Real-Time Scale Selection in Hybrid Multi-scale Representations
Open accessThe DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Furthermore, as the Frobenius norm remains constant for our filters, they are already scale normalised [26].”
From SURF: Speeded Up Robust Features (2006) · cites this paper as [26]
Citations
Cites
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 1×
“…invariant image features for further processing, scale selection mechanisms have proven highly useful for interest point detection (Mikolajczyk & Schmid 2002) with applications to object recognition (Lowe 1999, Hall et al. 2000) and tracking (Bretzner & Lindeberg 1998, Laptev & Lindeberg 2001).”
BackgroundThe Laplacian pyramid as a compact image code
Burt, P., & Adelson, E. (1983) · IEEE Transactions on Communications · doi:10.1109/tcom.1983.1095851 · Cited by 6,077 · cited 2×
“Both pyramids (Burt & Adelson 1983, Crowley & Parker 1984, Jähne 1995, Simoncelli & Freeman 1995) and scale-space representations (Witkin 1983, Koenderink 1984, Lindeberg 1994, Florack 1997) have been developed from the idea of representing images at multiple scales in such a way that the resulting…”
BackgroundMethodFeature detection with automatic scale selection
Lindeberg, T. (1998) · International Journal of Computer Vision · doi:10.1023/a:1008045108935 · Cited by 2,541 · cited 1×
“This principle has been applied to various problems relating to the detection of image features ( Lindeberg 1998b, Lindeberg 1998a, Chomat et al. 2000, Almansa & Lindeberg 2000, Pedersen & Nielsen 2000, Nielsen & Lillholm 2001, Kadir & Brady 2001).”
MethodSelf-citationKoenderink, J. J. (1984) · Biological Cybernetics · doi:10.1007/bf00336961 · Cited by 2,452 · cited 1×
“Both pyramids (Burt & Adelson 1983, Crowley & Parker 1984, Jähne 1995, Simoncelli & Freeman 1995) and scale-space representations (Witkin 1983, Koenderink 1984, Lindeberg 1994, Florack 1997) have been developed from the idea of representing images at multiple scales in such a way that the resulting…”
BackgroundWitkin, A. P. (1987) · Readings in Computer Vision · doi:10.1016/b978-0-08-051581-6.50036-2 · Cited by 2,359 · cited 1×
“Both pyramids (Burt & Adelson 1983, Crowley & Parker 1984, J¨ ahne 1995, Simoncelli & Freeman 1995) and scale-space representations ( Witkin 1983, Koenderink”
BackgroundScale-Space Theory in Computer Vision
Lindeberg, T. (1994) · Springer eBooks · doi:10.1007/978-1-4757-6465-9 · Cited by 2,169
Self-citationAn Affine Invariant Interest Point Detector
Mikolajczyk, K., & Schmid, C. (2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-47969-4_9 · Cited by 1,325 · cited 1×
“…obtaining zoom invariant image features for further processing, scale selection mechanisms have proven highly useful for interest point detection (Mikolajczyk & Schmid 2002) with applications to object recognition (Lowe 1999, Hall et al. 2000) and tracking (Bretzner & Lindeberg 1998, Laptev &…”
MethodSaliency, Scale and Image Description
Kadir, T., & Brady, M. (2001) · International Journal of Computer Vision · doi:10.1023/a:1012460413855 · Cited by 1,195 · cited 1×
“This principle has been applied to various problems relating to the detection of image features (Lindeberg 1998b, Lindeberg 1998a, Chomat et al. 2000, Almansa & Lindeberg 2000, Pedersen & Nielsen 2000, Nielsen & Lillholm 2001, Kadir & Brady 2001).”
MethodSato, Y., Nakajima, S., Shiraga, N., Atsumi, H., Yoshida, S., Koller, T., Gerig, G., & Kikinis, R. (1998) · Medical Image Analysis · doi:10.1016/s1361-8415(98)80009-1 · Cited by 1,163 · cited 1×
“…ridge detection may be highly sensitive to the choice of scale level, special emphasis has been on the detection of ridges for medical image analysis (Pizer et al. 1994, Eberly et al. 1994, Koller et al. 1995, Lorenz et al. 1997, Sato et al. 1998, Staal et al. 1999, Frangi et al. 1999, Majer 2001).”
BackgroundIndexing based on scale invariant interest points
Mikolajczyk, K., & Schmid, C. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937561 · Cited by 1,101
Research works printed but not linked: 2
- Bretzner, L., Laptev, I. & Lindeberg, T. (2002), Hand-gesture recognition using multiscale colour features, hierarchical features and particle filtering, Face and Gesture’02, 63–74.
- Lindeberg, T. & Bretzner, L (2003), Real-time scale selection in hybrid multi-scale representations, Technical report, KTH, Stockholm, Sweden.
Cited by
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
“Furthermore, as the Frobenius norm remains constant for our filters, they are already scale normalised [26].”
BackgroundSpeeded-Up Robust Features (SURF)
Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2007.09.014 · Cited by 13,557
“As the Frobenius norm remains constant for our filters at any size, they are already scale normalised, and no further weighting of the filter response is required, see [22].”
BackgroundLaptev, I. (2005) · International Journal of Computer Vision · doi:10.1007/s11263-005-1838-7 · Cited by 2,629
Laptev, & Lindeberg (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238378 · Cited by 1,300
“During recent years, the problem of automatic scale selection has been addressed in several different ways, based on the maximization of normalized derivative expressions over scale, or the behavior of entropy measures or error measures over scales (see Lindeberg and Bretzner (2003) for a review).”
BackgroundSelf-citationScale Invariant Feature Transform
Lindeberg, T. (2012) · Scholarpedia · doi:10.4249/scholarpedia.10491 · Cited by 621
“Another way of detecting scalespace extrema of the Laplacian efficiently for realtime implementation has been presented by Lindeberg and Bretzner (2003) based on a hybrid pyramid.”
MethodSelf-citationImage Matching Using Generalized Scale-Space Interest Points
Lindeberg, T. (2015) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-014-0541-0 · Cited by 208
“The underlying theory for real-time scale selection based on a hybrid pyramid representation was then reported in Lindeberg and Bretzner [112].”
BackgroundSelf-citationMulti-scale digital soil mapping with deep learning
Behrens, T., Schmidt, K., MacMillan, R. A., & Viscarra Rossel, R. A. (2018) · Scientific Reports · doi:10.1038/s41598-018-33516-6 · Cited by 164
State‐of‐the‐Art in GPU‐Based Large‐Scale Volume Visualization
Beyer, J., Hadwiger, M., & Pfister, H. (2015) · Computer Graphics Forum · doi:10.1111/cgf.12605 · Cited by 124
Hadwiger, M., Beyer, J., Jeong, W., & Pfister, H. (2012) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2012.240 · Cited by 106
“This would also facilitate the efficient representation of sampled scale space, such as with a hybrid pyramid scheme [24].”
BackgroundThe structure-from-motion reconstruction pipeline – a survey with focus on short image sequences
Häming, K., & Peters, G. (2010) · Czech digital mathematics library · Cited by 101
Multiscale Deep Learning for Detection and Recognition: A Comprehensive Survey
Jiao, L., Wang, M., Liu, X., Li, L., Liu, F., Feng, Z., Yang, S., & Hou, B. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3389454 · Cited by 100
“Furthermore, he proposed a hybrid multiscale representation that trades off the high efficiency of pyramid representation and the systematicity of scale-space representation, to address the computational efficiency problem in automatic scale selection methods [31].”
Prasath, V. B. S., Воротников, Д. А., Pelapur, R., Jose, S., Seetharaman, G. S., & Palaniappan, K. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2479471 · Cited by 78
The Hessian Blob Algorithm: Precise Particle Detection in Atomic Force Microscopy Imagery
Marsh, B., Chada, N., Gari, R. R. S., Sigdel, K. P., & King, G. M. (2018) · Scientific Reports · doi:10.1038/s41598-018-19379-x · Cited by 76
Robust threshold estimation for images with unimodal histograms
Coudray, N., Buessler, J.-L., & Urban, J.-P. (2010) · Pattern Recognition Letters · doi:10.1016/j.patrec.2009.12.025 · Cited by 67
Multiscale symmetric part detection and grouping
Levinshtein, A., Dickinson, S., & Sminchisescu, C. (2009) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2009.5459472 · Cited by 64
Xie, H., Gao, K., Zhang, Y., Tang, S., Li, J., & Liu, Y. (2011) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2011.2167224 · Cited by 59
Time-Causal and Time-Recursive Spatio-Temporal Receptive Fields
Lindeberg, T. (2015) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-015-0613-9 · Cited by 53
Self-citationA Survey of GPU-Based Large-Scale Volume Visualization
Beyer, J., Hadwiger, M., & Pfister, H. (2014) · Digital Access to Scholarship at Harvard (DASH) (Harvard University) · doi:10.2312/eurovisstar.20141175 · Cited by 51
Multiscale Symmetric Part Detection and Grouping
Levinshtein, A., Sminchisescu, C., & Dickinson, S. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0614-3 · Cited by 51
“precision of [10], we prune small parts to increase precision: (1)”
BackgroundMethodInfluentialDiscrete Approximations of Gaussian Smoothing and Gaussian Derivatives
Lindeberg, T. (2024) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-024-01196-9 · Cited by 47
“…differences, the numerical estimates of derivatives obtained by applying this approach to monomials of the same order as the order of spatial differentiation do, on the other hand, lead to derivative estimates exactly equal to their continuous counterparts, and also over the entire scale range.”
Self-citationDetecting Curved Symmetric Parts Using a Deformable Disc Model
Lee, T. S. H., Fidler, S., & Dickinson, S. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.220 · Cited by 45
“Example approaches in this domain include the multiscale peak paths of Crowley and Parker [9], the multiscale blobs of Shokoufandeh et al. [32], the ridge detectors of Mikolajczyk and Schmid [22], and the multiscale blobs and ridges of Lindeberg and Bretzner [14], and Shokoufandeh et al. [31].”
MethodInvariance of visual operations at the level of receptive fields
Lindeberg, T. (2013) · PLoS ONE · doi:10.1371/journal.pone.0066990 · Cited by 44
Self-citationLocal spatio-temporal image features for motion interpretation
Laptev, I. (2004) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 46
Idealized Computational Models for Auditory Receptive Fields
Lindeberg, T., & Friberg, A. (2015) · PLoS ONE · doi:10.1371/journal.pone.0119032 · Cited by 32
Self-citationInterest Point Detection and Scale Selection in Space-Time
Laptev, I., & Lindeberg, T. (2003) · Lecture notes in computer science · doi:10.1007/3-540-44935-3_26 · Cited by 32
“During recent years, the problem of automatic scale selection has been addressed in several different ways, based on the maximisation of normalised derivative expressions over scale, or the behaviour of entropy measures or error measures over scales (see the companion paper by Lindeberg and Bretzner (2003) for a revie…”
BackgroundSelf-citationLindeberg, T. (2014) · Springer eBooks · doi:10.1007/978-0-387-31439-6_242 · Cited by 28
“Indeed, the variations over time in the characteristic scale estimates obtained during feature tracking can, if appropriately implemented, be robust enough for computing estimates of time-to-collision [20,25].”
BackgroundInfluentialSelf-citationSpatio-Temporal Scale Selection in Video Data
Lindeberg, T. (2017) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-017-0766-9 · Cited by 26
“For discrete approximation of scale-normalized derivatives, one can perform either (i) variance normalization, by multiplying the discrete derivative approximations by the scale parameter s raised to an appropriate power γ or by (ii) l p-normalization, by normalizing the equivalent discrete derivative approximation ke…”
MethodSelf-citationScale selection for anisotropic scale-space: application to volumetric tumor characterization
Okada, K., Comaniciu, D., & Krishnan, A. (2004) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2004.1315086 · Cited by 25
Learning Hierarchical Shape Models from Examples
Levinshtein, A., Sminchisescu, C., & Dickinson, S. (2005) · Lecture notes in computer science · doi:10.1007/11585978_17 · Cited by 23
“We seek a decomposition of an image into a set of qualitative parts and attachment relations, and adopt the multi-scale blob and ridge decomposition proposed in [18].”
MethodKeypoint Detection in RGBD Images Based on an Anisotropic Scale Space
Karpushin, M., Valenzise, G., & Dufaux, F. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2590305 · Cited by 21
“More precisely, we search for keypoints in a multiscale representation obtained in a similar way to [49], by progressively smoothing and subsampling the input image.”
Temporal Scale Selection in Time-Causal Scale Space
Lindeberg, T. (2017) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-016-0691-3 · Cited by 21
Self-citationMultiscale 3D feature extraction and matching with an application to 3D face recognition
Fadaifard, H., Wolberg, G., & Haralick, R. H. (2013) · Graphical Models · doi:10.1016/j.gmod.2013.01.002 · Cited by 16
A Distance Measure and a Feature Likelihood Map Concept for Scale-Invariant Model Matching
Laptev, I., & Lindeberg, T. (2003) · International Journal of Computer Vision · doi:10.1023/a:1022947906601 · Cited by 16
Self-citationPhysical activity recognition based on motion in images acquired by a wearable camera
Zhang, H., Li, L., Jia, W., Fernstrom, J. D., Sclabassi, R. J., Mao, Z., & Sun, M. (2011) · Neurocomputing · doi:10.1016/j.neucom.2011.02.014 · Cited by 14
Reducing dense local feature key-points for faster iris recognition
Sahu, B., Kumar, P., Bakshi, S., & Sangaiah, A. K. (2018) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2017.12.048 · Cited by 14
Video object tracking using SIFT and mean shift
Zhu, C. (2011) · Cited by 12
Using SIFT Method for Global Topological Localization for Indoor Environments
Boroş, E., Roşca, G., & Iftene, A. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15751-6_34 · Cited by 11
“Our system is based mainly on SIFT algorithm [5, 6] and it has the aim to implement a method for extracting distinctive invariant features [3, 4 ] from images that can be used to perform reliable matching between different views of an object or scene (See Figure 1). The features have to be invariant to a lot of change…”
MethodA Unified B-Spline Framework for Scale-Invariant Keypoint Detection
Zheng, Q., Gong, M., You, X., & Tao, D. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-021-01568-3 · Cited by 10
“Fortunately, hybrid multi-scale representation brought flexible trade-offs between computational cost and accuracy, which enabled real-time processing at that moment (Lindeberg and Bretzner 2003) and was used in a real-time hand gesture recognition system (Bretzner et al. 2002).”
BackgroundSteering in Scale Space to Optimally Detect Image Structures
Ng, J., & Bharath, A. A. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24670-1_37 · Cited by 10
Fagerström, D. (2007) · Springer eBooks · doi:10.1007/978-3-540-72823-8_28 · Cited by 9
“The one in space can be computed with an explicit scheme for the heat equation with sub sampling as described in [13].”
MethodAn image smoothing operator for fast and accurate scale space approximation
Karpushin, M., Valenzise, G., & Dufaux, F. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7471999 · Cited by 9
“The focus of this paper is image smoothing complexity in context of salient visual point detection.”
BackgroundSpatio-Temporal Scale Selection in Video Data
Lindeberg, T. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-58771-4_1 · Cited by 8
Self-citationEaton, R. S., Stevens, M. R., McBride, J. C., Foil, G., & Snorrason, M. S. (2006) · International Conference on Computer Vision Systems · doi:10.1109/icvs.2006.9 · Cited by 9
“Lindeberg and Bretzner [8] describe the hybrid pyramid scale space representation and show that l p –normalization of derivatives is more accurate than variance-based normalization.”
BackgroundHessian-Laplace feature detector and Haar descriptor for image matching
Bhatia, A. (2007) · uO Research (University of Ottawa) · doi:10.20381/ruor-12087 · Cited by 8
“This latter representation has been investigated by Lindeberg and Bretzner[43, 2003] and was used in their work to test its efficiency for blob detection.”
BackgroundMethodPerzanowski, A., & Lindeberg, T. (2025) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-025-01245-x · Cited by 7
“An empirical observation, however, was that a denser scale sampling of the scale levels by a factor of √ 2 or lower can lead to substantially better results, both regarding pyramids and regarding classical scale-space algorithms (Lindeberg 1993, Lindeberg and Bretzner 2003).”
Self-citationLindeberg, T. (2020) · Springer eBooks · doi:10.1007/978-3-030-03243-2_242-1 · Cited by 7
Self-citationChristensen, N. B. (2018) · Near Surface Geophysics · doi:10.1002/nsg.12018 · Cited by 6
“The relation between the binomial filters and the Gaussian function is that, in the limit N → ∞, we have (Lindeberg and Bretzner 2003): ( N”
BackgroundCamera-based navigation for service robots using pictographs on the crossing point
Chugo, D., Hirose, K., Nakashima, K., Yokota, S., Kobayashi, H., & Hashimoto, H. (2012) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2012.6389224 · Cited by 6
Service robots navigation using pictographs detection for indoor environment
Hirose, K., Chugo, D., Yokota, S., & Takase, K. (2011) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2011.6119644 · Cited by 6
“For improving the calculation speed for template detection, SURF (Speeded Up Robust Feature) [10-13] is proposed.”
MethodCamera-based localization for indoor service robots using pictographs
Hirose, K., Chugo, D., Yokota, S., & Takase, K. (2011) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2011.6027131 · Cited by 6
“For improving the calculation speed for template detection, SURF (Speeded Up Robust Feature) [10] [11] [12] [13] is proposed.”
MethodSpeed-up Feature Detector using Adaptive Accelerated Segment Test
Biadgie, Y., & Sohn, K.-A. (2016) · IETE Technical Review · doi:10.1080/02564602.2015.1103669 · Cited by 6
“LOG score has been proven to produce stable key points across the scale-space representation of an input image [18].”
BackgroundMethodAccurate and Efficient Approximation of the Continuous Gaussian Scale-Space
Köthe, U. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-28649-3_43 · Cited by 6
“Up to now, attempts to access images in real-valued coordinate systems have been based on simple interpolation schemes such as linear interpolation, low order polynomial fits, or the facet model [5,8,3].”
BackgroundMethodColor Edge Saliency Boosting using Natural Image Statistics
Vigo, D. A. R., van de Weijer, J., & Gevers, T. (2010) · Conference on Colour in Graphics Imaging and Vision · doi:10.2352/cgiv.2010.5.1.art00037 · Cited by 5
“A very similar approach is a hybrid multi-scale representation [38] which was tested for local feature detection in [39].”
BackgroundUAIC: Participation in ImageCLEF 2009 Robot Vision Task.
Boroş, E., Roşca, G., & Iftene, A. (2009) · CLEF (Working Notes) · Cited by 5
Canonical subsets of image features
Denton, T., Shokoufandeh, A., Novatnack, J., & Nishino, K. (2008) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2008.06.002 · Cited by 5
“Lindeberg and Bretzner [ 50 ] that detects blobs and ridges.”
BackgroundDirect occlusion handling for high level image processing algorithms
Kelso, C. R. (2009) · RIT Scholar Works (Rochester Institute of Technology) · Cited by 5
Lindeberg, T. (2025) · Frontiers in Signal Processing · doi:10.3389/frsip.2024.1447841 · Cited by 4
“…approaches in terms of pyramid rep-resenations (Burt and Adelson 1983, Crowley 1984, Simon-celli et al. 1992, Simoncelli and Freeman 1995, Lindeberg and Bretzner 2003, Crowley and Riff 2003, Lowe 2004), Fourier-based implementations, splines (Unser et al. 1991, 1993, Wang and Lee 1998,…”
Self-citationDevelopment of Speed Up Robust Feature Algorithm for aerial image feature extraction
Banerjee, S., Chaturvedi, S. K., & Tiwari, S. P. (2019) · INCAS BULLETIN · doi:10.13111/2066-8201.2019.11.4.5 · Cited by 4
Automatic Detection of Vehicles in Satellite Images for Economic Monitoring
Hill, C. (2021) · Digital Commons - University of South Florida (University of South Florida) · Cited by 4
Deep Video Analysis Methods for Surgical Skills Assessment in Cataract Surgery
Tanin, U. (2022) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2022-15129 · Cited by 4
“[48] T. Lindeberg and L. Bretzner, “Real-time scale selection in hybrid multi-scale representations,” in Scale Space Methods in Computer Vision, L. D. Griffin and M. Lillholm, Eds.”
MethodThe Role of Mid-Level Shape Priors in Perceptual Grouping and Image Abstraction
Dickinson, S., Levinshtein, A., Sala, P., & Sminchisescu, C. (2013) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-5195-1_1 · Cited by 3
“4 Overview of our approach for multiscale symmetric part detection and grouping: (a) original image; (b) set of multiscale superpixel segmentations (different superpixel resolutions); (c) the graph of affinities shown for one scale (superpixel resolution); (d) the set of regularized symmetric parts extracted from all…”
BackgroundA Framework for Symmetric Part Detection in Cluttered Scenes
Lee, T., Fidler, S., Levinshtein, A., Sminchisescu, C., & Dickinson, S. (2015) · Symmetry · doi:10.3390/sym7031333 · Cited by 3
“(1999) [25], the ridge detectors of Mikolajczyk & Schmid (2002) [26], and the multiscale blobs and ridges of Lindeberg & Bretzner (2003) [27], and Shokoufandeh et al .”
Learning Scan Paths for Object Recognition with Relational Reinforcement Learning
Häming, K., & Peters, G. (2010) · IASTED International Conference on Signal Processing, Pattern Recognition and Applications / Computer Graphics and Imaging (SPPRA/CGIM) · doi:10.2316/p.2010.678-018 · Cited by 3
“To comply with this requirement, we use a scale space Harris detector, combining the real time scale space of Lindeberg [6] with the Harris detector [7], while modifying the latter to make it work in a scale space pyramid [8].”
MethodKarpushin, M., Valenzise, G., & Dufaux, F. (2016) · European Signal Processing Conference (EUSIPCO) · doi:10.1109/eusipco.2016.7760683 · Cited by 3
Phase Invariant Keypoint Detection
Bharath, A. A., & Kingsbury, N. G. (2007) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/icdsp.2007.4288615 · Cited by 3
“The first enhancement of this paper is a scheme for removing keypoints that are induced by jaggedness in images that are poorly bandlimited.”
BackgroundImage Features and Feature Processing
Xu, L., Lin, W., & Kuo, C. ‐. J. (2015) · Springer briefs in electrical and computer engineering · doi:10.1007/978-981-287-468-9_3 · Cited by 3
Lindeberg, T. (2021) · Springer eBooks · doi:10.1007/978-3-030-63416-2_242 · Cited by 3
Self-citationFrom pictures to 3D : global optimization for scene reconstruction
Chandraker, M. K. (2009) · eScholarship (California Digital Library) · Cited by 3
Perceptual Grouping Using Superpixels
Dickinson, S., Levinshtein, A., & Sminchisescu, C. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-31149-9_2 · Cited by 2
“For example, classical multiscale blob and ridge detectors, such as [13] (Fig.”
BackgroundFast Freehand Acquisition of 3D Objects and Their Visualization
Peters, G., Peters, Klaus, & haming (2010) · Journal of Communication and Computer · Cited by 2
Investigating the effects of scale in MRF texture classification
Blunsden, S. J. (2005) · International Conference on Visual Information Engineering (VIE) · doi:10.1049/cp:20050100 · Cited by 2
“Previous methods [8, 9, 5, 6] did not incorporate this type of information into their definition of scale.”
MethodDetecting changed areas in images from different view points
Kulasekara, D., & Harshanath, S. M. B. (2013) · International Conference on Computer Science & Education (ICCSE) · doi:10.1109/iccse.2013.6553966 · Cited by 2
Evaluación de Operadores Diferenciales -Normalizados para Selección Automática de Escalas
Sánchez, J. (2008) · Mecánica Computacional (Asociación Argentina de Mecánica Computacional) · Cited by 2
Mathematical Properties of Pyramid-Transform-Based Resolution Conversion and Its Applications
Hosoya, K., Nozawa, K., Itoh, H., & Imiya, A. (2023) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-023-01166-7 · Cited by 2
“Furthermore, the hybrid pyramid transform [80] has also been introduced with a generalisation of sampling schemes of the pyramid transform.”
Discrete approximations of the affine Gaussian derivative model for visual receptive fieldsPreprint
Lindeberg, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.02127 · Cited by 2
“8 1 16 1 8 1 16 1 C C C C A : (73) This kernel is a common iteration kernel for computing pyramid representations (Crowley [8]; Crowley and Parker [10, 9]; Lindeberg [37, 39]; Lindeberg and Bretzner [48]). Specically, applying the underlying one-dimensional kernel (1=4;1=2;1=4) for separable convolution twice in the s…”
BackgroundInfluentialSelf-citationRegistration of synthetic aperture imagery using feature matching.
Wang, V. T. (2018) · UC Research Repository (University of Canterbury) · doi:10.26021/1636 · Cited by 2
“The Frobenius norm of the filters is kept constant so that they are effectively scale-normalised [Lindeberg and Bretzner 2003].”
BackgroundLizcano, J. A. M. (2015) · UPM Digital Archive (Technical University of Madrid) · doi:10.20868/upm.thesis.39251 · Cited by 2
Visual navigation in unmanned air vehicles with simultaneous location and mapping (SLAM)
Li, X. (2014) · CERES (Cranfield University) · Cited by 2
Relational Reinforcement Learning Applied to Appearance-Based Object Recognition
Häming, K., & Peters, G. (2009) · Communications in computer and information science · doi:10.1007/978-3-642-03969-0_28 · Cited by 1
“To comply with this requirement, we use a scale space Harris detector, combining the real time scale space of Lindeberg [6] with the Harris detector [7], while modifying the latter to make it work in a scale space pyramid [8].”
MethodThe Application of SIFT Algorithm in Blind Road Environmental Image Matching
Shi, S., Yu, M., Xue, C., & Zhou, Y. (2012) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.155-156.1137 · Cited by 1
Detectors and Descriptors of Interest Points
Distante, A., & Distante, C. (2020) · Springer eBooks · doi:10.1007/978-3-030-42374-2_6 · Cited by 1
Directional SIFT -- An Improved Method Using Elliptical Gaussian Pyramid
Xu, X., & Yang, J. J. (2010) · Chinese Conference on Pattern Recognition · doi:10.1109/ccpr.2010.5659135 · Cited by 1
“Lindeberg concluded that normalized Laplacian of Gaussian will automatically select scales [4, 5, 6 ] . Combined with Harris corner”
BackgroundTroncoso, J. M. C. (2011) · UNED repository · Cited by 1
Spatio-Temporal Scale-Space Theory
Fagerström, D. (2011) · DiVA (Digitala Vetenskapliga Arkivet) · Cited by 1
A rectification strategy for state estimation of qudarotors based on parallel tracking and mapping
Li, X., Zhang, Y., Yang, F., & Wu, B. (2015) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2015.7279811
Real-time Dynamic Visualization Techniques for Massive Geospatial Data
Yanan, Z., Xiaodong, H., & Li, J. (2014) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2014.174
LEARNING DECOMPOSITIONAL SHAPE MODELS FROM EXAMPLES
Levinshtein, A. (2005)
Casamento de modelos baseado em projeções radiais e circulares invariante a pontos de vista.
Lopez, G. A. P. (2016) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.3.2016.tde-24052016-150250
Object tracking with SURF: ARM-Based platform Implementation
Hassnaoui, H., BADRI, A. B., Sahel, A., & Akil, M. (2017) · International Journal of Computer Applications Technology and Research · doi:10.7753/ijcatr0606.1002
An Efficient Implementation of Image Mipmapping using Frequency Domain Techniques
SreenivasaRao, C., Dudekula, B., & Nukala, S. (2017) · International Journal of Engineering and Technology · doi:10.21817/ijet/2017/v9i3/1709030288
Troncoso, J. M. C. (2012) · Tesis Doctorals en Xarxa (Consorci de Serveis Universitaris de Catalunya)
Image matching using rotating filters
Venkatrayappa, D. (2015) · theses.fr (ABES) · doi:10.70675/c964adcczfb83z4086zabd7z7ada6dc6f4fe
A Unified Theory of Image Scaling: Point Spread Functions, Discrete Kernels, and Scale-SpacesPreprint
Shocher, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.22472
“From a few axioms, it derives one semigroup of Gaussian kernels [12–14], with discrete [15, 16], affine [17], and pyramid [18] versions.”
Metadata
- Authors
- Lindeberg, T., & Bretzner, L.
- Affiliations
- KTH Royal Institute of Technology (SE)
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2003
- Pages
- 148-163
- ISSN
- 0302-9743 (ISSN-L)
- OpenAlex
- W1684301558
- Cited by
- 85
- References
- 60
- Citations by year
- 2025: 2 · 2024: 2 · 2023: 1 · 2022: 2 · 2021: 2 · 2020: 2 · 2019: 1 · 2018: 4 · 2017: 4 · 2016: 5 · 2015: 9 · 2014: 4 · 2013: 6 · 2012: 5
- FWCI
- 3.45
- Type
- conference paper
- Language
- en
- Open access
- green
- urn.kb.se
- Licence
- other-oa
- Locations
- Lecture notes in computer science (publishedVersion)
- KTH Publication Database DiVA (KTH Royal Institute of Technology) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- scale selection, scale space, variance normalization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.