on Computer Vision,
Cambridge, England, april 1996.
Springer-Verlag LNCS Vol 1064, pages 229--240.
(PostScript 0.4Mb)
(PDF 0.4Mb)
-
Bretzner and
Lindeberg (1998)
``Feature tracking with automatic selection of spatial scales'',
Computer Vision and Image Understanding.
vol. 71, pp. 385--392, Sept. 1998.
(PostScript 1.8 Mb)
(PDF 319 kb)
Spatio-temporal image features, image descriptors, velocity adaptation and Galilean diagonalization with application to recognition of motion patterns, human actions and spatio-temporal events
Direct methods for recognizing spatio-temporal events with associated activities based on the local spatio-temporal image structure, without explicit inclusion of tracking mechanisms or other temporal trajectories. To handle a priori unknown relative motions relative to the observer, a general notion of local velocity adaptation is introduced. For parameterizing the spatio-temporal second-moment matrix/structure tensor and other related spatio-temporal image descriptors, we propose the notion of Galilean diagonalization, which gives a much more natural parameterization of purely spatial components and combined spatio-temporal relations compared to previous approaches in terms of eigenvalues that correspond to a non-physical rotation of space-time. These works also include the first formulation of local scale-adapted histograms of spatio-temporal gradients and optic flow, which can be seen as generalizations of the SIFT descriptor from space to space-time.
-
Laptev, Caputo, Schuldt and
Lindeberg (2007)
``Local velocity-adapted motion events for spatio-temporal recognition'',
In: Computer Vision and Image Understanding,
volume 108, pages 207-229, 2007.
(PDF 2.2 Mb)
-
Laptev and
Lindeberg (2004)
``Local descriptors for spatio-temporal recognition'',
In: ECCV'04 Workshop on Spatial Coherence for Visual Motion Analysis, Prague, Czech Republic, 2004, Springer LNCS Vol.3667, pp. 91-103.
(PDF 757 kb)
-
Laptev and
Lindeberg (2004)
``Velocity adaptation of space-time interest points'',
Proc. ICPR'04, Cambridge, UK, 2004, pages I:52-56.
(PDF 570 kb)
-
Lindeberg, Akbarzadeh and
Laptev (2004)
``Galilean-corrected spatio-temporal interest operators'',
In: Proc. ICPR'04, Cambridge, UK, 2004, pages I:57-62.
(PDF 549 kb)
(Longer technical report with more extensive theory and more experiments: 586 kb)
-
Laptev and
Lindeberg (2003)
``Space-time interest points'',
In: Proc. International Conference on Computer Vision,
Nice, France, 2003, pages I:432-439.
(PDF 1.0 Mb)
-
Laptev and
Lindeberg (2003)
``Interest point detection and scale selection in space-time'',
In: Proc. Scale-Space Methods in Computer Vision,
Isle of Skye, UK, 2003,
Springer LNCS vol.2695, pages 372-387
(PDF 1.1 Mb)
-
Laptev and
Lindeberg (2004)
``Velocity-adaptation of spatio-temporal receptive fields for direct recognition of activities: An experimental study'',
Image and Vision Computing, volume 22, pages 105-116, 2004.
Earlier version in Proc. ECCV'02 Workshop on Statistical Methods in Video Processing, Copenhagen, Denmark, 2002, pages 61-66.
(PDF 1.1 Mb)
Estimation of affine image deformations and direct computation of cues to surface shape including the theories for multi-scale second moment matrices/structure tensors and affine shape adaptation
Theories and algorithms for
shape from texture and shape from disparity gradients
based on local affine deformations of 2-D brightness patterns.
Specifically, this framework includes a theory for local affine normalization
of local image descriptors by affine shape adaptation, which makes
it possible to define affine invariant image features and
to perform affine invariant image and feature matching.
These papers also outline the theory for multi-scale second-moment
matrices, also referred to as multi-scale structure tensors.
-
Garding and
Lindeberg (1996)
``Direct computation of shape cues using scale-adapted
spatial derivative operators'',
International Journal of Computer Vision,
vol 17(2), pp. 163--191, 1996.
(PostScript 1.4Mb)
(PDF 0.8Mb)
-
Lindeberg and
Garding (1997)
``Shape-adapted smoothing in estimation of 3-D depth cues from
affine distortions of local 2-D brightness structure'',
In: J.-O. Eklundh (ed.)
Proc. 3rd European Conf. on Computer Vision,
(Stockholm, Sweden),
vol. 800 of Lecture Notes in Computer Science,
pp. 389--400, Springer-Verlag, May 1994.
(PostScript 0.4Mb)
(PDF 0.2Mb)
Extended version in Image and Vision Computing,
vol. 15, pp. 415--434, 1997.
(PostScript 0.5Mb)
(PDF 0.5Mb)
-
Lindeberg (1998)
``A scale selection principle for estimating image deformations''
Image and Vision Computing,
vol. 16, no. 14, pp. 961--977, 1998.
(PDF 374kb)
-
Lindeberg (1995)
``Direct estimation of affine deformations of brightness patterns using visual front-end operators with automatic scale selection''
Proc. 5th International Conference on Computer Vision,
(Cambridge, MA), pp. 134--141, June 1995.
(PDF 311kb)
-
Garding and
Lindeberg (1994)
``Direct estimation of local surface shape in a fixating binocular
vision system'',
In: J.-O. Eklundh (ed.)
Proc. 3rd European Conf. on Computer Vision,
(Stockholm, Sweden),
vol. 800 of Lecture Notes in Computer Science,
pp. 365--376, Springer-Verlag, May 1994.
(PostScript 0.2Mb)
(PDF 0.2Mb)
-
Lindeberg and
Garding (1993)
``Shape from texture from a multi-scale perspective''.
Shortened version in: H.-H. Nagel (ed.) Proc. 4th Int. Conf. on Computer Vision,
(Berlin, Germany), pp. 683--691, May 1993.
(PostScript 0.8Mb)
(PDF 0.5Mb).
Extended version available as (printed) technical report ISRN KTH/NA/P--93/03--SE from KTH.
Structure and motion estimation (including visual control based on the 3-D hand mouse)
Methods for computing 3-D structure and motion from rigid point and line configurations that are projected from 3-D to 2-D using an affine projection model. The papers and the patent applications also show how the motion of a controlled object A can be controlled using motion estimates that are computed by visually observing another controlling object B (visual servoing).
-
Bretzner and Lindeberg (1999)
``Structure and motion estimation using sparse point and line correspondences in multiple affine views''.
.
Technical report ISRN KTH/NA/P--99/13--SE.
(PostScript 931kb)
(PDF 473kb)
-
Bretzner and Lindeberg (1998)
``Use your hand as a 3-D mouse or relative orientation from
extended sequences of sparse point and line correspondences using the affine trifocal tensor'',
in Proc. 5th European Conference on Computer Vision (H. Burkhardt and B. Neumann, eds.),
vol. 1406 of Lecture Notes in Computer Science, (Freiburg, Germany), pp. 141--157, Springer
Verlag, Berlin, June 1998.
(PostScript 195kb)
(PDF 272kb)
-
T. Lindeberg and L. Bretzner (1999):
``Method and arrangement for controlling means for three-dimensional
transfer of information by motion detection'',
International patent application PCT/SE1999/000402, 1999
(now released).
-
T. Lindeberg and L. Bretzner (1998)
``Forfarande och anordning for overforing av information
genom rorelsedetektering, samt anvandning av anordningen'',
Swedish patent 9800884-0, March 1998 (now released).
Hand tracking and gesture recognition
Methods for real-time tracking of hand motions and recognition of hand poses based on scale-invariant image features, including the use of hand gestures for controlling other equipment using no other interface equipment than the user's own hand gestures. A real-time prototype system was demonstrated for the general public already in 2001, to try by themselves to experience how it is like to control other objects at distance using just hand gestures.
-
Bretzner,
Laptev and Lindeberg (2002)
``Hand-gesture recognition using multi-scale colour features, hierarchical features and particle filtering'',
Proc. Face and Gesture,
(Washington D.C., USA), pp. 63--74, May 2002.
(PDF 159kb)
-
Bretzner,
Laptev, Lindeberg, Lenman and Sundblad (2001)
``A prototype system for computer vision based human computer interaction'',
Technical report ISRN KTH NA/P--01/09--SE.
Department of Numerical Analysis
and Computer Science, KTH (Royal Institute of Technology), S-100 44 Stockholm, Sweden,
April 23-25, 2001.
Demo presented at the Swedish IT-fair Connect 2001, "Alvsjom"assan, Stockholm, Sweden, April 2001.
(PDF 522kb)
- Laptev and Lindeberg (2001)
"Tracking of multi-state hand models
using particle filtering and a hierarchy of multi-scale image features",
Technical report ISRN KTH/NA/P-00/12-SE, September 2000.
Shortened version in
IEEE Workshop on Scale-Space and Morphology,
Vancouver, Cacsc, July 2001,
M. Kerckhove (Ed.), Volume 2106 of Springer Verlag
Lecture Notes in Computer Science, pages 63--74.
(PostScript 1.5 Mb)
(PostScript 778 kb)
(PDF 726 kb)
(PDF 270 kb)
-
Laptev and Lindeberg (2001)
"A multi-scale feature likelihood map for
direct evaluation of object hypotheses",
Technical report ISRN KTH/NA/P-01/03-SE, March 2001.
Shortened version in
IEEE Workshop on Scale-Space and Morphology,
Vancouver, Cacsc, July 2001,
M. Kerckhove (Ed.), Volume 2106 of Springer Verlag
Lecture Notes in Computer Science, pages 98--110.
(PostScript 600 kb)
(PDF 375 kb)
Medical image analysis
Methods for detecting brain activations in functional PET images and for automatically segmenting the brain from other tissue in an MRI image of a human head. In the European project Neurogenerator, we also developed a database with functional PET and fMRI images and cytoarchitectonically classified anatomical regions in the brain, including tools for metaanalysis to relate the functionally activated regions from different tasks to corresponding cytoarchitectonically defined neuroanatomical regions in the brain.
-
Undeman and Lindeberg (2003)
``Fully automatic segmentation of MRI brain images using probabilistic anisotropic diffusion and multi-scale watersheds'',
Proc. Scale-Space'03
Isle of Skye, Scotland, June 2002. Springer LNCS vol 2695, 641--656.
(PostScript 420 kb)
(PDF 219 kb)
-
Roland, Svensson, Lindeberg, Risch, Baumann, Dehmel, Frederiksson, Halldorson, Forsberg, Young and Zilles (2001)
``A database generator for human brain imaging'',
Trends in Neurosciences,
vol. 24 number 10, pages 562-564, 2001.
(PDF 427 kb)
-
Rosbacke, Lindeberg and Roland (2001)
"Evaluation of using absolute vs. relative base level when analyzing brain activation images using the scale-space primal sketch"
,
Technical report ISRN KTH NA/P--99/14--SE, 1999.
Journal of Medical Image Analysis, vol. 5, Issue 2, pp. 89--110, 2001.
(PostScript 409 kb)
(PDF 665 kb)
-
Lindeberg, Lidberg and Roland (1999)
"Analysis of brain activation patterns using a 3-D scale-space primal sketch"
,
Technical report ISRN KTH/NA/P--98/18--SE.
Human Brain Mapping, vol 7, no 3, pp 166--194, 1999.
Earlier version presented in
Proc. 3rd International Conference on Functional Mapping of the
Human Brain Mapping, Copenhagen, Denmark, May 19--23, 1997.
Neuroimage, Vol. 5, No. 4, p. 393, 1997.
(PostScript 3.5Mb)
(PDF 1.0Mb)
Applications
Applications of scale-space techniques to different types
of more specific computer vision problems:
-
Almansa
and Lindeberg (2000)
``Fingerprint enhancement by shape adaptation of scale-space operators with automatic scale-selection'',
IEEE Transactions on Image Processing,
volume 9, number 12, pp 2027-2042, 2000
(PostScript 2.7 Mb)
(PDF 1.5 Mb)
.
Earlier version presented as
Almansa and Lindeberg (1997)
"Enhancement of finger-print images using shape-adapted scale-space operators"
Chapter 3 in J. Sporring, M. Nielsen, L. Florack, and P. Johansen (eds.)
Gaussian Scale-Space Theory: Proc. PhD School on Scale-Space Theory,
(Copenhagen, Denmark, May 1996), pages 21-30, Kluwer Academic Publishers/Springer, 1997.
-
Lindeberg and Li (1997)
``Segmentation and classification of edges using
minimum description length approximation
and complementary junction cues'',
Proc. 9th Scandinavian Conference on Image Processing,
Uppsala, Sweden,
June 1995, pages 767-776.
Extended version in
Computer Vision and Image Understanding,
vol. 67, no. 1, pp. 88-98, 1997.
(PostScript 1.2Mb)
(PDF 1.0Mb)
-
Bretzner and Lindeberg (2000)
``Qualitative multi-scale feature hierarchies for object tracking'',
Journal of Visual Communication and Image Representation,
vol. 11, pp. 115--129, 2000
(PDF 348 kb)
-
Shokoufandeh, Dickinson, Jonsson, Bretzner and Lindeberg (2002)
``On the representation and matching of qualitative shape at multiple scales'',
Proc. 7th European Conf. on Computer Vision,
Copenhagen, Denmark, May 2002. Springer LNCS volume 2352, pages 3:759-775, 2002.
(PDF 600kb)
-
Wiltschi, Pinz and Lindeberg (2000)
``An automatic assessment scheme for steel quality inspection'',
Technical report ISRN KTH/NA/P--98/20--SE.
(Extended TR: PostScript 10.9Mb)
(Extended TR: PDF 5.8Mb)
Machine Vision and Applications, volume 12, pp 113-128, 2000.
-
Wiltschi, Lindeberg and Pinz (1997)
``Classification of carbide distributions using scale selection and
directional distributions'',
Proc. 4th International Conference on Image Processing ICIP'97,
(Santa Barbara, California), vol. II, pp. 122--125, Oct. 1997.
(PostScript 1.1Mb)
(Extended TR: PostScript 7.1Mb)
(Extended TR: PDF 0.4Mb)
External links
-
Encyclopedia entry on scale-space in Encyclopedia of Computer Science and Engineering.
-
Wikipedia articles on scale-space
-
Wikipedia articles on feature detection
-
Wikipedia articles on computer vision
-
Wikipedia articles on gesture recognition
-
Scholarpedia article on scale invariant feature transform (SIFT)
-
Encyclopedia entry on scale-space theory in Encyclopedia of Mathematics (Local copy)
-
Encyclopedia entry on edge detection
-
Encyclopedia entry on corner detection
-
Powers of ten interactive Java tutorial at Molecular Expressions website.
-
The SIFT descriptor for object recognition includes a combined scale selection and blob detection stage to obtain scale invariant interest points for subsequent matching, where the differences-of-Gaussian blob detector (DoG) can be seen as an approximation of scale-space extrema of our scale-normalized Laplacian operator (developed by David Lowe at University of British Columbia).
-
The SURF descriptor for image matching and object recognition builds upon similar ideas of automatic scale selection to obtain scale invariant interest points with associated image descriptors. Specifically, the blob detector in the SURF descriptor can be seen as an approximation of scale-space extrema of our scale-normalized determinant of the Hessian operator with the underlying second-order Gaussian derivatives replaced by Haar wavelets and using an constant L1-norm normalization of the responses to obtain appropriate scale selection properties in analogy with our discrete normalization of operator responses in a real-time hybrid pyramid representation (Herbert Bay, Tinne Tuytelaars and Luc Van Gool at ETH in Zurich).
-
Integration of automatic scale selection and affine shape adaptation into schemes for performing wide baseline stereo matching (Adam Baumberg at Canon Research in Guildford, U.K.; Frederik Schaffalitzky and Andrew Zisserman at Oxford University; Tinne Tuytelaars and Luc Van Gool at University of Leuven, Belgium>) and for detecting scale invariant and affine invariant interest points (Krystian Mikolajczyk and Cordelia Schmid at INRIA Rhone-Alpes). The affine invariant and scale invariant properties of these approaches are based on our theories for scale-invariant image feature and affine invariant fixed points. Our previously developed scale-adaptive image features in terms of scale-space extrema of the scale-normalized Laplacian, determinant of the Hessian, the scale-normalized rescaled level curve curvature were indeed originally defined to be truly scale invariant. Specifically, our notion of gamma-normalized derivatives was derived axiomatically from the requirement that image features obtained from local extrema over scales should be preserved under scaling transformations and be transformed in a scale covariant way. Moreover, our affine invariant fixed-point property of the second-moment matrix implies that provided that our proposed affine shape adaptation procedure converges, the resulting affine normalized image patch should be preserved under affine transformations. This in turn means that the corresponding features will be affine invariant up to an unessential undetermined rotation that can be easily compensated for by a complementary orientation alignment.
-
Using combinations of scale selection and model-based ridge detection for
blood vessel segmentation (Alejandro Frangi et al at Utrecht University) and
detection of tubular structures (Karl Krissian et al at INRIA Sophia Antipolis) in medical 3-D images, which constitute extensions of our scale-adaptive and scale-invariant ridge detection methodology from 2-D to 3-D.
Further reading
Further publications on these and related topics are available from:
Responsible for this page: Tony Lindeberg
|