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 501–600 of 1,001
Automatic detection of pleural effusion in chest radiographs
Maduskar, P., Philipsen, R. H. H. M., Melendez, J., Scholten, E. T., Chanda, D. M., Ayles, H., Sánchez, C. I., & van Ginneken, B. (2015) · Medical Image Analysis · doi:10.1016/j.media.2015.09.004 · Cited by 41
“D ridgeness measure is calculated using the two eigenvalues of the Hessian matrix at multiple scales (Lindeberg (1998)).”
MethodSaliency Detection Based on Multiscale Extrema of Local Perceptual Color Differences
Ishikura, K., Kurita, N., Chandler, D. M., & Ohashi, G. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2767288 · Cited by 38
“By filtering the L∗, a∗, and b∗ channels with h(x, y, σ ) over a range of σ values, we can obtain a collection of filtered channels representing local changes in L∗, a∗, and b∗, where the degree of localization varies according to σ [61].”
Brook, A., & Ben‐Dor, E. (2011) · Remote Sensing · doi:10.3390/rs3010065 · Cited by 38
“The longest vector defines the orientation of the point of interest [18].”
BackgroundQiu, W., Wang, X., Bai, X., Yuille, A., & Tu, Z. (2014) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2014.6835734 · Cited by 39
“Based on this idea, Laplacian of Gaussian (LoG) [10] and Difference of Gaussian (DoG) [16] are widely used.”
MethodLearning Traversability From Point Clouds in Challenging Scenarios
Bellone, M., Reina, G., Caltagirone, L., & Wahde, M. (2017) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2769218 · Cited by 37
“to specific characteristics of the space as features [11], [12].”
BackgroundScale-Covariant and Scale-Invariant Gaussian Derivative Networks
Lindeberg, T. (2021) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-021-01057-9 · Cited by 44
“monstrated that scale-space theory constitutes a powerful paradigm for constructing scale-covariant and scaleinvariant feature detectors and making visual operations robust to scaling transformations [3,4,5,6,7,8]. In the area of deep learning, a corresponding framework for handling general scaling transformations has…”
BackgroundMethodSelf-citationInterest Point Detector and Feature Descriptor Survey
Krig, S. (2016) · Springer eBooks · doi:10.1007/978-3-319-33762-3_6 · Cited by 44
Sidorenko, I. N., Nizamov, S., Hergenröder, R., Zybin, A., Kuzmichev, A., Kiwull, B., Nießner, R., & Mirsky, V. M. (2015) · Microchimica Acta · doi:10.1007/s00604-015-1599-0 · Cited by 37
Accurate Object Recognition with Shape Masks
Marszałek, M., & Schmid, C. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-011-0479-2 · Cited by 41
“2 Sample interest point detections Schmid 2004) responding to corner-like regions and the Laplacian detector (Lindeberg 1998) extracting blob-like re- gions.”
MethodA blob detector in color images
Ming, A., & Ma, H. (2007) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1282280.1282335 · Cited by 37
“4 Our Work Our work described in the following Section is mainly inspired by the pioneer work of Lindeberg [1], and the Forstner method [7] while our work extends it to more generic structures.”
BackgroundMethodInfluentialVision-based Global Localization Using a Visual Vocabulary
Wang, J., Cipolla, R., & Zha, H. (2006) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2005.1570770 · Cited by 47
Generalized Axiomatic Scale-Space Theory
Lindeberg, T. (2013) · Advances in imaging and electron physics · doi:10.1016/b978-0-12-407701-0.00001-7 · Cited by 44
“Specifically, mechanisms for scale invariance as obtained as one of the consequences of this theory (Lindeberg 1998, Lindeberg 2013c) have allowed for breakthroughs regarding methods for image matching and object recognition with important follow-up consequences for constructing computer vision…”
BackgroundMethodSelf-citationOn the Representation and Matching of Qualitative Shape at Multiple Scales
Shokoufandeh, A., Dickinson, S., Jönsson, C., Bretzner, L., & Lindeberg, T. (2002) · Lecture notes in computer science · doi:10.1007/3-540-47977-5_50 · Cited by 37
“Blob and ridge extraction is performed using automatic scale selection, as described in previous work (see [ 8 ] and [7]).”
MethodSelf-citationHodneland, E., Bukoreshtliev, N. V., Eichler, T. W., Tai, X., Gurke, S., Lundervold, A., & Gerdes, H.-H. (2009) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2008.2011522 · Cited by 36
Multifeature‐based medical image segmentation
Kurmi, Y., & Chaurasia, V. (2018) · IET Image Processing · doi:10.1049/iet-ipr.2017.1020 · Cited by 36
A Novel Keypoint Detector Combining Corners and Blobs for Remote Sensing Image Registration
Ye, Y., Wang, M., Hao, S., & Zhu, Q. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.2980620 · Cited by 36
“The scale invariance is based on the fact that the LoG extreme can locate the characteristic scales of keypoints in the scale space [7].”
BackgroundMDGHM-SURF: A robust local image descriptor based on modified discrete Gaussian–Hermite moment
Kang, T., Choi, I.-H., & Lim, M. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.06.022 · Cited by 38
Local Scale Measure from the Topographic Map and Application to Remote Sensing Images
Luo, B., Aujol, J., & Gousseau, Y. (2009) · Multiscale Modeling and Simulation · doi:10.1137/080730627 · Cited by 36
“Lindeberg [ 26 ] has proposed to use normalized derivatives in the linear scale space in order to select characteristic scales in an image.”
InfluentialMay, K. A., & Georgeson, M. A. (2007) · Vision Research · doi:10.1016/j.visres.2007.02.012 · Cited by 42
“But in fact, as noted by Lindeberg himself, we can view his algorithm as a ‘‘pattern matcher’’ (Lindeberg, 1998b, p. 83): the algorithm is formally equivalent to treating the 1st derivative of the edge as a spatial ‘‘signature’’, and then finding the best-fitting template.”
BackgroundMethodInfluentialVisual Attention Using Game Theory
Ramström, O., & Christensen, H. I. (2002) · Lecture notes in computer science · doi:10.1007/3-540-36181-2_46 · Cited by 38
“If this variation would interfere a more complex process should be applied, such as (Lindeberg 1998).”
BackgroundSpecies-Agnostic Patterned Animal Re-identification by Aggregating Deep Local Features
Nepovinnykh, E., Chelak, I., Eerola, T., Immonen, V., Kalviainen, H. A., Kholiavchenko, M., & Stewart, C. V. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02071-1 · Cited by 47
“This method is combined with the multiscale approach from (Lindeberg, 1998)whichusesLaplacianofGaussiantofindextremainthe scale space.”
Koo, H. I., & Cho, N. I. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15552-9_31 · Cited by 35
A Learning-Based Approach for Fast and Robust Vessel Tracking in Long Ultrasound Sequences
Luca, V. D., Tschannen, M., Székely, G. J., & Tanner, C. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40811-3_65 · Cited by 35
“A scale-space approach (local maxima of a Difference-of-Gaussian (DoG)) [15, 20] is used to detect the most likely blob in ROIj(t0).”
MethodAutomatic co-registration of 3D multi-sensor point clouds
Persad, R. A., & Armenakis, C. (2017) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.05.014 · Cited by 38
An automatic panoramic image mosaic method based on graph model
Wang, Z., Chen, Y., Zhu, Z., & Zhao, W. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2619-0 · Cited by 35
“For example, a scale-invariant blob detector was developed by Lindeberg [10], where a blob is a circle centered at a maximum point of the normalized Laplacian measure and with radius proportional to the scale.”
MethodUsing hidden scale for salient object detection
Chalmond, B., Francesconi, B., & Herbin, S. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.877380 · Cited by 35
“With these notations the logistic models are defined as P s,eβ (a) .= P (Aes = a|Des) = exp[(β0 + ∑ c βcD e s(c))a] 1 + exp(β0 + ∑ c βcD e s(c)) = exp[(βT D̃es)a] 1 + exp(βT D̃es) (6) and P sλ(e) .= P ( s = e|Hs) = exp(λHes )∑ e′ exp(λHe ′ s ) (7) whereλ is a positive scalar parameter.”
MethodMultiscale Isotropic Matched Filtering for Individual Tree Detection in LiDAR Images
Palenichka, R. M., & Zaremba, M. B. (2007) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2007.908875 · Cited by 37
“This method can be considered as an example of a type of visual-attention operator capable of fast detection of multiple and local objects in large images [20]–[23].”
BackgroundMethodIntrinsic Geometric Scale Space by Shape Diffusion
Zou, G., Hua, J., Lai, Z., Gu, X. D., & Dong, M. (2009) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2009.159 · Cited by 35
“For 2D images, the Laplacian normalized with the scale parameter t has proved to be a more stable feature detector, compared to a range of other possible candidates, such as the gradient, Hessian, or Harris corner function [18, 19, 20].”
BackgroundMethodMRI tools for assessment of microstructure and nephron function of the kidney
Xie, L., Bennett, K. M., Liu, C., Johnson, G. A., Zhang, J. L., & Lee, V. S. (2016) · American Journal of Physiology-Renal Physiology · doi:10.1152/ajprenal.00134.2016 · Cited by 35
“The Laplacian of Gaussian algorithm can be used for 2D slices or 3D images to segment glomeruli (61).”
MethodMade to measure: An introduction to quantifying microscopy data in the life sciences
Culley, S., Caballero, A. C., Burden, J. J., & Uhlmann, V. (2023) · Journal of Microscopy · doi:10.1111/jmi.13208 · Cited by 35
“This can be achieved through strong priors, as exploited by blob detectors 63 and the Hough transform, 64 or through a curated example of the object of interest, as is the case in template matching.”
MethodVisual Features—From Early Concepts to Modern Computer Vision
Weinmann, M. (2013) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-5520-1_1 · Cited by 40
Extremal Regions Detection Guided by Maxima of Gradient Magnitude
Faraji, M., Shanbehzadeh, J., Nasrollahi, K., & Moeslund, T. B. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2477215 · Cited by 34
“ing works with scale-selection and feature detection [7], shape affine adaptation [16], and the theoretical concepts of image matching [17], has contributed to the literature significantly.”
BackgroundA perceptual scheme for fully automatic video shot boundary detection
Birinci, M., & Kiranyaz, S. (2014) · Signal Processing Image Communication · doi:10.1016/j.image.2013.12.003 · Cited by 37
“The scale invariant version of the Harris detector was proposed by Lindeberg [21], which is also referred as Harris–Laplace detector.”
MethodDefocus Blur-Invariant Scale-Space Feature Extractions
Saad, E., & Hirakawa, K. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2555702 · Cited by 37
“High level image features describing the shape are more dependable for real scenarios [2].”
BackgroundInfluentialZagoris, K., Pratikakis, I., & Gatos, B. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2700721 · Cited by 34
“Scale space theory [30], [31] allows to develop scale invariant properties by representing an image as a one-parameter function of different scaled images, the scale-space representation, and selecting the one that maximizes the above function.”
BackgroundImage Classification Based on SIFT and SVM
Li, Q., & Wang, X. (2018) · IEEE/ACIS International Conference on Computer and Information Science (ICIS) · doi:10.1109/icis.2018.8466432 · Cited by 34
Cotton Yield Estimation Using the Remotely Sensed Cotton Boll Index from UAV Images
Shi, G., Du, X., Du, M., Li, Q., Tian, X., Ren, Y., Zhang, Y., & Wang, H. (2022) · Drones · doi:10.3390/drones6090254 · Cited by 35
Improving the robustness in feature detection by local contrast enhancement
Vonikakis, V., Chrysostomou, D., Kouskouridas, R., & Gasteratos, A. C. (2012) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist.2012.6295482 · Cited by 34
“in [8], where interest point extraction is accomplished by the LoG and several other derivative based operators.”
MethodMendoza, J., & Pedrini, H. (2019) · Computational Intelligence · doi:10.1111/coin.12241 · Cited by 36
“Instead, multiscale detectors localize blob-like structures by finding local extrema on the response of differential expressions calculated using normalized-derivatives of L .”
Rotation invariant feature extraction using Ridgelet and Fourier transforms
Chen, G. Y., Bui, T., & Krzyżak, A. (2006) · Pattern Analysis and Applications · doi:10.1007/s10044-006-0028-8 · Cited by 35
Frangi, A. F., Niessen, W. J., Nederkoorn, P. J., Elgersma, O. E. H., & Viergever, M. A. (2002) · IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA) · doi:10.1109/mmbia.2000.852367 · Cited by 34
A pseudo-distance map for the segmentation-free skeletonization of gray-scale images
Jang, J.-H., & Hong, K.-S. (2002) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2001.937586 · Cited by 34
Automatic selection of parameters for vessel/neurite segmentation algorithms
Abdul‐Karim, M., Roysam, B., Dowell‐Mesfin, N., Jeromin, A., Yüksel, M., & Kalyanaraman, S. (2005) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.852462 · Cited by 34
Distance based similarity models for content based multimedia retrieval
Beecks, C., & Seidl, T. (2013) · RWTH Publications (RWTH Aachen) · Cited by 36
Anti-Impulse-Noise Edge Detection via Anisotropic Morphological Directional Derivatives
Shui, P., & Wang, F. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2726190 · Cited by 33
A computer vision-based vibration measurement method for wind tunnel tests of high-rise buildings
Huang, M., Zhang, B., & Lou, W. (2018) · Journal of Wind Engineering and Industrial Aerodynamics · doi:10.1016/j.jweia.2018.09.022 · Cited by 33
Paul, S. K., Chowdhury, M. T., Nicolescu, M., Nicolescu, M. N., & Feil-Seifer, D. (2021) · Transactions on computational science and computational intelligence · doi:10.1007/978-3-030-71051-4_10 · Cited by 39
Spatial and temporal patterns of Holocene precipitation change in the Iberian Peninsula
Ilvonen, L., Sáez, J. A. L., Holmström, L., Alba‐Sánchez, F., Díaz, S. P., Carrión, J. S., Ramos-Roman, M. J., Camuera, J., Jiménez‐Moreno, G., Ruha, L., et al. (2022) · Boreas · doi:10.1111/bor.12586 · Cited by 33
“(Lindeberg 1998), enhancing the comparisonof declines”
An evaluation of conventional and deep learning‐based image‐matching methods on diverse datasets
Ji, S., Zeng, C., Zhang, Y., & Duan, Y. (2023) · The Photogrammetric Record · doi:10.1111/phor.12445 · Cited by 36
“Blob features have also been widely used, such as Laplacian of Gaussian (LoG) (Lindeberg, 1998) and the Hessian matrix.”
MethodEdge descriptors for robust wide-baseline correspondence
Meltzer, J., & Soatto, S. (2008) · 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.2008.4587684 · Cited by 33
“This pair of ordered lists of histograms comprises the descriptor for a single edge, φ(I|Li).”
BackgroundTexture Classification in Extreme Scale Variations Using GANet
Liu, L., Chen, J., Zhao, G., Fieguth, P., Chen, X., & Pietikainen, M. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2903300 · Cited by 33
“Lindeberg [22] investigated scale for texture description, suggesting that texture characteristics strongly depend upon it.”
BackgroundMethodInfluentialGeneralized Flooding and Multicue PDE-Based Image Segmentation
Sofou, A., & Maragos, P. A. (2008) · IEEE Transactions on Image Processing · doi:10.1109/tip.2007.916156 · Cited by 33
Local spatio-temporal image features for motion interpretation
Laptev, I. (2004) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 42
A survey on non-filter-based monocular Visual SLAM systems.Preprint
Younes, G., Asmar, D., & Shammas, E. (2016) · arXiv (Cornell University) · Cited by 37
Local Symmetry Detection in Natural Images Using a Particle Filtering Approach
Widynski, N., Moevus, A., & Mignotte, M. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2365140 · Cited by 32
On the design of a novel JPEG quantization table for improved feature detection performance
Chao, J., Chen, H., & Steinbach, E. G. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738345 · Cited by 32
“Index Terms— JPEG, Quantization table, Feature detectors, Scale-space”
MethodA Saliency-Based Band Selection Approach for Hyperspectral Imagery Inspired by Scale Selection
Su, P., Liu, D., Li, X., & Liu, Z. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2018.2800034 · Cited by 32
“The trace and determinant of a Hessian matrix have a strong ability to describe local structures of an image [28], [31], [32], so the Hessian matrix is used to measure the saliency of a band.”
MethodDetecting Stable Keypoints from Events through Image Gradient Prediction
Chiberre, P., Perot, E., Sironi, A., & Lepetit, V. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00153 · Cited by 32
“We observe that many gray-level corner detectors rely on image derivatives rather than intensity values [11, 33, 18, 19].”
BackgroundLocal Statistic Based Region Segmentation with Automatic Scale Selection
Piovano, J., & Papadopoulo, T. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88688-4_36 · Cited by 32
“In [15] the authors tackled similar problems with the purpose of extracting edges and ridges from images.”
BackgroundReal-time Automated Visual Inspection using Mobile Robots
Neto, H. V., & Nehmzow, U. (2007) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-007-9146-9 · Cited by 32
Local 3D structure recognition in range images
Flint, A., Dick, A., & van den Hengel, A. (2008) · IET Computer Vision · doi:10.1049/iet-cvi:20080037 · Cited by 32
SIFT and SURF Performance Evaluation for Mobile Robot-Monocular Visual Odometry
Benseddik, H. E., Djekoune, O., & Belhocine, M. (2014) · Journal of Image and Graphics · doi:10.12720/joig.2.1.70-76 · Cited by 32
“It has been proven, that the information given by a camera system is sufficient to Manuscript received January 4, 2013; revised May 5, 2014. estimate the motion of a moving camera in a static environment, called visual odometry [1].”
BackgroundTafti, A. P., Baghaie, A., Kirkpatrick, A. B., Holz, J. D., Owen, H. A., D’Souza, R. M., & Yu, Z. (2016) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2016.1152201 · Cited by 32
“A wide plethora of detectors anddescriptors,aswellastheirperformancecomparisonscanbe found in the literature (Lindeberg 1998; Ke & Sukthankar 2004; Lowe 2004; Mikolajczyk et al. 2005).”
BackgroundMethodLiu, J., Jung, H., Dubra, A., & Tam, J. (2018) · Investigative Ophthalmology & Visual Science · doi:10.1167/iovs.18-24734 · Cited by 34
Motion Segmentation and Depth Ordering Using an Occlusion Detector
Feldman, D., & Weinshall, D. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.70766 · Cited by 32
Ou, Y., Shen, D. G., Feldman, M. D., Tomaszewski, J., & Davatzikos, C. A. (2009) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvpr.2009.5204347 · Cited by 32
Plane Registration Leveraged by Global Constraints for Context‐Aware AEC Applications
Feng, C., & Kamat, V. R. (2012) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/j.1467-8667.2012.00795.x · Cited by 31
“Interest point detection algorithms are usually applied in this step, such as Harris corner detector (Harris and Stephens, 1988), FAST (Rosten and Drummond, 2006), Difference of Gaussian (DoG) (Lowe, 2004), and Laplacian of Gaussian (LoG) (Lindeberg, 1998).”
MethodBlob Detection With Wavelet Maxima Lines
Damerval, C., & Meignen, S. (2006) · IEEE Signal Processing Letters · doi:10.1109/lsp.2006.879830 · Cited by 31
“It is usually a first step toward more complicated tasks, such as the determination of local deformations in images [3], [4] or the extraction of scale-invariant interest points [5], [7].”
BackgroundThermographic Laplacian-pyramid filtering to enhance delamination detection in concrete structure
Cheng, C., Na, R., & Shen, Z. (2018) · Infrared Physics & Technology · doi:10.1016/j.infrared.2018.12.039 · Cited by 31
“To detect different sizes of blobs, a multiscale approach was introduced based on scale-space theory (Lindeberg 1998) in the later subsection 2.3.”
MethodInfluentialSIFT-CCH: Increasing the SIFT distinctness by Color Co-occurrence Histograms
Ancuți, C., & Bekaert, P. (2007) · International symposium on image and signal processing and analysis/ISPA ... · doi:10.1109/ispa.2007.4383677 · Cited by 39
“A 4x4 orientation histogram is built on the 4x4 sub-region of the feature point from a 16x16 region centered on the feature point location.”
BackgroundFingerprint authentication using geometric features
M., S. K. K., Rajeev, S., Panetta, K. A., & Agaian, S. С. (2017) · IEEE Conference on Technologies for Homeland Security (HST) · doi:10.1109/ths.2017.7943449 · Cited by 31
“There are various feature detectors which have been proposed [15, 27-29] and a comparative study has been provided in [3].”
BackgroundMethodInfluentialKalia, R., Lee, K., Samir, B., Je, S.-K., & Oh, W.-G. (2011) · Korea-Japan Joint Workshop on Frontiers of Computer Vision · doi:10.1109/fcv.2011.5739756 · Cited by 36
“Mikolajczyk and Schmid refined Lindeberg’s idea [3] and created robust and scale-invariant feature detectors with high repeatability, which they termed as Harris-Laplace and Hessian-Laplace [9].”
BackgroundNeural Mechanisms for the Robust Representation of Junctions
Hansen, T., & Neumann, H. (2004) · Neural Computation · doi:10.1162/089976604773135087 · Cited by 32
“Multiscale Processing for Junction Detection A number of studies have stressed the importance of multiple scales for the proper extraction of corner and junction information (Lindeberg, 1998; Mokhtarian and Suomela, 1998; Würtz and Lourens, 2000).”
BackgroundBlurring the Line Between Structure and Learning to Optimize and Adapt Receptive FieldsPreprint
Shelhamer, E., Wang, D., & Darrell, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.11487 · Cited by 33
“Our learning and inferring covariance relates to scale selection [24], as exemplified by the scale invariant feature transform [26].”
BackgroundRapantzikos, K. E., Avrithis, Y., & Kollias, S. (2007) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1282280.1282326 · Cited by 30
“INTRODUCTION As collections of video data grow automatic systems for efficiently querying this data about abstract or specific events have become a significant need.”
BackgroundImage matching based on orientation–magnitude histograms and global consistency
Liang, J., Liao, Z., Yang, S., & Wang, Y. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.03.026 · Cited by 30
The JCMT Gould Belt Survey: constraints on prestellar core properties in Orion A North
Salji, C. J., Richer, J. S., Buckle, J. V., Hatchell, J., Kirk, H., Beaulieu, S. F., Berry, D., Broekhoven-Fiene, H., Currie, M. J., Fich, M., et al. (2015) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stu2297 · Cited by 30
“The theoretical framework outlined below pioneered by Lindeberg (1998), Koenderink (1984) and Witkin (1983) was originally designed for the enhancement of vessel structures in medical imaging (Frangi et al. 1998), however, here we apply a generalized form of filtering for a variety of desired…”
MethodFully automatic face recognition framework based on local and global features
Geng, C., & Jiang, X. (2012) · Machine Vision and Applications · doi:10.1007/s00138-012-0423-7 · Cited by 30
Murakami, Y., Ikeda, Y., Nakatake, S., Tachibana, T., Fujiwara, K., Yoshida, N., Notomi, S., Nakao, S., Hisatomi, T., Miller, J. W., et al. (2015) · Cell Death Discovery · doi:10.1038/cddiscovery.2015.58 · Cited by 30
Prostate fiducial marker detection with the use of multi-parametric magnetic resonance imaging
Fernandes, C. D., Dinh, C. V., Steggerda, M. J., ter Beek, L. C., Smolic, M., van Buuren, L. D., Pos, F. J., & van der Heide, U. A. (2017) · Physics and Imaging in Radiation Oncology · doi:10.1016/j.phro.2017.02.001 · Cited by 30
Wang, Y., Zhang, H., Qiu, C., & Xia, S. (2018) · Computational Intelligence and Neuroscience · doi:10.1155/2018/5078268 · Cited by 30
de Vries, E. T., Tang, Q., Faez, S., & Raoof, A. (2021) · Advances in Water Resources · doi:10.1016/j.advwatres.2021.104086 · Cited by 30
Automatic Road Extraction From Remote Sensing Images Based on a Normalized Second Derivative Map
Bae, Y., Lee, W., Choi, Y., Jeon, Y. W., & Ra, J. B. (2015) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2015.2431268 · Cited by 30
Rotation Invariant Matching of Partial Shoeprints
Nibouche, O., Bouridane, A., Gueham, M., & Laadjel, M. (2009) · International Machine Vision and Image Processing Conference (IMVIP) · doi:10.1109/imvip.2009.24 · Cited by 30
“It takes account of feature detection with automatic characteristic scale selection as shown in [13], where LoG has been demonstrated to be successful in scale selection.”
MethodAutomatic selection of edge detector parameters based on spatial and statistical measures
Koren, R., & Yitzhak Yitzhaky, B. (2006) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2006.01.005 · Cited by 30
Image‐based 3D reconstruction using helical nanobelts for localized rotations
Kratochvil, B. E., Dong, L., Zhang, L., & Nelson, B. J. (2009) · Journal of Microscopy · doi:10.1111/j.1365-2818.2009.03313.x · Cited by 30
A general framework for vessel segmentation in retinal images
Wu, C., Gady Agam, B., & Stanchev, P. L. (2007) · IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA) · doi:10.1109/cira.2007.382924 · Cited by 30
“By convolving with Gaussian kernels of various sizes, the normalized second order derivatives [14] can indicate the scale and orientation of vessels.”
MethodAirway Tree Extraction with Locally Optimal Paths
Lo, P., Jon Sporring, A., Pedersen, J. J. H., & de Bruijne, M. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04271-3_7 · Cited by 30
“The scale is selected for each voxel independently using the scale normalized [12] Frobenius norm of the Hessian matrix ω(σi) = σ 2 i √”
MethodMulti-scale Nodule Detection in Chest Radiographs
Schilham, A. M. R., van Ginneken, B., & Loog, M. (2003) · Lecture notes in computer science · doi:10.1007/978-3-540-39899-8_74 · Cited by 30
“The method consists of: i) Lung field segmentation with an Active Shape Model [1]; ii) Nodule candidate detection by Lindeberg’s multi-scale blob detector [2] and quadratic classification; iii) Blob segmentation by multi-scale edge focusing; iv) k Nearest neighbor classification.”
MethodLaptev, I., & Lindeberg, T. (2003) · Image and Vision Computing · doi:10.1016/j.imavis.2003.07.002 · Cited by 30
“Specifically, combinations of automatic scale selection in the spatial domain [17] with histogram based recognition schemes have been presented by [4] [10].”
BackgroundMethodSelf-citationMikolajczyk, K. (2002) · HAL · Cited by 30
Linde, O., & Lindeberg, T. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.12.003 · Cited by 29
“With regard to approaches based on interest points, Mikolajczyk and Schmid [46] combined the ideas of scale selection and scale-adapted image features (Lindeberg [42]) with affine normalization”
MethodSelf-citationAn Accurate Two-Step ISAR Cross-Range Scaling Method for Earth-Orbit Target
Du, Y., Jiang, Y., & Zhou, W. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2725986 · Cited by 29
“from the RD image automatically using blob detection [11].”
MethodStratoulias, D., Tolpekin, V. A., de By, R., Zurita‐Milla, R., Retsios, V., Bijker, W., Hasan, M. A., & Vermote, E. F. (2017) · Remote Sensing · doi:10.3390/rs9101048 · Cited by 29
“automatic scale detection [42] based on the identification of objects was developed in-house.”
BackgroundFu, M., Kuntz, A., Webster, R. J., III, & Alterovitz, R. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593407 · Cited by 29
Learning-Free Text Line Segmentation for Historical Handwritten Documents
Barakat, B. K., Cohen, R., Droby, A., Rabaev, I., & El‐Sana, J. (2020) · Applied Sciences · doi:10.3390/app10228276 · Cited by 29
“Normally, the differential descriptor for forming a blob is the Laplacian of an isotropic Gaussian (LoG) [42].”
BackgroundMethodJaiswal, A., Godinez, W. J., Eils, R., Lehmann, M. J., & Rohr, K. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2458174 · Cited by 29
Saliency of Interest Points under Scale Changes
Hall, D., Leibe, B., & Schiele, B. (2002) · British Machine Vision Conference (BMVC) · doi:10.5244/c.16.63 · Cited by 29
“For all image features, it scans the scale space and returns an intrinsic scale.”
BackgroundHe, S., & Lau, R. W. H. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.40 · Cited by 34
“This bias can be eliminated by ‘γ-normalization’, which is typically used to select the best filtering scale [20].”
MethodFailure detection and isolation in ceramic tile edges based on contour descriptor analysis
Hocenski, Ž., & Keser, T. (2007) · Mediterranean Conference on Control and Automation (MED) · doi:10.1109/med.2007.4433713 · Cited by 29
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.