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 401–500 of 14,752
Phishing or Not Phishing? A Survey on the Detection of Phishing Websites
Zieni, R., Massari, L., & Calzarossa, M. C. (2023) · IEEE Access · doi:10.1109/access.2023.3247135 · Cited by 158
“Techniques, such as Scale-Invariant Feature Transform (SIFT) [62], Speeded-Up Robust Features (SURF) [63], Contrast Context Histogram (CCH) [64], are applied to detect keypoints and construct descriptors of their visual characteristics.”
MethodFacial Sentiment Analysis Using AI Techniques: State-of-the-Art, Taxonomies, and Challenges
Patel, K., Mehta, D., Mistry, C., Gupta, R., Tanwar, S., Kumar, N., & Alazab, M. (2020) · IEEE Access · doi:10.1109/access.2020.2993803 · Cited by 157
“From this selected orientation, we make a squared region, and the SURF descriptor is extracted [114].”
MethodFully affine invariant SURF for image matching
Pang, Y., Li, W., Yuan, Y., & Pan, J. S. (2012) · Neurocomputing · doi:10.1016/j.neucom.2011.12.006 · Cited by 156
High-Performance SIFT Hardware Accelerator for Real-Time Image Feature Extraction
Huang, F. S., Huang, S., Ker, J.-W., & Chen, Y. (2011) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2011.2162760 · Cited by 156
Khaliq, A., Ehsan, S., Chen, Z., Milford, M. J., & McDonald-Maier, K. D. (2019) · IEEE Transactions on Robotics · doi:10.1109/tro.2019.2956352 · Cited by 182
LATCH: Learned arrangements of three patch codes
Levi, G., & Hassner, T. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477723 · Cited by 182
Chen, L., Tang, W. J., John, N. W., Wan, T. R., & Zhang, J. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.02.006 · Cited by 175
“Since ORB [40] is a binary feature point descriptor, it is an order of magnitude faster than SURF [1] and more than two orders faster than SIFT [27] with better accuracy.”
Deep Homography Estimation for Dynamic Scenes
Le, H. M., Liu, F., Zhang, S., & Agarwala, A. (2020) · 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/cvpr42600.2020.00767 · Cited by 192
Verma, M., & Raman, B. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4834-3 · Cited by 165
“ciently compute a rough approximation of the Hessian matrix [4].”
BackgroundMethodVisual and Visual‐Inertial SLAM: State of the Art, Classification, and Experimental Benchmarking
Servières, M., Renaudin, V., Dupuis, A., & Antigny, N. (2021) · Journal of Sensors · doi:10.1155/2021/2054828 · Cited by 181
TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
Doersch, C., Yang, Y., Vecerik, M., Gokay, D., Gupta, A., Aytar, Y., Carreira, J., & Zisserman, A. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00923 · Cited by 161
“Keypoint Correspondence methods aim at sparse keypoint matching given image pairs, from hand-defined discriminative feature descriptors [3, 36, 37, 57] to deep learning based methods [12, 29, 39, 45].”
MethodLarge-Margin Multi-Modal Deep Learning for RGB-D Object Recognition
Wang, A., Lu, J., Cai, J., Cham, T.-J., & Wang, G. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2476655 · Cited by 153
Multiple 3D Object tracking for augmented reality
Park, Y., Lepetit, V., & Woo, W. (2008) · 2008 7th IEEE/ACM International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2008.4637336 · Cited by 143
“Other methods for this wide baseline matching, or recognition, of feature points are available [5, 1], but [8] is very simple to implement and very fast.”
MethodLocal Transform Features and Hybridization for Accurate Face and Human Detection
Jun, B., Choi, I., & Kim, D. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.219 · Cited by 165
Abbas, Q., Fondón, I., Sarmiento, A., Jiménez, S., & Alemany, P. (2017) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-017-1638-6 · Cited by 166
Luo, X., Li, H., Cao, D., Yu, Y., Yang, X., & Huang, T. (2018) · Automation in Construction · doi:10.1016/j.autcon.2018.07.011 · Cited by 152
ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive BiasPreprint
Xu, Y., Zhang, Q., Zhang, J., & Tao, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.03348 · Cited by 228
POEM: Power-efficient occupancy-based energy management system
Erickson, V. L., Achleitner, S., & Cerpa, A. E. (2013) · International Symposium on Information Processing in Sensor Networks · doi:10.1145/2461381.2461407 · Cited by 191
Qian, J., Zi, B., Wang, D., Ma, Y., & Zhang, D. (2017) · Sensors · doi:10.3390/s17092073 · Cited by 166
Critical Design and Control Issues of Indoor Autonomous Mobile Robots: A Review
Niloy, M. A., Shama, A., Chakrabortty, R. K., Ryan, M. J., Badal, F. R., Tasneem, Z., Ahamed, M. H., Moyeen, S. I., Das, S. K., Ali, M. F., et al. (2021) · IEEE Access · doi:10.1109/access.2021.3062557 · Cited by 189
A review of computer vision-based approaches for physical rehabilitation and assessment
Debnath, B., O'Brien, M. R., Yamaguchi, M., & Behera, A. (2021) · Multimedia Systems · doi:10.1007/s00530-021-00815-4 · Cited by 185
PVNet: Pixel-Wise Voting Network for 6DoF Object Pose Estimation
Peng, S., Zhou, X., Liu, Y., Lin, H., Huang, Q., & Bao, H. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3047388 · Cited by 172
Vision‐Based Fatigue Crack Detection of Steel Structures Using Video Feature Tracking
Kong, X., & Li, J. (2018) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12353 · Cited by 157
SUES-200: A Multi-Height Multi-Scene Cross-View Image Benchmark Across Drone and Satellite
Zhu, R., Yin, L., Yang, M., Wu, F., Yang, Y., & Hu, W. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3249204 · Cited by 246
OuluVS2: A multi-view audiovisual database for non-rigid mouth motion analysis
Anina, I., Zhou, Z., Zhao, G., & Pietikainen, M. (2015) · 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG) · doi:10.1109/fg.2015.7163155 · Cited by 147
“We then calculated the SURF features from images, matched the feature points and estimated the image transformation matrix for each pair of consecutive images [20].”
MethodMulti-modal Semantic Place Classification
Pronobis, A., Martínez Mozos, O., Caputo, B., & Jensfelt, P. (2010) · The International Journal of Robotics Research · doi:10.1177/0278364909356483 · Cited by 149
Visual and semantic similarity in ImageNet
Deselaers, T., & Ferrari, V. (2011) · 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.2011.5995474 · Cited by 169
Domain Adaptation on the Statistical Manifold
Baktashmotlagh, M., Harandi, M. T., Lovell, B. C., & Salzmann, M. (2014) · 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.2014.318 · Cited by 149
Visual domain adaptation via transfer feature learning
Tahmoresnezhad, J., & Hashemi, S. (2016) · Knowledge and Information Systems · doi:10.1007/s10115-016-0944-x · Cited by 153
Cachier: Edge-Caching for Recognition Applications
Drolia, U., Guo, K., Tan, J., Gandhi, R., & Narasimhan, P. (2017) · 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2017.94 · Cited by 148
“Some notable local features are SIFT [28], SURF [13] and ORB [34].”
BackgroundExemplar-Based Image Inpainting Using Multiscale Graph Cuts
Liu, Y., & Caselles, V. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2218828 · Cited by 162
Visual inspection of hydroelectric dams using an autonomous underwater vehicle
Ridao, P., Carreras, M., Ribas, D., & García, R. (2010) · Journal of Field Robotics · doi:10.1002/rob.20351 · Cited by 152
Zaffar, M., Garg, S., Milford, M. J., Kooij, J. F. P., Flynn, D., McDonald-Maier, K. D., & Ehsan, S. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01469-5 · Cited by 212
“The most popular lo-cal feature descriptors developed in the vision community include Scale Invariant Feature Transform (SIFT Lowe (2004)) and Speeded Up Robust Features (SURF Bay et al. (2006)).”
BackgroundPerception and Navigation in Autonomous Systems in the Era of Learning: A Survey
Tang, Y. S., Zhao, C., Wang, J., Zhang, C., Sun, Q., Zheng, W. X., Du, W., Qian, F., & Kurths, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3167688 · Cited by 199
Data Fusion: Concepts and Ideas
Mitchell, H. B. (2012) · Springer eBooks · doi:10.1007/978-3-642-27222-6 · Cited by 177
Vision-based place recognition: how low can you go?
Milford, M. J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913490323 · Cited by 143
“Many of the state of the art feature detectors such as scale-invariant feature transforms (SIFT) (Lowe, 1999) and speeded up robust features (SURF) (Bay et al., 2006) exhibit desirable properties such as scale and rotation invariance, and a limited degree of illumination invariance.”
BackgroundCompressed Histogram of Gradients: A Low-Bitrate Descriptor
Chandrasekhar, V., Gabriel Takacs, A., Chen, D. M., Tsai, S. S., Reznik, Y. A., Grzeszczuk, R., & Girod, B. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-011-0453-z · Cited by 143
Tracklet Descriptors for Action Modeling and Video Analysis
Raptis, M., & Soatto, S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15549-9_42 · Cited by 147
“2 Simplest instantiation and inference of the representation Following the derivation above, given a video sequence {I(x, t), x ∈ Ω}t=1, we first select candidate regions via any feature detector [23, 10, 1], and track them over time using a contrast-compensated translational tracker to obtain a number of trajectories…”
MethodDynamically partitioning applications between weak devices and clouds
Chun, B.-G., & Maniatis, P. (2010) · doi:10.1145/1810931.1810938 · Cited by 145
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
Țapu, R., Mocanu, B., Bursuc, A., & Zaharia, T. B. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.65 · Cited by 146
OpenRatSLAM: an open source brain-based SLAM system
Ball, D., Heath, S., Wiles, J., Wyeth, G. F., Corke, P., & Milford, M. J. (2013) · Autonomous Robots · doi:10.1007/s10514-012-9317-9 · Cited by 152
“At their core, most approaches are based on detecting conventional visual features, such as SIFT (Lowe 1999) or SURF (Bay et al. 2006), extracted from relatively high resolution monocular or stereo vision images.”
MethodAn efficient technique for object recognition using Shi-Tomasi corner detection algorithm
Bansal, M., Kumar, M., Kumar, M., & Kumar, K. (2020) · Soft Computing - A Fusion of Foundations, Methodologies and Applications · doi:10.1007/s00500-020-05453-y · Cited by 136
“SURF was introduced by Bay et al. (2006) for object recognition.”
MethodRodríguez-Canosa, G. R., Thomas, S., del Cerro, J., Barrientos, A., & MacDonald, B. A. (2012) · Remote Sensing · doi:10.3390/rs4041090 · Cited by 148
As-rigid-as-possible mosaicking and serial section registration of large ssTEM datasets
Saalfeld, S., Cardona, A., Hartenstein, V., & Tomančák, P. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btq219 · Cited by 143
AutoFocus: Efficient Multi-Scale Inference
Najibi, M., Singh, B., & Davis, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00984 · Cited by 137
“Classic features like SIFT [43] / SURF [2], combine two major components - the detector and the descriptor.”
MethodArtieda, J., Sebastian, J. M., Campoy, P., Correa, J. F., Mondragon, I. F., Martínez, C., & Olivares, M. (2009) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-008-9304-8 · Cited by 177
Registration of Multimodal Remote Sensing Image Based on Deep Fully Convolutional Neural Network
Zhang, H., Ni, W., Yan, W., Xiang, D., Wu, J., Yang, X., & Hui, B. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2916560 · Cited by 154
“[3] H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded up robust features,” in Proc.”
BackgroundMethodInfluentialGraphical Representation for Heterogeneous Face Recognition
Peng, C., Gao, X., Wang, N., & Li, J. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2542816 · Cited by 144
Image processing and recognition for biological images
Uchida, S. (2013) · Development Growth & Differentiation · doi:10.1111/dgd.12054 · Cited by 168
“In their paper, DoG, Harris-Affine, and Hessian-Affine are used as detectors, and SIFT (Scale-Invariant Feature Transform), SURF (Speeded Up Robust Features) (Bay et al. 2006) and their extensions, shape and context, are used as descriptors.”
MethodLNIFT: Locally Normalized Image for Rotation Invariant Multimodal Feature Matching
Li, J., Xu, W., Shi, P., Zhang, Y., & Hu, Q. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3165940 · Cited by 193
“, scale-invariant feature transform (SIFT) [1], speededup robust features (SURF) [2], and shape context [3]) are only suitable for same-source images with linear radiation distortions [4], [5].”
BackgroundMethodInfluentialSIFT, SURF and seasons : long-term outdoor localization using local features
Valgren, C., & Lilienthal, A. J. (2007) · DiVA (Digitala Vetenskapliga Arkivet) · Cited by 170
Visual topometric localization
Badino, H., Huber, D., & Kanade, T. (2011) · 2011 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2011.5940504 · Cited by 141
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
Multiple Hypotheses Image Segmentation and Classification With Application to Dietary Assessment
Zhu, F. M., Bosch, M., Khanna, N., Boushey, C. J., & Delp, E. J. (2014) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2014.2304925 · Cited by 159
Video pornography detection through deep learning techniques and motion information
Pérez, M., Avila, S., Moreira, D., Moraes, D., Testoni, V., Junior, E. A. D. V., Goldenstein, S. K., & Rocha, A. D. R. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.12.017 · Cited by 159
“More recently, Moreira et al. [16] proposed the Temporal Robust Features (TroF), a fast spatio-temporal interest point detector and descriptor, which is directly inspired by the still-image Speeded-Up Robust Features (SURF) [53].”
A Novel Two-Step Registration Method for Remote Sensing Images Based on Deep and Local Features
Ma, W., Zhang, J., Wu, Y., Jiao, L., Zhu, H., & Zhao, W. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2893310 · Cited by 150
Review on image-stitching techniques
Wang, Z., & Yang, Z. (2020) · Multimedia Systems · doi:10.1007/s00530-020-00651-y · Cited by 146
“SURF, a robust image recognition algorithm, was firstly proposed in 2006 [61].”
Thrift: Local 3D Structure Recognition
Flint, A., Dick, A., & van den Hengel, A. (2007) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2007.4426794 · Cited by 152
“Several techniques such as the Harris corner detector, and more recently SURF [1], have been developed to identify these points.”
MethodFlip-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
Neuropathic pain caused by miswiring and abnormal end organ targeting
Gangadharan, V., Zheng, H., Taberner, F. J., Landry, J. J. M., Nees, T. A., Pistolic, J., Agarwal, N., Männich, D., Beneš, V., Helmstaedter, M. N., et al. (2022) · Nature · doi:10.1038/s41586-022-04777-z · Cited by 153
Computer-aided colorectal tumor classification in NBI endoscopy using local features
Tamaki, T., Yoshimuta, J., Kawakami, M., Raytchev, B., Kaneda, K., Yoshida, S., Takemura, Y., Onji, K., Miyaki, R., & Tanaka, S. (2012) · Medical Image Analysis · doi:10.1016/j.media.2012.08.003 · Cited by 158
Combining Scale-Space and Similarity-Based Aspect Graphs for Fast 3D Object Recognition
Ulrich, M., Wiedemann, C., & Steger, C. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.266 · Cited by 136
Content-based processing and analysis of endoscopic images and videos: A survey
Münzer, B., Schoeffmann, K., & Böszörményi, L. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-016-4219-z · Cited by 152
Image Quality Assessment Using Human Visual DOG Model Fused With Random Forest
Pei, S.-C., & Chen, L.-H. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2440172 · Cited by 132
Real-time loop detection with bags of binary words
Gálvez‐López, D., & Tardós, J. D. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094885 · Cited by 158
Event detection and recognition for semantic annotation of video
Ballan, L., Bertini, M., Bimbo, A. D., Seidenari, L., & Serra, G. (2010) · Multimedia Tools and Applications · doi:10.1007/s11042-010-0643-7 · Cited by 159
Vision-based Navigation in Image-Guided Interventions
Mirota, D. J., Ishii, M., & Hager, G. D. (2011) · Annual Review of Biomedical Engineering · doi:10.1146/annurev-bioeng-071910-124757 · Cited by 137
Learning Spread-Out Local Feature Descriptors
Zhang, X., Yu, F. X., Kumar, S., & Chang, S.-F. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.492 · Cited by 132
Active Shape Models with SIFT Descriptors and MARS
Milborrow, S., & Nicolls, F. (2014) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004680003800387 · Cited by 166
Fast SIFT Design for Real-Time Visual Feature Extraction
Chiu, L.-C., Chang, T., Chen, J.-Y., et al. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2259841 · Cited by 136
Video Caching, Analytics, and Delivery at the Wireless Edge: A Survey and Future Directions
Jedari, B., Premsankar, G., Illahi, G. K., Francesco, M. D., Mehrabi, A., & Ylä-Jääski, A. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3035427 · Cited by 155
A Computer Vision based Framework for Visual Gun Detection Using Harris Interest Point Detector
Tiwari, R. K., & Verma, G. K. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.06.083 · Cited by 134
The stanford mobile visual search data set
Chandrasekhar, V., Chen, D. M., Tsai, S. S., Cheung, N. M., Chen, H., Takacs, G., Reznik, Y. A., Vedantham, R., Grzeszczuk, R., Bach, J., et al. (2011) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/1943552.1943568 · Cited by 144
VizWiz::LocateIt - enabling blind people to locate objects in their environment
Bigham, J. P., Jayant, C., Miller, A., White, B., & Yeh, T. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops · doi:10.1109/cvprw.2010.5543821 · Cited by 135
“In the first scheme, a homography between each captured frame and the overview image is computed based on the correspondences of SURF features [21].”
MethodCombining Harris interest points and the SIFT descriptor for fast scale-invariant object recognition
Azad, P., Asfour, T., & Dillmann, R. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354611 · Cited by 150
Accurate Detection and Recognition of Dirty Vehicle Plate Numbers for High-Speed Applications
Panahi, R., & Gholampour, I. (2016) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2016.2586520 · Cited by 153
Cvišić, I., Ćesić, J., Marković, I., & Petrović, I. (2018) · Journal of Field Robotics · doi:10.1002/rob.21762 · Cited by 133
Fast and robust dynamic hand gesture recognition via key frames extraction and feature fusion
Tang, H., Liu, H., Wei, X., & Sebe, N. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.11.038 · Cited by 149
All-environment visual place recognition with SMART
Pepperell, E., Corke, P., & Milford, M. J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907067 · Cited by 131
“The use of features in such systems, such as SIFT [15] and SURF [16] allows invariance to scale and rotation, but leads to poor performance across extreme perceptual change [9].”
MethodZhu, C., Bichot, C., & Chen, L. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.01.003 · Cited by 142
“The color OC-LBP descriptors outperform CS-LBP, SURF, HOG, SIFT, as well as the intensity-based OC-LBP, and achieve comparable results with the color SIFT descriptors.”
MethodInfluentialFast scale invariant feature detection and matching on programmable graphics hardware
Cornelis, N., & Gool, L. V. (2008) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2008.4563087 · Cited by 134
“Although the pyramid creation proposed for SURF in [1] allows for fast filtering and parallelism at scale-level, it is not suited for an efficient GPU-implementation.”
MethodSelf-citationFrom handcrafted to learned representations for human action recognition: A survey
Zhu, F., Shao, L., Xie, J., & Fang, Y. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.06.007 · Cited by 148
Scalable Multi-View Semi-Supervised Classification via Adaptive Regression
Tao, H., Hou, C., Nie, F., Zhu, J., & Yi, D. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2717191 · Cited by 149
Search and rescue under the forest canopy using multiple UAVs
Tian, Y., Liu, K., Ok, K., Tran, L., Allen, D., Roy, N., & How, J. P. (2020) · The International Journal of Robotics Research · doi:10.1177/0278364920929398 · Cited by 167
“For visual data, popular descriptors include scale-invariant feature transform (SIFT; Lowe, 2004), speeded up robust features (SURF; Bay et al., 2006), binary robust independent elementary features (BRIEF; Calonder et al.”
MethodHRIPCB: a challenging dataset for PCB defects detection and classification
Huang, W., Peng, W., Zhang, M., & Liu, H. (2020) · The Journal of Engineering · doi:10.1049/joe.2019.1183 · Cited by 185
Introduction to the Bag of Features Paradigm for Image Classification and RetrievalPreprint
O′Hara, S., & Draper, B. A. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1101.3354 · Cited by 228
“An alternative to the SIFT descriptor that has gained increasing popularity is SURF (Speeded Up Robust Features) (Bay et al, 2006).”
MethodHeterogeneous Feature Selection With Multi-Modal Deep Neural Networks and Sparse Group LASSO
Zhao, L., Hu, Q., & Wang, W. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2477058 · Cited by 132
Reshaping Visual Datasets for Domain Adaptation
Gong, B., Grauman, K. L., & Sha, F. (2013) · neural information processing systems · Cited by 141
CODE: Coherence Based Decision Boundaries for Feature Correspondence
Lin, W.-Y., Wang, F., Cheng, M., Yeung, S.-K., Torr, P. H. S., Do, M. N., & Lu, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2652468 · Cited by 146
Content-based image retrieval with compact deep convolutional features
Alzu’bi, A., Amira, A., & Ramzan, N. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.03.072 · Cited by 146
“scale-invariant features transform (SIFT) [1] and speed-up robust features (SURF) [2] descriptors.”
Neural network Reinforcement Learning for visual control of robot manipulators
Miljković, Z., Mitić, M., Lazarević, M. P., & Babić, B. (2012) · Expert Systems with Applications · doi:10.1016/j.eswa.2012.09.010 · Cited by 136
Unified Real-Time Tracking and Recognition with Rotation-Invariant Fast Features
Gabriel Takacs, A., Chandrasekhar, V., Tsai, S. S., Chen, D. M., Grzeszczuk, R., & Girod, B. (2010) · 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.2010.5540116 · Cited by 133
Low-Rank Sparse Coding for Image Classification
Zhang, T., Ghanem, B., Liu, S., Xu, C., & Ahuja, N. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.42 · Cited by 137
A multiple-camera system calibration toolbox using a feature descriptor-based calibration pattern
Li, B., Heng, L., Köser, K., & Pollefeys, M. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696517 · Cited by 143
Chan, L., Chen, Y., Hsieh, C.-H., Liang, R.-H., & Chen, B. (2015) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/2807442.2807450 · Cited by 133
“Figure 11 shows that, once CyclopsRing activates the interaction, motion input is enabled by estimating hand movements from displacements of matched SURF features [2] in the consecutive undistorted fisheye images.”
MethodMachine Learning-based for Automatic Detection of Corn-Plant Diseases Using Image Processing
Kusumo, B. S., Heryana, A., Mahendra, O., & Pardede, H. F. (2018) · International Conference on Computer, Control, Informatics and its Applications · doi:10.1109/ic3ina.2018.8629507 · Cited by 164
“Since SIFT, SURF, and ORB are extracting local features from images, their dimensions may vary for different images.”
BackgroundMethodInfluentialDeep Learning for Retail Product Recognition: Challenges and Techniques
Wei, Y.-C., Tran, S. N., Xu, S., Kang, B. H., & Springer, M. (2020) · Computational Intelligence and Neuroscience · doi:10.1155/2020/8875910 · Cited by 183
“For the challenge of large-scale classification in Section 3, the traditional hand-crafted feature extraction methods, e.g., SIFT [24, 25] and SURF [26, 27], seem to be overtaken by the convolutional neural network (CNN) [66] due to their limitations for exploring deep information from images.”
BackgroundMethodHPatches: A benchmark and evaluation of handcrafted and learned local descriptors
Balntas, V., Lenc, K., Vedaldi, A., Tuytelaars, T., Matas, J., & Mikolajczyk, K. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2915233 · Cited by 132
“Efficient computation of features similar to SIFT [1] was targeted in SURF [49], which approximates convolutional kernels by a set of box-type filters and integral images.”
Self-citationLarge scale graph-based SLAM using aerial images as prior information
Kümmerle, R., Steder, B., Dornhege, C., Kleiner, A., Grisetti, G., & Burgard, W. (2010) · Autonomous Robots · doi:10.1007/s10514-010-9204-1 · Cited by 128
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.