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 701–800 of 1,001
Maximally Stable Local Description for Scale Selection
Dorkó, G., & Schmid, C. (2006) · Lecture notes in computer science · doi:10.1007/11744085_39 · Cited by 27
“We chose two widely used complementary methods, Harris [8] and the Laplacian [15, 16].”
MethodLitjens, G. J. S., Barentsz, J. O., Karssemeijer, N., & Huisman, H. J. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.911061 · Cited by 23
Bioimage Informatics in the context of Drosophila research
Jug, F., Pietzsch, T., Preibisch, S., & Tomančák, P. (2014) · Methods · doi:10.1016/j.ymeth.2014.04.004 · Cited by 23
Local Image Features for Shoeprint Image Retrieval
Su, H., Crookes, D., Bouridane, A., & Gueham, M. (2007) · British Machine Vision Conference (BMVC) · doi:10.5244/c.21.38 · Cited by 23
“Mikolajczyk et al in [6] have proposed a new Harris-Laplace detector by using the benefit from the Harris corner detector [26] (high accuracy of location) and that from LoG [27] (robust scale selection).”
MethodToews, M., & Wells, W. M. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2750978 · Cited by 23
“at which it is observed [22].”
GPU acceleration of the KAZE image feature extraction algorithm
Ramkumar, B., Laber, R., Bojinov, H., & Hegde, R. S. (2019) · Journal of Real-Time Image Processing · doi:10.1007/s11554-019-00861-2 · Cited by 23
“The main idea of scale-space construction is to obtain a separable structures of images from the original image, such that only fine-scale image structures exist in the multiscale representation [18, 26].”
BackgroundMethodLindeberg, T. (2019) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-019-00915-x · Cited by 28
“For example, if we choose to express the first differential operator D1,s1 in a basis in terms of scale-normalized derivatives [36] (here with the multi-index notation ∂ x = ∂x1 1 .”
BackgroundMethodInfluentialSelf-citationPATTERN RECOGNITION WITH LOCAL INVARIANT FEATURES
Schmid, C., Dorkó, G., Lazebnik, S., Mikolajczyk, K., & Ponce, J. (2005) · WORLD SCIENTIFIC eBooks · doi:10.1142/9789812775320_0005 · Cited by 24
Mobile robot localization using panoramic vision and combinations of feature region detectors
Arnau Ramisa, A., Tapus, A., de Mántaras, R. L., & Toledo, R. (2008) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2008.4543262 · Cited by 23
“It first detects Harris corners in the scale-space with automatic scale selection using the approach proposed by Lindeberg in [15], and then estimates an elliptical affine covariant region around the detected Harris corners.”
MethodReciprocal Image Features for Uncalibrated Helmholtz Stereopsis
Zickler, T. E. (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.2006.241 · Cited by 23
“For example, Lindeberg [6] detects regions by computing extrema of the normalized Laplacian of Gaussian in scale-space, and Lowe [7, 8] presents an efficient approximation of this method based on the differenceof Gaussian function.”
MethodSantos, A. F., Zaltsman, A. B., Martin, R. C., Kuzmin, A., Alexandrov, Y., Roquemore, E. P., Jessop, R. A., van Erck, M. G. M., & Verheijen, J. H. (2008) · Assay and Drug Development Technologies · doi:10.1089/adt.2008.146 · Cited by 23
Mosaicing of microscope images based on SURF
Rong, W., Chen, H., Liu, J., Xu, Y., & Haeusler, R. (2009) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2009.5378399 · Cited by 23
Image segmentation using iterative watersheding plus ridge detection
Chen, L., Jiang, M., & Chen, J. (2009) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2009.5413757 · Cited by 23
Brand Identification Using Gaussian Derivative Histograms
Pélisson, F., Hall, D., Riff, O., & Crowley, J. L. (2003) · Lecture notes in computer science · doi:10.1007/3-540-36592-3_47 · Cited by 23
Fitting Parametric Curve Models to Images Using Local Self-adapting Separation Criteria
Hanek, R. (2004) · mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) · Cited by 23
Kjer, H. M., Andersson, M., He, Y., Pacureanu, A. T. J., Daducci, A., Pizzolato, M., Salditt, T., Robisch, A.-L., Eckermann, M., Töpperwien, M., et al. (2025) · eLife · doi:10.7554/elife.94917 · Cited by 24
“Depending on the sample, such a mask can be generated by thresholding either FA - or image intensity values, followed by morphological operations (opening, closing) to close holes and remove small spurious regions.”
Biological Basis and Computer Vision Applications of Image Phase Congruency: A Comprehensive Survey
Tian, Y., Wen, M., Lu, D., Zhong, X., & Wu, Z. (2024) · Biomimetics · doi:10.3390/biomimetics9070422 · Cited by 26
“Multiscale image analysis typically de-composes an image into multiple components, each corresponding to a different scale [73,74].”
BackgroundKim, M., Lee, D., Kim, T., Oh, S., & Cho, H. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104642 · Cited by 23
Hessian-Based Affine Adaptation of Salient Local Image Features
Lakemond, R., Sridharan, S., & Fookes, C. (2011) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-011-0317-8 · Cited by 22
“In [19] it is proposed that some combination of gamma normalised derivatives computed in the vicinity of an image structure will assume a local maximum at the scale corresponding to the structure size.”
BackgroundMethodA Feature-Based Developmental Model of the Infant Brain in Structural MRI
Toews, M., Wells, W. M., & Zöllei, L. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33418-4_26 · Cited by 25
“The model is based on scale-invariant features [14,15], distinctive image patterns that can be robustly extracted in the presence of global image deformations including scale changes, and that can therefore offer an information source complementary to typical growth measures such as volume change.”
BackgroundEfficient Implementation of Canny Edge Detection Filter for ITK Using CUDA
Lourenço, L. H. A., Weingaertner, D., & Todt, E. (2012) · Symposium on Computer Systems (WSCAD-SSC) · doi:10.1109/wscad-ssc.2012.21 · Cited by 22
FEATURE EXTRACTION USING SURF ALGORITHM FOR OBJECT RECOGNITION
Swapnali, B., & Kayastha Vijay, S. (2014) · Cited by 22
FPGA-Based Parallel Implementation of SURF Algorithm
Chen, W., Shuaishuai, D., Chai, Z., He, D., Zhang, W., Zhang, G., Peng, Q., & Luo, W. (2016) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads.2016.0049 · Cited by 22
“Harris [1] proposed a second-moment matrix method that provides rotational invariance but lacks scale invariance.”
A Geometric Model of Multi-scale Orientation Preference Maps via Gabor Functions
Baspinar, E., Citti, G., & Sarti, A. (2018) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-018-0803-3 · Cited by 22
“Lindeberg, in [24], describes a scale selection technique in terms of Gaussian derivatives normalized by scale.”
BackgroundHigh-accuracy calibration of cameras without depth of field and target size limitations
Yan, F., Liu, Z., Pan, X., & Shen, Y. (2020) · Optics Express · doi:10.1364/oe.402826 · Cited by 22
Agarwal, H., & Husain, F. (2021) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2021.102846 · Cited by 22
A KD curvature based corner detector
Chen, S., Meng, H., Zhang, C., & Liu, C. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.01.102 · Cited by 22
Fast and Efficient Evaluation of Building Damage From Very High Resolution Optical Satellite Images
Dubois, D., & Lepage, R. (2014) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2014.2336236 · Cited by 22
Estimates of Leaf Vein Density Are Scale Dependent
Price, C. A., Munro, P. R. T., & Weitz, J. S. (2013) · PLANT PHYSIOLOGY · doi:10.1104/pp.113.224451 · Cited by 22
“The tradeoff between field of view (FOV; i.e. the physical size of the object studied) and the resolution of measurement underlies image analysis in fields ranging from cosmology to biology (Lindeberg, 1998).”
BackgroundScale 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
Increasing the accuracy of feature evaluation benchmarks using differential evolution
Cordes, K., Rosenhahn, B., & Östermann, J. (2011) · IEEE Symposium on Differential Evolution (SDE) · doi:10.1109/sde.2011.5952056 · Cited by 22
“These characteristics are usually assembled to a vector which describes the feature.”
BackgroundGeometrically invariant watermarking using affine covariant regions
Deng, C. D., Gao, X., Tao, D., & Li, X. (2008) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2008.4711779 · Cited by 22
“Lindeberg [8] extended the notion of scale space to affine Gaussian scale-space.”
Feature Learning and Deep Learning Architecture Survey
Krig, S. (2016) · Springer eBooks · doi:10.1007/978-3-319-33762-3_10 · Cited by 25
Diagnosis of breast tissue in mammography images based local feature descriptors
Matos, C., Souza, J. C., Diniz, J., Bráz, G., de Paiva, A. D., de Almeida, J. D. S., da Rocha, S. V., & Silva, A. C. (2018) · Multimedia tools and applications · doi:10.1007/s11042-018-6390-x · Cited by 18
“The SURF detector is based on Hessian matrices [37, 44] and is called Fast-Hessian Detector due to its good computational performance in terms of execution time and accuracy.”
MethodQuantifying the complexity of black-and-white images
Zanette, D. H. (2018) · PLoS ONE · doi:10.1371/journal.pone.0207879 · Cited by 23
“According to this formulation, for an image portraying a pattern with a well defined typical length, the gray-level mean variance V ( S ) attains a maximum at a scale which is directly related to that length [24].”
BackgroundMethodInfluentialIntelligent Video Surveillance
Ma, Y., & Qian, G. (2009) · CRC Press eBooks · doi:10.1201/9781439813300 · Cited by 22
Local appearance space for recognition of navigation landmarks
de Verdière, V. C., & Crowley, J. L. (2000) · Robotics and Autonomous Systems · doi:10.1016/s0921-8890(99)00076-7 · Cited by 22
Improving the selection of feature points for tracking
Živković, Z., & van der Heijden, F. (2004) · Pattern Analysis and Applications · doi:10.1007/s10044-004-0210-9 · Cited by 22
“Another ad-hoc idea would be to select scale for each point as discussed in [13].”
BackgroundNatural image profiles are most likely to be step edges
Griffin, L. D., Lillholm, M., & Nielsen, M. (2003) · Vision Research · doi:10.1016/j.visres.2003.09.025 · Cited by 23
“…& Davis, 1995, Zhou, Friedman & von der Heydt, 2000), such a processing step is common in engineered vision systems (e.g. edge (Canny, 1986, Griffin, Colchester & Robinson, 1992, Marr, 1982) and corner detection (Lindeberg, 1998), surface classification (Koenderink & van Doorn, 1993), etc.).”
Kernel-based Recognition of Human Actions Using Spatiotemporal Salient Points
Oikonomopoulos, A., Patras, I., & Pantić, M. (2006) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2006.114 · Cited by 22
“Lindeberg et al. [13] integrate a scale-space approach for corner detection and search for local extremes across scales.”
BackgroundLearning Covariant Feature DetectorsPreprint
Lenc, K., & Vedaldi, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.01224 · Cited by 22
“Covariant detectors differ by the type of features that they extract: points [11,16,36,6], circles [17,19,23], or ellipses [18,42,2,35,22,24].”
BackgroundDerivative-Based Scale Invariant Image Feature Detector With Error Resilience
Mainali, P., Lafruit, G., Tack, K., Gool, L. V., & Lauwereins, R. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2315959 · Cited by 21
Liu, Z., Jiang, Y., Wang, Y., Du, Y., & Wang, J. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3125055 · Cited by 21
Computer Assistance Image Processing Spores Counting
Xu, P., & Li, J. (2009) · International Asia Conference on Informatics in Control, Automation and Robotics · doi:10.1109/car.2009.10 · Cited by 21
Two-Tier Tissue Decomposition for Histopathological Image Representation and Classification
Gültekin, T., Koyuncu, C., Sökmensüer, C., & Gündüz-Demir, Ç. (2014) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2014.2354373 · Cited by 21
“This metric uses the idea of blob definition, which is frequently employed in different computer vision applications such as salient point localization [15]–[17] and object tracking [18], [19].”
MethodFast, Compact, and Discriminative: Evaluation of Binary Descriptors for Mobile Applications
Madeo, S., & Bober, M. Z. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2615521 · Cited by 23
“For instance, blob detectors consider local extrema of the response of scale-invariant filters, usually designed to be approximations of the Laplacian of Gaussian (LoG) [28], [29], while corner detectors are based on 2D points having two dominant and different edge directions in their local neighborhood [6].”
BackgroundRidge and furrow pattern classification for acral lentiginous melanoma using dermoscopic images
Yang, S., Oh, B. H., Hahm, S., Chung, K. Y., & Lee, B.-U. (2016) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2016.09.019 · Cited by 21
Improving Performances of MSER Features in Matching and Retrieval Tasks
Sluzek, A. S. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-49409-8_63 · Cited by 21
Multi-script text versus non-text classification of regions in scene images
Sriman, B., & Schomaker, L. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.04.007 · Cited by 21
“P ð x Þ ¼ det ð l ð x ; r I ; r D ÞÞ (cid:4) a trace 2 ð l ð x ; r I ; r D ÞÞ ð 3 Þ It then selects appropriate scales, which were extensively studied by Lindeberg [20].”
AutoScaler: Scale-Attention Networks for Visual Correspondence
Wang, S., Luo, L., Zhang, N., & Li, L.-J. (2017) · British Machine Vision Conference (BMVC) · doi:10.5244/c.31.185 · Cited by 22
Spatially-Sensitive Affine-Invariant Image Descriptors
Bronstein, A. M., & Bronstein, M. M. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15552-9_15 · Cited by 21
Shape Analysis for Brain Structures
Ng, B., Toews, M., Durrleman, S., & Shi, Y. (2014) · Lecture notes in computational vision and biomechanics · doi:10.1007/978-3-319-03813-1_1 · Cited by 21
Resolution- Independent Characteristic Scale Dedicated to Satellite Images
Luo, B., Aujol, J., Gousseau, Y., Ladjal, S., & Maître, H. (2007) · IEEE Transactions on Image Processing · doi:10.1109/tip.2007.906004 · Cited by 21
“As discussed by Lindeberg [2], any normalized Gaussian derivative can be considered to achieve scale invariance.”
BackgroundMethodInfluentialExtracting Scale and Illuminant Invariant Regions through Color
Unnikrishnan, R., & Hebert, M. (2006) · British Machine Vision Conference (BMVC) · doi:10.5244/c.20.52 · Cited by 21
“Firstly, by moving from our original vector-valued image to a scalar-valued image we make the available theory [11] and its proven guarantees of scale-invariant behavior directly applicable to our data.”
MethodPerformance Analysis of Oriented Feature Detectors
Ayres, F. J., & Rangayyan, R. M. (2005) · Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI) · doi:10.1109/sibgrapi.2005.38 · Cited by 21
Feature extraction on 3-D TexMesh using scale-space analysis and perceptual evaluation
Cheng, I., & Boulanger, P. (2005) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2005.854234 · Cited by 21
“In the discrete case, e.g., with a real image, summation is used instead of integrals, and the Gaussian weights are normalized so that the sum of all the weights equals 1.”
BackgroundIllumination invariant feature point matching for high-resolution planetary remote sensing images
Wu, B., Zeng, H., & Hu, H. (2018) · Planetary and Space Science · doi:10.1016/j.pss.2018.01.007 · Cited by 20
“To remove the prerequisite of known image geometry for robust image matching and thereby overcome the problems of scale and rotation deformation, theories of the scale space of images (Lindeberg, 1993, 1998) and the dominant orientation of feature points (Lowe, 2004) have been developed.”
BackgroundRobust Keypoint Detection Using Higher-Order Scale Space Derivatives: Application to Image Retrieval
Park, U., Park, J.-S., & Jain, A. K. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2321755 · Cited by 20
A New Global Alignment Method for Feature Based Image Mosaicing
Elibol, A., García, R., Delaunoy, O., & Gracias, N. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-89646-3_25 · Cited by 20
“In both methods mentioned feature detection is based on Hessian or Laplacian detectors (the “Difference of Gaussians” of SIFT is an approximation to the Laplacian, and SURF uses an approximation to the Hessian).”
MethodRobust image copy detection using multi-resolution histogram
Xu, Z., Ling, H., Zou, F., Lu, Z., & Li, P. (2010) · Multimedia Information Retrieval · doi:10.1145/1743384.1743410 · Cited by 20
A novel image copy detection scheme based on the local multi-resolution histogram descriptor
Xu, Z., Ling, H., Zou, F., Lu, Z., & Li, P. (2010) · Multimedia Tools and Applications · doi:10.1007/s11042-009-0438-x · Cited by 20
“Based on the knowledge of scale invariant space theory [14], it is inaccurate to construct a local region with geometric resilience using only a single-resolution image.”
BackgroundOn the Convergence of Planar Curves Under Smoothing
Zhong, B., & Ma, K. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2046807 · Cited by 20
Automated Detection of Adenoviral Conjunctivitis Disease from Facial Images using Machine Learning
Günay, M., Göçeri, E., & Danışman, T. (2015) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2015.232 · Cited by 20
“Several researchers ([21], [22], [23], [24]) have introduced techniques for vessel or ridge extraction using the eigen decomposition of the Hessian matrix computed at each pixel.”
MethodRani, R., Kumar, R., & Singh, A. P. (2017) · Pattern Analysis and Applications · doi:10.1007/s10044-017-0641-8 · Cited by 21
“To accommodate for the scale invariance, Lindeberg [31] proposed a circular symmetric operator which finds difference in all directions and where blobs are used as features.”
MethodStable Clustering for VANETs on Highways
Cheng, X., Huang, B., & Cheng, W. (2018) · IEEE/ACM Symposium on Edge Computing (SEC) · doi:10.1109/sec.2018.00053 · Cited by 22
“The blob detection algorithm [9] is used to detect the centers of regions on the map where the gray pixel value is greater.”
MethodAutomated detection of block falls in the north polar region of Mars
Fanara, L., Gwinner, K., Hauber, E., & Oberst, J. (2019) · Planetary and Space Science · doi:10.1016/j.pss.2019.104733 · Cited by 20
Novelty Detection as an Intrinsic Motivation for Cumulative Learning Robots
Nehmzow, U., Gatsoulis, Y., Kerr, E., Condell, J. V., Siddique, N. H., & McGinnity, T. M. (2012) · Springer eBooks · doi:10.1007/978-3-642-32375-1_8 · Cited by 25
“In order to resolve these scaling issues, Nehmzow and Neto (2006) and Neto and Nehmzow (2007b) suggested a technique, based on the work of Lindeberg (1998), which is able to select the size of the image patches automatically.”
MethodImage feature detection on content-based meshes
Coleman, S., Scotney, B. W., & Herron, M. G. (2003) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2002.1038157 · Cited by 20
Scale Selection for Compact Scale-Space Representation of Vector-Valued Images
Vanhamel, I., Mihai, C., Hichem Sahli, B., Katartzis, A., & Pratikakis, I. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-008-0154-4 · Cited by 20
“in image segmentation, where the scale-space framework is used to include scale in the corresponding feature detectors (Lindeberg 1998), or directly for segmentation (Pratikakis 1998; Mukhopadhyay and Chanda 2003; Vanhamel et al.”
MethodInfluentialAutomatic system for operational traffic monitoring using very-high-resolution satellite imagery
Larsen, S. Ø., Salberg, A.-B., & Eikvil, L. (2013) · International Journal of Remote Sensing · doi:10.1080/01431161.2013.782708 · Cited by 20
“Jin and Davis (2007) implemented a circular blob detector following the approach of Lindeberg (1998) as a baseline algorithm to be compared with their MSNN approach (mentioned earlier).”
MethodInfluentialXie, Y., Xing, L., Gu, J., & Liu, W. (2013) · Physics in Medicine and Biology · doi:10.1088/0031-9155/58/11/3615 · Cited by 20
Protecting IP Multimedia Subsystem (IMS) Service Delivery Platform from Time Independent Attacks
Sher, M., & Magedanz, T. (2007) · International Conference on Information Assurance and Security (IAS) · doi:10.1109/ias.2007.78 · Cited by 20
“[27] T.”
Background3D Line Drawing for Archaeological Illustration
Luo, T., Li, R., & Zha, H. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-010-0394-y · Cited by 20
“In [13], analogous to the automatic scale selection method proposed in [9], the scale is determined where the normalized feature response is maximized across a set of discrete scales.”
Mid-level Image Representation for Fruit Fly Identification (Diptera: Tephritidae)
Leonardo, M. M., Avila, S., Zucchi, R. A., & Faria, F. A. (2017) · IEEE International Conference on eScience · doi:10.1109/escience.2017.33 · Cited by 20
“Therefore, in this experiment, we have compared five different feature detectors, FAST [27], ORB [28], DoG (SIFT detector) [18], STAR [26], and FastHessian (SURF detector) [50].”
Methodα-shapes for local feature detection
Varytimidis, C., Rapantzikos, K. E., Avrithis, Y., & Kollias, S. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.08.016 · Cited by 20
“In his inspiring work, Lindeberg et al. [15] studied scale-invariant detectors and established the theoretical foundations for making them af fi ne-invariant [16].”
Tracking talking faces with shape and appearance models
Odisio, M., Bailly, G., & Elisei, F. (2004) · Speech Communication · doi:10.1016/j.specom.2004.10.008 · Cited by 20
Local Feature Detectors, Descriptors, and Image Representations: A SurveyPreprint
Uchida, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.08368 · Cited by 20
“In [65], a blob detector that searches for scale space extrema of a scale-normalized Laplacian-of-Gaussian (LoG) σ(2)∇(2)L, where”
BackgroundExploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges
Jansson, Y., & Lindeberg, T. (2020) · DiVA (Digitala Vetenskapliga Arkivet) · Cited by 20
Self-citationCorrespondence Generation and Matching of 3D Shape Subparts
Novotni, M., & Degener, P. (2005) · Cited by 20
Spatially-Variant Morpho-Hessian Filter: Efficient Implementation and Application
Tankyevych, O., Talbot, H., Dokládal, P., & Passat, N. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03613-2_13 · Cited by 19
Bilateral symmetry detection based on scale invariant structure feature
Atadjanov, I. R., & Lee, S. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351444 · Cited by 19
Feature detection and matching in images with radial distortion
Lourenço, M., Barreto, J. P., & Malti, A. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509282 · Cited by 19
“Moreover the computational efficiency of the convolution can be largely improved by taking advantage of the decoupling properties in X and Y of the gaussian [9].”
BackgroundMethodLabscale fluidized bed granulator instrumented with non-invasive process monitoring devices
Leskinen, J. T. T., Okkonen, M.-A. H., Toiviainen, M., Poutiainen, S., Tenhunen, M., Teppola, P., Lappalainen, R., Ketolainen, J., & Järvinen, K. (2010) · Chemical Engineering Journal · doi:10.1016/j.cej.2010.08.064 · Cited by 19
3D face recognition by SURF operator based on depth image
Yunqi, L., Haibin, L., & Xutuan, J. (2010) · IEEE International Conference on Computer Science and Information Technology · doi:10.1109/iccsit.2010.5563632 · Cited by 19
Shen, I., & Cheng, W.-H. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2405350 · Cited by 20
“Based on the above observation, an edge-aware multi-scale representation is instead used to replace the traditional Gaussian pyramid in our work [40], [5].”
MethodIntegrated Clustering and Feature Selection Scheme for Text Documents.
Thangamani, & Thangaraj, P. (2010) · Journal of Computer Science · doi:10.3844/jcssp.2010.536.541 · Cited by 19
“Ontology, comprising the logical component of the knowledge base, defines rules that formally describe how the field of interest looks like (Lindeberg, 2004).”
BackgroundSegmentation of Breast Ultrasound Images Using Neural Networks
Othman, A. A., & Tizhoosh, H. R. (2011) · IFIP International Federation for Information Processing/IFIP · doi:10.1007/978-3-642-23957-1_30 · Cited by 19
“Lindeberg [15] proposes a systematic methodology for dealing with the problem of how to select appropriate local scales for further analysis.”
Lessard, S., Kauffmann, C., Pfister, M., Cloutier, G., Thérasse, É., de Guise, J. A., & Soulez, G. (2015) · Medical Engineering & Physics · doi:10.1016/j.medengphy.2015.07.007 · Cited by 19
Optimal-flow minimum-cost correspondence assignment in particle flow tracking
Matov, A., Edvall, M. M., Yang, G., & Danuser, G. M. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.01.001 · Cited by 19
“Speckle detection To identify speckles in each frame of the time-lapse sequence we used a three-step detection approach [33] based on scale-space theory [34].”
MethodOptimal edge filters explain human blur detection
McIlhagga, W., & May, K. A. (2012) · Journal of Vision · doi:10.1167/12.10.9 · Cited by 19
“The N1 and N3 þ models (Georgeson et al., 2007), based upon the theoretical work of Lindeberg (1994, 1998), also assume that the image is analyzed by a bank of filters of different scales.”
InfluentialFace recognition system using PCA-ANN technique with feature fusion method
Toufiq, R., & Islam, M. R. (2014) · International Conference on Electrical Engineering and Information Communication Technology · doi:10.1109/iceeict.2014.6919110 · Cited by 19
A HYBRID FILTERING APPROACH TO RETINAL VESSEL SEGMENTATION
Wu, C., Gady Agam, B., & Stanchev, P. L. (2007) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2007.356924 · Cited by 19
“By convolving with Gaussian kernels of various sizes, the normalized second order derivatives [12] can indicate the scale and orientation of vessels.”
MethodMedical image blob detection with feature stability and KNN classification
Inthajak, K., Duanggate, C., Uyyanonvara, B., Makhanov, S. S., & Barman, S. A. (2011) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse.2011.5930107 · Cited by 19
Segmentation and wake removal of seafaring vessels in optical satellite images
Bouma, H., Dekker, R. J., Schoemaker, R. M., & Mohamoud, A. A. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2029791 · Cited by 19
“The segmentation of small vessels is based on hysteresis thresholding where the boundaries of the watershed are removed in the segmentation of the lower threshold and where the segmentation of the high response of the Laplacian is used as seed.”
MethodInfluentialSong, J., Xiao, L., & Lian, Z. (2015) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2015.2504422 · Cited by 19
Dense Scale Selection Over Space, Time, and Space-Time
Lindeberg, T. (2018) · SIAM Journal on Imaging Sciences · doi:10.1137/17m114892x · Cited by 22
“Would it at all be possible to generate hypotheses about interest scale levels before recognizing the objects we are interested in or defining the specific purpose for which the scale estimates are to be used? Research of Lindeberg [33, 35, 34], as well as follow-up work by Bretzner et al.”
BackgroundMethodInfluentialSelf-citationLi, O., & Shui, P. (2020) · Signal Processing · doi:10.1016/j.sigpro.2020.107495 · Cited by 19
On determining a signature for skeletal maturity
da Silva, A. M. M., Olabarriaga, S. D., Dietrich, C. A., & Schmitz, C. (2002) · Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI) · doi:10.1109/sibgrapi.2001.963062 · Cited by 19
An automatic system forin vitrocell migration studies
Degerman, J., Thorlin, T., Faijerson, J., ALTHOFF, K., Eriksson, P. S., PUT, R. V. D., & Gustavsson, T. (2009) · Journal of Microscopy · doi:10.1111/j.1365-2818.2008.03108.x · Cited by 23
“Inspired by Lindeberg (1998) and scale-space theory we used normalized Gaussian derivatives and adaptive scale selection.”
MethodAccuracy in Prediction of Catheter Rotation in IVUS With Feature-Based Optical Flow—A Phantom Study
Danilouchkine, M. G., Mastik, F., & van der Steen, A. F. W. (2008) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2007.905864 · Cited by 19
“” The theoretical advantages of the scale–space lie beyond the scope of this paper, and the interested reader is referred to [16] and [17].”
Background
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.