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 4,101–4,200 of 14,752
Learning two-pathway convolutional neural networks for categorizing scene images
Bai, S., Li, Z., & Hou, J. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3900-6 · Cited by 15
Extended Kalman Filter for Stereo Vision-Based Localization and Mapping Applications
Wong, X. I., & Majji, M. (2017) · Journal of Dynamic Systems Measurement and Control · doi:10.1115/1.4037784 · Cited by 15
Managing the uncertainty of conformity assessment in environmental testing by machine learning
D’Emilia, G., Gasbarro, D. D., Gaspari, A., et al. (2017) · Measurement · doi:10.1016/j.measurement.2017.12.034 · Cited by 15
A Comparison of Feature Detectors for Underwater Sonar Imagery
Tueller, P., Kastner, R., & Diamant, R. (2018) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans.2018.8604786 · Cited by 20
“SURF, for example, has the best performance in the Sand dataset, but average in the others, while ORB performed quite well in the Ripple dataset, in contrast to Harris, Shi-Tomasi, SIFT, and STAR, all of which yielded very poor performance in that particular dataset.”
MethodMonocular Neural Image Based Rendering with Continuous View Control
Song, J., Chen, X., & Hilliges, O. (2019) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-b-000384064 · Cited by 49
Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition
Wang, C., Chen, S., Song, Y., Xu, R., Zhang, Z., Zhang, J., Yang, H., Zhang, Y., Fu, K., Du, S., et al. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i7.32811 · Cited by 17
“One-Stage VPR: The one-stage VPR approaches produce global representations for image matching by aggregating early handcrafted local features (Bay, Tuytelaars, and Van Gool 2006) or deep learning-based features from convolutional neural networks (Arandjelovic et al. 2016), MLPs (Ali-bey,…”
Comprehensive empirical evaluation of feature extractors in computer vision
Işık, M. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2415 · Cited by 24
Realtime and robust object matching with a large number of templates
Hong, C., Zhu, J., Yu, J., Cheng, J. S., & Chen, X. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2305-7 · Cited by 13
An improved image retrieval method based on SIFT algorithm and saliency map
Liu, J., Meng, F., Mu, F., & Zhang, Y. (2014) · International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) · doi:10.1109/fskd.2014.6980933 · Cited by 14
“There have been many improved methods for its defects, such as some classic algorithm PCA-SIFT [4] and SURF (Speeded Up Robust Features) [5].”
MethodChan, F. K.-S., & Kong, A. W. (2014) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2014.94 · Cited by 14
“Many feature detectors, including Harris detector [7], SIFT [8], PCA-SIFT [9] and SURF [10] have been considered.”
MethodClassification of fragments of objects by the Fourier masks pattern recognition system
Barajas-García, C., Solorza-Calderón, S., & Álvarez-Borrego, J. (2016) · Optics Communications · doi:10.1016/j.optcom.2016.01.059 · Cited by 14
Multimedia Queries in Digital Libraries
Bartolini, I., & Patella, M. (2015) · Data-centric systems and applications · doi:10.1007/978-3-319-20062-0_15 · Cited by 15
“• a video segmented into scenes of homogeneous visual content [8], • an image divided into regions of pixels sharing common color and/or texture [2, 9] • an image represented by way of its salient points [19, 10].”
BackgroundEffective pedestrian detection using deformable part model based on human model
Choi, H. J., Lee, Y. S., Shim, D.-S., Lee, C.-G., & Choi, K. N. (2016) · International Journal of Control Automation and Systems · doi:10.1007/s12555-016-0322-1 · Cited by 15
“In the first step, the image features used in object detection include Haar-like features [8], HOG [6], speed-up robust feature (SURF) [9] and local binary pattern (LBP) [10] (see Table.”
MethodBrogan, J., Bestagini, P., Bharati, A., Pinto, A. D. S., Moreira, D., Bowyer, K. W., Flynn, P. J., Rocha, A. D. R., & Scheirer, W. J. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8297049 · Cited by 15
“In our proposed search method, we extract 500 SURF keypoints [5] with the relative 64-dimensional descriptors to describe each image.”
MethodView-invariant object recognition using homography constraints
Lotfian, S., & Foroosh, H. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296352 · Cited by 14
Design of Robot Monitoring System for Aviation
Mohan, R., Suraj, A. K., Agarawal, S., Majumdar, S., & Nath, V. (2018) · Lecture notes in electrical engineering · doi:10.1007/978-981-13-0776-8_50 · Cited by 15
GA-Based Optimization of SURF Algorithm and Realization Based on Vivado-HLS
Özdemir, H., Sever, R., & Polat, Ö. (2019) · Traitement du signal · doi:10.18280/ts.360501 · Cited by 14
“[2] aims to develop a detector that does not compromise performance, can perform fast calculations, find enough distinguishing features and reduce the descriptor size and complexity.”
BackgroundMethodDistributed in-memory vocabulary tree for real-time retrieval of big data images
Duan, H., Peng, Y., Min, G., Xiang, X., Zhan, W., & Zou, H. (2015) · Ad Hoc Networks · doi:10.1016/j.adhoc.2015.05.006 · Cited by 14
“Introduction (SIFT) [2] or Speeded Up Robust Features (SURF) [3] With the rapid development of the Internet, the number of images available is growing explosively.”
MethodA Review of Object Detectors in Deep Learning
Song, C., Xu, C. L., Gu, Y., Chen, B., & Fu, Z. (2020) · Journal on artificial intelligence · doi:10.32604/jai.2020.010193 · Cited by 14
Real-Time Nonrigid Mosaicking of Laparoscopy Images
Zhou, H., & Jayender, J. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3065030 · Cited by 16
Velazquez, D. A., Gonfaus, J. M., Rodríguez, P., Roca, F. X., Ozawa, S., & Gonzàlez, J. (2021) · IEEE Access · doi:10.1109/access.2021.3101297 · Cited by 17
Ilioudi, A., Dabiri, A., Wolf, B. J., & Schutter, B. D. (2022) · IEEE Access · doi:10.1109/access.2022.3162827 · Cited by 19
“Several algorithms have been developed to extract properties such as corners, edges, and regions of interest from images [2], [12], [40], [74], [88].”
MethodXiu, Y., Zhu, S., Xu, R. C., & Li, M. (2022) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2022.08.009 · Cited by 16
Relative Pose from SIFT Features
Baráth, D., & Kúkelová, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19824-3_27 · Cited by 14
CCVO: Cascaded CNNs for Fast Monocular Visual Odometry Towards the Dynamic Environment
Zhang, T., Li, N., Gong, G., Yang, C., Hou, G., & Lin, X. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3214790 · Cited by 14
“We compare the repeatability rate [22] of the Multitask-Net with 5 classical feature points detectors, which are SIFT [23], SURF [25], Shi [26], and ORB [24] detectors in the OpenCV Library, and ORB detector designed by the ORB-SLAM2 system [3] (denoted by ORBE).”
MethodMuhle, D., Koestler, L., Demmel, N., Bernard, F., & Cremers, D. (2022) · 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/cvpr52688.2022.00186 · Cited by 15
Ding, J., Zhang, Z., Yu, X., Zhao, X., & Yan, Z. (2023) · Applied Sciences · doi:10.3390/app13084854 · Cited by 18
Continuous Structural Displacement Monitoring Using Accelerometer, Vision, and Infrared (IR) Cameras
Choi, J., Ma, Z., Kim, K., et al. (2023) · Sensors · doi:10.3390/s23115241 · Cited by 14
Real-time-based Object Recognition using SIFT algorithm
Vaithiyanathan, D., & Muniraj, M. (2023) · International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT) · doi:10.1109/iceeict56924.2023.10157675 · Cited by 14
Hu, Z., Yuan, J., Gao, Y., Wang, B., & Zhang, X. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3303355 · Cited by 14
Asymmetric Feature Fusion for Image Retrieval
Wu, H., Wang, M., Zhou, W., Lu, Z., & Li, H. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01066 · Cited by 26
“Hand-crafted local features [2, 24] are widely used in early image retrieval systems [27,32, 40].”
BackgroundDynamic Keypoint Detection Network for Image Matching
Gao, Y., He, J., Zhang, T., Zhang, Z., & Zhang, Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3307889 · Cited by 19
A Generalizable D-VIO and Its Fusion With GNSS/IMU for Improved Autonomous Vehicle Localization
Yusefi, A., Durdu, A., Bozkaya, F., Tığlıoğlu, Ş., Yılmaz, A., & Sungur, C. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3316361 · Cited by 17
Shared Coupling-Bridge Scheme for Weakly Supervised Local Feature Learning
Sun, J., Ji, L., & Zhu, J. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3278172 · Cited by 19
“Early efforts [10]–[12], [14]–[16] usually adopt hand-crafted detectors and descriptors.”
Deep learning-based 3D brain multimodal medical image registration
Deng, L., Lan, Q., Zhi, Q., Huang, S., Wang, J., & Yang, X. N. (2023) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-023-02941-9 · Cited by 22
“Therefore, to expedite the calculation process of SIFT features, Han et al. [4] made enhancements to the SIFT operator and employed the SURF (Speeded-Up Robust Features) operator for registering lung computed tomography images.”
Monocular Depth Estimation: A Survey
Wang, D., Liu, Z., Shao, S., Wu, X., Chen, W., & Li, Z. G. (2023) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon51785.2023.10311687 · Cited by 20
S-TREK: Sequential Translation and Rotation Equivariant Keypoints for local feature extraction
Santellani, E., Sormann, C., Rossi, M., Kühn, A., & Fraundorfer, F. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00892 · Cited by 19
Reddy, S. S., Rao, V. V. R. M., Sravani, K., & Nrusimhadri, S. (2024) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v13i2.5947 · Cited by 16
“[21].”
Chen, T., & Wang, N. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3385387 · Cited by 16
“To be specific, traditional machine learning-based approaches (e.g., SIFT [13], SURF [14], and HOG [15]) can only extract rather limited low-level feature including color, texture, and edge by predesigned hand-craft descriptors.”
MethodBALF: Simple and Efficient Blur Aware Local Feature Detector
Zhao, Z. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00333 · Cited by 60
A Detection Algorithm for Citrus Huanglongbing Disease Based on an Improved YOLOv8n
Xie, W., Feng, F., & Zhang, H. (2024) · Sensors · doi:10.3390/s24144448 · Cited by 25
Practical Gaze Tracking on Any Surface With Your Phone
Cao, J., Chen, J., Lin, C., Liu, Y., Wang, K., & Li, Z. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3445373 · Cited by 16
Zhu, B., Ye, Y., Dai, J., Peng, T., Deng, J., & Zhu, Q. (2024) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2024.09.016 · Cited by 18
Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World
Fu, H., Peng, F., Li, X., Li, Y., Wang, X., & Ma, H. (2024) · 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/cvpr52733.2024.00293 · Cited by 15
“The luminance and resolution variations resulting from lens zoom during the image capture can challenge widely used image alignment algorithms like ORB [26], SURF [2], and SIFT [21].”
MethodDINO-Mix enhancing visual place recognition with foundational vision model and feature mixing
Huang, G., Zhou, Y., Hu, X., Zhang, C., Zhao, L., & Gan, W. (2024) · Scientific Reports · doi:10.1038/s41598-024-73853-3 · Cited by 32
Li, H., Hu, L. Y., Ye, J., Wei, W., Gao, X., Qian, Z., & Long, Y. (2024) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02526-9 · Cited by 20
Reconstruction of 3D Surface and Restoration of Flat Document Image from Monocular Image Sequence
Shibayama, H., Watanabe, Y., & Ishikawa, M. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37447-0_27 · Cited by 14
Suzuki, T., & Ikenaga, T. (2012) · Cited by 14
An efficient feature descriptor based on synthetic basis functions and uniqueness matching strategy
Desai, A., Lee, D.-J., & Ventura, D. A. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.09.005 · Cited by 17
Robust hazard matching approach for visual navigation application in planetary landing
Yu, M., & Cui, H. (2015) · Aerospace Science and Technology · doi:10.1016/j.ast.2015.09.028 · Cited by 13
Sensor Fusion of Cameras and a Laser for City-Scale 3D Reconstruction
Bok, Y., Choi, D., & Kweon, I. S. (2014) · Sensors · doi:10.3390/s141120882 · Cited by 14
Local Features and a Two-Layer Stacking Architecture for Semantic Concept Detection in Video
Markatopoulou, F., Mezaris, V., Pittaras, N., & Patras, I. (2015) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2015.2418714 · Cited by 15
Carlo, S. D., Gambardella, G., Prinetto, P., et al. (2014) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2014.2357181 · Cited by 14
Real-time retinal vessel mapping and localization for intraocular surgery
Becker, B. C., & Riviere, C. N. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631345 · Cited by 16
Real-Time Keypoint Recognition Using Restricted Boltzmann Machine
Yuan, M., Tang, H., & Li, H. (2014) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2014.2303478 · Cited by 13
“To tackle this bottleneck, the speeded up robust features (SURF) method was proposed in [16], which is a robust and efficient descriptor using a Haar wavelet approximation of the determinant of an Hessian Blob detector.”
MethodLarge-scale classification of traffic signs under real-world conditions
Hazelhoff, L., Creusen, I. M., van de Wouw, D. W. J. M., & de With, P. H. N. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.910490 · Cited by 14
An innovative hand-held vision-based digitizing system for 3D modelling
Coudrin, B., Devy, M., Orteu, J., & Brèthes, L. (2011) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2011.05.004 · Cited by 17
Linear time offline tracking and lower envelope algorithms
Gu, S., Zheng, Y., & Tomasi, C. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126451 · Cited by 15
“Step 1: Given an arbitrary frame and a specified window, compute the set of SIFT [24] features (other features [32, 7, 31, 17] can be used as well) and put all the features within the window into M and the rest into a background model B.”
MethodHacking Chinese Touclick CAPTCHA by Multi-Scale Corner Structure Model with Fast Pattern Matching
Shen, Y., Ji, R., Cao, D., & Wang, M. (2014) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2647868.2655017 · Cited by 14
“As an alternative solution, we implemented other feature detectors, i.e., SIFT [9], FAST [14], BRISK [8], Hessian affine region [11], SURF [2], and MSER [10], to compare with our Shi-Tomasi corner detector.”
MethodPoint-of-interest detection for range data
Vikstén, F., Nordberg, K., & Kalms, M. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4761179 · Cited by 14
A GPU-based high-throughput image retrieval algorithm
Zhu, F., Chen, P., Yang, D., Zhang, W., Chen, H., & Zang, B. (2012) · doi:10.1145/2159430.2159434 · Cited by 14
Context-Aware Discriminative Vocabulary Learning for Mobile Landmark Recognition
Chen, T., & Yap, K. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2254978 · Cited by 14
“For example, in [14], local features, such as speeded up robust feature (SURF) [16] or scale invariant feature transform (SIFT) [17] are first extracted from the query image, followed by a scalable vocabulary tree (SVT) [18] to quantize these features into a bag-of-words (BoW) histogram, which is then encoded and tran…”
MethodSURF algorithm in FPGA: a novel architecture for high demanding industrial applications
Battezzati, N., Colazzo, S., Maffione, M., et al. (2012) · Design, Automation, and Test in Europe · doi:10.5555/2492708.2492748 · Cited by 14
Real-time barrier lakes monitoring and warning system based on wireless sensor network
Liu, Z., Huang, J., Wang, Q., et al. (2013) · International Conference on Intelligent Control and Information Processing · doi:10.1109/icicip.2013.6568136 · Cited by 14
Triangle-Constraint for Finding More Good Features
Guo, X., & Cao, X. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.344 · Cited by 14
“And numerous feature extraction schemes have been proposed, like Harris corner detector [3], SIFT [7] and SURF [1], to capture distinctive and stable features.”
MethodMobile image retrieval using multi-photos as query
Xue, Y., Qian, X., & Zhang, B. (2013) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2013.6618255 · Cited by 14
Appearance-based odometry and mapping with feature descriptors for underwater robots
Botelho, S. S. D. C., Drews, P., Figueiredo, M. D. S., Haffele, C., & Oliveira, G. L. (2009) · Journal of the Brazilian Computer Society · doi:10.1007/bf03194505 · Cited by 15
Creating and using RoboEarth object models
Marco, D. D., Koch, A., Zweigle, O., Häußermann, K., Schießle, B., Levi, P. A., Gálvez‐López, D., Riazuelo, L., Civera, J., Montiel, J. M. M., et al. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6224858 · Cited by 16
Protecting IP Multimedia Subsystem (IMS) Service Delivery Platform from Time Independent Attacks
Sher, M., & Magedanz, T. (2007) · International Conference on Information Assurance and Security (IAS) · doi:10.1109/ias.2007.78 · Cited by 20
REAL-TIME 3D RECONSTRUCTION FROM IMAGES TAKEN FROM AN UAV
Zingoni, A., Diani, M., Corsini, G. U., et al. (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-3-w3-313-2015 · Cited by 14
MediaCCNY at TRECVID 2012: Surveillance Event Detection.
Yang, X., Yi, C., Cao, L., & Tian, Y. (2012) · TRECVID · Cited by 15
BE-SIFT: A More Brief and Efficient SIFT Image Matching Algorithm for Computer Vision
Zhao, J. C., Liu, H., Feng, Y., Yuan, S., & Cai, W. (2015) · IEEE International Conference on Computer and Information Technology (CIT) · doi:10.1109/cit/iucc/dasc/picom.2015.81 · Cited by 16
“SIFT was published in 2004 on the foundation of Professor David Lowe’s summary of the existing feature detection methods based on invariant, and it is a kind of local feature extraction and description algorithm which is able to keep invariance against image transformations, such as scale, translation, rotation, illum…”
MethodRotation-invariant histograms of oriented gradients for local patch robust representation
Luo, Z., Chen, J., Takiguchi, T., & Ariki, Y. (2015) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2015.7415502 · Cited by 15
“To invariantly describe the non-linear information of the images, well-known local feature descriptors, such as SIFT [1], SURF [2], etc.”
MethodInfluentialAction recognition by joint learning
Yuan, Y., Qi, L., & Lu, X. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.04.001 · Cited by 14
Fall detection in RGB-D videos by combining shape and motion features
Kumar, D. P., Yun, Y., & Gu, I. Y. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7471894 · Cited by 15
Euclidean and Hamming Embedding for Image Patch Description with Convolutional Networks
Liu, Z., Li, Z., Zhang, J., & Liu, L. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.146 · Cited by 14
“Many works have been done to design such local features, aiming for a better tradeoff between distinctiveness and robustness, including SIFT [14], SURF [2], DAISY [24], ORB [20], BRIEF [4], MIOP [28], etc.”
BackgroundVistas and Wall-Floor Intersection Features: Enabling Autonomous Flight in Man-made Environments
Ok, K., Ta, D.-N., & Dellaert, F. (2012) · Cited by 14
Navigation Aiding by a Hybrid Laser-Camera Motion Estimator for Micro Aerial Vehicles
Atman, J., Popp, M. R., Ruppelt, J. P., & Trommer, G. F. (2016) · Sensors · doi:10.3390/s16091516 · Cited by 14
Matching-range-constrained real-time loop closure detection with CNNs features
Bai, D., Wang, C., Zhang, B., Yi, X., & Tang, Y. (2016) · Robotics and Biomimetics · doi:10.1186/s40638-016-0047-x · Cited by 16
Content-based image retrieval optimization by differential evolution
Grycuk, R., Gabryel, M., Nowicki, R. K., et al. (2016) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2016.7743782 · Cited by 14
“Speeded-Up Robust Features is a method which allows to detect and match local features of an image [23].”
MethodClassification of brain disease in magnetic resonance images using two-stage local feature fusion
Li, T., Li, W., Yang, Y., & Zhang, W. (2017) · PLoS ONE · doi:10.1371/journal.pone.0171749 · Cited by 16
Fusion of appearance and motion-based sparse representations for multi-shot person re-identification
Khedher, M. I., El‐Yacoubi, M. A., & Dorizzi, B. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.11.073 · Cited by 14
“…two functions A and B of two discrete variables i and j is defined as follows: E The determinant of the Hessian H σ p p q is finally approximated as follows (Eq.5), where w is a constant empirically selected [21]: The SURF detector uses the integral image to accelerate the convolution calculation.”
MethodDatabase construction for vision aided navigation in planetary landing
Yu, M., Cui, H., Li, S., & Tian, Y. (2017) · Acta Astronautica · doi:10.1016/j.actaastro.2017.07.041 · Cited by 15
Volkova, A., & Gibbens, P. W. (2017) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-017-0650-2 · Cited by 16
“…feature-based algorithms [1] mostly use corner-based features, such as Scale-invariant feature transform (SIFT) [2] or Speeded Up Robust Features (SURF) [3] have been successfully used for the task of visual global positioning of UAV [4, 5], image registration [6–8] and urban feature detection [9].”
MethodDufek, J., Xiao, X., & Murphy, R. R. (2017) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr.2017.8088149 · Cited by 14
“The first was SURF algorithm [11], which is the speeded-up version of SIFT [12].”
MethodEstimation of intersection traffic density on decentralized architectures with deep networks
Yeshwanth, C., Sooraj, P. S. A., Sudhakaran, V., & Raveendran, V. (2017) · IEEE International Smart Cities Conference (ISC2) · doi:10.1109/isc2.2017.8090799 · Cited by 14
Alignment of 3D point clouds with a dominant ground plane
Pandey, G., Giri, S., & Mcbride, J. R. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206031 · Cited by 12
Gil, G., Savino, G., Piantini, S., & Pierini, M. (2018) · Sensors · doi:10.3390/s18010295 · Cited by 17
An Approach to Navigation for the Humanoid Robot Nao in Domestic Environments
Wei, C., Xu, J., Wang, C., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-43645-5_33 · Cited by 14
“Several approaches such as SIFT [11], SURF [12], and their derivatives, Harris-SIFT [13] and AnySURF [14], can be used.”
MethodODDS: Real-Time Object Detection Using Depth Sensors on Embedded GPUs
Mithun, N. C., Munir, S., Guo, K., & Shelton, C. (2018) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1109/ipsn.2018.00051 · Cited by 16
“SIFT [33], HOG [15] and SURF [10] are all examples of local feature descriptors that describe the salient regions around key points in an image.”
Identifying Gambling and Porn Websites with Image Recognition
Li, L., Gou, G., Xiong, G., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-77383-4_48 · Cited by 14
Real- Time Hyperspectral Stereo Processing for the Generation of 3D Depth Information
Heide, N. F., Frese, C., Emter, T., et al. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451194 · Cited by 14
“Stereo matching techniques divide into feature-based techniques producing sparse point clouds [3, 4], and correlationbased techniques generating considerably denser point clouds [5].”
BackgroundRobust image retrieval for lacy and embroidered fabric
Yao, L., & Ke, H. (2018) · Textile Research Journal · doi:10.1177/0040517518798648 · Cited by 14
DSR: Direct Self-Rectification for Uncalibrated Dual-Lens Cameras
Xiao, R., Sun, W., Pang, J., et al. (2018) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2018.00070 · Cited by 14
KLASIFIKASI EKSPRESI WAJAH MENGGUNAKAN BAG OF VISUAL WORDS
Muhathir, M. (2018) · JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING · doi:10.31289/jite.v1i2.1426 · Cited by 16
Automatic Mackerel Sorting Machine Using Global and Local Features
Nagaoka, Y., Miyazaki, T., Sugaya, Y., & Omachi, S. (2019) · IEEE Access · doi:10.1109/access.2019.2917554 · Cited by 15
“They used scale invariant feature transformation [14] and SURF (speeded up robust features) [15] in the feature extraction phase, and a SVM (support vector machine), artificial neural networks, and K-nearest neighbor in the classification stage.”
MethodMaize Leaf Disease Image Classification Using Bag of Features
Syarief, M., Prastiti, N., & Setiawan, W. (2019) · JURNAL INFOTEL · doi:10.20895/infotel.v11i2.428 · Cited by 14
Combining Convolutional Neural Network and Photometric Refinement for Accurate Homography Estimation
Kang, L., Wei, Y., Xie, Y., et al. (2019) · IEEE Access · doi:10.1109/access.2019.2933635 · Cited by 14
A hybrid egocentric video summarization method to improve the healthcare for Alzheimer patients
Sultan, S., Javed, A., Irtaza, A., et al. (2019) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-019-01444-6 · Cited by 14
“This approach is used to educate the Alzheimer patients to memorize the use of objects (Bay et al. 2006).”
MethodAn Adaptive Local Descriptor Embedding Zernike Moments for Image Matching
Zhou, B., Duan, X., Wei, W., Ye, D., Woźniak, M., & Damaševičius, R. (2019) · IEEE Access · doi:10.1109/access.2019.2960203 · Cited by 14
“SIFT, BRISK and SURF find more than 20 matches in average while the other four find less than 5 in average.”
BackgroundMethodInfluential
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.