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 101–200 of 14,752
A review of multimodal image matching: Methods and applications
Jiang, X., Ma, J., Xiao, G., Shao, Z., & Guo, X. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.02.012 · Cited by 532
Context tracker: Exploring supporters and distracters in unconstrained environments
Dinh, T. B., Vo, N., & Medioni, G. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995733 · Cited by 510
Convolutional Neural Network Architecture for Geometric Matching
Rocco, I., Arandjelovic, R., & Sivic, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.12 · Cited by 496
Content-based image retrieval using color difference histogram
Liu, G.-H., & Yang, J.-Y. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2012.06.001 · Cited by 507
A survey of structure from motion.
Özyeşil, O., Voroninski, V., Basri, R., & Singer, A. (2017) · Acta Numerica · doi:10.1017/s096249291700006x · Cited by 489
Plant Species Identification Using Computer Vision Techniques: A Systematic Literature Review
Wäldchen, J., & Mäder, P. (2018) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-016-9206-z · Cited by 489
“Nguyen et al. [103] studied speeded up robust features (SURF) for leaf classification, which was first introduced by [9].”
BackgroundA fast local descriptor for dense matching
Tola, E., Lepetit, V., & Fua, P. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587673 · Cited by 480
Shin, H.-C., Orton, M. R., Collins, D. J., Doran, S. J., & Leach, M. O. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.277 · Cited by 488
Beyond Sharing Weights for Deep Domain Adaptation
Rozantsev, A., Salzmann, M., & Fua, P. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2814042 · Cited by 462
Adaptive and Generic Corner Detection Based on the Accelerated Segment Test
Mair, E., Hager, G. D., Burschka, D., Suppa, M., & Hirzinger, G. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15552-9_14 · Cited by 477
Dardas, N. H., & Georganas, N. D. (2011) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2011.2161140 · Cited by 481
“speeded up robust features (SURF) [15].”
InfluentialLearning object class detectors from weakly annotated video
Prest, A., Leistner, C., Civera, J., Schmid, C., & Ferrari, V. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248065 · Cited by 443
Real-time monocular SLAM: Why filter?
Strasdat, H., Montiel, J. M. M., & Davison, A. J. (2010) · 2010 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2010.5509636 · Cited by 475
Face alignment by coarse-to-fine shape searching
Zhu, S., Li, C., Loy, C. C., & Tang, X. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299134 · Cited by 450
A rapid learning algorithm for vehicle classification
Wen, X., Shao, L., Xue, Y., & Fang, W. (2015) · Information Sciences · doi:10.1016/j.ins.2014.10.040 · Cited by 479
Lupton, T., & Sukkarieh, S. (2012) · IEEE Transactions on Robotics · doi:10.1109/tro.2011.2170332 · Cited by 469
Du, G., Wang, K., Lian, S., & Zhao, K. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-020-09888-5 · Cited by 475
“2D detection SIFT Lowe (1999), FAST Rosten and Drummond (2005), SURF Bay et al. (2006), ORB Rublee et al. (2011), OverFeat Sermanet et al. (2013), Erhan et al. (2014), Szegedy et al. (2014), RCNN Girshick et al. (2014), Fast R-CNN Girshick (2015), Faster RCNN Ren et al. (2015), R-FCN Dai et al. (2016), FPN Lin et al.…”
MethodInfluentialUnsupervised Domain Adaptation by Domain Invariant Projection
Baktashmotlagh, M., Harandi, M. T., Lovell, B. C., & Salzmann, M. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.100 · Cited by 448
Learning With Augmented Features for Supervised and Semi-Supervised Heterogeneous Domain Adaptation
Li, W., Duan, L., Xu, D., & Tsang, I. W. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.167 · Cited by 449
Deep learning for monocular depth estimation: A review
Ming, Y., Meng, X., Fan, C., & Yu, H. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.12.089 · Cited by 454
Mobile Augmented Reality Survey: From Where We Are to Where We Go
Chatzopoulos, D., Bermejo, C., Huang, Z., & Hui, P. (2017) · IEEE Access · doi:10.1109/access.2017.2698164 · Cited by 442
VisualRank: Applying PageRank to Large-Scale Image Search
Jing, Y., & Baluja, S. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.121 · Cited by 441
LifeLogging: Personal Big Data
Gurrin, C., Smeaton, A. F., & Doherty, A. R. (2014) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000033 · Cited by 434
“Bell and Gemmell (2009) in their book “Total Recall” provide a positive and optimistic bigger picture of the potential of lifelogging.”
BackgroundMethodInfluentialOptical flow modeling and computation: A survey
Fortun, D., Bouthemy, P., & Kervrann, C. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.02.008 · Cited by 431
“The similarity measures can be patch-based distances (see Section 3.1.2), or more complex and sparse feature descriptions often based on histogram of oriented gradients [20,71,169,282], or segment matching [258].”
BackgroundInfluentialMedical image retrieval using deep convolutional neural network
Qayyum, A., Anwar, S. M., Awais, M., & Majid, M. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.05.025 · Cited by 433
CosyPose: Consistent multi-view multi-object 6D pose estimationPreprint
Labbé, Y., Carpentier, J., Aubry, M., & Šivic, J. (2020) · arXiv (Cornell University) · Cited by 434
Robotic tactile perception of object properties: A review
Luo, S., Bimbo, J., Dahiya, R., & Liu, H. (2017) · Mechatronics · doi:10.1016/j.mechatronics.2017.11.002 · Cited by 425
Pose tracking from natural features on mobile phones
Wagner, D., Reitmayr, G., Mulloni, A., Drummond, T., & Schmalstieg, D. (2008) · 2008 7th IEEE/ACM International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2008.4637338 · Cited by 420
Gesture recognition for human-robot collaboration: A review
Liu, H., & Wang, L. (2018) · International Journal of Industrial Ergonomics · doi:10.1016/j.ergon.2017.02.004 · Cited by 422
“Learning algorithms such as Support Vector Machine (SVM), Arti fi cial Neural Networks (ANN) and Random Decision Forests (RDF) are widely applied in gesture recognition systems (Ronfard et al., 2002; Lee et al., 2003; Tang et al., 2014).”
A Survey of Urban Reconstruction
Musialski, P., Wonka, P., Aliaga, D. G., Wimmer, M., van Gool, L., & Purgathofer, W. (2013) · Computer Graphics Forum · doi:10.1111/cgf.12077 · Cited by 429
“One of the key inventions which advanced this research field are robust feature-point detection algorithms, like SIFT [Low04] and SURF [BTvG06, BETvG08].”
BackgroundSelf-citation3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
Yew, Z. J., & Lee, G. H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01267-0_37 · Cited by 392
Classification of Breast Cancer Based on Histology Images Using Convolutional Neural Networks
Bardou, D., Zhang, K., & Ahmad, S. M. (2018) · IEEE Access · doi:10.1109/access.2018.2831280 · Cited by 414
Tang, J., Deng, C., Huang, G.-B., & Zhao, B. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2335751 · Cited by 407
Evaluation of deep convolutional nets for document image classification and retrieval
Harley, A. W., Ufkes, A., & Derpanis, K. G. (2015) · 2015 13th International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2015.7333910 · Cited by 394
CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
Hu, S., Feng, M., Nguyen, R. M. H., & Lee, G. H. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00758 · Cited by 394
“This causes cross-view matching with traditional handcrafted features like SIFT [25] and SURF [7] to fail.”
MethodTransfer learning for image classification using VGG19: Caltech-101 image data set
Bansal, M., Kumar, M., Sachdeva, M., & Mittal, A. (2023) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03488-z · Cited by 394
“It is developed by Bay et al. (2006). The interest points of an image are detected by approximating the Laplacian-of-Gaussian (LoG) with a Box filter.”
MethodRemote Sensing Image Registration With Modified SIFT and Enhanced Feature Matching
Ma, W., Wen, Z., Wu, Y., Jiao, L., Gong, M., Zheng, Y., & Liu, L. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2016.2600858 · Cited by 389
“Considering the results in Table I, SIFT, SAR-SIFT, and SURF fail to register the test pair P-A.”
MethodInfluentialReal-time stereo visual odometry for autonomous ground vehicles
Howard, A. (2008) · 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2008.4651147 · Cited by 383
Image matching across wide baselines: From paper to practice
Jin, Y., Mishkin, D., Mishchuk, A., Matas, J., Fua, P., Yi, K. M., & Trulls, E. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01385-0 · Cited by 388
“The first includes full, hand-crafted pipelines: SIFT [48] (and RootSIFT [6]), SURF [15], ORB [73], and AKAZE [4].”
BackgroundMethodPlace Recognition with ConvNet Landmarks: Viewpoint-Robust, Condition-Robust, Training-Free
Suenderhauf, N., Shirazi, S., Jacobson, A., Dayoub, F., Pepperell, E., Upcroft, B., & Milford, M. (2015) · Robotics: Science and Systems XI · doi:10.15607/rss.2015.xi.022 · Cited by 379
Color-to-Grayscale: Does the Method Matter in Image Recognition?
Kanan, C., & Cottrell, G. W. (2012) · PLoS ONE · doi:10.1371/journal.pone.0029740 · Cited by 384
Berg, T., & Belhumeur, P. N. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.128 · Cited by 372
From BoW to CNN: Two Decades of Texture Representation for Texture Classification
Liu, L., Chen, J., Fieguth, P., Zhao, G., Chellappa, R., & Pietikäinen, M. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-018-1125-z · Cited by 375
“This gave rise to the development of local invariant descriptors, particularly milestone texture features such as Scale Invariant Feature Transform (SIFT) [135], Speeded Up Robust Features (SURF) [12] and LBP [163].”
BackgroundMethodResearch Advances and Challenges of Autonomous and Connected Ground Vehicles
Eskandarian, A., Wu, C., & Sun, C. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2958352 · Cited by 381
PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
Bai, X., Luo, Z., Zhou, L., Chen, H., Li, L., Hu, Z., Fu, H., & Tai, C.-L. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01560 · Cited by 366
RTM3D: Real-Time Monocular 3D Detection from Object Keypoints for Autonomous Driving
Li, P., Zhao, H., Liu, P., & Cao, F. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58580-8_38 · Cited by 365
“The SIFT, SUFT and other traditional keypoint detection methods [26, 1]computed an image pyramid to solve the scaleinvariant problem.”
BackgroundMethodAutonomous multi-floor indoor navigation with a computationally constrained MAV
Shen, S., Michael, N., & Kumar, V. (2011) · 2011 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2011.5980357 · Cited by 357
Fang, W., Ding, L., Zhong, B., Love, P. E. D., & Luo, H. (2018) · Advanced Engineering Informatics · doi:10.1016/j.aei.2018.05.003 · Cited by 356
R2D2: Repeatable and Reliable Detector and Descriptor
Revaud, J., Weinzaepfel, P., de Souza, C. R., Pion, N., Csurka, G., Cabon, Y., & Humenberger, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.06195 · Cited by 334
“Classical approaches to implement this ability are based on a two-stage pipeline that first detects keypoint locations [28, 17, 27, 26] and then computes a local descriptor for each keypoint [4, 25].”
MethodEfficient Subwindow Search: A Branch and Bound Framework for Object Localization
Lampert, C. H., Blaschko, M. B., & Hofmann, T. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.144 · Cited by 344
Description of Interest Regions with Center-Symmetric Local Binary Patterns
Heikkilä, M., Pietikäinen, M., & Schmid, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11949619_6 · Cited by 348
“For some interesting recent work on interest region description done after this study, see [8,9,10,11].”
BackgroundA review of 3D reconstruction techniques in civil engineering and their applications
Ma, Z., & Liu, S. (2018) · Advanced Engineering Informatics · doi:10.1016/j.aei.2018.05.005 · Cited by 347
“In SURF detector [31,32], a scale space is generated based on integral images, and the approximated determinant of the Hessian of each pixel in the scale space is calculated.”
BackgroundMethodUsing Inertial Sensors for Position and Orientation Estimation
Kok, M., Hol, J. D., & Schön, T. B. (2017) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000094 · Cited by 347
Efficient large-scale multi-view stereo for ultra high-resolution image sets
Tola, E., Strecha, C., & Fua, P. (2012) · Machine Vision and Applications · doi:10.1007/s00138-011-0346-8 · Cited by 328
State of the Art on 3D Reconstruction with RGB‐D Cameras
Zollhöfer, M., Stotko, P., Görlitz, A., Theobalt, C., Nießner, M., Klein, R., & Kolb, A. (2018) · Computer Graphics Forum · doi:10.1111/cgf.13386 · Cited by 339
TILDE: A Temporally Invariant Learned DEtector
Verdie, Y., Yi, K. M., Fua, P., & Lepetit, V. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299165 · Cited by 332
Text-based CAPTCHA strengths and weaknesses
Bursztein, E., Martin, M., & Mitchell, J. (2011) · Proceedings of the 18th ACM conference on Computer and communications security · doi:10.1145/2046707.2046724 · Cited by 340
Deep Fuzzy Hashing Network for Efficient Image Retrieval
Lu, H., Zhang, M., Xu, X., Li, Y., & Shen, H. T. (2021) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2020.2984991 · Cited by 340
“Earlier work commonly utilizes hand-crafted real-valued features [1], [2], [7]–[9] for image representations and rank the images in the database regarding their”
MethodColor Invariants for Person Reidentification
Kviatkovsky, I., Adam, A., & Rivlin, E. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.246 · Cited by 333
“Hamdoun et al. [5] perform person reidentification by matching SURF interest points descriptors accumulated through short video sequences.”
Real-Time Detection and Tracking for Augmented Reality on Mobile Phones
Wagner, D., Reitmayr, G., Mulloni, A., Drummond, T., & Schmalstieg, D. (2010) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2009.99 · Cited by 334
Multiple feature hashing for real-time large scale near-duplicate video retrieval
Song, J., Yang, Y., Huang, Z., Shen, H. T., & Hong, R. (2011) · Proceedings of the 19th ACM international conference on Multimedia · doi:10.1145/2072298.2072354 · Cited by 334
“The well-known local feature based approaches include keypoint based local feature detection approach (e.g., SIFT [14]) and some others [2].”
MethodPeriocular Biometrics in the Visible Spectrum
Park, U., Jillela, R. R., Ross, A., & Jain, A. K. (2011) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2010.2096810 · Cited by 332
Image driven machine learning methods for microstructure recognition
Chowdhury, A., Kautz, E., Yener, B., & Lewis, D. (2016) · Computational Materials Science · doi:10.1016/j.commatsci.2016.05.034 · Cited by 326
A Scalable Approach to Activity Recognition based on Object Use
Wu, J., Osuntogun, A., Choudhury, T., Philipose, M., & Rehg, J. M. (2007) · 2007 IEEE 11th International Conference on Computer Vision · doi:10.1109/iccv.2007.4408865 · Cited by 324
“SURF features [2]) could be used to replace SIFT features.”
MethodImage retrieval based on micro-structure descriptor
Liu, G.-H., Li, Z.-Y., Zhang, L., & Xu, Y. (2011) · Pattern Recognition · doi:10.1016/j.patcog.2011.02.003 · Cited by 323
Learning to Localize Objects with Structured Output Regression
Blaschko, M. B., & Lampert, C. H. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88682-2_2 · Cited by 324
An Overview to Visual Odometry and Visual SLAM: Applications to Mobile Robotics
Yousif, K., Bab-Hadiashar, A., & Hoseinnezhad, R. (2015) · Intelligent Industrial Systems · doi:10.1007/s40903-015-0032-7 · Cited by 322
“Speeded Up Robust Features (SURF) [10] is a feature (blob) detector and descriptor that is largely inspired by SIFT.”
MethodA Robust and Efficient Video Representation for Action Recognition
Wang, H., Oneata, D., Verbeek, J., & Schmid, C. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-015-0846-5 · Cited by 317
“We extract speeded-up robust features (SURF; Bay et al, 2006) and match them based on the nearest neighbor rule.”
Comparative Evaluation of Hand-Crafted and Learned Local Features
Schonberger, J. L., Hardmeier, H., Sattler, T., & Pollefeys, M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.736 · Cited by 310
Learning with Augmented Features for Heterogeneous Domain Adaptation
Duan, L., Xu, D., & Tsang, I. (2012) · arXiv · doi:10.48550/arxiv.1206.4660 · Cited by 320
Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors
Qin, D., Gammeter, S., Bossard, L., Quack, T., & van Gool, L. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995373 · Cited by 305
Self-citationObject Detection Using Deep Learning, CNNs and Vision Transformers: A Review
Amjoud, A. B., & Amrouch, M. (2023) · IEEE Access · doi:10.1109/access.2023.3266093 · Cited by 318
“To do this, we apply methods such as Haar-Like features [46], HOG [37], Scale-Invariant Feature Transform (SIFT) [47], Speeded Up Robust Feature (SURF) [48], and Binary Robust Independent Elementary Features (BRIEF) [49].”
MethodA Linear Time Histogram Metric for Improved SIFT Matching
Pele, O., & Werman, M. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88690-7_37 · Cited by 305
“1 Introduction Histograms of oriented gradient descriptors [3–6] are ubiquitous tools in numerous computer vision tasks.”
BackgroundA Partial Intensity Invariant Feature Descriptor for Multimodal Retinal Image Registration
Chen, J., Tian, J., Lee, N., Zheng, J., Smith, R. T., & Laine, A. F. (2010) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2010.2042169 · Cited by 311
“Another local feature named speeded up robust features (SURF) [57] has also been proposed, which is several times faster and more robust against different image transformations than SIFT claimed by its authors.”
InfluentialAutomatic Extrinsic Calibration of a Camera and a 3D LiDAR Using Line and Plane Correspondences
Zhou, L., Li, Z., & Kaess, M. (2018) · 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593660 · Cited by 308
“In [30], they solve the extrinsic calibration problem by minimizing the SURF descriptor [31] error of the projection of the laser points among different frames.”
Image Forgery Detection Using Adaptive Oversegmentation and Feature Point Matching
Pun, C.-M., Yuan, X.-C., & Bi, X.-L. (2015) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2015.2423261 · Cited by 305
Weakly Supervised Localization and Learning with Generic Knowledge
Deselaers, T., Alexe, B., & Ferrari, V. (2012) · International Journal of Computer Vision · doi:10.1007/s11263-012-0538-3 · Cited by 272
“We use SURF descriptors (Bay et al. 2008; Lampert et al. 2009b) and quantize them into 2000 words using k-means.”
InfluentialScaramuzza, D., Achtelik, M. C., Doitsidis, L., Friedrich, F., Kosmatopoulos, E., Martinelli, A., Achtelik, M. W., Chli, M., Chatzichristofis, S., Kneip, L., et al. (2014) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2014.2322295 · Cited by 299
Understanding network failures in data centers: measurement, analysis, and implications
Gill, P., Jain, N., & Nagappan, N. (2011) · ACM SIGCOMM Computer Communication Review · doi:10.1145/2043164.2018477 · Cited by 304
Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors
Li, F., Shirahama, K., Nisar, M., Köping, L., & Grzegorzek, M. (2018) · Sensors · doi:10.3390/s18020679 · Cited by 302
Remote Sensing Object Detection in the Deep Learning Era—A Review
Gui, S., Song, S., Qin, R., & Tang, Y. (2024) · Remote Sensing · doi:10.3390/rs16020327 · Cited by 305
Fast Matching of Binary Features
Muja, M., & Lowe, D. G. (2012) · 2012 Ninth Conference on Computer and Robot Vision · doi:10.1109/crv.2012.60 · Cited by 297
Performance evaluation of local colour invariants
Burghouts, G. J., & Geusebroek, J.-M. (2009) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2008.07.003 · Cited by 295
Face Anti-Spoofing using Speeded-Up Robust Features and Fisher Vector Encoding
Boulkenafet, Z., Komulainen, J., & Hadid, A. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2630740 · Cited by 275
Symmetry-driven accumulation of local features for human characterization and re-identification
Bazzani, L., Cristani, M., & Murino, V. (2013) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2012.10.008 · Cited by 295
Robertson, S., Azizpour, H., Smith, K., & Hartman, J. (2018) · Translational Research · doi:10.1016/j.trsl.2017.10.010 · Cited by 295
“Until a few years ago, the most common types of image representations used in the literature as well as industry were hand-crafted by humans, such as scale-invariant feature transform, 131 speeded-up robust features, 132 and local binary patterns.”
BackgroundDeepFake Detection for Human Face Images and Videos: A Survey
Malik, A., Kuribayashi, M., Abdullahi, S. M., & Khan, A. N. (2022) · IEEE Access · doi:10.1109/access.2022.3151186 · Cited by 297
Large-Scale Video Summarization Using Web-Image Priors
Khosla, A., Hamid, R., Lin, C.-J., & Sundaresan, N. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.348 · Cited by 283
“We extracted SURF [4] descriptors in a dense grid with grid spacing of 6 and learn a codebook of size 256 using k-means clustering.”
MethodEitz, M., Richter, R., Boubekeur, T., Hildebrand, K., & Alexa, M. (2012) · ACM Transactions on Graphics · doi:10.1145/2185520.2185527 · Cited by 287
Back to the Feature: Learning Robust Camera Localization from Pixels to Pose
Sarlin, P.-E., Unagar, A., Larsson, M., Germain, H., Toft, C., Larsson, V., Pollefeys, M., Lepetit, V., Hammarstrand, L., Kahl, F., et al. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00326 · Cited by 297
Total recall II: Query expansion revisited
Chum, O., Mikulik, A., Perdoch, M., & Matas, J. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995601 · Cited by 287
“Virtually all aspects of particular object BoW-type retrieval have been intensively studied: feature detectors and descriptors [14, 5, 25, 15, 16], vocabulary construction [23, 18, 21, 9, 17], spatial verification and re-ranking [21, 9], document metric learning [12, 10, 6] and dimensionality reduction [11, 20].”
BackgroundWeb AR: A Promising Future for Mobile Augmented Reality—State of the Art, Challenges, and Insights
Qiao, X., Ren, P., Dustdar, S., Liu, L., Ma, H., & Chen, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2895105 · Cited by 293
Appearance-Guided Monocular Omnidirectional Visual Odometry for Outdoor Ground Vehicles
Scaramuzza, D., & Siegwart, R. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2004490 · Cited by 292
Registration of Laser Scanning Point Clouds: A Review
Cheng, L., Chen, S., Liu, X., Xu, H., Wu, Y., Li, M., & Chen, Y. (2018) · Sensors · doi:10.3390/s18051641 · Cited by 287
Going Deep in Medical Image Analysis: Concepts, Methods, Challenges, and Future Directions
Altaf, F., Islam, S. M. S., Akhtar, N., & Janjua, N. K. (2019) · IEEE Access · doi:10.1109/access.2019.2929365 · Cited by 286
Sakaridis, C., Dai, D., & Van Gool, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00747 · Cited by 281
Self-citationGirod, B., Chandrasekhar, V., Chen, D., Cheung, N.-M., Grzeszczuk, R., Reznik, Y., Takacs, G., Tsai, S., & Vedantham, R. (2011) · IEEE Signal Processing Magazine · doi:10.1109/msp.2011.940881 · Cited by 283
Highly scalable appearance-only SLAM - FAB-MAP 2.0
Cummins, M., & Newman, P. (2009) · Robotics: Science and Systems V · doi:10.15607/rss.2009.v.039 · Cited by 282
“In this paper, the raw sensor data of interest is imagery, processed with the SURF feature detector [17], though in principle the approach is applicable to any sensor or combination of sensors, and we have explored multisensory applications elsewhere [18].”
MethodDeep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation
Kehl, W., Milletari, F., Tombari, F., Ilic, S., & Navab, N. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_13 · Cited by 283
Chaves, D., Fidalgo, E., Alegre, E., Alaiz-Rodríguez, R., Jáñez-Martino, F., & Azzopardi, G. (2020) · Sensors · doi:10.3390/s20164491 · Cited by 286
“After that, many works followed this direction and more features were proposed with a similar structure of the Viola-Jones detector, including SURF [19], HoG [20] and LBP [21].”
Method
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.