Feature Detection with Automatic Scale Selection
Open accessThe DOI matches its Crossref record; 56 of the 61 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
“We base our detector on the Hessian matrix because of its good performance in computation time and accuracy.”
From SURF: Speeded Up Robust Features (2006) · cites this paper as [1]
Citations
Cites
Handbook of Mathematical Functions
McQuarrie, D. A. (1966) · American Journal of Physics · doi:10.1119/1.1972842 · Cited by 40,433
Singularity detection and processing with wavelets
Mallat, S., & Hwang, W. L. (1992) · IEEE Transactions on Information Theory · doi:10.1109/18.119727 · Cited by 3,863 · cited 2×
“A main difference between the scale selection mechanism suggested here and the work in (Lindeberg, 1991; Mallat and Hwang, 1992), however, here it is shown that how these notions can be applied to large classes of non-linear differential invariants computed in a scale-space representation.”
BackgroundMethodRelations between the statistics of natural images and the response properties of cortical cells
Field, D. J. (1987) · Journal of the Optical Society of America A · doi:10.1364/josaa.4.002379 · Cited by 3,241 · cited 1×
“It is well-known that natural images often show a qualitative behaviour similar to this ( Field, 1987 ).”
BackgroundCharacterization of signals from multiscale edges
Mallat, S., & Zhong, S. (1992) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.142909 · Cited by 3,200
Koenderink, J. J. (1984) · Biological Cybernetics · doi:10.1007/bf00336961 · Cited by 2,452 · cited 2×
“…to the construction of multi-scale representations of image data, obtained by embedding any given signal into a one-parameter family of derived signals (Burt, 1981; Crowley, 1981; Witkin, 1983; Koenderink, 1984; Yuille and Poggio, 1986; Florack et al., 1992; Lindeberg, 1994a; Haar Romeny, 1994).”
BackgroundResultWitkin, A. P. (1987) · Readings in Computer Vision · doi:10.1016/b978-0-08-051581-6.50036-2 · Cited by 2,359
Scale-Space Theory in Computer Vision
Lindeberg, T. (1994) · Springer eBooks · doi:10.1007/978-1-4757-6465-9 · Cited by 2,169
Self-citation(1964) · doi:10.1115/1.3625776 · Cited by 1,796
Modeling visual attention via selective tuning
Tsotsos, J. K., Culhane, S. M., Kei Wai, W. Y., Lai, Y., Davis, N., & Nuflo, F. (1995) · Artificial Intelligence · doi:10.1016/0004-3702(95)00025-9 · Cited by 1,143 · cited 1×
“When combined with feature detection modules, the general approach of scale selection can serve as a primitive mechanism for guiding the focus of attention (Lindeberg, 1993a; Tsotsos et al., 1995) and provide qualitative context information for other early visual modules.”
MethodEdge Detection and Ridge Detection with Automatic Scale Selection
Lindeberg, T. (1998) · International Journal of Computer Vision · doi:10.1023/a:1008097225773 · Cited by 1,024 · cited 5×
“…1993b, 1994d, 1994a, 1996c) as well as applications of the general ideas to various problem domains (Lindeberg and Gårding, 1993, 1997; Gårding and Lindeberg, 1996; Lindeberg and Li, 1995, 1997; Bretzner and Lindeberg, 1998, 1997; Almansa and Lindeberg, 1996; Wiltschi et al., 1997; Lindeberg,…”
BackgroundMethodInfluentialSelf-citation
Research works printed but not linked: 9
- Blom, J. 1992. Topological and geometrical aspects of image structure. Ph.D. Thesis. Dept. Med. Phys. Physics, Univ. Utrecht, NL-3508 Utrecht, Netherlands.
- Bretzner, L. and Lindeberg, T. 1996. Feature tracking with automatic selection of spatial scales. Technical Report ISRN KTH/NA/P-96/21-SE, Dept. of Numerical Analysis and Computing Science, KTH, Stockholm, Sweden. Revised version in Computer Vision and Image Understanding.
- Förstner, W.A. and Gülch, E. 1987. A fast operator for detection and precise location of distinct points, corners and centers of circular features. In Proc. Intercommission Workshop of the Int. Soc. for Photogrammetry and Remote Sensing, Interlaken, Switzerland.
- Johansen, P., Skelboe, S., Grue, K., and Andersen, J.D. 1986. Representing signals by their top points in scale-space. In Proc. 8th Int. Conf. on Pattern Recognition, Paris, France, pp. 215- 217.
- Lindeberg, T. 1993. On scale selection for differential operators. In Proc. 8th Scandinavian Conf. on Image Analysis, Tromsø, Norway, K. Heia K.A. Høgdra, B. Braathen (Ed.), pp. 857-866.
- Lindeberg, T. 1996a. Feature detection with automatic scale selection. Technical Report ISRN KTH/NA/P-96/18-SE, Dept. of Numerical Analysis and Computing Science, KTH, Stockholm, Sweden.
- Marr, D. 1982. Vision. W.H. Freeman: New York.
- Voorhees, H. and Poggio, T. 1987. Detecting textons and texture boundaries in natural images. In Proc. 1st Int. Conf. on Computer Vision, London, England.
- Young, R.A. 1985. The Gaussian derivative theory of spatial vision: Analysis of cortical cell receptive field line-weighting pro-files. Technical Report GMR-4920, Computer Science Department, General Motors Research Lab., Warren, Michigan.
Cited by
Items 401–500 of 1,001
Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences
Fathy, M. E., Tran, Q.-H., Zia, M. Z., Vernaza, P., & Chandraker, M. K. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01267-0_49 · Cited by 54
A FAST-BRISK Feature Detector with Depth Information
Liu, Y., Zhang, H., Guo, H., & Xiong, N. N. (2018) · Sensors · doi:10.3390/s18113908 · Cited by 51
“Many well-known feature point detection algorithms based on image gradient information use Hessian matrix to calculate their corresponding feature point response functions, such as LoG [16], SURF [7], KAZE [17], AKAZE [18],and so on.”
MethodAutomatic Detection of Small Icebergs in Fast Ice Using Satellite Wide-Swath SAR Images
Soldal, I. H., Dierking, W., Korosov, A. A., & Marino, A. (2019) · Remote Sensing · doi:10.3390/rs11070806 · Cited by 50
Distinctive image features from illumination and scale invariant keypoints
Tang, G., Liu, Z., & Xiong, J. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7566-8 · Cited by 52
Corner Detection Using Second-Order Generalized Gaussian Directional Derivative Representations
Zhang, W., & Sun, C. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2949302 · Cited by 50
Lillholm, M., Nielsen, M., & Griffin, L. D. (2003) · International Journal of Computer Vision · doi:10.1023/a:1022995822531 · Cited by 55
“Considering the complexity of corners and the design of traditional corner detectors (Harris and Stephens, 1988; Lindeberg, 1998), it seems reasonable to incorporate the 2nd order structure at corner points as well, as this captures, along with first order structure, the isophote curvature.”
BackgroundMethodPark, S., Ionascu, D., Hacker, F., Mamon, H. J., & Berbeco, R. (2009) · Medical Physics · doi:10.1118/1.3218845 · Cited by 50
Psychophysics with Junctions in Real Images
McDermott, J. H. (2004) · Perception · doi:10.1068/p5265 · Cited by 55
“(e) Three aperture sizes are used; occlusion point can only be seen over a large region at full resolution. would be produced by sensor noise alone (see also Morrone et al 1995; Lindeberg 1998).”
BackgroundResultWeakly Supervised Learning of Visual Models and Its Application to Content-Based Retrieval
Schmid, C. (2003) · International Journal of Computer Vision · doi:10.1023/b:visi.0000004829.38247.b0 · Cited by 50
“However, invariance to scale changes requires the use of scale invariant descriptors (Lindeberg, 1998; Mikolajczyk and Schmid, 2001).”
BackgroundA Comparative Analysis of Feature Detectors and Descriptors for Image Stitching
Sharma, S. K., Jain, K. K., & Shukla, A. K. (2023) · Applied Sciences · doi:10.3390/app13106015 · Cited by 55
Hybrid retinal image registration using phase correlation
Kolář, R., Harabiš, V., & Odstrčilík, J. (2012) · The Imaging Science Journal · doi:10.1179/1743131x11y.0000000065 · Cited by 49
Anisotropic Diffusion for Hyperspectral Imagery Enhancement
Wang, Y., Niu, R., & Yu, X. (2010) · IEEE Sensors Journal · doi:10.1109/jsen.2009.2037800 · Cited by 49
A Solitary Feature-Based Lung Nodule Detection Approach for Chest X-Ray Radiographs
Li, X., Shen, L., & Luo, S. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2661805 · Cited by 49
“Lindeberg’s multi-scale blob detection algorithm [32] to extract lung nodule candidates.”
MethodYang, G., Zhuang, X., Khan, H. R., Haldar, S., Nyktari, E. G., Li, L., Wage, R., Ye, X., Slabaugh, G., Mohiaddin, R. H., et al. (2018) · Medical Physics · doi:10.1002/mp.12832 · Cited by 51
Fusion of depth maps with multiple scales
Fuhrmann, S., & Goesele, M. (2011) · ACM Transactions on Graphics · doi:10.1145/2070781.2024182 · Cited by 54
Ground Truth Data, Content, Metrics, and Analysis
Krig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_7 · Cited by 53
Naveed, K., Daud, F., Madni, H. A., Khan, M. A. U., Khan, T. M., & Naqvi, S. R. (2021) · Diagnostics · doi:10.3390/diagnostics11010114 · Cited by 48
“In doing so, we address the inherent checkerboard artifact problem in S-BM3D by suggesting a novel ensemble filtering approach to mitigate these artifacts without compromising the quality of the recovered details.”
Liu, Z., Li, F., Li, X., & Zhang, G. (2014) · Measurement · doi:10.1016/j.measurement.2014.11.027 · Cited by 48
Learning to Recognize Objects with Little Supervision
Carbonetto, P. S., Dorkó, G., Schmid, C., Kück, H., & de Freitas, N. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-007-0067-7 · Cited by 52
“All the other columns state the performance obtained using the proposed Bayesian model with regions extracted by various detectors (from left to right): Harris–Laplace (H–L) (Mikolajczyk and Schmid 2001), Kadir–Brady (K–B) entropy detector (Kadir and Brady 2001), Laplacian of Gaussians (LoG) (Lindeberg 1998), and comb…”
MethodExtracting Salient Brain Patterns for Imaging-Based Classification of Neurodegenerative Diseases
Rueda, A., Gonzalez, F. A., & Romero, E. (2014) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2014.2308999 · Cited by 53
Junction detection for linear structures based on Hessian, correlation and shape information
Su, R., Sun, C., & Pham, T. D. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.04.013 · Cited by 48
“Blobs and junctions are often hard to differentiate in existing methods [40,36] due to their similarity with junctions in structures.”
BackgroundSIFT-based ear recognition by fusion of detected keypoints from color similarity slice regions
Kisku, D. R., Mehrotra, H., Gupta, P., & Sing, J. K. (2009) · International Conference on Advances in Computational Tools for Engineering Applications · doi:10.1109/actea.2009.5227958 · Cited by 48
3-D Object Map Building Using Dense Object Models with SIFT-based Recognition Features
Tomono, M. (2006) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2006.282312 · Cited by 48
“The scale space analysis is necessary in order to detect edge points invariant to scale change [12].”
BackgroundDense Correspondences across Scenes and Scales
Tau, M., & Hassner, T. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2474356 · Cited by 50
“In his pioneering work, Lindeberg [23], [24] was one of the first to suggest seeking image pixels which have welldefined, characteristic scales.”
BackgroundCoding Images with Local Features
Dickscheid, T., Schindler, F., & Förstner, W. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-010-0340-z · Cited by 47
“Mikolajczyk and Schmid (2004) is theoretically related to LOWE, as it is also based on the theory of Lindeberg (1998b) and relies on the second derivatives of the image function over scale space.”
BackgroundMethodInfluentialYan, T., Hu, Z., Qian, Y., Qiao, Z., & Zhang, L. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.107065 · Cited by 47
Training of a crater detection algorithm for Mars crater imagery
Vinogradova, T., Burl, M. C., & Mjolsness, E. (2003) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero.2002.1035297 · Cited by 47
An improved edge detection algorithm for depth map inpainting
Chen, W., Yue, H., Wang, J., & Wu, X. (2013) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2013.10.025 · Cited by 46
Probabilistic learning for fully automatic face recognition across pose
Sarfraz, M. S., & Hellwich, O. (2009) · Image and Vision Computing · doi:10.1016/j.imavis.2009.07.008 · Cited by 46
A feature-based robust digital image watermarking against geometric attacks
Wang, X., Hou, L.-M., & Wu, J. (2007) · Image and Vision Computing · doi:10.1016/j.imavis.2007.10.014 · Cited by 46
Computer-Aided Detection of Diagnostic and Therapeutic Operations in Colonoscopy Videos
Cao, Y., Liu, D., Tavanapong, W., Wong, J., Oh, J., & de Groen, P. C. (2007) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2007.890734 · Cited by 46
Line and circle detection using dense one-to-one Hough transforms on greyscale images
Antoine Manzanera, B., Nguyễn, T. P., & Xu, X. (2016) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-016-0149-y · Cited by 51
“It could be selected automatically from the image [40], but simply aggregating the votes at the different scales with their different weights is actually faster and closer to the Hough spirit.”
BackgroundContrast normalization steps for increased sensitivity of a retinal image segmentation method
Soomro, T. A., Khan, M. A. U., Gao, J., Khan, T. M., & Paul, M. (2017) · Signal Image and Video Processing · doi:10.1007/s11760-017-1114-7 · Cited by 46
“Optimal values of α and β are calculated for ideal ridge patterns in [25], which are α = 1.”
BackgroundGeneralized Boundaries from Multiple Image Interpretations
Leordeanu, M., Sukthankar, R., & Sminchisescu, C. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.17 · Cited by 46
Rodrigues, J. M. F., & du Buf, J. M. H. (2006) · Biosystems · doi:10.1016/j.biosystems.2006.02.019 · Cited by 46
“We add that we will not employ the multi-scale line/edge representation that also exists in area V1, in order to emphasise the importance of the information provided by keypoints.”
BackgroundMethodInfluentialA scale selection principle for estimating image deformations
Lindeberg, T. (1998) · Image and Vision Computing · doi:10.1016/s0262-8856(98)00065-1 · Cited by 48
Self-citationA new accurate and flexible model based multi-corner detector for measurement and recognition
Gustavo Olague, A., & Hernández, B. (2004) · Pattern Recognition Letters · doi:10.1016/j.patrec.2004.08.026 · Cited by 46
“A great deal of effort has been spent by the computer vision and photogrammetric communities on this problem, see (Ackermann, 1984; Gruen, 1985; Foerstner, 1986; Medioni and Yasumoto, 1987; Gruen and Baltsavias, 1988; Mehrotra and Nichani, 1990; Rohr, 1992; Deriche and Giraudon, 1993; Rosin, 1996; Baker et al., 1998;…”
BackgroundHamming Embedding and Weak Geometry Consistency for Large Scale Image Search - extended version
Jeǵou, H., Douze, M., & Schmid, C. (2008) · HAL · Cited by 46
A Performance Evaluation of Volumetric 3D Interest Point Detectors
Yu, T.-H., Woodford, O. J., & Cipolla, R. (2012) · International Journal of Computer Vision · doi:10.1007/s11263-012-0563-2 · Cited by 49
“The DoH interest point is similar to the Harris detector with respect to formulation (Lindeberg 1998); instead of computing the second-moment matrix M, it is based on the Hessian matrix H in (5):”
BackgroundMethodInfluentialHeartbeat of a nest: Using imagers as biological sensors
Ko, T. H., Ahmadian, S., Hicks, J., Rahimi, M. H., Estrin, D. L., Soatto, S., Coe, S. J., & Hamilton, M. P. (2010) · ACM Transactions on Sensor Networks · doi:10.1145/1754414.1754415 · Cited by 45
A scale- and orientation-adaptive extension of Local Binary Patterns for texture classification
Hegenbart, S., & Uhl, A. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.02.024 · Cited by 47
“This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).”
BackgroundInfluentialAn improved Bag-of-Words framework for remote sensing image retrieval in large-scale image databases
Yang, J., Liu, J., & Dai, Q. (2014) · International Journal of Digital Earth · doi:10.1080/17538947.2014.882420 · Cited by 46
Visual novelty detection with automatic scale selection
Neto, H. V., & Nehmzow, U. (2007) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2007.05.012 · Cited by 45
“However, other alterations in appearance such as changes in scale, rotations or affine-transformations need more elaborated image encoding to be dealt with efficiently.”
BackgroundEfficient Small Blob Detection Based on Local Convexity, Intensity and Shape Information
Zhang, M., Wu, T., Beeman, S. C., Cullen‐McEwen, L. A., Bertram, J. F., Charlton, J. R., Baldelomar, E. J., & Bennett, K. M. (2015) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2015.2509463 · Cited by 45
“One classic approach is the Laplacian of Gaussian (LoG) [8].”
BackgroundMethodInfluentialSmith, A., Metz, J., & Pagliara, S. (2019) · Scientific Reports · doi:10.1038/s41598-019-46567-0 · Cited by 50
On the potential of QuickBird data for archaeological prospection
Lasaponara, R., & Masini, N. (2006) · International Journal of Remote Sensing · doi:10.1080/01431160500333983 · Cited by 45
“The edge detection was performed by applying a multiscale approach based on the scale-space theory (Lindeberg 1998) that uses Gaussian smoothing kernels.”
MethodEarthquake Damage Detection in Urban Areas Using Curvilinear Features
Brett, P. T. B., & Raffaella Guida, A. (2013) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2013.2271564 · Cited by 44
Visual SLAM and Moving-object Detection for a Small-size Humanoid Robot
Wang, Y.-T., Lin, M.-C., & Ju, R.-C. (2010) · International Journal of Advanced Robotic Systems · doi:10.5772/9700 · Cited by 47
“The basic concept of a scale-invariant method is to detect image features by investigating the determinant of Hessian matrix H (Lindeberg, T., 1998).”
MethodSparse Color Interest Points for Image Retrieval and Object Categorization
Stöttinger, J., Hanbury, A., Sebe, N., & Gevers, T. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2186143 · Cited by 47
Features for recognition: viewpoint invariance for non-planar scenes
Vedaldi, A., & Soatto, S. (2005) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2005.99 · Cited by 44
“10In particular, translation invariance g ∈ R2 [21], scale invariance g ∈ R3 [27]; Euclidean invariance (g ∈ SE(2)) and Similarity invariance (g ∈ SE(2) × R) [29]; Affine invariance g ∈ A(2) [32] are all well-known.”
BackgroundFast Computation of Scale Normalised Gaussian Receptive Fields
Crowley, J. L., & Riff, O. (2003) · Lecture notes in computer science · doi:10.1007/3-540-44935-3_41 · Cited by 44
“The binomial filters b2(m) (with coefficients [1, 2, 1]) and b4(m) (with coefficients [1, 4, 6, 4, 1]) are of special interest.”
BackgroundMethodFacial features detection robust to pose, illumination and identity
Gourier, N., Hall, D., & Crowley, J. L. (2005) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2004.1398368 · Cited by 44
A Probabilistic Sensor for the Perception and the Recognition of Activities
Chomat, O., Martin, J. R., & Crowley, J. L. (2000) · Lecture notes in computer science · doi:10.1007/3-540-45054-8_32 · Cited by 47
Improved Harris Feature Point Set for Orientation-Sensitive Urban-Area Detection in Aerial Images
Kovacs, A., & Szirányi, T. (2012) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2012.2224315 · Cited by 43
“blob detector Laplacian of Gaussian (LoG) [13] in [17].”
BackgroundWang, J., Zhan, Q., & Guo, H. (2015) · Remote Sensing · doi:10.3390/rs8010018 · Cited by 44
“The characteristic scale of a point on the surface should best manifest the local feature at that point [47,48].”
BackgroundProgressive Large Scale-Invariant Image Matching in Scale Space
Zhou, L., Zhu, S., Shen, T., Wang, J., Fang, T., & Quan, L. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.259 · Cited by 44
“Since it is intractable to undertake matching directly, we draw inspiration from the scale space theory [21, 20] and propose a novel scale-invariant image matching approach.”
BackgroundXu, Y., Wu, T., Gao, F., Charlton, J. R., & Bennett, K. M. (2020) · Scientific Reports · doi:10.1038/s41598-019-57223-y · Cited by 43
“Recently, the Laplacian of Gaussian (LoG) detector 22,23 , from scale space theory, has attracted attention in blob detection 8,24 .”
BackgroundMulti scale Harris corner detector based on Differential Morphological Decomposition
Gueguen, L., & Pesaresi, M. (2011) · Pattern Recognition Letters · doi:10.1016/j.patrec.2011.07.021 · Cited by 43
“In (Lindeberg, 1998), the Laplacian-of-Gaussian (LoG) is used, as a scale space representation, for selecting the image blob characteristic scales, and the scale normalized Laplacian operator is defined by: LoGðp;rNÞ ¼ r2NðLxxðp;rNÞ þ Lyyðp;rNÞÞ; ð3Þ where Lxx, Lyy are the second image derivatives…”
MethodLocal Scale Selection for Gaussian Based Description Techniques
Chomat, O., de Verdière, V. C., Hall, D., & Crowley, J. L. (2000) · Lecture notes in computer science · doi:10.1007/3-540-45054-8_8 · Cited by 43
Li, H., Soto-Montoya, H., Voisin, M., Valenzuela, L. F., & Prakash, M. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/684423 · Cited by 46
“The second step uses a blob detector based on the Laplacian of Gaussian 205 (LoG) [39, 40] to detect fluorescent spots of different sizes and intensities.”
MethodHötte, K., Koch, M., Hof, L., Tuppi, M., Moreth, T., Verstegen, M. M. A., van der Laan, L. J. W., Stelzer, E. H. K., & Pampaloni, F. (2019) · Scientific Reports · doi:10.1038/s41598-019-53380-2 · Cited by 43
“Marker points for the watershed algorithm were detected by a multiscale Laplacian of Gaussian seed detector with a minimal range of eight and a maximum range of twelve voxels (33, 34).”
MethodPritee, Z. T., Anik, M. H., Alam, S. B., Jim, J. R., Kabir, M. M., & Mridha, M. F. (2024) · Computers & Security · doi:10.1016/j.cose.2024.103747 · Cited by 52
Space-time Facet Model for Human Activity Classification
Samanta, S., & Chanda, B. (2014) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2014.2326734 · Cited by 42
“[64] calculated a Hessian matrix in spatiotemporal domain extending the saliency measure [29] and used the determinant of this Hessian matrix as a measure of strength of interest points at a certain scale.”
MethodCamuera, J., Ramos-Roman, M. J., Jiménez‐Moreno, G., García‐Alix, A., Ilvonen, L., Ruha, L., Gil‐Romera, G., González‐Sampériz, P., & Seppä, H. (2022) · Scientific Reports · doi:10.1038/s41598-022-12047-1 · Cited by 42
Object Recognition Using Coloured Receptive Fields
Hall, D., de Verdière, V. C., & Crowley, J. L. (2000) · Lecture notes in computer science · doi:10.1007/3-540-45054-8_11 · Cited by 44
Image Matching Using Generalized Scale-Space Interest Points
Lindeberg, T. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-38267-3_30 · Cited by 41
Self-citationA new global alignment approach for underwater optical mapping
Elibol, A., García, R., & Gracias, N. (2011) · Ocean Engineering · doi:10.1016/j.oceaneng.2011.05.013 · Cited by 41
“Feature detection is based on either Hessian or Laplacian detectors (the ‘‘Difference of Gaussians’’ of SIFT is an approximation to the Laplacian, and SURF uses an approximation to the Hessian).”
MethodMartínez, F., Romero, E., Dréan, G., Simon, A., Haigron, P., de Crevoisier, R., & Acosta, O. (2014) · Physics in Medicine and Biology · doi:10.1088/0031-9155/59/6/1471 · Cited by 41
“applying a classical multiscale non-maximum suppression strategy, consisting in detecting the maximum gradient magnitude for each particular direction as cited in[44].”
BackgroundMethodInfluentialModeling visual clutter perception using proto-object segmentation
Yu, C.-P., Samaras, D., & Zelinsky, G. J. (2014) · Journal of Vision · doi:10.1167/14.7.4 · Cited by 47
“Orabona, Metta, and Sandini (2007) proposed a model based on proto-objects that are segmented using blob detectors, operators that extract blobs using Difference-of-Gaussian (Collins, 2003) or Laplacian-of-Gaussian (Lindeberg, 1998) filters (Lindeberg, 1998; Collins, 2003), which are combined into a saliency map for t…”
BackgroundLocal Variance-Controlled Forward-and-Backward Diffusion for Image Enhancement and Noise Reduction
Wang, Y., Zhang, L., & Li, P. (2007) · IEEE Transactions on Image Processing · doi:10.1109/tip.2007.899002 · Cited by 41
Robust 3D face recognition based on resolution invariant features
Zhang, G., & Wang, Y. (2011) · Pattern Recognition Letters · doi:10.1016/j.patrec.2011.02.004 · Cited by 41
An algebraic model for fast corner detection
Willis, A., & Sui, Y. (2009) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2009.5459443 · Cited by 52
“Scale invariant versions of corner detectors include [8, 10] and [11] which provide increasingly sophisticated models for corner detection that are affine-invariant and robust to illumination changes.”
BackgroundTime-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 new framework for on-line object tracking based on SURF
Miao, Q., Wang, G., Shi, C., Lin, X., & Ruan, Z. (2011) · Pattern Recognition Letters · doi:10.1016/j.patrec.2011.05.017 · Cited by 40
“Based on Lindeberg (1998), several approaches to scale-invariant interest point detection have been proposed, such as the detector based on Harris-Laplace and Hessian-Laplace by Mikolajczyk and Schmid (2001), Difference of Gaussians (DoG) in SIFT by Lowe (2004), and Hessians approximated in SURF by…”
BackgroundMethodRobust vision-based robot localization using combinations of local feature region detectors
Arnau Ramisa, A., Tapus, A., Aldavert, D., Toledo, R., & de Mántaras, R. L. (2009) · Autonomous Robots · doi:10.1007/s10514-009-9136-9 · Cited by 40
“We decided to use combinations of the following three feature region detectors: MSER (Maximally Stable Extremal Regions) (Matas et al, 2002), Harris-Affine (Lindeberg, 1998), and Hessian-Affine (Mikolajczyk and Schmid, 2004), which have shown to perform better when compared to other region detectors.”
Skurikhin, A. N., Garrity, S. R., McDowell, N. G., & Cai, D. M. (2012) · Remote Sensing Letters · doi:10.1080/2150704x.2012.749361 · Cited by 40
“Our approach is based on scale-space theory (Witkin 1983, Lindeberg 1998) and recent advancements in feature-based image segmentation (Skurikhin 2008, 2010, Loss et al. 2009) and object recognition in computer vision (Linde and Lindeberg 2004, Lowe 2004, Mikolajczyk and Schmid 2004).”
BackgroundMethodReal-time Hand Gesture Recognition from Depth Images Using Convex Shape Decomposition Method
Qin, S., Zhu, X., Yang, Y., & Jiang, Y. (2013) · Journal of Signal Processing Systems · doi:10.1007/s11265-013-0778-7 · Cited by 40
“Since Lindberg [9] published his work on scale-space framework for geometric features detection, scale-space feature detection has been widely applied in object recognition, image processing and registering etc. Bretzner et al. [3] and Fang et al. [10, 11] have employed scale-space feature…”
BackgroundDetection of Fragmented Rectangular Enclosures in Very High Resolution Remote Sensing Images
Zingman, I., Saupe, D., Penatti, O. A. B., & Lambers, K. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2545919 · Cited by 34
Multiscale Segmentation via Bregman Distances and Nonlinear Spectral Analysis
Zeune, L. L., van Dalum, G., Terstappen, L. W. M. M., van Gils, S. A., & Brüne, C. (2017) · SIAM Journal on Imaging Sciences · doi:10.1137/16m1074503 · Cited by 43
“In relation to those, several methods to detect and analyze interesting scales have been proposed; see, for example, [44, 60, 58, 45, 31, 43].”
MethodPapaya Tree Detection with UAV Images Using a GPU-Accelerated Scale-Space Filtering Method
Jiang, H., Chen, S., Li, D., Wang, C., & Yang, J. (2017) · Remote Sensing · doi:10.3390/rs9070721 · Cited by 41
“The scale-space filtering (SSF) analyzes the same image at different observation scales [11].”
BackgroundPHOTOGRAMMETRIC 3D BUILDING RECONSTRUCTION FROM THERMAL IMAGES
Maset, E., Fusiello, A., Crosilla, F., Toldo, R., & Zorzetto, D. (2017) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-iv-2-w3-25-2017 · Cited by 50
“The first step of Samantha is key-points extraction through the detector proposed by (Lindeberg, 1998), where blobs with associated scale levels are identified from scale-space extrema of the scale-normalized Laplacian.”
BackgroundMultiscale Structure Tensor for Improved Feature Extraction and Image Regularization
Prasath, V. B. S., Pelapur, R., Seetharaman, G. S., & Palaniappan, K. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2924799 · Cited by 40
A model-based approach to junction detection using radial energy
Sinzinger, E. D. (2007) · Pattern Recognition · doi:10.1016/j.patcog.2007.06.032 · Cited by 40
A modular multi-camera framework for team sports tracking
Hayet, J.-B., Mathes, T., Czyz, J., Piater, J., Verly, J., & Macq, B. M. M. (2006) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2005.1577318 · Cited by 41
“We want to update this scale without having to use the costly methods commonly used to compute it [7].”
MethodThe Improbability of Harris Interest Points
Loog, M., & Lauze, F. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.53 · Cited by 41
Liu, J., Jung, H., Dubra, A., & Tam, J. (2017) · Investigative Ophthalmology & Visual Science · doi:10.1167/iovs.16-21003 · Cited by 41
Hanek, R., & Beetz, M. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000025799.44214.29 · Cited by 40
“Scale-space theory provides means for automatic scale selection (Lindeberg, 1998).”
An approach for object tracking, categorization, and autopilot guidance for passive homing missiles
Pandey, D., Wairya, S., Sharma, M., Gupta, A., Kakkar, R., & Pandey, B. K. (2022) · Aerospace Systems · doi:10.1007/s42401-022-00150-0 · Cited by 39
“[7, 8] SURF has two major advantages over typical algorithms: it uses the Laplacian of Gaussian to discriminate between background and foreground features, and it uses a 64-dimensional vector rather than the 128-dimensional vector used by regular approaches.”
MethodAdaptive Spot Detection With Optimal Scale Selection in Fluorescence Microscopy Images
Basset, A., Boulanger, J., Salamero, J., Bouthémy, P., & Kervrann, C. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2450996 · Cited by 44
“Since the LoG filter is negative and spots are bright in the input image, we focus on the negative extreme values of H f , which leads us to the concept of (negative) blob as defined in [44].”
Decision-Based Fusion for Pansharpening of Remote Sensing Images
Luo, B., Khan, M. M., Bienvenu, T., Chanussot, J., & Zhang, L. (2012) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2012.2189933 · Cited by 39
“Classical approaches are based on the linear scale space [10], [11].”
BackgroundScaramuzza, D., Siegwart, R., & Martinelli, A. (2009) · The International Journal of Robotics Research · doi:10.1177/0278364908099858 · Cited by 46
Optimization of SIFT algorithm for fast-image feature extraction in line-scanning ophthalmoscope
He, Y., Deng, G., Wang, Y., Wei, L., Yang, J., Li, X., & Zhang, Y. (2017) · Optik · doi:10.1016/j.ijleo.2017.09.075 · Cited by 39
Krig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_2 · Cited by 45
What Do Features Tell about Images?
Nielsen, M., & Lillholm, M. (2001) · Springer eBooks · doi:10.1007/3-540-47778-0_4 · Cited by 39
Invariance of visual operations at the level of receptive fields
Lindeberg, T. (2013) · PLoS ONE · doi:10.1371/journal.pone.0066990 · Cited by 44
Self-citationMasini, N., & Lasaponara, R. (2006) · Journal of Geophysics and Engineering · doi:10.1088/1742-2132/3/3/004 · Cited by 39
Combining interest points and edges for content-based image retrieval
Wang, J., Zha, H., & Cipolla, R. (2005) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2005.1530627 · Cited by 41
“According to [3], local extrema over scales of normalized derivatives indicates the presence of the characteristic local structures.”
BackgroundBottom-Up & Top-down Object Detection using Primal Sketch Features and Graphical Models
Kokkinos, I., Maragos, P. A., & Yuille, A. (2006) · 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.2006.74 · Cited by 39
“Scale invariance can be introduced as in [19], but this sequence of operations seems fragile, since it is susceptible to noise, (self-) occlusions and object deformations.”
BackgroundMethodInfluentialThe representation and matching of categorical shape
Shokoufandeh, A., Bretzner, L., Macrini, D., Demirci, M. F., Jönsson, C., & Dickinson, S. (2006) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2006.05.001 · Cited by 39
“Blob and ridge extraction is performed using automatic scale selection, as described in previous work (see [29,28]).”
MethodYuan, F. (2013) · Digital Signal Processing · doi:10.1016/j.dsp.2013.12.005 · Cited by 38
Metadata
- Authors
- Lindeberg, T.
- Venue
- International Journal of Computer Vision
- Published
- 1998-11
- Volume
- 30
- Issue
- 2
- Pages
- 79-116
- ISSN
- 0920-5691 (ISSN-L)
- 1573-1405
- OpenAlex
- W2109200236
- Cited by
- 2,541
- References
- 61
- Citations by year
- 2026: 36 · 2025: 35 · 2024: 46 · 2023: 38 · 2022: 41 · 2021: 60 · 2020: 83 · 2019: 100 · 2018: 111 · 2017: 119 · 2016: 110 · 2015: 147 · 2014: 170 · 2013: 153 · 2012: 158
- FWCI
- 20.33
- Type
- journal article
- Language
- en
- Open access
- green
- urn.kb.se
- Licence
- other-oa
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- International Journal of Computer Vision (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 and Object Detection Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- scale-space theory, feature detection, local extrema, blob detection, junction detection, edge detection, ridge detection, local frequency estimation
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.