SURF: Speeded Up Robust Features
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index; none of the 18 sources its claims cite is checked for support yet.
Overview
CoChat Summary
TL;DR
SURF is a scale- and rotation-invariant interest point detector and descriptor that uses integral images, Hessian-based detection, and Haar-wavelet responses to be faster than prior methods while matching or exceeding their repeatability and distinctiveness. It reports strong results on standard benchmarks and a museum object recognition task.
Key findings
- The Fast-Hessian detector is more than 3× faster than DoG and 5× faster than Hessian-Laplace, with comparable or better repeatability on Graffiti, Leuven, Boat, and Wall; on the first Graffiti image (800×640), computation times were 120 ms for Fast-Hessian, 400 ms for DoG, 650 ms for Hessian-Laplace, and 1800 ms for Harris-Laplace.
- SURF’s 64-dimensional descriptor outperformed GLOH, SIFT, and PCA-SIFT in most comparisons, sometimes by more than 10% improvement in recall for the same precision; SURF-128 was slightly better but slower to match.
- Joint detector-descriptor computation times on the first Graffiti image were 255 ms for U-SURF, 354 ms for SURF, 391 ms for SURF-128, and 1036 ms for SIFT.
- In museum object recognition, recognition rates were 85.7% for SURF-128, 83.8% for U-SURF, 82.6% for SURF, 78.3% for GLOH, 78.1% for SIFT, and 72.3% for PCA-SIFT.
Methods
- Design: a scale- and rotation-invariant detector/descriptor. The detector uses the determinant of the Hessian with box-filter approximations evaluated via integral images; the descriptor uses Haar-wavelet responses in a 4×4 subregion grid, producing a 64-dimensional vector, with an upright U-SURF variant and an extended SURF-128 variant.
- Data: standard evaluation sequences from Mikolajczyk (including Graffiti, Wall, Boat, Leuven, Bikes, Trees, and Ubc; Bark excluded from descriptor evaluations) and a real-life museum object recognition database of 216 images of 22 objects, with 116 test images at 320×240.
- Analysis: detector repeatability scores, descriptor recall-(1-precision) graphs under similarity-threshold and nearest-neighbour-ratio matching, recognition rates, and computation timings on a standard Linux PC (Pentium IV, 3 GHz).
Limitations
- The paper has no explicit limitations section. It states that space limitations prevent showing results on all sequences, and it assumes skew, anisotropic scaling, and perspective effects are second-order effects covered only by overall descriptor robustness.
- Evident from the text: the method is scale- and rotation-invariant but not affine-invariant; Fig. 4 notes the interest points are not affine invariant, and the descriptor does not use colour.
- Evident from the text: the object recognition experiment uses small 320×240 test images and matching without additional geometric constraints, which the authors say would reduce false positives but were omitted for comparison purposes.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
0 Valid · 2 Not valid · 12 Not checked · 30 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The number of interest points found is on average very similar for all detectors.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 4 × 4 sub-region division solution provided the best results.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SURF outperformed the other descriptors for almost all the comparisons.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The SURF descriptor outperforms the other descriptors in a systematic and significant way, with sometimes more than 10% improvement in recall for the same level of precision.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in the results section, the performance is comparable to the one using the discretised and cropped Gaussians.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
8 more claims
Create a free account to see all 44 claims and every source verdict.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 1
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
“This transition marked a new era, where we moved beyond the classic approaches and task-specific feature engineering of earlier days [Lowe 2004; Bay et al. 2006; Rosten and Drummond 2006] towards models that could be trained once over large amounts of data, and then adapted for a broad variety of tasks, such as image recognition, object detection, and image segmentation [Krizhevsky et al. 2012; Sz”
From On the Opportunities and Risks of Foundation Models (2021) · cites this paper as Bay et al. 2006
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · cited 14×
“This PCA-SIFT yields a 36-dimensional descriptor which is fast for matching, but proved to be less distinctive than SIFT in a second comparative study by Mikolajczyk et al. [8] and slower feature computation reduces the effect of fast matching.”
BackgroundMethodResultInfluentialMarr, D., & Hildreth, E. (1980) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1980.0020 · Cited by 6,510
PCA-SIFT: a more distinctive representation for local image descriptors
Ke, Y., & Sukthankar, R. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.183 · Cited by 3,932
Robust wide-baseline stereo from maximally stable extremal regions
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.02.006 · Cited by 3,686
Scalable Recognition with a Vocabulary Tree
Nister, D., & Stewenius, H. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.264 · Cited by 3,579
Scale & Affine Invariant Interest Point Detectors
Mikolajczyk, K., & Schmid, C. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000027790.02288.f2 · Cited by 3,436
Cited by
Items 6,301–6,400 of 14,752
Object detection methods for Image-based Visual Servoing of 6-DOF Industrial robot
Krishnan, M. G., & Ashok, S. (2022) · IEEE Region 10 Symposium (TENSYMP) · doi:10.1109/tensymp54529.2022.9864432 · Cited by 7
A novel country-level integrated image mosaic system using optical remote sensing imagery
Misra, I., Rohil, M. K., Moorthi, S. M., & Dhar, D. (2022) · Earth Science Informatics · doi:10.1007/s12145-022-00865-w · Cited by 10
SLAM Back-End Optimization Algorithm Based on Vision Fusion IPS
Xia, Y., Cheng, J., Cai, X., et al. (2022) · Sensors · doi:10.3390/s22239362 · Cited by 7
“, SURF [1], SIFT [2] and ORB [3]) and matching with data, and then performs pose estimation by minimizing the feature point reprojection error.”
MethodAl-Shemarry, M. S., Li, Y., & Abdulla, S. (2022) · IEEE Intelligent Transportation Systems Magazine · doi:10.1109/mits.2022.3210226 · Cited by 7
Liu, J., Sun, K., Jiang, S., Li, K., & Tao, W. (2023) · Remote Sensing · doi:10.3390/rs15040926 · Cited by 7
SIFT-ONN: SIFT Feature Detection Algorithm Employing ONNs for Edge Detection
Abernot, M., Gauthier, S., Gonos, T., & Todri‐Sanial, A. (2023) · Neuro Inspired Computational Elements Conference (NICE) · doi:10.1145/3584954.3584999 · Cited by 10
“SIFT-ONN is compared with SURF, ORB, BRISK, SIFT, and KAZE as they are state-of-the-art feature detection and description algorithms.”
BackgroundMethodInfluentialEnabling edge computing ability in view-independent vehicle model recognition
Liu, C., Pu, Z., Li, Y., Jiang, Y., Wang, Y., & Du, Y. (2023) · International Journal of Transportation Science and Technology · doi:10.1016/j.ijtst.2023.03.007 · Cited by 8
Learning General Descriptors for Image Matching With Regression Feedback
Rao, Y., Ju, Y., Li, C., Rigall, E., Yang, J., Fan, H., & Dong, J. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3267279 · Cited by 10
PhotoMatch: An Open-Source Tool for Multi-View and Multi-Modal Feature-Based Image Matching
de Oña, E. R., Barbero-García, I., González‐Aguilera, D., et al. (2023) · Applied Sciences · doi:10.3390/app13095467 · Cited by 7
Geodesic Based Image Matching Network for the Multi-scale Ground to Aerial Geo-localization
Amit, R. A., & Mohan, C. K. (2023) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero55745.2023.10115935 · Cited by 7
Shang, Z., & Blumensath, T. (2023) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2023.3281268 · Cited by 7
Zhu, Z., Chen, T., Rowlinson, S., et al. (2023) · Buildings · doi:10.3390/buildings13061473 · Cited by 7
Image stitching using double features-based global similarity constraint and improved seam-cutting
Wang, J., Ma, M., Yan, S., et al. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15976-9 · Cited by 7
Use of Machine Learning in Forensics and Computer Security
Ojha, N. K., Kumar, A., Tyagi, N., Ranjan, P., & Vaish, A. (2023) · Advanced technologies and societal change · doi:10.1007/978-981-99-2115-7_9 · Cited by 10
Zargham, A., Haq, I. U., Shloul, T. A., Riaz, S., Husnain, G., Assam, M., Ghadi, Y. Y., & Mohamed, H. G. (2023) · Applied Sciences · doi:10.3390/app13148092 · Cited by 7
Face Detection and Recognition Using Raspberry PI Computer
Dubovečak, M., Dumić, E., & Bernik, A. (2023) · Tehnički glasnik · doi:10.31803/tg-20220321232047 · Cited by 10
A Bag-of-Prototypes Representation for Dataset-Level Applications
Tu, W., Deng, W., Gedeon, T., & Zheng, L. (2023) · 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/cvpr52729.2023.00282 · Cited by 19
Tracking and Identification of Ice Hockey Players
Chen, Q., & Poullis, C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44137-0_1 · Cited by 7
Davydko, O., Pavlov, V. A., & Longo, L. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-44064-9_36 · Cited by 10
Oliveira, A. J., Ferreira, B. M., Cruz, N. A., et al. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3354126 · Cited by 7
Single-shot global localization via graph-theoretic correspondence matching
Matsuzaki, S., Koide, K., Oishi, S., Yokozuka, M., & Banno, A. (2024) · Advanced Robotics · doi:10.1080/01691864.2024.2307607 · Cited by 9
“such as SIFT [12] and SURF [13] between a query image and a pre-computed map and optimizing the pose based on the feature correspondences [4, 14].”
MethodUAV image matching from handcrafted to deep local features
Zhang, X., Feng, X., Zheng, M., & Xie, Z. (2024) · European Journal of Remote Sensing · doi:10.1080/22797254.2024.2307619 · Cited by 8
“SURF uses a Hessian matrix determinant approximation of the image.”
InfluentialExtended Neighborhood Consensus With Affine Correspondence for Outlier Filtering in Feature Matching
Shen, L. C., Zhang, Y., Chen, C., Wang, L.-T., Zhu, J., & He, Y. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3388580 · Cited by 7
“Note that the scale and rotation invariant detectors, such as SURF [11], SIFT [10], SAR-SIFT [75], and OS-SIFT [13], can also provide partial LAFs, while the correspondence is called partial affine correspondence [65], [76].”
MethodCo-ranking Images and Tags via Random Walks on a Heterogeneous Graph
Wu, L. Y., Wang, Y., & Shepherd, J. A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-35725-1_21 · Cited by 7
“In order to quantize the similarity between images, we use two feature descriptors: the SURF-based appearance feature descriptor [2] and the pyramid histogram of oriented gradients-based shape feature descriptor[3].”
MethodContent-Based Filtering for Fast 3D Reconstruction from Unstructured Web-Based Image Data
Makantasis, K., Doulamis, A. D., Doulamis, N. D., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13695-0_9 · Cited by 7
A Combination of Spatial Pyramid and Inverted Index for Large-Scale Image Retrieval
Nguyen, V.-T., Ngo, T. D., Tran, M., et al. (2015) · International Journal of Multimedia Data Engineering and Management · doi:10.4018/ijmdem.2015040103 · Cited by 7
GPU based non-overlapping multi-camera vehicle tracking
Gamage, T. D., Samarawickrama, J. G., & Pasqual, A. A. (2014) · International Conference on Information and Automation for Sustainability (ICIAfS) · doi:10.1109/iciafs.2014.7069550 · Cited by 7
A hierarchical hybrid model for intelligent cyber-physical systems
Claudi, A., Sernani, P., Dolcini, G., et al. (2013) · Università Politecnica delle Marche (Università Politecnica delle Marche) · Cited by 7
Yao, Y., & Li, C. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41939-3_53 · Cited by 7
Evaluating the applicability of BRISK for the geometric registration of remote sensing images
Schwind, P., & d’Angelo, P. (2015) · Remote Sensing Letters · doi:10.1080/2150704x.2015.1058986 · Cited by 7
The new approach for reliable UAV navigation based on onboard camera image processing
Lukashevich, P., Belotserkovsky, A., & Nedzved, A. (2015) · International Conference on Information and Digital Technologies (IDT) · doi:10.1109/dt.2015.7222975 · Cited by 7
Pixel-Based Hyperparameter Selection for Feature-Based Image Registration
Brunet, F., Bartoli, A., Navab, N., & Malgouyres, R. (2010) · Eurographics · doi:10.2312/pe/vmv/vmv10/033-040 · Cited by 7
“This time, the keypoints were extracted us-ing the SURF detector of [BETG08] and approximately 12% of the 621 point correspondences were erroneous.”
MethodEstimating the 3D Position of Humans Wearing a Reflective Vest Using a Single Camera System
Mosberger, R., & Andreasson, H. (2013) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-40686-7_10 · Cited by 7
A Stable Graph-Based Representation for Object Recognition through High-Order Matching
Albarelli, A., Bergamasco, F., Rossi, L., Andrea Torsello, A., & Vascon, S. (2012) · Aston Publications Explorer (Aston University) · Cited by 7
Graph-Based Object Class Discovery
Xia, S., & Hancock, E. R. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03767-2_47 · Cited by 7
“A variety of feature detectors have been developed [14][15][16][17], and these include SIFT [14] and SURF ( Speeded Up Robust Features ) [15].”
Method3D Map Registration using Vision/Laser and Inertial Sensing.
Mirisola, L. G. B., Lobo, J., & Dias, J. M. M. (2007) · Cited by 8
Efficient Object Pixel-Level Categorization Using Bag of Features
Aldavert, D., Arnau Ramisa, A., Toledo, R., & de Mántaras, R. L. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-10331-5_5 · Cited by 10
A Feasibility Study on the Use of Binary Keypoint Descriptors for 3D Face Recognition
Križaj, J., Štruc, V., & Mihelič, F. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-07491-7_15 · Cited by 7
“The SURF [1] keypoint detector relies on a similar approach, but uses the determinant of the Hessian matrix to detect keypoints.”
MethodSURF feature detection method used in object tracking
Zhou, Z., Ou, X., & Xu, J. W. (2013) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc.2013.6890899 · Cited by 7
“H(f(x,y)) = a2f a2f ax2 aX0; a2f a2f aX0; 0;2 (7)”
Combining SURF with MSER for image matching
Leí, T., Jing, X., Sun, S., et al. (2013) · IEEE International Conference on Granular Computing (GrC) · doi:10.1109/grc.2013.6740423 · Cited by 7
Visual concept detection of web images based on group sparse ensemble learning
Sun, Y., Sudo, K., & Taniguchi, Y. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2179-8 · Cited by 7
The application of image based visual servo control system for smart guard
Li, L., Wang, B., Li, B., et al. (2013) · International Conference on Control and Automation · doi:10.1109/icca.2013.6564898 · Cited by 7
Toward autonomous navigation using an RGB-D camera for flight in unknown indoor environments
Tang, L., Yang, S. Y., Cheng, N., & Li, Q. (2014) · IEEE CSAA Guidance, Navigation and Control Conference (CGNCC) · doi:10.1109/cgncc.2014.7007485 · Cited by 7
Rotation invariant face recognition survey
Castaneda, G., Khoshgoftaar, T. M., & Wald, R. (2014) · IEEE International Conference on Information Reuse and Integration (IRI) · doi:10.1109/iri.2014.7051976 · Cited by 7
“One such new approach is the SURF operator [6], which not only has distinguishing features such as invariance of scaling and rotation, strong robustness, and prominent separating capacity between different features (just like the SIFT features), but also has a rapid arithmetic speed compared to…”
BackgroundEvaluation of an Area-Based matching algorithm with advanced shape models
Re, C., Roncella, R., Forlani, G., et al. (2014) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsarchives-xl-4-215-2014 · Cited by 7
Performance optimization of vision apps on mobile application processor
Cheng, K.-T. T., Yang, X. Y., & Wang, Y.-C. (2013) · International Conference on Systems, Signals and Image Processing · doi:10.1109/iwssip.2013.6623485 · Cited by 7
Feature detection and tracking for extraction of crowd dynamics
Gunduz, A. E., Temizel, A., & Temizel, T. T. (2013) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2013.6531572 · Cited by 7
“Bu çalışmada kullanılacak ilgili algoritmalar SIFT[4], SURF[5], uSURF[5], ORB[6] ve BRIEF[7] olarak belirlenmiştir.”
BackgroundNovel Similarity Measures for Differential Invariant Descriptors for Generic Object Retrieval
Balmashnova, E. E., & Florack, L. M. J. (2008) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-008-0079-0 · Cited by 7
An approach for X-ray image mosaicing based on Speeded-Up Robust Features
Gong, J.-H., Zhang, J., An, Z., et al. (2012) · doi:10.1109/icwamtip.2012.6413530 · Cited by 7
“In 2006, Bay and Tuytelaars [3] proposed speeded up robust features algorithm and used integral images for image convolutions and Fast-Hessian detector, which created a new tide of robust feature detection method.”
MethodKeypoint-based binocular distance measurement for pedestrian detection system
Mammeri, A., Boukerche, A., & Zhao, M. (2014) · doi:10.1145/2656346.2656365 · Cited by 7
“SURF (Speeded Up Robust Features) is a SIFT-like feature descriptor [5].”
Large scalability in document image matching using text retrieval
Moraleda, J. (2011) · Pattern Recognition Letters · doi:10.1016/j.patrec.2011.10.013 · Cited by 7
“A number of techniques such as SIFT (Lowe, 2004) and SURF (Bay et al., 2006) have been published for the problem of image matching using local descriptors extracted from high resolution natural images.”
MethodTerrain adaptive detector selection for visual odometry in natural scenes
Otsu, K., Otsuki, M., Ishigami, G., & Kubota, T. (2013) · Advanced Robotics · doi:10.1080/01691864.2013.843789 · Cited by 7
“The interest point detectors used in the comparative study are Harris [19], Shi-Tomasi [21], DoG [14], FAST [23], Fast Hessian [25], and STAR [16].”
MethodA vote of confidence based interest point detector
Miao, Z., & Jiang, X. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6637893 · Cited by 7
LTD: Local Ternary Descriptor for image matching
Gao, Y., Qiao, Y., Li, Z., & Xu, C. (2013) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2013.6720508 · Cited by 6
Semantic structure from motion with object and point interactions
Bao, S. Y., Bagra, M., & Savarese, S. (2011) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2011.6130358 · Cited by 7
“Point observations are obtained by a feature detector such as [28, 12, 16, 21].”
Wang, Z., Taylor, C. E., Cao, Q., et al. (2011) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/2070942.2071008 · Cited by 7
Multi-Sensor System for Vehicle Positioning in Dense Urban Areas
Popovic, Z., Soloviev, A., & Mochizuki, Y. (2011) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2011-01-1035 · Cited by 7
A Method of Protein Model Classification and Retrieval Using Bag-of-Visual-Features
Ma, J., Ma, Z., Kang, B., et al. (2014) · Computational and Mathematical Methods in Medicine · doi:10.1155/2014/269394 · Cited by 7
A novel image matching algorithm based on sliding histograms of oriented gradients
Miramontes-Jaramillo, D., Kober, V. I., Diaz-Ramirez, V. H., et al. (2014) · Journal of Communications Technology and Electronics · doi:10.1134/s1064226914120146 · Cited by 7
“Parameters of the first two algorithms were taken from [1, 2].”
MethodEvaluating the robustness of feature correspondence using different feature extractors
El-Mashad, S. Y., & Shoukry, A. (2014) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2014.6957371 · Cited by 7
Disparity search range estimation based on dense stereo matching
Li, R., Ham, B., Oh, C., et al. (2013) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2013.6566468 · Cited by 7
“determined the search range based on a feature matching algorithm such as the speeded up robust features (SURF) [6].”
MethodInfluentialHuman action classification using surf based spatio-temporal correlated descriptors
Sabri, A. Q. M., Boonært, J., Lecœuche, S., et al. (2012) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2012.6467131 · Cited by 7
“Our contribution is to use their idea of spatio-temporal correlatons, and combine it with the usage of SURF based video-words based on the works of [3].”
MethodInfluentialFrame feature tracking for speed estimation
Bandara, Y. M. P. C. Y., Niroshika, U. A. A., & Abeygunawardhane, T. U. (2014) · International Conference on Advances in ICT for Emerging Regions · doi:10.1109/icter.2014.7083875 · Cited by 7
SLAM-Based Navigation Scheme for Pinpoint Landing on Small Celestial Body
Cocaud, C., & Kubota, T. (2012) · Advanced Robotics · doi:10.1080/01691864.2012.685227 · Cited by 7
A learning algorithm for model based object detection
Guodong, C., Xia, Z., Sun, R., et al. (2011) · International Conference on Ubiquitous Robots and Ambient Intelligence · doi:10.1109/urai.2011.6145941 · Cited by 7
Research on Image Based on Improved SURF Feature Matching
Sihang, Y. L. (2014) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid.2014.133 · Cited by 7
“Lowe [7] proposed SIFT in 2004.”
Face Matching for Post-Disaster Family Reunification
Borovikov, E., Vajda, S., Lingappa, G., et al. (2013) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi.2013.23 · Cited by 7
Deformable 3D Reconstruction with an Object Database
Alcantarilla, P. F., & Bartoli, A. (2012) · British Machine Vision Conference (BMVC) · doi:10.5244/c.26.133 · Cited by 8
Object following based on SURF for mobile robots
Huang, P.-T., Li, C.-Y., Hsu, C.-C. J., et al. (2012) · doi:10.1109/gcce.2012.6379634 · Cited by 7
Performance evaluation of whole-image descriptors in visual loop closure detection
Liu, Y., & Zhang, H. (2013) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2013.6720388 · Cited by 7
Image features-based mobile robot visual SLAM
Lin, R., Li, M., & Sun, L. (2013) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2013.6739847 · Cited by 7
Adaptive Feature Extraction and Image matching Based on Haar Wavelet Transform and SIFT
Zhang, M., Li, Z., -, C. Z., et al. (2012) · International Journal of Digital Content Technology and its Applications · doi:10.4156/jdcta.vol6.issue7.1 · Cited by 7
“Furthermore Bay drawn on the approximate idea used in SIFT in [10] and [11], which made the calculation speed three times faster than the conventional SIFT by using a box filter approximation of second-order Gaussian partial derivatives.”
MethodHierarchical visual mapping with omnidirectional images
Korrapati, H., Üzer, F., & Mezouar, Y. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696882 · Cited by 7
Yang, X. Y., Huang, C. X., & Cheng, K.-T. T. (2014) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2647868.2654888 · Cited by 7
“Notable results include SIFT [5] and SURF [6].”
ResultInteractive Web Video Advertising with Context Analysis and Search
Wang, B., Wang, J., Duan, L., et al. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.795 · Cited by 7
Walking support system with robust image matching for users with visual impairment
Yamamoto, K., Suganuma, K., Sugimori, D., Murotani, M., Iwamoto, T., & Matsumoto, M. (2011) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2011.6083821 · Cited by 9
“Our method therefore uses the Speed-Up Robust Features (SURF) algorithm [7][8], which identifies position, direction, and movement at any time during the daytime.”
MethodMariappan, M. B., Guo, X., & Prabhakaran, B. (2011) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2011.13 · Cited by 7
Rotation-invariant categorization of colour images using the Radon transform
Papliński, A. P. (2012) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2012.6252559 · Cited by 7
Low-Rate Image Retrieval with Tree Histogram Coding
Chandrasekha, V., Chen, D. M., Li, Z., Takacs, G., Tsai, S. S., Grzeszczuk, R., & Girod, B. (2009) · EAI International Conference on Mobile Multimedia Communications (MobiMedia) · doi:10.4108/icst.mobimedia2009.7496 · Cited by 7
A Novel Watermarking Algorithm based on SURF and SVD
Wang, W., Li, W., Wang, C., et al. (2013) · TELKOMNIKA Indonesian Journal of Electrical Engineering · doi:10.11591/telkomnika.v11i3.2305 · Cited by 7
Ranking Images Based on Aesthetic Qualities
Gaur, A., & Mikolajczyk, K. (2014) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2014.587 · Cited by 9
“SURF which is related to SIFT was later proposed, where a speed-up of the order of 3-7 can be achieved over SIFT without consequential loss of quality [14].”
MethodImproved SURF Detection Combined with Dual FLANN Matching and Clustering Analysis
Li, J. F., Wang, G., & Li, Q. (2014) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.556-562.2792 · Cited by 7
“Based on SIFT, Bay [3] proposed SURF which improves efficiency greatly while remain invariant to target rotation, scale zoom and brightness variations.”
Zhu, Z., & Davari, K. (2014) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000381 · Cited by 7
Mobile robot localization by matching 2D image features to 3D point cloud
Kim, H., Oh, T., Lee, D., et al. (2013) · International Conference on Ubiquitous Robots and Ambient Intelligence · doi:10.1109/urai.2013.6677364 · Cited by 7
Detection of cluster of microcalcifications based on watershed segmentation algorithm
Marrocco, C., Molinara, M., Tortorella, F., et al. (2012) · IEEE International Symposium on Computer-Based Medical Systems (CBMS) · doi:10.1109/cbms.2012.6266365 · Cited by 7
Human Activity Recognition Using Hierarchically-Mined Feature Constellations
Oikonomopoulos, A., & Pantić, M. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41914-0_16 · Cited by 7
Jayaraman, U., Gupta, A. K., Prakash, S., et al. (2011) · International Conference on Communications · doi:10.1109/icc.2011.5962658 · Cited by 7
“2) Preprocessing: During indexing, the features f 1 , f 2 , ..., f m are extracted for all models using SURF algorithm [19].”
MethodLearning visual object detection and localisation using icVision
Leitner, J., Harding, S., Chandrashekhariah, P., Frank, M., Förster, A., Triesch, J., & Schmidhuber, J. (2013) · Biologically Inspired Cognitive Architectures · doi:10.1016/j.bica.2013.05.009 · Cited by 12
“Various methods of detecting features in literature, such as, SIFT (Lowe, 1999) and SURF (Bay et al., 2006), as well as, the FAST corner detection algorithm (Rosten et al., 2010).”
MethodLopar, M., & Ribarič, S. (2014) · Proceedings of the Croatian Computer Vision Workshop · doi:10.20532/ccvw.2013.0010 · Cited by 7
Trinh, H.-H., Kim, D.-N., & Jo, K.-H. (2010) · Applied Intelligence · doi:10.1007/s10489-010-0221-8 · Cited by 7
Recognizing the formations of CVBG based on multiviewpoint context
Deng, C., Cao, Z., Xiao, Y., et al. (2015) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2015.140141 · Cited by 7
“First, the problem of scale and rotation invariance is often addressed in fixed coordinate systems [20, 25, 35], which cannot obtain enough information about a CVBG.”
BackgroundMobile image search with multimodal context-aware queries
Yang, X. Y., Pang, S., & Cheng, K.-T. T. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543246 · Cited by 7
On the Use of Computer Vision for Numismatic Research
Zambanini, S., Kampel, M., & Schlapke, M. (2008) · Eurographics · doi:10.2312/vast/vast08/017-024 · Cited by 7
Feature-Based Full-Frame Image Stabilization
Chung, C.-Y., & Chen, H. H. (2007) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2007.4412362 · Cited by 7
Simultaneous mapping and stereo extrinsic parameter calibration using GPS measurements
Kelly, J. W., Matthies, L. H., & Sukhatme, G. S. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980443 · Cited by 7
A new area efficient SURF hardware structure and its application to Object tracking
Do, Y.-S., & Jeong, Y.-J. (2013) · doi:10.1109/tencon.2013.6718962 · Cited by 7
A method to quantify a descriptor's illumination variance
Ross, P., English, A., Ball, D., & Corke, P. (2014) · QUT ePrints (Queensland University of Technology) · Cited by 7
Estimation of the absolute camera pose for environment recognition of industrial robotics
Schmitt, R. H., Cai, Y., & Jatzkowski, P. (2012) · Production Engineering · doi:10.1007/s11740-012-0436-0 · Cited by 7
“However, in spite of the constant further development in matching techniques (popular feature detectors are Harris [6], SIFT [17], SURF [1], etc.), the correspondencesearching acrossdifferent imagesremains a non-trivial problem [21].”
BackgroundRelative Position-Based Visual Servoing Control for Quadrotors
Tribou, M. J., Akhtar, A., & Waslander, S. L. (2012) · AIAA Guidance, Navigation, and Control Conference and Exhibit · doi:10.2514/6.2012-5049 · Cited by 7
FT-RANSAC: Towards robust multi-modal homography estimation
Barclay, A., & Kaufmann, H. (2014) · IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS) · doi:10.1109/prrs.2014.6914290 · Cited by 7
Metadata
- Authors
- Bay, H., Tuytelaars, T., & Van Gool, L.
- Affiliations
- ETH Zurich (CH)
- KU Leuven (BE)
- ORCID
- Tuytelaars, Tinne
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2006
- Pages
- 404-417
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1677409904
- Semantic Scholar
- 9ad3179098eb9ac7f0c81bf89b6bdcde91752880
- Cited by
- 14,955
- References
- 39
- Citations by year
- 2026: 210 · 2025: 519 · 2024: 727 · 2023: 757 · 2022: 878 · 2021: 975 · 2020: 978 · 2019: 1036 · 2018: 968 · 2017: 976 · 2016: 930 · 2015: 1079 · 2014: 1006 · 2013: 982 · 2012: 884
- FWCI
- 196.80
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Lecture notes in computer science (publishedVersion)
- Lirias (KU Leuven) (submittedVersion, other-oa)
- Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Object Detection Techniques
- Keywords
- SURF, keypoint detection, feature descriptors, scale invariance, rotation invariance, integral image, Hessian matrix, feature matching, object recognition, repeatability
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.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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.