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 1,901–2,000 of 14,752
RSILC: Rotation- and Scale-Invariant, Line-based Color-aware descriptor
Candemir, S., Borovikov, E., Santosh, K., Antani, S., & THOMA, G. E. (2015) · Image and Vision Computing · doi:10.1016/j.imavis.2015.06.010 · Cited by 37
Voice Interaction Recognition Design in Real-Life Scenario Mobile Robot Applications
Li, S., Liu, Y., Chen, Y.-C., Feng, H.-M., Shen, P.-K., & Wu, Y.-C. (2023) · Applied Sciences · doi:10.3390/app13053359 · Cited by 46
Progressive Neighbor Consistency Mining for Correspondence Pruning
Liu, X., & Yang, J. (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/cvpr52729.2023.00919 · Cited by 62
MASt3R-SfM: A Fully-Integrated Solution for Unconstrained Structure-from-Motion
Duisterhof, B. P., Žust, L., Weinzaepfel, P., Leroy, V., Cabon, Y., & Revaud, J. (2025) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv66043.2025.00008 · Cited by 201
“Matching, i.e . the task of finding pixel correspondences across different images observing the same 3D points, has been extensively studied in the past decades, beginning from handcrafted keypoints [7,31,42] and more recently being surpassed by data-driven strategies [12,13,14,15,22,41,43,52,63].”
BackgroundChange detection using Synthetic Aperture Sonar: Preliminary results from the Larvik trial
Midtgaard, Ø., Hansen, R. E., Sæbø, T. O., et al. (2011) · doi:10.23919/oceans.2011.6107272 · Cited by 37
“the pixel coordinates of the second image, interest points (landmarks) are extracted from the images using the SURF algorithm [22].”
MethodLocalizing global descriptors for content-based image retrieval
Iakovidou, C., Anagnostopoulos, N., Kapoutsis, A. C., Boutalis, Y. S., Lux, M., & Chatzichristofis, S. A. (2015) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-015-0262-6 · Cited by 36
“Among the most popular Points of Interest (POI) detectors are corner detectors Harris, Shi-Tomasi and FAST [9, 10, 11] and blob detectors SIFT [12], SURF [13], to name a few.”
BackgroundAdaptive registration algorithm of color images based on SURF
Huang, L., Chen, C., Shen, H., & He, B. (2015) · Measurement · doi:10.1016/j.measurement.2015.01.011 · Cited by 37
Real-time optical SLAM-based mosaicking for unmanned underwater vehicles
Ferreira, F., Veruggio, G., Caccia, M., & Bruzzone, G. (2011) · Intelligent Service Robotics · doi:10.1007/s11370-011-0103-x · Cited by 39
Payá, L., Amorós, F., Fernández, L., & Reinoso, Ó. (2014) · Sensors · doi:10.3390/s140203033 · Cited by 40
Real-time image composition of bladder mosaics in fluorescence endoscopy
Behrens, A., Bommes, M., Stehlé, T., Groß, S., Leonhardt, S. K., & Aach, T. (2010) · Computer Science - Research and Development · doi:10.1007/s00450-010-0135-z · Cited by 37
A low-bandwidth camera sensor platform with applications in smart camera networks
Chen, P., Hong, K., Naikal, N., et al. (2013) · ACM Transactions on Sensor Networks · doi:10.1145/2422966.2422978 · Cited by 37
Vessel Inspection: A Micro-Aerial Vehicle-based Approach
Ortiz, A., Bonnin‐Pascual, F., & Garcia‐Fidalgo, E. (2013) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-013-9852-4 · Cited by 40
“as SIFT [21] and SURF [6], and relatively new fast detectors and descriptors with less computational requirements: FAST [28], ORB [29], BRIEF [11], and FREAK [25].”
MethodDEFEATnet—A Deep Conventional Image Representation for Image Classification
Gao, S., Duan, L., & Tsang, I. W.-H. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2389413 · Cited by 40
“Here, X can be any kind of local features, like SIFT [6], HOG [7], SURF [8], and so on.”
BackgroundInfluentialBarazzetti, L., Fabio Remondino, A., & Scaioni, M. (2009) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.825638 · Cited by 36
Evaluation of structure from motion for soil microtopography measurement
Nouwakpo, S. K., James, M. R., Weltz, M. A., et al. (2014) · The Photogrammetric Record · doi:10.1111/phor.12072 · Cited by 37
Your reactions suggest you liked the movie: automatic content rating via reaction sensing
Bao, X., Fan, S., Varshavsky, A., Li, K., & Choudhury, R. R. (2013) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2493432.2493440 · Cited by 39
Machine learning and pattern classification in identification of indigenous retinal pathology
Jelinek, H. F., Rocha, A., Carvalho, T., et al. (2011) · doi:10.1109/iembs.2011.6091471 · Cited by 37
Expanded Parts Model for Semantic Description of Humans in Still Images
Sharma, G., Jurie, F., & Schmid, C. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2537325 · Cited by 41
“[93], stereo correspondences by Veksler [94] and visual tracking by Adam et al.”
MethodConsistent data association in multi-robot systems with limited communications
Aragues, R., Montijano, E., & Sagues, C. (2010) · Robotics: Science and Systems VI · doi:10.15607/rss.2010.vi.013 · Cited by 37
“Each robot acquires one image with its onboard camera and extracts SURF features [3].”
MethodHoG based real-time multi-target tracking in Bayesian framework
Ullah, M., Cheikh, F. A., & Imran, A. S. (2016) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2016.7738080 · Cited by 36
“) and local descriptors (SIFT [18], SURF [6] etc.”
BackgroundA new robust video watermarking algorithm based on SURF features and block classification
Bahrami, Z., & Tab, F. A. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-4226-0 · Cited by 37
3D Models in Cultural Heritage
Agosto, E., & Bornaz, L. (2017) · International Journal of Computational Methods in Heritage Science · doi:10.4018/ijcmhs.2017010101 · Cited by 37
“Operators such as SIFT: Scale Invariant Feature Transform (Lowe, 2004) or SURF: Speed Up Robust Feature (Bay et al., 2006) offer a chance to digital photogrammetry to automatically identify tie points in different images; the following image matching problem is then solved by stereo matching…”
MethodKnyaz, V. A., Выголов, О. В., Kniaz, V. V., Vizilter, Y. V., Сергеевич, Г. В., Lühmann, T., & Conen, N. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.252 · Cited by 42
“Most of the modern software for 3D object reconstruction use approaches based on analytically developed feature descriptors [36, 1].”
MethodMSIM: A change detection framework for damage assessment in natural disasters
Qin, D. L., Zhou, X., Zhou, W., Huang, G., Ren, Y., Horan, B., He, J., & Kito, N. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.12.038 · Cited by 37
Human action recognition using SIFT and HOG method
Qazi, H. A., Jahangir, U., Yousuf, B. M., & Noor, A. (2017) · International Conference on Information and Communication Technologies · doi:10.1109/icict.2017.8320156 · Cited by 38
“For feature extraction SURF feature extraction, which is type of SIFT feature, was compared with HOG features.”
InfluentialTowards Zero Re-Training for Long-Term Hand Gesture Recognition via Ultrasound Sensing
Yang, X., Zhou, D., Zhou, Y., Huang, Y., & Liu, H. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2867539 · Cited by 37
“Speeded-up robust features (SURF) was therefore applied in this paper, which was immune to scale, rotation and illumination changes of the image [21].”
BackgroundMethodInfluentialRao, D. M. R. N., Prasad, V. V. R., Teja, P. S. R., et al. (2018) · International Journal of Engineering & Technology · doi:10.14419/ijet.v7i2.32.15399 · Cited by 37
Fusion of Underwater Image Enhancement and Restoration
Sethi, R., & Indu, S. (2019) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001420540075 · Cited by 39
Cyclic Multiplexed-Immunofluorescence (cmIF), a Highly Multiplexed Method for Single-Cell Analysis
Eng, J. R., Thibault, G., Luoh, S., Gray, J. W., Chang, Y. H., & Chin, K. (2019) · Methods in molecular biology · doi:10.1007/978-1-4939-9773-2_24 · Cited by 37
Jang, J., Shin, M., Lim, S., Park, J., Kim, J., & Paik, J. (2019) · Sensors · doi:10.3390/s19214738 · Cited by 40
Three-dimensional Visual Mapping of Underwater Ship Hull Surface Using Piecewise-planar SLAM
Hong, S., & Kim, J. (2020) · International Journal of Control Automation and Systems · doi:10.1007/s12555-019-0646-8 · Cited by 37
Progressive Feature Matching: Incremental Graph Construction and Optimization
Lee, S., Lim, J., & Suh, I. H. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2996092 · Cited by 37
“To improve the performance of feature detection and description in the first step of the pipeline, many local feature detection algorithms such as BRISK [20], BRIEF [21], ORB [22], ASIFT [23], and KAZE [19] were developed after SIFT [1] and SURF [2].”
MethodInfluentialAnomaly Detection-Based Unknown Face Presentation Attack Detection
Baweja, Y., Oza, P., Perera, P., & Patel, V. M. (2020) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb48548.2020.9304935 · Cited by 60
Jacobson, A., Zeng, F., Smith, D., Boswell, N., Peynot, T., & Milford, M. J. (2020) · Journal of Field Robotics · doi:10.1002/rob.21978 · Cited by 41
“The classical approach to visual place recognition involves the extraction of handcrafted features, like SIFT (Lowe, 1999), SURF (Bay et al., 2006) or ORB (Rublee et al.”
Background500-Fps Omnidirectional Visual Tracking Using Three-Axis Active Vision System
Jiang, M., Sogabe, R., Shimasaki, K., Hu, S., Senoo, T., & Ishii, I. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3053971 · Cited by 37
FusionVLAD: A Multi-View Deep Fusion Networks for Viewpoint-Free 3D Place Recognition
Yin, P., Xu, L., Zhang, J., & Choset, H. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3061375 · Cited by 42
Object Detection Under Challenging Lighting Conditions Using High Dynamic Range Imagery
Mukherjee, R., Bessa, M., Melo‐Pinto, P., & Chalmers, A. G. (2021) · IEEE Access · doi:10.1109/access.2021.3082293 · Cited by 42
“Rana et al. [35] conducted a study to understand the potential of HDR in feature extraction using traditional feature extractors such as Harris corner detector [36] and SURF [37].”
MethodDifferential Morph Face Detection using Discriminative Wavelet Sub-bands
Chaudhary, B., Aghdaie, P., Soleymani, S., Dawson, J. M., & Nasrabadi, N. M. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00158 · Cited by 47
“This method is explored in [37], using LBP, BSIF, SIFT, SURF, and HOG descriptors.”
MethodFine-Grained Elastic Partitioning for Distributed DNN Towards Mobile Web AR Services in the 5G Era
Ren, P., Qiao, X., Huang, Y., Liu, L., Pu, C., & Dustdar, S. (2021) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2021.3098816 · Cited by 46
“The traditional object recognition methods need to first extract the local feature points [11], [12], [13] from the video frames captured by the camera in real time, and then complete the recognition process through object retrieval [14].”
MethodMulti-scale Matching Networks for Semantic Correspondence
Zhao, D., Song, Z., Ji, Z., Zhao, G., Ge, W., & Yu, Y. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00334 · Cited by 51
“Methods for semantic correspondence can be roughly categorized into several groups: handcrafted feature based methods [31, 2, 42, 7, 48], learnable feature based methods [26, 27, 35, 49], graph matching and optimization based methods [52, 30, 58, 56], meth-ods focusing on geometry displacement [5,…”
MethodAutomated weed detection system in smart farming for developing sustainable agriculture
Rani, S. V. J., Kumar, P. S., Priyadharsini, R., Srividya, S. J., & Harshana, S. (2021) · International Journal of Environmental Science and Technology · doi:10.1007/s13762-021-03606-6 · Cited by 39
“After pre-processing, the SURF method (Bay and Tuytelaars 2006) was used to extract features from the image.”
MethodWang, J., Zhao, J. K., Liu, Y., & Shan, J. (2021) · Structural Control and Health Monitoring · doi:10.1002/stc.2832 · Cited by 39
“The SURF detector is a robust blob detector and descriptor with scale invariance and fairly fast speed.(38) Such detection algorithms are widely utilized in feature-based object tracking tasks, thus presenting many reliable implementations.”
MethodFinding objects for assisting blind people
Yi, C., Flores, R., Chincha, R., & Tian, Y. (2013) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-013-0026-x · Cited by 45
Topological simultaneous localization and mapping: a survey
Boal, J., Miralles, Á. S., & Arranz, Á. (2013) · Robotica · doi:10.1017/s0263574713001070 · Cited by 45
“Later on, Bay et al. 9 developed Speeded-Up Robust Features (SURF) with the aim of reducing the computational burden of SIFT.”
BackgroundFeature Detector and Descriptor for Medical Images
Sargent, D., Chen, C.-I., Tsai, C.-M., et al. (2009) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.811210 · Cited by 37
“Our method is based on two popular state-of-the-art discrete feature detection algorithms, SIFT[3,7] and SURF[2].”
MethodModel Based Markerless 3D Tracking applied to Augmented Reality
Lima, J. P., Simões, F., Figueiredo, L. S., & Kelner, J. (2010) · Journal on Interactive Systems · doi:10.5753/jis.2010.560 · Cited by 37
A Survey of Blob Detection Algorithms for Biomedical Images
Han, K. T. M., & Uyyanonvara, B. (2016) · International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES) · doi:10.1109/ictemsys.2016.7467122 · Cited by 37
Recognizing heterogeneous cross-domain data via generalized joint distribution adaptation
Hsieh, Y.-T., Tao, S.-Y., Tsai, Y.-H. H., Yeh, Y.-R., & Wang, Y.-C. F. (2016) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2016.7552878 · Cited by 43
“More-over, two types of features are used: SURF [21] and De-CAF [22].”
MethodCollell, G., & Moens, M. (2016) · Lirias · Cited by 52
Classification of SURF image features by selected machine learning algorithms
Horák, K., Klečka, J., Boštík, O., & Davídek, D. (2017) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2017.8076064 · Cited by 38
Classification and Localization of Multi-Type Abnormalities on Chest X-Rays Images
Elhanashi, A., Saponara, S., & Zheng, Q. (2023) · IEEE Access · doi:10.1109/access.2023.3302180 · Cited by 36
“[ 54], [55].”
General Place Recognition Survey: Toward Real-World Autonomy
Yin, P., Jiao, J., Zhao, S., Xu, L., Huang, G. P., Choset, H., Scherer, S., & Han, J. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3550771 · Cited by 71
“Local descriptors, such as SURF [22] identify a set of keypoints and compute corresponding descriptors for local image regions, but requiring extensive matching to compare visual similarity between images.”
A fast object detector based on high-order gradients and Gaussian process regression for UAV images
Moranduzzo, T., Melgani, F., Bazi, Y., & Alajlan, N. (2015) · International Journal of Remote Sensing · doi:10.1080/01431161.2015.1043760 · Cited by 38
“Some other works exploit local descriptors such as Scale-Invariant Feature Transform (SIFT) (Lowe 2004) or Speeded Up Robust Features (SURF) (Bay, Tuytelaars, and Van Gool 2006) to identify the targets.”
MethodTranslation-Symmetry-Based Perceptual Grouping with Applications to Urban Scenes
Park, M., Brocklehurst, K., Collins, R. T., & Liu, Y. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19318-7_26 · Cited by 36
“2.3 Translation-Symmetry-based Grouping We seek a (t 1 , t 2 )-vector pair that represents the generators of the translation symmetry subgroup using a RANSAC-based method, similar to the work of Park (a) KLT (b) MSER (c) SURF Fig.”
BackgroundInfluentialVision‐based Simultaneous Localization and Mapping in Changing Outdoor Environments
Milford, M. J., Vig, E., Scheirer, W. J., & Cox, D. (2014) · Journal of Field Robotics · doi:10.1002/rob.21532 · Cited by 34
Extremal Regions Detection Guided by Maxima of Gradient Magnitude
Faraji, M., Shanbehzadeh, J., Nasrollahi, K., & Moeslund, T. B. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2477215 · Cited by 34
“As both methods are able to report all pixels that contribute to a region, we extract SURF descriptors based on the detected extremal regions’ pixels (Distinguished Regions [18]).”
MethodInfluentialA General Purpose Feature Extractor for Light Detection and Ranging Data
Li, Y., & Olson, E. (2010) · Sensors · doi:10.3390/s101110356 · Cited by 36
Learning convolutional filters for interest point detection
Richardson, A., & Olson, E. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630639 · Cited by 36
Group-Sensitive Multiple Kernel Learning for Object Recognition
Yang, J., Tian, Y., Duan, L., Huang, T., & Gao, W. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2183139 · Cited by 38
Preserving SIFT features in JPEG-encoded images
Chao, J., & Steinbach, E. G. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6116299 · Cited by 35
“SURF [10]) will be addressed in our future work.”
BackgroundInfluentialCONTEXT-BASED URBAN TERRAIN RECONSTRUCTION FROM UAV-VIDEOS FOR GEOINFORMATION APPLICATIONS
Bulatov, D., Solbrig, P., Gross, H., Wernerus, P., Repasi, E., & Heipke, C. (2012) · 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-xxxviii-1-c22-75-2011 · Cited by 35
“References: Bay, H., Tuytelaars, T., Van Gool, L., 2006, SURF: Speeded up robust features, In: Proc.”
ResultHu, Y.-T., Lin, Y., Chen, H., Hsu, K.-J., & Chen, B. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2496305 · Cited by 32
DaLI: Deformation and Light Invariant Descriptor
Simo‐Serra, E., Carme Torras, A., & Moreno-Noguer, F. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0805-1 · Cited by 45
“For instance, the SIFT descriptor (Lowe 2004) and many of its variants (Bay et al. 2006; Ke and Sukthankar 2004; Mikola-jczyk and Schmid 2005; Morel and Yu 2009; Tola et al. 2010) have been proven to be robust to affine deformations of both spatial and intensity domains.”
BackgroundMethodVisual control of vehicles using two-view geometry
Nicolás, G. L., Guerrero, J. J., & Sagüés, C. (2010) · Mechatronics · doi:10.1016/j.mechatronics.2010.01.005 · Cited by 36
Distributed Data Association in Robotic Networks With Cameras and Limited Communications
Montijano, E., Aragüés, R., & Sagüés, C. (2013) · IEEE Transactions on Robotics · doi:10.1109/tro.2013.2273843 · Cited by 41
Counting Moving People in Videos by Salient Points Detection
Conte, D., Foggia, P., Percannella, G., et al. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.431 · Cited by 36
Action unit classification using active appearance models and conditional random fields
van der Maaten, L. J. P., & Hendriks, E. A. (2011) · Cognitive Processing · doi:10.1007/s10339-011-0419-7 · Cited by 44
“To address this problem, image representations based on image gradients are often more successful (Lowe 2004; Ke and Sukthankar 2004; Dalal and Triggs 2005; Bay et al. 2008).”
BackgroundGraph based construction of textured large field of view mosaics for bladder cancer diagnosis
Weibel, T., Daul, C., Wolf, D., Rösch, R., & Guillemin, F. H. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.05.023 · Cited by 39
Real-Time SURF-Based Video Stabilization System for an FPGA-Driven Mobile Robot
Nou‐Shene, T., Sridharan, K., & Sudha, N. (2016) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2016.2551684 · Cited by 36
“Since interest points are based on the Hessian, they are known to be stable and repeatable [6], [9], [10].”
BackgroundMethodInfluentialA new copy move forgery detection technique with automatic threshold determination
Üstübioğlu, B., Ulutaş, G., Ulutaş, M., & Nabiyev, V. V. (2016) · AEU - International Journal of Electronics and Communications · doi:10.1016/j.aeue.2016.05.005 · Cited by 36
Wetzel, A. W., Bakal, J., Dittrich, M., Hildebrand, D. G. C., Morgan, J. L., & Lichtman, J. W. (2016) · 2016 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) · doi:10.1109/aipr.2016.8010595 · Cited by 36
A novel panoramic image stitching algorithm based on ORB
Wang, M., Niu, S., & Yang, X. (2017) · International Conference on Applied System Innovation · doi:10.1109/icasi.2017.7988559 · Cited by 36
Gaussian field consensus: A robust nonparametric matching method for outlier rejection
Wang, G., Chen, Y., & Zheng, X. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.09.029 · Cited by 36
Versapipe: a versatile programming framework for pipelined computing on GPU
Zheng, Z., Oh, C., Zhai, J., Shen, X., Yi, Y., & Chen, W. (2017) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3123939.3123978 · Cited by 44
Panoramic Robust PCA for Foreground–Background Separation on Noisy, Free-Motion Camera Video
Moore, B. E., Gao, C., & Nadakuditi, R. R. (2019) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2019.2891389 · Cited by 44
Multimodal Medical Image Registration Based on Feature Spheres in Geometric Algebra
Cao, W., Lyu, F., He, Z., Cao, G., & He, Z. (2018) · IEEE Access · doi:10.1109/access.2018.2818403 · Cited by 36
“SURF ALGORITHM In this section, we briefly introduce the SURF algorithm, which has been widely used in computer vision applications [12].”
MethodIntelligent video surveillance for real-time detection of suicide attempts
Bouachir, W., Gouiaa, R., Li, B., & Noumeir, R. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.03.018 · Cited by 36
Toward Improving Safety in Neurosurgery with an Active Handheld Instrument
Moccia, S., Foti, S., Routray, A., Prudente, F., Perin, A., Sekula, R. F., Mattos, L. S., Balzer, J. R., Fellows-Mayle, W. K., Momi, E. D., et al. (2018) · Annals of Biomedical Engineering · doi:10.1007/s10439-018-2091-x · Cited by 37
“When compared to SURF- and FLANN-based 3D reconstruction, the computational cost was higher than the one required by SURF and FLANN (0.11s).”
MethodInfluentialRemote Sensing Image Matching Based Improved ORB in NSCT Domain
Ma, D., & Lai, H. (2019) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-019-00958-y · Cited by 36
“Speed up robust feature (SURF) algorithm is first presented in 2006 by Bay et al. (2006), it is faster and more robust than the SIFT.”
MethodRethinking Planar Homography Estimation Using Perspective Fields
Zeng, R., Denman, S., Sridharan, S., & Fookes, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20876-9_36 · Cited by 37
“First, a hand-crafted detector, such as SIFT [17], ORB [22], KLT [9], SURF [2] etc., is used to extract key points using local invariant features from each image.”
MethodBaig, F., Mehmood, Z., Rashid, M., Javid, M. A., Rehman, A. U., Saba, T., & Adnan, A. (2019) · Iranian Journal of Science and Technology Transactions of Electrical Engineering · doi:10.1007/s40998-019-00237-z · Cited by 46
“After that, SURF (Bay et al. 2006) and CoHOG (Watanabe et al. 2010) features are extracted from the approximation coefficient of the L 3-decomposed image.”
MethodExploiting artificial intelligence for digitally enriched museum visits
Ioannakis, G., Bampis, L., & Koutsoudis, A. (2019) · Journal of Cultural Heritage · doi:10.1016/j.culher.2019.07.019 · Cited by 46
A comparative study for brain tumor detection in MRI images using texture features
Bhagat, P. K., Choudhary, P., & Singh, K. M. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-819361-7.00013-0 · Cited by 44
Multi-Level Features Extraction for Discontinuous Target Tracking in Remote Sensing Image Monitoring
Zhou, B., Duan, X., Ye, D., Wei, W., Woźniak, M., Połap, D., & Damaševičius, R. (2019) · Sensors · doi:10.3390/s19224855 · Cited by 35
Novel Vision-Based Abnormal Behavior Localization of Pantograph-Catenary for High-Speed Trains
Luo, Y., Yang, Q., & Liu, S. (2019) · IEEE Access · doi:10.1109/access.2019.2955707 · Cited by 36
“Traditional object detection is based on image color, shape, and texture, with common feature-extraction methods including speeded up robust features (SURF) [39], the deformable part model (DPM) [40], and methods based on the histogram of oriented gradients (HOGs) [41].”
MethodWang, D., Zhang, Y., Pan, Y., Peng, B., Liu, H., & Ma, R. (2020) · IEEE Access · doi:10.1109/access.2020.2994275 · Cited by 34
DMIB: Dual-Correlated Multivariate Information Bottleneck for Multiview Clustering
Hu, S., Shi, Z., & Ye, Y. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3025636 · Cited by 36
“Three features are adopted to represent images, including SURF [71], Color Attention [67], and TPLBP [69].”
MethodA Log-Rectilinear Transformation for Foveated 360-degree Video Streaming
Li, D., Du, R., Babu, A., Brumar, C. D., & Varshney, A. (2021) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2021.3067762 · Cited by 36
Mozaffarzadeh, M., Moore, C., Barzegar-Golmoghani, E., Mantri, Y., Hariri, A., Jorns, A., Fu, L., Verweij, M. D., Orooji, M., de Jong, N., et al. (2021) · Biomedical Optics Express · doi:10.1364/boe.417345 · Cited by 37
SuperThermal: Matching Thermal as Visible Through Thermal Feature Exploration
Lu, Y., & Lu, G. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3060699 · Cited by 36
“Therefore, traditional interest point detection algorithms that are widely used in practical applications like SIFT [5], SURF [6] and the corresponding descriptors usually fail to obtain accurate matching.”
BackgroundMethodInfluentialUncalibrated stereo vision with deep learning for 6-DOF pose estimation for a robot arm system
Abdelaal, M., Farag, R., Saad, M. S., Bahgat, A., Emara, H. M., & El-Dessouki, A. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103847 · Cited by 43
Bahaghighat, M., Abedini, F., Xin, Q., Zanjireh, M. M., & Mirjalili, S. (2021) · Energy Reports · doi:10.1016/j.egyr.2021.07.077 · Cited by 41
Khan, N. Y., McCane, B., & Mills, S. J. (2015) · Machine Vision and Applications · doi:10.1007/s00138-015-0689-7 · Cited by 48
“Despite these claims, SIFT (or its faster variant SURF [7]) is usually the initial descriptor of choice for imaging system builders.”
MethodFast Target Recognition Based on Improved ORB Feature
Xie, Y., Wang, Q., Chang, Y., & Zhang, X. (2022) · Applied Sciences · doi:10.3390/app12020786 · Cited by 39
“[5] proposed a fast robust feature extraction registration algorithm Speed-Up Robust Features (SURF) in 2006 based on the SIFT algorithm.”
MethodAudio Watermarking for Security and Non-Security Applications
Charfeddine, M., Mezghani, E., Masmoudi, S., Amar, C. B., & Alhumyani, H. A. (2022) · IEEE Access · doi:10.1109/access.2022.3145950 · Cited by 42
Locality-Guided Global-Preserving Optimization for Robust Feature Matching
Xia, Y., & Ma, J. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3192993 · Cited by 57
An improved augmented reality system based on AndAR
Chen, P., Peng, Z., Li, D., & Yang, L. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.06.016 · Cited by 36
“As can be seen from [12] and [13], it takes respectively 5228.7 (ms), 217.3 (ms), 8.87 (ms), and 15.3 (ms) for SIFT, SURF, BRIEF-32 and ORB to process one frame.”
MethodInfluentialMap Building and Monte Carlo Localization Using Global Appearance of Omnidirectional Images
Payá, L., Fernández, L., Gil, A., & Reinoso, Ó. (2010) · Sensors · doi:10.3390/s101211468 · Cited by 35
Model-based spacecraft pose estimation and motion prediction using a photonic mixer device camera
Tzschichholz, T., Ma, L., & Schilling, K. (2010) · Acta Astronautica · doi:10.1016/j.actaastro.2010.10.003 · Cited by 36
A blob detector in color images
Ming, A., & Ma, H. (2007) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1282280.1282335 · Cited by 37
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.