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 101–200 of 1,001
Image 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
“In Lindeberg [93,95,100,101] a general framework for automatic scale selection was proposed based on the idea of detecting local extrema over scale of γ -normalized derivatives according to (5).”
BackgroundMethodResultInfluentialSelf-citationA Real-Time Hand Gesture Recognition Method
Fang, Y., Wang, K., Cheng, J., & Lu, H. (2007) · Multimedia and Expo, 2007 IEEE International Conference on · doi:10.1109/icme.2007.4284820 · Cited by 213
“Ellipse parameters such as orientation and axis length are defined by a windowed second moment matrix in (3) as described in [15].”
BackgroundInfluentialControlled double-slit electron diffraction
Bach, R., Pope, D. T., Liou, S.-H., & Batelaan, H. (2013) · New Journal of Physics · doi:10.1088/1367-2630/15/3/033018 · Cited by 206
Ma, C., Luo, G., & Wang, K. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2805821 · Cited by 200
“Based on the multiscale theory [24], the class of each voxel is predicted by taking into account both local and contextual information that is captured from different scales of 3D neighboring regions”
BackgroundWink, O., Niessen, W. J., & Viergever, M. A. (2004) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2003.819920 · Cited by 214
“For a comparison of the response at the different scales, the image L(x) is convolved with normalized second order Gaussian derivatives [6]”
MethodWeakly Supervised Scale-Invariant Learning of Models for Visual Recognition
Fergus, R., Perona, P., & Zisserman, A. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-006-8707-x · Cited by 197
“The saliency of each of these candidates is measured by H (with appropriate normalization for scale (Kadir and Brady, 2001; Lindeberg, 1998)).”
BackgroundMethodInfluentialSymmetrical SURF and Its Applications to Vehicle Detection and Vehicle Make and Model Recognition
Hsieh, J.-W., Chen, L.-C., & Chen, D.-Y. (2014) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2013.2294646 · Cited by 200
“D scene reconstruction.”
Local Descriptors for Spatio-temporal Recognition
Laptev, I., & Lindeberg, T. (2006) · Lecture Notes in Computer Science · doi:10.1007/11676959_8 · Cited by 192
“Due to the scale normalization in combination with the scale selection procedure, the N -jets will be scale invariant over both space and time [14, 11].”
BackgroundMethodInfluentialSelf-citationEnhanced Patterns of Oriented Edge Magnitudes for Face Recognition and Image Matching
Vu, N.-S., & Caplier, A. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2166974 · Cited by 194
A maximum entropy framework for part-based texture and object recognition
Lazebnik, S., Schmid, C., & Ponce, J. (2005) · Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 · doi:10.1109/iccv.2005.10 · Cited by 190
“scale-invariant Laplacian blob detector [12].”
BFSIFT: A Novel Method to Find Feature Matches for SAR Image Registration
Wang, S., You, H., & Fu, K. (2012) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2011.2177437 · Cited by 192
“Gaussian kernel is the only linear kernel to build the scale space [13], and BF uses two Gaussian kernels which can be related to the PM equation.”
BackgroundInteresting Interest Points: A Comparative Study of Interest Point Performance on a Unique Data Set
Aanæs, H., Dahl, A. L., & Steenstrup Pedersen, K. (2012) · International Journal of Computer Vision · doi:10.1007/s11263-011-0473-8 · Cited by 183
“The Hessian detector tend to find blobs and ridges and was originally proposed by Lindeberg (1998b, 1998a).”
BackgroundMethodSmall Target Detection Utilizing Robust Methods of the Human Visual System for IRST
Kim, S., Yang, Y., Lee, J., & Park, Y. (2009) · Journal of Infrared, Millimeter, and Terahertz Waves · doi:10.1007/s10762-009-9518-2 · Cited by 189
“an image as a set of images with different resolutions [16].”
BackgroundMethodA multi-scale convolutional neural network for phenotyping high-content cellular images
Godinez, W. J., Hossain, I., Lazic, S. E., Davies, J. W., & Zhang, X. (2017) · Bioinformatics · doi:10.1093/bioinformatics/btx069 · Cited by 183
“The values are selected based on a geometric series that covers an exponential range of scales (Lindeberg, 1998).”
Background$n$-SIFT: $n$-Dimensional Scale Invariant Feature Transform
Cheung, W., & Hamarneh, G. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2024578 · Cited by 179
“The use of doG in the -SIFT approach evokes similar work in blob detection, such as the MSER blob detector [11] and work by Lindeberg [12], [13].”
MethodQuaternion Zernike moments and their invariants for color image analysis and object recognition
Chen, B., Shu, H., Zhang, H., Chen, G., Toumoulin, C., Dillenseger, J., & Luo, L. (2011) · Signal Processing · doi:10.1016/j.sigpro.2011.07.018 · Cited by 185
“The scale factor between two images is obtained with the automatic scale selection [39].”
Toward large-area mosaicing for underwater scientific applications
Pizarro, O., & Singh, H. (2003) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2003.819154 · Cited by 182
“The characteristic scale of a feature is considered to be the scale at which the scale-normalized Laplacian is maximum [ 44 ].”
BackgroundScale Invariant Feature Transform on the Sphere: Theory and Applications
Cruz-Mota, J., Bogdanova, I., Paquier, B., Bierlaire, M., & Thiran, J.-P. (2012) · International Journal of Computer Vision · doi:10.1007/s11263-011-0505-4 · Cited by 175
“This is based on the work of Lindeberg (1998), and the convolution of an image with ψ(x,y,σ) can be computed as the difference of consecutive images in the scale-space representation of the image, choosing properly the value of k .”
MethodKeyframe-based monocular SLAM: design, survey, and future directions
Younes, G., Asmar, D., Shammas, E., & Zelek, J. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.09.010 · Cited by 191
“…detector (Beaudet, 1978), Harris detector (Harris and Stephens, 1988), Shi-Tomasi corners (Shi and Tomasi, 1994), Laplacian of Gaussian detector (Lindeberg, 1998), MSER (Matas et al, 2002), Difference of Gaussian (Lowe, 2004) and the accelerated segment test family of detectors (FAST, AGAST,…”
BackgroundQuanz, S. P., Amara, A., Meyer, M. R., Girard, J. H., Kenworthy, M. A., & Kasper, M. (2015) · The Astrophysical Journal · doi:10.1088/0004-637x/807/1/64 · Cited by 170
“For further discussion of image feature detection using Hessian matrix methods and others we refer the reader to, e.g., Lindeberg (1998) and Bay et al. (2008).”
MethodA Probabilistic Framework to Detect Buildings in Aerial and Satellite Images
Sirmacek, B., & Unsalan, C. (2011) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2010.2053713 · Cited by 176
“Different from our previous study, if a building is in construction, then we do not expect our method to detect it here.”
MethodHigh-level event recognition in unconstrained videos
Jiang, Y.-G., Bhattacharya, S., Chang, S.-F., & Shah, M. (2013) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-012-0024-2 · Cited by 172
“detectors include Harris–Laplace [72], Hessian [88], maximally stable extremal regions (MSERs) [85], etc.”
BackgroundInfluentialContextual weighting for vocabulary tree based image retrieval
Wang, X., Yang, M., Cour, T., Zhu, S., Yu, K., & Han, T. X. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126244 · Cited by 173
“In recent years, retrieval of visually similar images based on local invariant features [10, 11] and the BoW representation [16] has been significantly scaled up by the use of large hierarchical vocabulary trees [12].”
BackgroundImage watermarking based on invariant regions of scale-space representation
Seo, J. S., & Yoo, C. D. (2006) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2006.870581 · Cited by 169
“A well-known property of the scale-space representation is that the amplitude of spatial derivatives in general decreases with scale [24], i.”
BackgroundMethodInfluentialSIFT and SURF Performance Evaluation against Various Image Deformations on Benchmark Dataset
Khan, N. Y., McCane, B., & Wyvill, G. (2011) · 2011 International Conference on Digital Image Computing: Techniques and Applications · doi:10.1109/dicta.2011.90 · Cited by 165
An Image-Based Approach to Video Copy Detection With Spatio-Temporal Post-Filtering
Douze, M., Jegou, H., & Schmid, C. (2010) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2010.2046265 · Cited by 165
“This region detector is invariant to several image transformations: • Scale change: The Hessian interest point detector in combination with automatic scale selection [20] is invariant to scale changes.”
BackgroundSize-based Transfer Functions: A New Volume Exploration Technique
Correa, C., & Ma, K.-L. (2008) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2008.162 · Cited by 168
“Lindeberg noted that feature detectors can be obtained by looking at the behavior of the derivatives of the scale space along the scale dimension [16].”
BackgroundEdge and corner detection by photometric quasi-invariants
van de Weijer, J., Gevers, T., & Geusebroek, J.-M. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.75 · Cited by 161
“Features based on derivatives of photometric invariants, which we will call full invariants, provide the desired robustness.”
BackgroundA sparse texture representation using affine-invariant regions
Lazebnik, S., Schmid, C., & Ponce, J. (2003) · 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings. · doi:10.1109/cvpr.2003.1211486 · Cited by 154
“Lindeberg [6] has extended this detector in the framework of automatic scale selection, where a “blob” is defined by a maximum of a normalized Laplacian measure in scale space.”
BackgroundLingua, A. M., Marenchino, D., & Nex, F. (2009) · Sensors · doi:10.3390/s90503745 · Cited by 157
“Lindeberg T. Feature detection with automatic scale selection.”
MethodInfluentialCAVIAR Context Aware Vision using Image-based Active Recognition
Crowley, J. L., Reignier, P., & Pesnel, S. (2005) · Cited by 157
Constructing Category Hierarchies for Visual Recognition
Marszałek, M., & Schmid, C. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88693-8_35 · Cited by 155
“Developments in image representation include research on interest point detectors [2, 3], SIFT features [4] and bag-of-features [5].”
Local velocity-adapted motion events for spatio-temporal recognition
Laptev, I., Caputo, B., Schüldt, C., & Lindeberg, T. (2007) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2006.11.023 · Cited by 183
“Interest points and their image neighborhoods provide part-based representations of images with possibility to invariance to photometric transformations as well as to similarity and affine transformations [35,32,36,41].”
BackgroundMethodSelf-citationSchilham, A. M. R., van Ginneken, B., & Loog, M. (2005) · Medical Image Analysis · doi:10.1016/j.media.2005.09.003 · Cited by 167
“In the CAD algorithm Lindeberg s multi-scale detection scheme (Lindeberg, 1998) is employed to deal with this range of sizes.”
MethodSpatial Weighting for Bag-of-Features
Marszaek, M., & Schmid, C. (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.2006.288 · Cited by 168
“We use two complementary local region detectors to extract salient image structures: the Harris-Laplace detector [17] responding to corner-like regions and the Laplacian detector [14] extracting blob-like regions.”
Neural edge enhancer for supervised edge enhancement from noisy images
Suzuki, K., Horiba, I., & Sugie, N. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1251151 · Cited by 152
A detection and recognition system of pointer meters in substations based on computer vision
Liu, Y., Liu, J., & Ke, Y. (2019) · Measurement · doi:10.1016/j.measurement.2019.107333 · Cited by 151
Applicability of the SIFT operator to geometric SAR image registration
Schwind, P., Suri, S., Reinartz, P. H., & Siebert, A. (2010) · International Journal of Remote Sensing · doi:10.1080/01431160902927622 · Cited by 151
“The scale at which the feature gets detected in the DoG pyramid is termed the feature's characteristic scale (CS) (Lindeberg 1998 )and it determines the region size that is used for SIFT descriptor calculations.”
MethodRivaMap: An automated river analysis and mapping engine
Isikdogan, F., Bovik, A., & Passalacqua, P. (2017) · Remote Sensing of Environment · doi:10.1016/j.rse.2017.03.044 · Cited by 149
“However, the singularity index response is expected to decrease with increasing scale, since the amplitudes of spatial derivatives generally decrease as the scale increases (Lindeberg, 1998).”
BackgroundMethodZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
Pang, Y., Zhao, X., Xiang, T.-Z., Zhang, L., & Lu, H. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3417329 · Cited by 184
“First , for accurate object location, we employ scale space theory [17], [18], [19] to imitate zooming in and out strategy.”
MethodScale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search
Leibe, B., & Schiele, B. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-28649-3_18 · Cited by 171
“In recent years, a range of scale-invariant interest point detectors have become available which can be used for this purpose [13–15, 10].”
BackgroundObject Recognition as Many-to-Many Feature Matching
Demirci, M. F., Shokoufandeh, A., Keselman, Y., Bretzner, L., & Dickinson, S. (2006) · International Journal of Computer Vision · doi:10.1007/s11263-006-6993-y · Cited by 146
“respectively, ([23, 22]).”
Pellegrino, F. A., Vanzella, W., & Torre, V. (2004) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2004.824147 · Cited by 146
Robust place recognition for 3D range data based on point features
Steder, B., Grisetti, G., & Burgard, W. (2010) · 2010 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2010.5509401 · Cited by 143
“In the following we will explain the individual steps in more detail.”
BackgroundAn algorithm for detecting brain tumors in MRI images
Badran, E. F., Mahmoud, E. G., & Hamdy, N. (2010) · International Conference on Computer Engineering & Systems (ICCES) · doi:10.1109/icces.2010.5674887 · Cited by 144
“One of the features extraction methods is LOG-Lindeberg algorithm [7] which follows these steps: • Read the image.”
MethodImgLib2—generic image processing in Java
Pietzsch, T., Preibisch, S., Tomančák, P., & Saalfeld, S. (2012) · Bioinformatics · doi:10.1093/bioinformatics/bts543 · Cited by 142
“…edge detection (Devernay, 1995), component trees (Niste´r and Stewe´nius, 2008) and automatically detected interest-points (e.g. DoG and MSER; Lindeberg, 1998; Matas et al. , 2002) are important tools for image segmentation, image registration and tracking; k -d trees enable fast n…”
BackgroundVessel-guided airway tree segmentation: A voxel classification approach
Lo, P., Sporring, J., Ashraf, H., Pedersen, J. J. H., & de Bruijne, M. (2010) · Medical Image Analysis · doi:10.1016/j.media.2010.03.004 · Cited by 154
“The scale for calculating the Hessian matrix was selected for each voxel independently using the scale normalized (Lindeberg, 1998) Frobenius norm of the Hessian matrix:”
MethodLinear Structures in Mammographic Images: Detection and Classification
Reyer Zwiggelaar, A., Astley, S., Boggis, C. R. M., & Taylor, C. (2004) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2004.828675 · Cited by 143
Matching images with different resolutions
Dufournaud, Y., Schmid, C., & Horaud, R. (2002) · Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662) · doi:10.1109/cvpr.2000.855876 · Cited by 141
Scale Selection Properties of Generalized Scale-Space Interest Point Detectors
Lindeberg, T. (2012) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-012-0378-3 · Cited by 142
“Specifically, it was shown in [35] that local extrema over scale of homogeneous polynomial differential invariants D γ − norm L expressed in terms of γ -normalized Gaussian derivatives are transformed in a scale-covariant way: If some scale-normalized differential invariant D γ − norm L assumes a…”
BackgroundMethodInfluentialSelf-citationFlip-Invariant SIFT for Copy and Object Detection
Zhao, W.-L., & Ngo, C.-W. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2226043 · Cited by 138
Involvement of Machine Learning for Breast Cancer Image Classification: A Survey
Nahid, A.-A., & Kong, Y. (2017) · Computational and Mathematical Methods in Medicine · doi:10.1155/2017/3781951 · Cited by 157
“Detector Single scale detector (1)Moravec’s Detector (MD) [9], (2)Harris Detector (HD) [10], (3) Smallest Univalue Segment Assimilating Nucleus (SUSAN) [11], (4) Features from Accelerated Segment Test (FAST) [12, 13], (5)Hessian Blob Detector (HBD) [14, 15].”
BackgroundZhang, J., Marszalek, M., Lazebnik, S., & Schmid, C. (2006) · 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06) · doi:10.1109/cvprw.2006.121 · Cited by 136
Selective spatio-temporal interest points
Chakraborty, B., Holte, M. B., Moeslund, T. B., & Gonzàlez, J. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.09.010 · Cited by 150
“Instead of applying local information for STIP detection Wong and Cipolla [51] propose a global information-based approach.”
MethodWavelet Domain Multifractal Analysis for Static and Dynamic Texture Classification
Ji, H., Yang, X., Ling, H., & Xu, Y. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2214040 · Cited by 139
“The scale-invariant blob detector used in this paper is the affine-adapted version [53] of the scale-invariant Laplacian-of-Gaussian (LOG) region detector [54].”
MethodPerformance evaluation of corner detectors using consistency and accuracy measures
Mokhtarian, F., & Mohanna, F. (2005) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2005.11.001 · Cited by 137
“Note that the issue of automatic selection of detection scales has also been addressed in [32] and [33].”
BackgroundFingerprint enhancement by shape adaptation of scale-space operators with automatic scale selection
Lindeberg, T., & Almansa, A. (2000) · IEEE Transactions on Image Processing · doi:10.1109/83.887971 · Cited by 119
Self-citationHardie, R. C., Rogers, S. K., Wilson, T., & Rogers, A. (2007) · Medical Image Analysis · doi:10.1016/j.media.2007.10.004 · Cited by 144
“[3, 6, 29–31], the average radial gradient (ARG) detector [4], convergence index (CI) filter based methods [14–16], and filtered image differencing [12, 13].”
Trainable COSFIRE Filters for Keypoint Detection and Pattern Recognition
Azzopardi, G., & Azzopardi, N. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.106 · Cited by 146
“Later, scaleinvariant approaches were proposed by selecting keypoints as the maxima points in a Laplacian [3] or Difference-ofGaussian (DoG) [4] scale space.”
MethodThe Autonomous Blimp Project of LAAS-CNRS: Achievements in Flight Control and Terrain Mapping
Hygounenc, E., Jung, I.-K., Souères, P., & Lacroix, S. (2004) · The International Journal of Robotics Research · doi:10.1177/0278364904042200 · Cited by 135
“In such cases, scale-invariant feature detection algorithms have recently been proposed (Lindeberg 1998; Lowe 1999; Mikolajczyk and Schmid 2001).”
BackgroundDeformation invariant image matching
Ling, H., & Jacobs, D. W. (2005) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2005.67 · Cited by 146
“For example, Lindeberg [11] proposed extracting scale invariant regions via the extremum of the scale space.”
MethodLearning Covariant Feature Detectors
Lenc, K., & Vedaldi, A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-49409-8_11 · Cited by 152
“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].”
BackgroundA review on MR vascular image processing: skeleton versus nonskeleton approaches: part II
Suri, J. S., Liu, K., Reden, L., & Laxminarayan, S. (2002) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2002.804136 · Cited by 143
The Discovery of Two Extremely Low Luminosity Milky Way Globular Clusters
Koposov, S., de Jong, J. T. A., Belokurov, V., Rix, H. ‐., Zucker, D. B., Evans, N. W., Gilmore, G., Irwin, M. J., & Bell, E. F. (2007) · The Astrophysical Journal · doi:10.1086/521422 · Cited by 132
A Unified Approach of Multi-scale Deep and Hand-Crafted Features for Defocus Estimation
Park, J., Tai, Y., Cho, D., & Kweon, I. S. (2017) · 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.2017.295 · Cited by 145
“Although there have been many works related to scale-space theories [20,23,24], there is still some ambiguity with regard to the relationship between the patch scale and the hand-crafted features, as they utilize global information in an image patch.”
BackgroundLung nodule classification using deep feature fusion in chest radiography
Wang, C., Elazab, A., Wu, J., & Hu, Q. (2016) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2016.11.004 · Cited by 146
The Cosmic Ballet: spin and shape alignments of haloes in the cosmic web
Veena, P. G., Cautun, M., van de Weygaert, R., Tempel, E., Jones, B. J. T., Rieder, S., & Frenk, C. S. (2018) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/sty2270 · Cited by 151
“The scale-space representation of a data set consists of a sequence of copies of the data at different resolutions (Florack et al. 1992; Lindeberg 1998).”
A local phase based invariant feature for remote sensing image matching
Ye, Y., Shan, J., Hao, S., Bruzzone, L., & Qin, Y. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2018.06.010 · Cited by 131
A coarse-to-fine strategy for multiclass shape detection
Amit, Y., Geman, D., & Fan, X. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.111 · Cited by 141
Novatnack, J., & Nishino, K. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88690-7_33 · Cited by 137
“In order to determine the intrinsic scale of each corner, we then search for local maxima of the corner detector responses across the scales as was originally proposed for 2D scale-space [14].”
MethodControlled Double-Slit Electron DiffractionPreprint
Bach, R., Pope, D. T., Liou, S. H., & Batelaan, H. (2012) · Cited by 128
The Gaussian Derivative model for spatial-temporal vision: I. Cortical model
Young, R. A., Lesperance, R. M., & Meyer, W. W. (2001) · Spatial Vision · doi:10.1163/156856801753253582 · Cited by 149
Grauman, K., & Leibe, B. (2011) · Synthesis Lectures on Artificial Intelligence and Machine Learning · doi:10.2200/s00332ed1v01y201103aim011 · Cited by 126
“It can be shown that the only operator that fulfills all necessary conditions for this purpose is the scale-normalized Gaussian kernel G(x, σ) and its derivatives (Lindeberg 1994, 1998).”
BackgroundMethodInfluentialLindeberg, T. (2010) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-010-0242-2 · Cited by 126
“QL = L(2)ξ + C L(2)ξξ = sL(2)x + C s(2)L(2)xx, (147) where ∂ξ = √s ∂x denotes normalized derivatives with respect to normalized coordinates ξ = x/√s [44] and where the constant C can be determined either to minimize the amount of ripples in the operator response (C = 2/3 ≈ 0.”
BackgroundSelf-citationRobust point matching method for multimodal retinal image registration
Wang, G., Wang, Z., Chen, Y., & Zhao, W. (2015) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2015.03.004 · Cited by 124
Accurate Junction Detection and Characterization in Natural Images
Xia, G.-S., Delon, J., & Gousseau, Y. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0640-1 · Cited by 131
“To the best of our knowledge, the only approaches which permit to obtain a similar coherence between scale detection and resolution are those which rely on linear scalespaces (Lindeberg 1998; Luo et al. 2007).”
BackgroundLi, Q., You, J., & Zhang, D. D. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.12.046 · Cited by 124
“Actually, this class of techniques is originated from the classical image processing problem: finding edges and ridges in an image (Gonzales & Woods, 2007; Lindeberg, 1998; Nikam & Agarwal, 2009; Steger, 1998).”
BackgroundMethodInfluentialAssessing the performance of corner detectors for point feature tracking applications
Tissainayagam, P., & Suter, D. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.02.001 · Cited by 129
Okada, K., Comaniciu, D., & Krishnan, A. (2005) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2004.843172 · Cited by 124
“When , represents the solution of the isotropic diffusion process [1] and also the Tikhonov regularized solution of a functional minimization problem, assuming that scale invariance and semi-group constraints are satisfied [32].”
InfluentialThe Topological Structure of Scale-Space Images
Florack, L. M. J., & Kuijper, A. (2000) · Journal of Mathematical Imaging and Vision · doi:10.1023/a:1008304909717 · Cited by 124
“The core problem—the embodiment of a decent topology—had already been addressed by the mathematical community well before practical considerations in signal and image analysis boosted the development of scale-space theory.”
Multiple Nuclei Tracking Using Integer Programming for Quantitative Cancer Cell Cycle Analysis
Li, F., Zhou, X., Ma, J., & Wong, S. T. C. (2009) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2009.2027813 · Cited by 123
“We detect the nuclei center using the gradientvectorfield (GVF) followedbyGaussianfiltering [17], [24].”
MethodHierarchical structure-and-motion recovery from uncalibrated images
Toldo, R., Gherardi, R., Farenzena, M., & Fusiello, A. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.05.011 · Cited by 131
“In this section we describe the stage of Samantha that is devoted to the automatic extraction and matching of keypoints among all the n available images.”
Principal Curvature-Based Region Detector for Object Recognition
Deng, H., Zhang, W., Mortensen, E. N., Dietterich, T. G., & Shapiro, L. G. (2007) · 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.2007.382972 · Cited by 123
“The Harris-affine and Hessian-affine detectors [17, 18] compute maximum determinants of the second moment matrix and the Hessian matrix respectively across scale space and then apply Laplacian-based characteristic scale selection [11] and second-moment-matrix-based shape adaptation [12, 2].”
MethodKeypoint based autonomous registration of terrestrial laser point-clouds
Barnea, S., & Filin, S. (2007) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2007.05.005 · Cited by 127
Scale and orientation adaptive mean shift tracking
Ning, J., Zhang, L., Zhang, D. D., & Wu, C. (2012) · IET Computer Vision · doi:10.1049/iet-cvi.2010.0112 · Cited by 121
A computational theory of visual receptive fields
Lindeberg, T. (2013) · Biological Cybernetics · doi:10.1007/s00422-013-0569-z · Cited by 153
“Specifically, this receptive field model makes it possible to compute scale-invariant image features and image descriptors (Crowley 1981; Crowley and Stern 1984; Lindeberg 1998a,b, 1999, 2013; Lowe 1999, 2004; Schiele and Crowley 2000; Chomat et al. 2000; Bay et al. 2008).”
Self-citationZhang, L., Liang, B., Barbera, G., Hawes, S., Zhang, Y., Stump, K., Baum, I., Yang, Y., Li, Y., & Lin, D. (2018) · Current Protocols in Neuroscience · doi:10.1002/cpns.56 · Cited by 128
“Neuron identification: A gradient-based automatic cell detection algorithm (Barbera et al., 2016; Lindeberg, 1998), the Spatio-Temporal Gradient Matching (STGM) method, is used to iteratively generate a cell map of all active neurons in each session (Supporting Video 1).”
MethodFeature Tracking with Automatic Selection of Spatial Scales
Bretzner, L., & Lindeberg, T. (1998) · Computer Vision and Image Understanding · doi:10.1006/cviu.1998.0650 · Cited by 121
Self-citationBalancing Deformability and Discriminability for Shape Matching
Ling, H., Yang, X., & Latecki, L. J. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15558-1_30 · Cited by 119
“For example, the popular scale invariant feature transform (SIFT) [24] selects scale invariant blob regions [20] for reliable key point matching.”
BackgroundMethodLocal feature-based identification and classification for orchard insects
Wen, C., Guyer, D. E., & Li, W. (2009) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2009.07.002 · Cited by 131
Li, Z., Liu, G., Yang, Y., & You, J. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2173697 · Cited by 118
Scale-Dependent 3D Geometric Features
Novatnack, J., & Nishino, K. (2007) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2007.4409084 · Cited by 118
“Rich visual features, including corners, edges, and blobs, can then be detected in this scale-space and their intrinsic scales can be identified [16].”
BackgroundA comparative experimental study of image feature detectors and descriptors
Mukherjee, D., Wu, Q. M. J., & Wang, G. (2015) · Machine Vision and Applications · doi:10.1007/s00138-015-0679-9 · Cited by 126
“[18] provided a definition of saliency under change of scale and evaluated Harris, the method proposed in [28] and Harris–Laplacian corner detector [31].”
MethodSingle-Molecule Kinetics in Living Cells
Elf, J., & Barkefors, I. (2018) · Annual Review of Biochemistry · doi:10.1146/annurev-biochem-013118-110801 · Cited by 126
“One can also design multiscale blob/spot detection tools following the adaptive space-scale approach(157).”
BackgroundAn Analysis of the SURF Method
Oyallon, E., & Rabin, J. (2015) · Image Processing On Line · doi:10.5201/ipol.2015.69 · Cited by 150
“Taking inspiration from the previous works of Lindeberg [12, 10, 11, 13] about scale-invariant detection, SURF [1, 2] uses scale-normalized determinant of Hessian to detect saddle points in images.”
Survey of Appearance-based Methods for Object Recognition
Roth, P. M., & Winter, M. (2008) · Cited by 140
Recurrent Scene Parsing with Perspective Understanding in the Loop
Kong, S., & Fowlkes, C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00106 · Cited by 114
Impact of ICA-Based Image Enhancement Technique on Retinal Blood Vessels Segmentation
Soomro, T. A., Khan, T. M., Khan, M. A. U., Gao, J., Paul, M., & Zheng, L. (2018) · IEEE Access · doi:10.1109/access.2018.2794463 · Cited by 114
“Optimal values for α and β are calculated for ideal ridge patterns in [35], and the values are α = 1.”
BackgroundState of the Art in Vision-Based Localization Techniques for Autonomous Navigation Systems
Alkendi, Y., Seneviratne, L. D., & Zweiri, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3082778 · Cited by 125
“…the literature include Harris detector [29], Shi–Tomasi corners [66], maximally stable extremal regions (MSER) [67], Laplacian of Gaussian detector [68], Difference of Gaussian [69], and features from accelerated segment test (FAST), adaptive and generic accelerated segment test (AGAST), and…”
BackgroundSegmentation and boundary detection using multiscale intensity measurements
Sharon, E., Brandt, A., & Basri, R. (2005) · 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.2001.990512 · Cited by 114
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.