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 501–600 of 14,752
SLAM-based automatic extrinsic calibration of a multi-camera rig
Carrera, G., Angeli, A., & Davison, A. J. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980294 · Cited by 149
Robust RGB-D Odometry Using Point and Line Features
Lu, Y., & Song, D. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.448 · Cited by 126
Fault Diagnosis for Rotating Machinery: A Method based on Image Processing
Lu, C., Wang, Y., Ragulskis, M., & Cheng, Y. (2016) · PLOS ONE · doi:10.1371/journal.pone.0164111 · Cited by 130
Chest X-ray pneumothorax segmentation using U-Net with EfficientNet and ResNet architectures
Abedalla, A., Abdullah, M., Al‐Ayyoub, M., & Benkhelifa, E. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.607 · Cited by 145
LDB: An ultra-fast feature for scalable Augmented Reality on mobile devices
Yang, X., & Cheng, K.-T. T. (2012) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2012.6402537 · Cited by 148
Murtiyoso, A., & Grussenmeyer, P. (2017) · The Photogrammetric Record · doi:10.1111/phor.12197 · Cited by 129
Scene recognition: A comprehensive survey
Xie, L., Lee, F., Liu, L., Kotani, K., & Chen, Q. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107205 · Cited by 162
DeepThin: A novel lightweight CNN architecture for traffic sign recognition without GPU requirements
Haque, W. A., Arefin, S., Shihavuddin, A., & Hasan, M. A. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114481 · Cited by 142
Visual Words on Baggage X-Ray Images
Baştan, M., Yousefi, M. R., & Breuel, T. M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23672-3_44 · Cited by 127
Multiple Representations-Based Face Sketch–Photo Synthesis
Peng, C., Gao, X., Wang, N., Tao, D., Li, X., & Li, J. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2464681 · Cited by 122
Automated Method to Determine Two Critical Growth Stages of Wheat: Heading and Flowering
Sadeghi‐Tehran, P., Sabermanesh, K., Virlet, N., & Hawkesford, M. J. (2017) · Frontiers in Plant Science · doi:10.3389/fpls.2017.00252 · Cited by 151
“SIFT was replaced by SURF as an alternative technique; however, although SURF performs faster as a result of using integral images and Hessian Matrix (Bay et al., 2006); SIFT still outperformed SURF ( Table 2 ) in our experiment.”
BackgroundMethodPerception, information processing and modeling: Critical stages for autonomous driving applications
Gruyer, D., Magnier, V., Hamdi, K., Claussmann, L., Orfila, O., & Rakotonirainy, A. (2017) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2017.09.012 · Cited by 157
Scalable triangulation-based logo recognition
Kalantidis, Y., Pueyo, L. G., Trevisiol, M., van Zwol, R., & Avrithis, Y. (2011) · International Conference on Multimedia Retrieval · doi:10.1145/1991996.1992016 · Cited by 123
Image Classification and Retrieval are ONE
Xie, L., Hong, R., Zhang, B., & Tian, Q. (2015) · International Conference on Multimedia Retrieval · doi:10.1145/2671188.2749289 · Cited by 145
“Handcrafted descriptors such as SIFT [28][58] and SURF [3] are extracted on the detected regions-of-interest (ROI) of an image [29][30].”
BackgroundRoy, S., Das, N., Kundu, M., & Nasipuri, M. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.03.004 · Cited by 133
Learning Discriminative and Transformation Covariant Local Feature Detectors
Zhang, X., Yu, F. X., Karaman, S., & Chang, S. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.523 · Cited by 132
“We compare our approach to scale-covariant handcrafted feature detectors (SIFT [9], SURF [1], MSER [11], Harris Laplace (HarLap) [14] and Hessian Laplace (HesLap) [14]), and affine-covariant feature detectors (Harris Affine (HarAff) [14] and Hessian Affine (HesAff) [14]).”
BackgroundMethodZhao, Z., Qi, H., Qi, Y., Zhang, K., Zhai, Y., & Zhao, W. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2969057 · Cited by 137
Artificial intelligence in tomato leaf disease detection: a comprehensive review and discussion
Thangaraj, R., Anandamurugan, S., Pandiyan, P., & Kaliappan, V. K. (2021) · Journal of Plant Diseases and Protection · doi:10.1007/s41348-021-00500-8 · Cited by 136
“2013), Speeded Up Robust Features (SURF) (Bay et al. 2006) etc.”
MethodVideo-based raindrop detection for improved image registration
Roser, M., & Geiger, A. (2009) · 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops · doi:10.1109/iccvw.2009.5457650 · Cited by 126
“In this paper we choose the SURF feature detector [1] as a baseline, which approximates the second order image derivatives with box filters.”
MethodStatistical segmentation and structural recognition for floor plan interpretation
Heras, L.-P. D. L., Ahmed, S., Liwicki, M., Valveny, E., & Sánchez, G. (2013) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-013-0215-2 · Cited by 124
“In addition to that, the authors have also studied the performance of the system using current state-ofthe-art descriptors such as SIFT [25] and SURF [6].”
BackgroundFAB-MAP 3D: Topological mapping with spatial and visual appearance
Paul, R., & Newman, P. (2010) · 2010 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2010.5509587 · Cited by 125
Lalys, F., Riffaud, L., Bouget, D., & Jannin, P. (2012) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2011.2181168 · Cited by 121
Learning Image Descriptors with Boosting
Trzcinski, T. P., Christoudias, C. M., & Lepetit, V. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2343961 · Cited by 133
Image Feature Matching and Object Detection Using Brute-Force Matchers
Jakubovic, A., & Velagić, J. (2018) · International Symposium ELMAR (ELMAR) · doi:10.23919/elmar.2018.8534641 · Cited by 149
“The SIFT [2], [3], SURF [4], [5], BRISK [6] and ORB [7] are comprehensive algorithms able to perform both tasks.”
MethodPooling the Convolutional Layers in Deep ConvNets for Video Action Recognition
Zhao, S., Liu, Y., Han, Y., Hong, R., Hu, Q., & Tian, Q. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2682196 · Cited by 130
Efficient Framework for Palm Tree Detection in UAV Images
Malek, S., Bazi, Y., Alajlan, N., Alhichri, H. S., & Melgani, F. (2014) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2014.2331425 · Cited by 136
Feature-based terrain classification for LittleDog
Filitchkin, P., & Byl, K. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386042 · Cited by 131
“More details on this process are available in [16].”
BackgroundShape Google: a computer vision approach to isometry invariant shape retrieval
Ovsjanikov, M., Bronstein, A. M., Bronstein, M. M., & Guibas, L. J. (2009) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2009.5457682 · Cited by 124
A review of monocular visual odometry
He, M., Zhu, C., Huang, Q., Ren, B., & Liu, J. (2019) · The Visual Computer · doi:10.1007/s00371-019-01714-6 · Cited by 140
“With full consideration to all kinds of problems on the process of image transformation, speeded-up robust features (SURF) [40] and scale-invariant feature transform (SIFT) [41] still cost a lot of computation.”
Robust Learning Through Cross-Task Consistency
Zamir, A., (Sasha), A. S., Cheerla, N., Suri, R., Cao, Z., Malik, J., & Guibas, L. J. (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/cvpr42600.2020.01121 · Cited by 175
“Examples of such tasks are 2D Edges and 2D Keypoints (SURF[2]), which are included in our dictionary.”
BackgroundHigh performing ensemble of convolutional neural networks for insect pest image detection
Nanni, L., Manfè, A., Maguolo, G., Lumini, A., & Brahnam, S. (2021) · Ecological Informatics · doi:10.1016/j.ecoinf.2021.101515 · Cited by 155
Robust point matching method for multimodal retinal image registration
Wang, G., Wang, Z., Chen, Y., & Zhao, W. (2015) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2015.03.004 · Cited by 124
SURF-Face: Face Recognition Under Viewpoint Consistency Constraints
Dreuw, P., Steingrube, P., Hanselmann, H., & Ney, H. (2009) · British Machine Vision Conference (BMVC) · doi:10.5244/c.23.7 · Cited by 138
CytoBrain: Cervical Cancer Screening System Based on Deep Learning Technology
Chen, H., Liu, J., Wen, Q.-M., Zuo, Z., Liu, J.-S., Feng, J. Q., Pang, B., & Xiao, D. (2021) · Journal of Computer Science and Technology · doi:10.1007/s11390-021-0849-3 · Cited by 138
“First, we utilize the SURF (Speeded-Up Robust Features) algorithm [23] to detect feature points that are used for locating nuclei in the WSI (Fig.”
MethodPractice makes perfect? Managing and leveraging visual experiences for lifelong navigation
Churchill, W., & Newman, P. (2012) · 2012 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2012.6224596 · Cited by 120
Local feature extraction and matching on range images: 2.5D SIFT
Lo, T.-W. R., & Siebert, J. P. (2009) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2009.06.005 · Cited by 131
SfM for Orthophoto to Generation: A Winning Approach for Cultural Heritage Knowledge
Chiabrando, F., Donadio, E., & Rinaudo, F. (2015) · 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-5-w7-91-2015 · Cited by 123
Keypoint design and evaluation for place recognition in 2D lidar maps
Bosse, M. C., & Zlot, R. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2009.07.009 · Cited by 132
Three-Dimensional Tracking of Construction Resources Using an On-Site Camera System
Park, M.-W., Koch, C., & Brilakis, I. (2011) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000168 · Cited by 125
A Novel Image Retrieval Based on Visual Words Integration of SIFT and SURF
Ali, N., Bajwa, K. B., Sablatnig, R., Chatzichristofis, S. A., Iqbal, Z., Rashid, M., & Habib, H. A. (2016) · PLoS ONE · doi:10.1371/journal.pone.0157428 · Cited by 122
Color texture description with novel local binary patterns for effective image retrieval
Singh, C., Walia, E., & Kaur, K. P. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.021 · Cited by 131
Detecting and Mitigating Adversarial Perturbations for Robust Face Recognition
Goswami, G., Agarwal, A., Ratha, N., Singh, R., & Vatsa, M. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-019-01160-w · Cited by 127
“Recently, Boulkenafet et al. (2017) have proposed a detection methodology using Fisher vector encoding and speeded-up robust features (SURF) (Bay et al. 2006) for spoofing attack detection with limited training data for a generalizable methodology that works well on unseen databases.”
MethodVisual SLAM for robot navigation in healthcare facility
Fang, B., Mei, G., Yuan, X., Wang, L., Wang, Z., & Wang, J. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107822 · Cited by 137
A Systematic Review of Drone Based Road Traffic Monitoring System
Bisio, I., Garibotto, C., Haleem, H., Lavagetto, F., & Sciarrone, A. (2022) · IEEE Access · doi:10.1109/access.2022.3207282 · Cited by 139
“Similarly, in [71] images are also divided into patches, where only areas con-796 taining objects were selected using SURF algorithm [19] for the training purpose.”
MethodEvaluating spatiotemporal interest point features for depth-based action recognition
Zhu, Y. M., Chen, W., & Guo, G. (2014) · Image and Vision Computing · doi:10.1016/j.imavis.2014.04.005 · Cited by 121
Globally consistent registration of terrestrial laser scans via graph optimization
Theiler, P. W., Wegner, J. D., & Konrad Schindler, B. (2015) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2015.08.007 · Cited by 130
Facade: Auto-generating Tactile Interfaces to Appliances
Guo, A., Kim, J., Chen, X. '., Yeh, T., Hudson, S. E., Mankoff, J., & Bigham, J. P. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025845 · Cited by 122
Assessment of Deep Convolutional Neural Networks for Road Surface Classification
Nolte, M., Kister, N., & Maurer, M. (2018) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2018.8569396 · Cited by 134
CAT-SLAM: probabilistic localisation and mapping using a continuous appearance-based trajectory
Maddern, W., Milford, M., & Wyeth, G. (2012) · The International Journal of Robotics Research · doi:10.1177/0278364912438273 · Cited by 118
Steder, B., Ruhnke, M., Grzonka, S., & Burgard, W. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094638 · Cited by 116
Performance Evaluation of Full Search Equivalent Pattern Matching Algorithms
Ouyang, W., Tombari, F., Mattoccia, S., Stefano, L. D., & Cham, W.-K. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.106 · Cited by 130
Semi-Supervised Optimal Transport for Heterogeneous Domain Adaptation
Yan, Y., Li, W., Wu, H., Min, H., Tan, M., & Wu, Q. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/412 · Cited by 114
Ai, J., Mao, Y., Luo, Q., Jia, L., & Xing, M. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3106915 · Cited by 166
“…features, various feature extraction operators are designed, such as histograms of oriented gradients (HOG) [20], scale-invariant feature transform (SIFT) [21], speeded up robust features (SURF) [22], local binary pattern (LBP) [23], completed local binary pattern (CLBP) [24], and haar-like [25].”
BackgroundKaur, P., Singh, G., & Kaur, P. (2019) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2019.01.001 · Cited by 125
Scene Signatures: Localised and Point-less Features for Localisation
McManus, C., Upcroft, B., & Newmann, P. (2014) · Robotics: Science and Systems X · doi:10.15607/rss.2014.x.023 · Cited by 117
Categorizing Dynamic Textures Using a Bag of Dynamical Systems
Ravichandran, A., Chaudhry, R., & Vidal, R. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.83 · Cited by 115
Wang, K., Liu, Y., & Li, L. (2014) · IEEE Transactions on Robotics · doi:10.1109/tro.2014.2317891 · Cited by 119
A comparative study of image low level feature extraction algorithms
El-Gayar, M. M., Soliman, H., & Mekky, N. E. (2013) · Egyptian Informatics Journal · doi:10.1016/j.eij.2013.06.003 · Cited by 119
Learning to Assign Orientations to Feature Points
Yi, K. M., Verdié, Y., Fua, P., & Lepetit, V. (2016) · 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.2016.19 · Cited by 138
Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey
Naseer, M., Khan, S. S., & Porikli, F. (2018) · IEEE Access · doi:10.1109/access.2018.2886133 · Cited by 156
Hwang, S., & Sugiyama, J. (2021) · Plant Methods · doi:10.1186/s13007-021-00746-1 · Cited by 156
“…wood identification performance of each model trained with well-known local feature extraction algorithms: SIFT, speeded up robust features (SURF) [19], oriented features-from-accelerated-segment-test (FAST), rotated binary-robust-independent-elementary-feature (BRIEF) (ORB) [126], and…”
BackgroundMethodRecent developments and applications of simultaneous localization and mapping in agriculture
Ding, H., Zhang, B., Zhou, J. C., Yan, Y., Tian, G., & Gu, B. (2022) · Journal of Field Robotics · doi:10.1002/rob.22077 · Cited by 146
A Novel Scenarios Engineering Methodology for Foundation Models in Metaverse
Li, X., Tian, Y., Ye, P., Duan, H., & Wang, F.-Y. (2023) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2022.3228594 · Cited by 119
STD: Stable Triangle Descriptor for 3D place recognition
Yuan, C., Lin, J., Zou, Z., Hong, X., & Zhang, F. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160413 · Cited by 176
Aggregating gradient distributions into intensity orders: A novel local image descriptor
Fan, B., Wu, F., & Hu, Z. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995385 · Cited by 117
Effect of human guidance and state space size on Interactive Reinforcement Learning
Suay, H. B., & Chernova, S. (2011) · IEEE RO-MAN · doi:10.1109/roman.2011.6005223 · Cited by 118
Learning an Invariant Hilbert Space for Domain Adaptation
Herath, S., Harandi, M. T., & Porikli, F. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.421 · Cited by 123
Creating Autonomous Vehicle Systems
Liu, S., Li, L., Tang, J., Wu, S., & Gaudiot, J. (2017) · Synthesis lectures on computer science · doi:10.2200/s00787ed1v01y201707csl009 · Cited by 135
GPS-Denied UAV Localization using Pre-existing Satellite Imagery
Goforth, H., & Lucey, S. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793558 · Cited by 124
“After solving for the optimal motion parameters, we convert them to GPS coordinates (latitude, longitude, and altitude) and plot error from ground truth, versus SURF odometry.”
MethodInfluentialTextRS: Deep Bidirectional Triplet Network for Matching Text to Remote Sensing Images
Abdullah, T., Bazi, Y., Rahhal, M. M. A., Mekhalfi, M. L., Rangarajan, L., & Zuair, M. (2020) · Remote Sensing · doi:10.3390/rs12030405 · Cited by 134
“There are various algorithms for describing local image regions such as the scale-invariant feature transform (SIFT) and speed up robust features (SURF) [19,20].”
Barnes, D., & Posner, I. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196835 · Cited by 140
Satellite and Scene Image Classification Based on Transfer Learning and Fine Tuning of ResNet50
Shabbir, A., Ali, N., Ahmed, J., Zafar, B., Rasheed, A., Sajid, M., Ahmed, A., & Dar, S. H. (2021) · Mathematical Problems in Engineering · doi:10.1155/2021/5843816 · Cited by 152
“In last two decades, extensive efforts are exerted by computer vision research community to develop the discriminating features such as Scale-Invariant Feature Transformation (SIFT) [21], Speeded-up Robust Features (SURF) [22], Histogram of Oriented Gradients (HOG) [23], and Maximally Stable Extremal Regions (MSER) [2…”
BackgroundBoW3D: Bag of Words for Real-Time Loop Closing in 3D LiDAR SLAM
Cui, Y., Chen, X., Zhang, Y., Dong, J., Wu, Q., & Zhu, F. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3221336 · Cited by 140
A new approach to vision-aided inertial navigation
Tardif, J.-P., George, M., Laverne, M., Kelly, A., & Stentz, A. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5651059 · Cited by 137
OverLay: Practical Mobile Augmented Reality
Jain, P., Manweiler, J., & Roy Choudhury, R. (2015) · Proceedings of the 13th Annual International Conference on Mobile Systems, Applications, and Services · doi:10.1145/2742647.2742666 · Cited by 116
Retrieving landmark and non-landmark images from community photo collections
Avrithis, Y., Kalantidis, Y., Tolias, G., & Spyrou, E. (2010) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1873951.1873973 · Cited by 121
“We have extracted SURF features and descriptors [2] and kept a maximum of 1, 000 features per image.”
MethodA review of visual moving target tracking
Pan, Z. Y., Liu, S., & Fu, W. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3647-0 · Cited by 120
Visual SLAM: What Are the Current Trends and What to Expect?
Tourani, A., Bavle, H., Sánchez-López, J. L., & Voos, H. (2022) · Sensors · doi:10.3390/s22239297 · Cited by 155
Stable Structure from Motion for Unordered Image Collections
Olsson, C., & Enqvist, O. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21227-7_49 · Cited by 112
Handling motion blur in multi-frame super-resolution
Ma, Z., Liao, R., Tao, X., Xu, L., Jia, J., & Wu, E. (2015) · 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.2015.7299159 · Cited by 127
“This is done via estimating homography matrices using RANSAC with a combination of SURF [1] and KLT [20] features, followed by a TV-L1 optical flow estimation [2, 21].”
MethodAshok, A., Gruteser, M., Mandayam, N. B., et al. (2010) · doi:10.1145/1859995.1860008 · Cited by 116
“Another example of SIFT variations is the SURF method [7] which achieve a 200ms computation speed for a typical image.”
MethodFlitton, G. T., Breckon, T. P., & Megherbi, N. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.02.008 · Cited by 123
“…the scale invariance challenge addressed by various interest point feature descriptors in 2D [12–14] and additionally the unpredictable nature of the metal artefacts to be akin to that of recognition in the presence of occlusion – an area in which such interest point detectors [12–14] perform well.”
BackgroundModeling and Understanding Visual Attributes of Mental Health Disclosures in Social Media
Manikonda, L., & De Choudhury, M. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025932 · Cited by 116
Efficient Discriminative Projections for Compact Binary Descriptors
Trzcinski, T. P., & Lepetit, V. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33718-5_17 · Cited by 125
Passieux, J., Bugarin, F., David, C., Périé, J., & Robert, L. (2014) · Experimental Mechanics · doi:10.1007/s11340-014-9872-4 · Cited by 127
Different Approaches for Extracting Information from the Co-Occurrence Matrix
Nanni, L., Brahnam, S., Ghidoni, S., Menegatti, E., & Barrier, T. (2013) · PLoS ONE · doi:10.1371/journal.pone.0083554 · Cited by 123
Zero-Shot Event Detection Using Multi-modal Fusion of Weakly Supervised Concepts
Wu, S., Bondugula, S., Luisier, F., Zhuang, X., & Natarajan, P. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.341 · Cited by 111
Feature-Based Deformable Surface Detection with Self-Occlusion Reasoning
Pizarro, D., & Bartoli, A. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-011-0452-0 · Cited by 113
“There exist several feature detectors and wide-baseline matching procedure in the literature, such as SIFT [10] and SURF [4].”
MethodMachine Learning for Plant Disease Incidence and Severity Measurements from Leaf Images
Mwebaze, E., & Owomugisha, G. (2016) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2016.0034 · Cited by 143
Random Matrix Based Extended Target Tracking With Orientation: A New Model and Inference
Tuncer, B., & Özkan, E. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3065136 · Cited by 115
“Various feature extraction algorithms can be used to obtain measurements from the vehicle such as Harris corner detection [35], Scale Invariant Feature Transform (SIFT) [36], Speeded Up Robust Features (SURF) [37] or similar.”
MethodStructure-Preserving Binary Representations for RGB-D Action Recognition
Yu, M., Liu, L., & Shao, L. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2491925 · Cited by 112
“As 3D versions of SURF [25], SIFT [8] and HOF [11], 3D speeded up robust features (SURF3D) [26], 3D scale invariant feature transforms (3D-SIFT) [27] and 3D motion features [28], [29] have been proposed for action recognition respectively.”
MethodFace detection using SURF cascade
Li, J., Wang, T., & Zhang, Y. (2011) · 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops) · doi:10.1109/iccvw.2011.6130518 · Cited by 112
“SURF (Speeded Up Robust Features) is a detector and descriptor of local scale- and rotation- invariant image features [1].”
BackgroundMethodInfluentialSOLAR: Second-Order Loss and Attention for Image Retrieval
Ng, T., Balntas, V., Tian, Y., & Mikolajczyk, K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58595-2_16 · Cited by 141
“these methods into global single-pass. Local Aggregation methods generally consist of two steps. First, local features are detected and described by hand-crafted operators such as SIFT [25] and SURF [9], or CNN-based local descriptors [4,31]. Second, the descriptors are combined into a compact vector. Early works on B…”
MethodBEBLID: Boosted efficient binary local image descriptor
Suárez, I., Sfeir, G., Buenaposada, J. M., & Baumela, L. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.04.005 · Cited by 128
Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey
Arshad, S., & Kim, G.-W. (2021) · Sensors · doi:10.3390/s21041243 · Cited by 115
Kernel Methods in Computer Vision
Lampert, C. H. (2009) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000027 · Cited by 133
A comparative experimental study of image feature detectors and descriptors
Mukherjee, D., Wu, Q. M. J., & Wang, G. (2015) · Machine Vision and Applications · doi:10.1007/s00138-015-0679-9 · Cited by 126
FLIRT - Interest regions for 2D range data
Tipaldi, G. D., & Arras, K. O. (2010) · 2010 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2010.5509864 · Cited by 112
Mobile Visual Location Recognition
Schroth, G., Huitl, R., Chen, D. M., Abu-Alqumsan, M., Al-Nuaimi, A., & Steinbach, E. G. (2011) · IEEE Signal Processing Magazine · doi:10.1109/msp.2011.940882 · Cited by 112
Multiclass transfer learning from unconstrained priors
Luo, J., Tommasi, T., & Caputo, B. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126454 · Cited by 121
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.