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 8,401–8,500 of 14,752
siftservice.com - Turning a Computer Vision algorithm into a World Wide Web ServicePreprint
Tafti, A. P., Hassannia, H., & Yu, Z. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.02840 · Cited by 4
“We just recall that in that work [9], we employed SURF [13] instead of SIFT, but other parts would be same.”
MethodOpenHEC: A Framework for Application Programmers to Design FPGA-based SystemsPreprint
Chai, Z., Wang, Z., Yang, W., Ding, S., & Zhang, Y. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1408.5347 · Cited by 5
Learning structured concept-segments for interactive video retrieval
Wang, Z., Wang, D., Li, J., et al. (2008) · doi:10.1145/1386352.1386364 · Cited by 4
Planning and exploration in stochastic relational worlds
Lang, T. (2011) · Universitätsbibliothek der FU Berlin Hochschulschriftenstelle u. Dokumentenserver · doi:10.17169/refubium-12370 · Cited by 5
Voice Modeling Methods for Automatic Speaker Recognition
Stadelmann, T. (2010) · Publikationsserver (Universitat Marburg) · doi:10.17192/z2010.0465 · Cited by 4
Kernelized Deep Convolutional Neural Network for Describing Complex ImagesPreprint
Liu, Z. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.04581 · Cited by 5
Passive approaches for digital image forgery detection.
Pravin, K. S. M. A. (2012) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/50595 · Cited by 5
Fast point features for accurate visual odometry
Cumani, A., & Guiducci, A. (2008) · International Conference on Systems · Cited by 4
Uncalibrated stereo vision applied to breast cancer treatment aesthetic assessment
Soares, J. M. T. (2011) · Open Repository of the University of Porto (University of Porto) · doi:10.34626/w73e-br10 · Cited by 4
Transferring Visual Category Models to New Domains
Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010) · UC Berkeley · Cited by 4
Morphological and statistical techniques for the analysis of 3D images
Meinhardt-Llopis, E. (2011) · TDX (Tesis Doctorals en Xarxa) · Cited by 6
Deep Multi-Modal Image Correspondence LearningPreprint
Liu, C., Wu, J., Kohli, P., & Furukawa, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.01225 · Cited by 8
“While feature detection and matching techniques based on descriptors such as SIFT [22] and SURF [7] have been successful for narrow-baseline problems, they perform poorly for large-baseline problems.”
MethodPlace Recognition for Indoor Blind Navigation
Brett Browning, A., & Dias, M. B. (2011) · Cited by 4
Shi, Y., & Watada, J. (2015) · ICIC Express Letters · Cited by 4
Managing belief states for service robots dynamic scene perception and spatio-temporal memory
Blodow, N. (2014) · Cited by 4
Where's your focus : personalized attention
Lin, S. (2017) · doi:10.14711/thesis-991012554569603412 · Cited by 4
Liu, F. (2018) · Libraries and Cultural Resources (University of Calgary) · doi:10.11575/prism/31740 · Cited by 4
Multimodal Sparse Bayesian Dictionary LearningPreprint
Fedorov, I., & Rao, B. D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.03740 · Cited by 6
Automatic Nonrigid Histological Image Registration with Adaptive Multistep AlgorithmPreprint
Wodziński, M., & Skalski, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.00982 · Cited by 4
“In the first step, three sets of features were calculated: SIFT [2], ORB [3], SURF [4].”
MethodOptical Flow Requires Multiple Strategies (but only one network)Preprint
Schuster, T., Wolf, L., & Gadot, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.05607 · Cited by 5
LATCH: Learned Arrangements of Three Patch CodesPreprint
Levi, G., & Hassner, T. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1501.03719 · Cited by 4
Descriptor learning for omnidirectional image matchingPreprint
Masci, J., Migliore, D., Bronstein, M. M., & Schmidhuber, J. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1112.6291 · Cited by 5
Learning Feature Descriptors using Camera Pose SupervisionPreprint
Wang, Q., Zhou, X., Hariharan, B., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.13324 · Cited by 4
3D Scene Geometry-Aware Constraint for Camera Localization with Deep LearningPreprint
Tian, M., Nie, Q., & Shen, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.06147 · Cited by 4
Generative Hierarchical Features from Synthesizing ImagesPreprint
Xu, Y., Shen, Y., Zhu, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.10379 · Cited by 4
“Traditional methods used manually designed features [40, 3, 7] for pattern matching and object detection.”
MethodTiwari, V., & Jain, S. C. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3356718 · Cited by 4
Relation Preserving Triplet Mining for Stabilizing the Triplet Loss in Vehicle Re-identification.Preprint
Ghosh, A., Shanmugalingam, K., & Lin, W.-Y. (2021) · arXiv (Cornell University) · Cited by 4
Non-Cooperative Spacecraft Pose Estimation Using Convolutional Neural Networks
Despond, F. (2021) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2021-14867 · Cited by 4
Investigation on the Mobile Robot Navigation in an Unknown Environment
Khusheef, A. S., Kothapalli, G., & Tolouei‐Rad, M. (2014) · Australasian Journal of Paramedicine · Cited by 4
An Efficient Human Action Recognition System Using Deep Learning‑Based MethodPreprint
Parui, S. K., Biswas, S. K., & Das, S. (2023) · Research Square · doi:10.21203/rs.3.rs-3400220/v1 · Cited by 4
Retraction: Hybrid approach for optimizing the face recognition based on SIFT, SURF and HOG features
Al-Dujaili, M. J., Ahily, H. J. S., & Fatlawi, A. (2023) · AIP conference proceedings · doi:10.1063/5.0181967 · Cited by 4
RetractedSemi-supervised detection of natural selection with positive-unlabeled learningPreprint
Arnab, S. P., dos Santos, A. L. C., Fumagalli, M., & DeGiorgio, M. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.08.15.670602 · Cited by 4
“Modern alternatives such as SIFT (Scale Invariant Feature Transfrom; [Lowe, 2004b]), SURF (Speeded-Up Robust Features; [Bay et al., 2006]), or ORB (Oriented FAST and Rotated BRIEF; [Rublee et al., 2011]) offer robust scale and rotation invariance.”
Pronobis, A., & Jensfelt, P. (2011) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 4
Design and control of UAV systems : a tri-rotor UAV case study
Kara-Mohamed, M. (2012) · BCU Open Access Repository (Birmingham City University) · Cited by 4
Sun, L. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3116313 · Cited by 38
How to Improve Video Analytics with Action Recognition: A Survey
Gayathri, T., & Mamatha, H. R. (2024) · ACM Computing Surveys · doi:10.1145/3679011 · Cited by 13
Rasel, M. A., Kareem, S. A., & Obaidellah, U. H. B. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106883 · Cited by 3
Low-dimensional multiscale fast SAR image registration method
Li, J., Yu, W., Wang, Z., et al. (2024) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2024.104266 · Cited by 3
Visual Route Recognition in Urban Spaces: A Scalable Approach Using Open Street View Data
Wu, M., Jia, Q., Yang, A., Zhong, Z., Ma, M., Chen, L., & Jing, N. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3524296 · Cited by 3
Smart surgical telementoring system with patch-to-pixel point tracking method
Qu, Y., Li, L., Li, T., Zheng, J., Tang, W., & Li, X. (2025) · EngMedicine · doi:10.1016/j.engmed.2025.100058 · Cited by 3
Hierarchical grid-constrained fusion network for image stitching
Zhang, Y., Ruan, B., Du, L., et al. (2025) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-025-00005-6 · Cited by 3
“Traditional image stitching methods typically rely on feature descriptors such as SIFT (Lowe 2004) and SURF (Bay et al. 2006), to extract features from input images.”
SalsaNext+: A Multimodal-Based Point Cloud Semantic Segmentation With Range and RGB Images
Sánchez-García, F., Montiel-Marín, S., Antunes, M., Gutiérrez-Moreno, R., Llamazares, Á., & Bergasa, L. M. (2025) · IEEE Access · doi:10.1109/access.2025.3559580 · Cited by 5
Image Provenance Analysis via Graph Encoding With Vision Transformer
Zhang, K., Kong, C., Wang, S., Rocha, A. D. R., & Li, H. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3559787 · Cited by 7
“…methods primarily rely on similarity calculations between image pairs, using features ranging from traditional descriptors like Scale-Invariant Feature Transform (SIFT) [19] and Speeded-Up Robust Features (SURF) [20] to more advanced Convolutional Neural Network (CNN) learned features [16], [21].”
Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks
Bonilla, S., Vece, C. D., Daher, R., Ju, X., Stoyanov, D. V., Vasconcelos, F., & Bano, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91989-3_8 · Cited by 13
An Integrated Interframe Stabilization and Fast Imaging Method for Video Synthetic Aperture Radar
Wang, S., Wang, G., Wang, Y., et al. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3580761 · Cited by 3
Low Texture 3D Reconstruction System Based on Manhattan Axis and 2D/3D Line Features
Hou, J., Pan, Z., Xu, C., et al. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3587275 · Cited by 3
“Visual methods are widely used in static, textured scenes [13], [14], [15], [16], [17], [18], [19].”
Context Graph-Based Visual-Language Place Recognition
Woo, S., & Kim, S.-W. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127699 · Cited by 6
“The use of BRIEF reduced the time required for feature extraction compared to traditional BoWs approaches that used SURF [16] and SIFT [4], resulting in a more efficient and robust system.”
Banerjee, S., & Saravanan, T. J. (2025) · Structural Health Monitoring · doi:10.1177/14759217251357232 · Cited by 3
EdgeRegNet: Edge Feature-Based Multimodal Registration Network Between Images and LiDAR Point Clouds
Yue, Y., Yuan, H., Miao, Q., Mao, X., Hamzaoui, R., & Eisert, P. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3613107 · Cited by 7
“Common traditional image descriptors include SIFT [20], SURF [21].”
Kang, J. (2025) · Sensors · doi:10.3390/s25196050 · Cited by 9
“Traditional feature-based VO/VIO approaches have utilized feature detectors such as SIFT [16], SURF [17], or ORB [18] to extract feature points from images.”
Song, B., Wu, B. H., Xiao, J. J., Hu, X., Shi, J., & Zhang, B. (2025) · The Visual Computer · doi:10.1007/s00371-025-04184-1 · Cited by 4
“…and efficiency of the final model Principal Component Analysis (PCA) for descriptor dimensionality reduction (trading accuracy for speed); Bay et al. [63, 64] developed Speeded Up Robust Features (SURF), optimizing detection via box filters and enhancing descriptors with Harris features and integral…”
MambaMatch: Establishing Reliable Correspondences via Multi-Scale State Space Model
Miao, X., Chen, S., Liu, X., Wang, S., Ду, С., He, L., & Xiao, G. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3631445 · Cited by 3
“Moreover, we introduce additional feature detectors, including SURF [50] and RootSIFT [51], to comprehensively evaluate MambaMatch’s performance on the YFCC100M, SUN3D, and PhotoTourism datasets.”
An Event-Based Fast Intensity Reconstruction Scheme for UAV Real-Time Perception
Dong, X., Zhang, Y., Cui, Y., et al. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3607233 · Cited by 3
“The effectiveness of FEDI has been demonstrated through the application of reconstructed images to various algorithms, including SURF [19], AprilTag [20], and VINS [21].”
HOMO-Feature: Cross-Arbitrary-Modal Image Matching with Homomorphism of Organized Major Orientation
Gao, C., Li, W., & Weng, D. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00981 · Cited by 9
“This enables matching of the features between the scenes after the changes, which is the core idea of these technologies [1, 2, 4, 29, 48].”
Kaeli, D. R., Mistry, P., Schaa, D., et al. (2015) · Elsevier eBooks · doi:10.1016/b978-0-12-801414-1.00009-0 · Cited by 3
Exploring the feasibility of traditional image querying tasks for industrial radiographs
Bray, I. E., Tsai, S. J., & Jimenez, E. S. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2195585 · Cited by 3
A graphical model approach for matching partial signatures
Du, X., Doermann, D., & AbdAlmageed, W. (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.2015.7298753 · Cited by 3
New fundamental matrix estimation method using global optimization
Xiao, X. (2010) · International Conference on Computer Application and System Modeling · doi:10.1109/iccasm.2010.5620116 · Cited by 3
What are the distance metrics for local features?
Mao, Z., Zhang, Y., & Tian, Q. (2013) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2502081.2502134 · Cited by 3
“INTRODUCTION L2 and L1 metrics are frequently used in matching traditional local features such as SIFT[4], SURF[1], while Hamming metric is frequently used in matching binary local features such as BRIEF [2], ORB [6], and BRISK [3].”
MethodInfluentialFeature-based tracking of urethral motion in low-resolution trans-perineal ultrasound
Jean, F., Albu, A. B., & Dumoulin, C. L. (2011) · doi:10.1109/iembs.2011.6091637 · Cited by 3
“The proposed tracking method identifies feature points using the SURF detector/descriptor.”
MethodReal-time query-by-image video search system
Araújo, A. D. M., Chen, D., Vajda, P., et al. (2014) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2647868.2654867 · Cited by 3
Creating Three-Dimensional Thermal Maps
Price, M., Green, J. B. A., & Dickens, J. (2011) · Cited by 3
Improving document matching performance by local descriptor filtering
Chazalon, J., Rusiñol, M., & Ogier, J.-M. (2015) · Proceedings of the International Conference on Document Analysis and Recognition · doi:10.1109/icdar.2015.7333957 · Cited by 3
“On the one hand, such binary descriptors are not so discriminant when compared with state-of-the-art local descriptors like SIFT [9] or SURF [10] for example.”
BackgroundPuttemans, S., & Goedemé, T. (2013) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004342108270830 · Cited by 5
Moment Symmetry: A novel method for interest point detection to match blurred and non-blurred images
Tong, Q. K., & Aoki, T. (2016) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc.2016.7571268 · Cited by 3
Registration Based on ORB and FREAK Features for Augmented Reality Systems
Yu, Y., Guo, Y., Wang, R., et al. (2017) · Transactions of Tianjin University · doi:10.1007/s12209-017-0028-3 · Cited by 3
Robust feature matching by learning descriptor covariance with viewpoint synthesis
Taira, H., Torii, A., & Okutomi, M. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899922 · Cited by 2
Demographic Face Profiling Based on Age, Gender and Race
Ghalleb, A. E. K., Boumaiza, S., & Amara, N. E. B. (2020) · International Conference on Advanced Technologies for Signal and Image Processing · doi:10.1109/atsip49331.2020.9231835 · Cited by 3
“[34].”
Heredia-Menor, K. A., & Mamani-Ticona, W. (2021) · Actas del Congreso Internacional de Ingeniería de Sistemas · doi:10.26439/ciis2020.5478 · Cited by 3
COMBINA: Relative Navigation for Unknown Uncooperative Resident Space Object
Maestrini, M., & Lizia, P. D. (2022) · AIAA SciTech Forum · doi:10.2514/6.2022-2384 · Cited by 9
DIGITAL TWINNING PROOF OF CONCEPT FOR UTILITY-SCALE SOLAR: BENEFITS, ISSUES, AND ENABLERS
Starkey, J., Hancock, C., Chen, L., & Meng, Q. (2022) · 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/isprs-archives-xlvi-5-w1-2022-231-2022 · Cited by 3
Image Stitching Algorithm Based on Region Division for Underwater Dam Crack Image
Huang, Y., Zhang, Z., & Xu, X. (2021) · IEEE International Conference on Progress in Informatics and Computing · doi:10.1109/pic53636.2021.9687041 · Cited by 3
A Robust Approach for Bridge Crack Image Mosaic Based on SURF Algorithm
孟, 帅. (2019) · Computer Science and Application · doi:10.12677/csa.2019.92042 · Cited by 3
A Novel Feature Combination Approach For Driver Fatigue Detection
Trimech, I. H., Messaoudi, N., & Amara, N. E. B. (2022) · International Multi-Conference on Systems, Signals & Devices (SSD) · doi:10.1109/ssd54932.2022.9955654 · Cited by 3
Feature Correspondences Increase and Hybrid Terms Optimization Warp for Image Stitching
Cong, Y., Wang, Y., Hou, W., et al. (2023) · Entropy · doi:10.3390/e25010106 · Cited by 3
Zheng, P., Qin, D., Bai, J., et al. (2023) · Micromachines · doi:10.3390/mi14061097 · Cited by 3
“In this paper, the classical blob feature extraction methods scale-invariant feature transform (SIFT) [35] and speeded up robust features (SURF) [36], as well as the corner feature extraction method oriented fast and rotated brief (ORB) [37], are selected to obtain image feature points.”
MethodInfluentialHiMoDepth: Efficient Training-Free High-Resolution On-Device Depth Perception
Zhang, J., Yang, H., Ren, J., et al. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3294188 · Cited by 3
“Furthermore, existing approaches that use image matching algorithms to make the FoVs identical, such as SIFT [19], SURF [20], ORB [21], only perform a homography transformation, resulting in unsatisfactory accuracy, as shown in Section VII-C1.”
MethodBogacki, P., & Dlugosz, R. T. (2023) · IEEE Access · doi:10.1109/access.2023.3322199 · Cited by 3
Simultaneous localization and mapping architecture for small bodies and space exploration
Bettens, A., Morrell, B. J., Coen, M. D., Wu, X., Gibbens, P. W., & Chamitoff, G. E. (2023) · Advances in Space Research · doi:10.1016/j.asr.2023.10.048 · Cited by 5
YOLOPoint: Joint Keypoint and Object Detection
Backhaus, A., Luettel, T., & Wuensche, H. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-45382-3_10 · Cited by 3
Automated Extraction of Sediment Core and Scale Segments from Core Scanner Images
Fazekas, S. Z., Isawa, S., & Obrochta, S. (2023) · doi:10.1109/icitee59582.2023.10317723 · Cited by 3
Staining Independent Nonrigid Iterative Registration Method, for Microscopic Samples
Paulik, R., Jónás, V. Z., Vincze, M., Kozlovszky, M., & Molnar, B. A. (2023) · Acta Polytechnica Hungarica · doi:10.12700/aph.20.8.2023.8.4 · Cited by 3
General Planar Motion from a Pair of 3D Correspondences
Dibene, J. C., Min, Z., & Dunn, E. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00740 · Cited by 3
Supporting ANFIS interpolation for image super resolution with fuzzy rough feature selection
Ismail, M., Shang, C., Yang, J., et al. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05445-7 · Cited by 3
“A comprehensive evaluation of benchmark datasets reveals its adaptiveness and high-quality performance as with state-of-the-art feature extraction algorithms such as SURF [33] and SIFT [29].”
Bensaad, A., Loukhaoukha, K., Sadoudi, S., & Snani, A. (2024) · Journal of Electronic Imaging · doi:10.1117/1.jei.33.4.043004 · Cited by 3
Gaze-Guided Semi-Autonomous Quadruped Robot for Enhanced Assisted Living
Joseph, P., Plozza, D., Pascarella, L., et al. (2024) · IEEE Sensors Applications Symposium (SAS) · doi:10.1109/sas60918.2024.10636523 · Cited by 3
“The first evaluated approach is named speeded up robust features (SURF) [31].”
BackgroundMethodADVANCES IN COMPUTER VISION: NEW HORIZONS AND ONGOING CHALLENGES
Majhi, R. K., & Waoo, A. A. (2024) · ShodhKosh Journal of Visual and Performing Arts · doi:10.29121/shodhkosh.v5.i5.2024.1893 · Cited by 6
Yacoub, M., Abdelwahab, M. M., Shiokawa, K., et al. (2024) · Advances in Space Research · doi:10.1016/j.asr.2024.09.071 · Cited by 3
Deep Unsupervised Homography Estimation for Single-Resolution Infrared and Visible Images Using GNN
Liao, Y. Y., Luo, Y., Fu, Q., Shu, C., Wu, Y., Liu, Q., & He, Y. (2024) · Electronics · doi:10.3390/electronics13214173 · Cited by 4
Multi-focus image registration based on optical flow tracking and Delaunay triangulation
Xia, X., Yang, D., Huo, S., Sun, J., & Xiang, H. (2024) · Signal Processing · doi:10.1016/j.sigpro.2024.109763 · Cited by 3
Learning Local Features by Jointly Semantic-Guided and Task Rewards
Wang, L., Zhang, Y., Ge, F., Bai, W., Zhang, J., & Wang, Y. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3490797 · Cited by 3
“Traditional methods extract stable local features based on inherent image properties, referred to as handcrafted features such as [10], [11], and [12].”
Báskay, J., Kivovics, M., Pénzes, D., et al. (2024) · Die Pathologie · doi:10.1007/s00292-024-01387-6 · Cited by 3
Image stitching algorithm based on two-stage optimal seam line search
Han, G., Zhang, Y., & Zhou, M. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.102256 · Cited by 3
A Biomimetic Pose Estimation and Target Perception Strategy for Transmission Line Maintenance UAVs
Zhuo, H., Yang, Z. X., Zhang, C., Xu, N., Xue, B., Zhu, Z., & Xie, Y. (2024) · Biomimetics · doi:10.3390/biomimetics9120745 · Cited by 4
“Renowned corner detection algorithms, such as SIFT [21] and SURF [22], have been widely applied in regard to image processing.”
SAVOR: Sonar-Aided Visual Odometry and Reconstruction for Autonomous Underwater Vehicles*
Coffelt, J. P., Kampmann, P., & Wehbe, B. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801846 · Cited by 5
“There are many popular approaches to this, including SIFT [21], SURF [22], ORB [23], and AKAZE [24].”
iLoc: An Adaptive, Efficient, and Robust Visual Localization System
Yin, P., Zhao, S., Wang, J., Ge, R., Ji, J., Hu, Y., Liu, H., & Han, J. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3530273 · Cited by 7
Dilmi, W., Ferik, S. E., Saif, A. A., et al. (2025) · Transportation research procedia · doi:10.1016/j.trpro.2025.03.113 · Cited by 3
Image Retrieval Using Multi-layer Orientation Histograms
Li, X., Liu, G., & Lu, F. (2025) · Neural Processing Letters · doi:10.1007/s11063-025-11719-z · Cited by 4
FPSelector: A Flexible Path Selector for Mobile Augmented Reality Offloading
Zhu, Y., Huang, Y., Qiao, X., Liu, X., Su, X. J., Brunström, A., Alay, Ö., & Tarkoma, S. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3556473 · Cited by 4
“This operation may have variable data sizes and computation complexities, depending on the specific algorithm used, such as Scale-Invariant Feature Transform (SIFT) [16], Oriented FAST and Rotated BRIEF (ORB) [17], and Speeded Up Robust Features (SURF) [18].”
Numata, Y., Sumali, B., Hayashida, K., Tsusaki, H., & Mitsukura, Y. (2025) · PLoS ONE · doi:10.1371/journal.pone.0319897 · Cited by 3
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.