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 7,501–7,600 of 14,752
Image retrieval using dictionary similarity measure
Ranjan, R., Gupta, S., & Venkatesh, K. S. (2018) · Signal Image and Video Processing · doi:10.1007/s11760-018-1359-9 · Cited by 5
“As the number of extracted SIFT feature vectors is not sufficient for training a dictionary, we propose to use both SIFT and SURF [3] (SIFT+SURF) feature vectors as training set.”
MethodParallel supervised land-cover classification system for hyperspectral and multispectral images
Garcia-Salgado, B. P., Ponomaryov, V. I., Sadovnychiy, S., et al. (2018) · Journal of Real-Time Image Processing · doi:10.1007/s11554-018-0828-2 · Cited by 5
Applying Compression to Hierarchical Clustering
Baruch, G., Klein, S. T., & Shapira, D. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-02224-2_12 · Cited by 5
Nagarkar, P., & Candan, K. S. (2018) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3269206.3271691 · Cited by 5
“In the case of images, for example, such feature sets can be extracted using popular localized feature extraction algorithms such as SIFT [13] or SURF [14].”
MethodFine Registration of Mobile and Airborne LiDAR Data Based on Common Ground Points
Chen, Y., Liu, X., Yao, M., et al. (2018) · doi:10.1109/prrs.2018.8486181 · Cited by 5
Registration of Dynamic Thermography Data of the Abdomen of Pregnant and Non-Pregnant Women
Ciantar, A., Falzon, O., Sammut, L., et al. (2018) · doi:10.1109/embc.2018.8513504 · Cited by 5
“The speeded up robust features (SURF) method [12] was subsequently applied to every image to determine salient”
MethodSalient Feature Selection for CNN-Based Visual Place Recognition
Chen, Y., Wenyan, G. A. N., Jiao, S., Xu, Y.-W., & Feng, Y. (2018) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2018edp7175 · Cited by 5
“As the most popular feature extraction methods, appearance-based methods mainly focus on hand-crafted feature extraction, such as SIFT (scale-invariant feature transforms) [2], SURF (speeded up robust features) [3] and FAB-MAP [4], [5].”
MethodFeature Regions Segmentation Based RGB-D Visual Odometry in Dynamic Environment
Zhang, Y., Dai, W., Peng, Z., Ping, L., & Fang, Z. (2018) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2018.8591053 · Cited by 5
“Considering the scale variation and rotation variation of images caused by the camera movement, SURF [23] is used to extract features for balancing the accuracy and performance.”
MethodFull-HD Accelerated and Embedded Feature Detection Video System with 63fps using ORB for FREAK
Kalms, L., Ibrahim, H., & Göhringer, D. (2018) · International Conference on ReConFigurable Computing and FPGAs (ReConFig) · doi:10.1109/reconfig.2018.8641706 · Cited by 5
“[2] E. Rublee, V. Rabaud, K. Konolige and G. Bradski, “ORB: An efficient alternative to SIFT or SURF,” International Conference on Computer Vision, Nov. 2011, pp. 2564-2571.”
MethodInfluentialRobust ConvNet Landmark-Based Visual Place Recognition by Optimizing Landmark Matching
Kong, Y., Liu, W., & Chen, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2901984 · Cited by 7
Toward Generating Human-Centered Video Annotations
Dilawari, A., Khan, M. U. G., Rehman, Z. U., Awan, K. M., Mehmood, I., & Rho, S. (2019) · Circuits Systems and Signal Processing · doi:10.1007/s00034-019-01143-9 · Cited by 5
An Image Processor Bill Acceptor for Iraqi Currency
Abbas, A. A. (2019) · Journal of Al-Nahrain University-Science · doi:10.22401/anjs.22.2.10 · Cited by 6
A Unified Object Detection Framework for Intelligent Retail Container Commodities
Zhao, L., Yao, J., Du, H., Zhao, J., & Zhang, R. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803536 · Cited by 5
“1 [4] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool, “SURF: Speeded up robust features,” in IEEE Conference on European Conference on Computer Vision (ECCV), 2006.”
MethodA Lightweight Leddar Optical Fusion Scanning System (FSS) for Canopy Foliage Monitoring
Xi, Z., Hopkinson, C., Rood, S. B., Barnes, C., Xu, F., Pearce, D., & Jones, E. (2019) · Sensors · doi:10.3390/s19183943 · Cited by 5
“extraction of SURF features [48] is added to the workflow in Figure 3, with outlier features filtered out using the homograph-based RANSAC algorithm [40].”
MethodSearching Document Repositories using 3D Model Reconstruction
Flagg, C., & Frieder, O. (2019) · ACM Symposium on Document Engineering (DocEng) · doi:10.1145/3342558.3345389 · Cited by 5
“These features are constructed using standard techniques (such as SIFT[15], SURF[4], and Fourier Transform[12]).”
MethodRobust template matching with angle location using dynamic feature pairs updating
Yang, Y., Ma, T., & Du, S. (2019) · Applied Soft Computing · doi:10.1016/j.asoc.2019.105804 · Cited by 5
Fusion of CT and MR Liver Images by SURF-Based Registration
Aslan, M. F., Durdu, A., & Sabancı, K. (2019) · International Journal of Intelligent Systems and Applications in Engineering · doi:10.18201/ijisae.2019457233 · Cited by 5
“In this application, SURF [19] matching based registration method was used for fusion of CT and MR images.”
MethodCombination of Wide Baseline Image Matching and Tracking for Autonomous UAV Approaches to a Window
Mueller, K., Atman, J., & Trommer, G. F. (2019) · Gyroscopy and Navigation · doi:10.1134/s2075108719040138 · Cited by 5
“Popular keypoint matching algorithms use, amongst others, Scale Invariant Features (SIFT) [2], Speeded Up Robust Features (SURF) [3], or ORB features [4].”
Method3D Reconstruction of Dense Model based on the Sparse Frames using RGBD Camera
Han, W., Liu, X., Song, S., & Meng, M. Q. ‐. (2019) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio49542.2019.8961428 · Cited by 5
“Acquisition of camera pose: Because the texture of the object and the surrounding background are not rich, it is difficult to solve the pose using the feature point method (such as ORB [2], [3], SIFT [4], SURF [5], etc) and its combination method (such as imu+camera [6], feature point + ICP [7], imu+ICP [8], etc) is n…”
MethodAnalysis and Trends on Moving Object Detection Algorithm Techniques
Pando, A. G., & Chacon-Murguia, M. I. (2019) · IEEE Latin America Transactions · doi:10.1109/tla.2019.8986414 · Cited by 6
Mortensen, U. A., Andersen, T. L., & Mikkelsen, L. P. (2020) · Journal of Composite Materials · doi:10.1177/0021998320902233 · Cited by 5
DeepMEL: Compiling Visual Multi-Experience Localization into a Deep Neural Network
Gridseth, M., & Barfoot, T. D. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197362 · Cited by 9
An Efficient Fragment Reconstruction Using RANSAC Algorithm
Shih, H.-C., Ma, C.-H., & Lu, C.-L. (2019) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce46687.2019.9015254 · Cited by 5
“Speeded Up Robust Features (SURF) [8] is an improve algorithm comparing with SIFT.”
MethodHuman action recognition based on multi-mode spatial-temporal feature fusion
Wang, D., Yang, J., & Zhou, Y. (2019) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion43075.2019.9011361 · Cited by 8
“For hand-crafted features, most popular descriptors are represented by HOG (histogram of oriented gradient) [3], SIFT (scale-invariant feature transform) [4], SURF (speeded up robust features) [5] and MBH (motion boundary histograms) [6].”
MethodPanoramic Video Separation with Online Grassmannian Robust Subspace Estimation
Gilman, K., & Balzano, L. (2019) · doi:10.1109/iccvw.2019.00078 · Cited by 5
“SIFT [17] or SURF [3], to find them and use RANSAC [13] to robustly estimate the H with the best objective value in (1).”
MethodConvolutional bag of words for diabetic retinopathy detection from eye fundus images
Costa, P., & Campilho, A. (2017) · doi:10.23919/mva.2017.7986827 · Cited by 5
Geolocation Error Estimation and Correction on Long-Term MWRI Data
Liu, J., Li, W., Peng, J., Shen, L., Han, H., Zhang, P., & Yang, L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3051199 · Cited by 6
Unsupervised Common Particular Object Discovery and Localization by Analyzing a Match Graph
Okuda, M., Satoh, S., Sato, Y., et al. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413549 · Cited by 5
A three-layer architecture to support disparity map construction in stereo vision systems
Vieira, G. D. S., de Lima, J. C., de Sousa, N. M., & Soares, F. A. A. D. M. N. (2021) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2021.200054 · Cited by 6
Hattab, A., & Behloul, A. (2018) · ICST Transactions on Scalable Information Systems · doi:10.4108/eai.20-10-2021.171547 · Cited by 6
CBIR for urban building using A-KAZE features
Orhei, C., Radu, L., Mocofan, M., et al. (2021) · IEEE International Symposium for Design and Technology in Electronic Packaging (SIITME) · doi:10.1109/siitme53254.2021.9663587 · Cited by 5
“For the incorporated CBIR solution they used SURF features [18] to ensure that the image matching algorithm is robust against variations in illumination, viewpoint, and scale.”
MethodA Smart and Robust Automatic Inspection of Printed Labels Using an Image Hashing Technique
Khan, M. A., Ahmed, F., Khan, M. D., Ahmad, J. E., R, H. K. G., & Pitropakis, N. (2022) · Electronics · doi:10.3390/electronics11060955 · Cited by 5
ROLE OF TIE-POINTS DISTRIBUTION IN AERIAL PHOTOGRAPHY
Kerner, S., Kaufman, I., & Raizman, Y. (2016) · 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-w4-41-2016 · Cited by 5
Image Processing in Intravascular OCT
Wang, Z., Wilson, D. L., Bezerra, H. G., & Rollins, A. M. (2015) · Springer eBooks · doi:10.1007/978-3-319-06419-2_17 · Cited by 5
FASTSLAM USING SURF FEATURES: AN EFFICIENT IMPLEMENTATION AND PRACTICAL EXPERIENCES
Neubert, P., Sünderhauf, N., & Protzel, P. (2007) · IFAC Proceedings Volumes · doi:10.3182/20070903-3-fr-2921.00083 · Cited by 5
Fundamentals of Machine Vision
Stiller, C., Bachmann, A., & Geiger, A. (2015) · Springer eBooks · doi:10.1007/978-3-319-12352-3_21 · Cited by 7
“Detecting and Describing Salient Feature Points Descriptor-based approaches such as SIFT (Lowe 2004), SURF (Bay et al. 2006), BRIEF (Calonder et al.”
MethodAn active monitoring system for real-time face-tracking based on mobile sensors
Saraceni, S., Claudi, A., & Dragoni, A. F. (2012) · Università Politecnica delle Marche (Università Politecnica delle Marche) · Cited by 5
Scalable Image Retrieval Based on Feature Forest
Song, J., Ma, Y., Hu, F., Zhao, Y., & Lao, S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-12297-2_49 · Cited by 5
IA Generative Model for True Orthorectification
Strecha, C., Gool, L. V., & Fua, P. (2008) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 5
Self-citationMarkerless Visual Tracking for Augmented Books
Cho, K., Yoo, J., & Yang, H. S. (2009) · Eurographics · doi:10.2312/egve/jvrc09/013-020 · Cited by 5
Cuevas, E., & Díaz-Cortés, M.-A. (2015) · Computational Intelligence and Neuroscience · doi:10.1155/2015/434263 · Cited by 5
“Such point pairs can be obtained as a result of applying an automatic algorithm of detection and matching [44, 45].”
MethodSession 5: Information security
Ji, Z., Zhou, F., Tian, X., Jiang, R., & Chen, Y. (2013) · IEEE International Conference on Information Science and Technology (ICIST) · doi:10.1109/icist.2013.6747555 · Cited by 5
ALICE: A smartphone assistant used to increase the mobility of visual impaired people
Țapu, R., Mocanu, B., & Zaharia, T. B. (2015) · Journal of Ambient Intelligence and Smart Environments · doi:10.3233/ais-150336 · Cited by 5
“However, we have to mention that we evaluated also with more powerful interest points extractor as SIFT [23] and SURF [1].”
On Feature Tracking in X-Ray Images
Klüppel, M., Wang, J., Bernecker, D., Fischer, P., & Joachim Hornegger, A. (2014) · Informatik aktuell · doi:10.1007/978-3-642-54111-7_28 · Cited by 5
“Despite its scale-space approach, SURF provides higher computational efficiency.”
MethodInfluentialScalable ranked retrieval using document images
Jain, R., Oard, D. W., & Doermann, D. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2038656 · Cited by 5
On Affine Invariant Descriptors Related to SIFT
Sadek, R., Constantinopoulos, C., Meinhardt, E., et al. (2012) · SIAM Journal on Imaging Sciences · doi:10.1137/100798739 · Cited by 5
Real-time Visual Odometry Estimation Based on Principal Direction Detection on Ceiling Vision
Wang, H., Mou, W., Seet, G., Li, M.-H., Lau, M. W. S., & Wang, D.-W. (2013) · Machine Intelligence Research · doi:10.1007/s11633-013-0736-7 · Cited by 5
“Moreover, the runtime for edge detection is much faster compared to scale-invariant feature transform (SIFT) [18] or speeded up robust features (SURF) [19] .”
MethodRobPosit, a robust pose estimator for operator controlled nanomanipulation
Ouarti, N., Sauvet, B., Haliyo, S. D., et al. (2013) · Journal of Micro-Bio Robotics · doi:10.1007/s12213-013-0066-4 · Cited by 5
Airport Runway FOD Detection from LFMCW Radar and Image Data
Guo, J., Luo, Y., Sui, Y., et al. (2015) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.719-720.1124 · Cited by 5
Li, L., Liu, Y., Wang, K., & Fang, M. (2014) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2014.7090502 · Cited by 5
“The processors included an Intel Core i7-2620 CPU and a NVIDIA GTX660 GPU for extracting and tracking SURF points [15] of the environment, matching them in the image sequence, and calculating the optical flow in real time.”
MethodHybrid tracking and visual search
Gao, J. (2008) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1459359.1459519 · Cited by 5
“MATCHING In a previous work we implemented the SURF algorithm [1] on the phone [2].”
BackgroundMethodMedical image registration using machine learning-based interest point detector
Sergeev, S., Zhao, Y., Linguraru, M. G., et al. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.911717 · Cited by 5
Humanoid Robot Navigation: Getting Localization Information from Vision
Wirbel, É., Bonnabel, S., Fortelle, A. D. L., et al. (2014) · Journal of Intelligent Systems · doi:10.1515/jisys-2013-0079 · Cited by 5
An OpenCL-based feature matcher
Condello, G., Pasteris, P., Pau, D. P., et al. (2012) · Signal Processing Image Communication · doi:10.1016/j.image.2012.06.002 · Cited by 5
Multiple-kernel based vehicle tracking using 3-D deformable model and license plate self-similarity
Lee, K.-H., Lee, Y.-J., & Hwang, J. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6637961 · Cited by 7
FEUDOR: Feature Extraction Using Distinctive Octagonal Regions
Emaminejad, A., & Brookes, M. (2008) · British Machine Vision Conference (BMVC) · doi:10.5244/c.22.95 · Cited by 5
Masmoudi, I., El’Arbi, M., & Amar, C. B. (2013) · International Conference on Hybrid Intelligent Systems (HIS) · doi:10.1109/his.2013.6920469 · Cited by 5
“The method SIFT proposed by David Lowe [4], [5] and the method Speeded Up Robust Features SURF [6] include both a key point detector and descriptor and are the most known methods in this methodology.”
MethodA vision-based mobile robot localization method
Chi, W., Zhang, W., Gu, J. J., et al. (2013) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2013.6739882 · Cited by 5
“SURF algorithm is based on the Hessian matrix [13].”
MethodRobustness evaluation of corner detectors for use in ultrasound image processing
Zukal, M., Beneš, R., Číka, P., et al. (2013) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2013.6614041 · Cited by 5
“We will focus in particular on blob detectors like Difference of Gaussians [18] and Fast Hessian [19] which are reported to give very good results on standard images.”
BackgroundA novel framework for semantic-based video retrieval
Nan, X., Zhao, Z., Cai, A., et al. (2009) · doi:10.1109/icicisys.2009.5357647 · Cited by 5
“This is achieved by using a Hessian matrix-based measure as the detector and a distribution-based descriptor [9].”
MethodMulti-Scale Spatial Concatenations of Local Features in Natural Scenes and Scene Classification
Zhu, X., & Yang, Z. (2013) · PLoS ONE · doi:10.1371/journal.pone.0076393 · Cited by 6
Chen, Y., Zhang, R., Shang, L., et al. (2013) · Review of Scientific Instruments · doi:10.1063/1.4809768 · Cited by 5
A SIFT based object recognition using contextual information
Zohrevand, A., Ahmadyfard, A., Pouyan, A., & Imani, Z. (2014) · Iranian Conference on Intelligent Systems (ICIS) · doi:10.1109/iraniancis.2014.6802534 · Cited by 5
“[3] also present a different descriptor so called Speeded Up Robust Features (SURF).”
BackgroundMethodSmart Booklet: Tour guide system with mobile augmented reality
Choi, H., Han, G. C., & Kim, I.-J. (2014) · International Conference on Consumer Electronics · doi:10.1109/icce.2014.6776038 · Cited by 5
An analyst-adaptive approach to focused crawlers
Zunino, R., Bisio, F., Peretti, C., et al. (2013) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1145/2492517.2500328 · Cited by 5
“The structural analysis applies feature-sensitive algorithms [23] and computes a probability distribution of the spatial density of feature points; this yields a 30-dimensional feature vector.”
MethodIdentifying universal facial emotion markers for automatic 3D facial expression recognition
Azazi, A., Lutfi, S. L., & Venkat, I. (2014) · International Conference on Computer and Information Sciences · doi:10.1109/iccoins.2014.6868369 · Cited by 5
“To implement this outline, we infused DE with SURF and SVM in one algorithm to search for the optimal facial markers that maximize the inter-class and minimize the intra-class discrimination between different classes.”
MethodInfluentialA Robust Edge-Based Corner Detector (EBCD)
Nachar, R. A., Inaty, E., Bonnin, P. J., et al. (2014) · International Journal of Image and Graphics · doi:10.1142/s0219467814500181 · Cited by 5
Dense 3D point-cloud model using optical flow for a monocular reconstruction system
Diskin, Y., & Asari, V. K. (2013) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2013.6749315 · Cited by 5
“As shown in Figure 1, the first step is SURF extraction, wherein we locate stable feature points within each frame using the SURF algorithm [7].”
MethodStereo Vision Based Motion Estimation for Underwater Vehicles
Gong, P., Zhang, Q., & Zhang, A. (2009) · International Conference on Intelligent Computation Technology and Automation · doi:10.1109/icicta.2009.646 · Cited by 5
Fast Estimation of Relative Poses for 6-DOF Image Localization
Song, Y., Chen, X., Wang, X., et al. (2015) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2015.10 · Cited by 5
“In consideration of the time efficiency, we use SURF [28] as the local feature which is faster than classical SIFT [29].”
MethodOn the Induction of Topological Maps from Sequences of Colour Histograms
Werner, F., Sitte, J., & Maire, F. (2007) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2007.4426792 · Cited by 5
A compact descriptor CHOG3D and its application in human action recognition
Ji, Y., Shimada, A., Nagahara, H., et al. (2012) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.21793 · Cited by 5
“Then an extended SURF [14] descriptor was used to describe the extracted interest points, which is named ‘ESURF’.”
MethodAn Improved Descriptor for Chinese Character Recognition
Wu, T., Qi, K., Zheng, Q., Chen, K., Chen, J., & Guan, H. (2009) · Intelligent Information Technology Application · doi:10.1109/iita.2009.276 · Cited by 5
“From then, a lot of similar work has been done, such as the Shape Context [5] and SURF [9].”
MethodInterest points as a focus measure
Mekyska, J., Zukal, M., Číka, P., & Smékal, Z. (2012) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2012.6256402 · Cited by 6
Device-tagged feature-based localization and mapping of wide areas with a PTZ camera
Bimbo, A. D., Lisa, G., Masi, I., et al. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543172 · Cited by 5
“The time variant world-to-image homography Gt : Π3D 7→ It is finally obtained as in [9]: Gt = H −1 t ︸ ︷︷ ︸ It←Ii · H−1ih ︸ ︷︷ ︸ Ii←Πh · HW ︸ ︷︷ ︸ Πh←Π3D (2) Localization performs real-time due to the fact that: 1) the keypoints detection and description is performed by exploiting Speed Up Robust Feature (SURF) [3]; 2…”
MethodInfluentialFeature-based calibration of distributed smart stereo camera networks
Mavrinac, A., Chen, X., & Tepe, K. E. (2008) · ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC) · doi:10.1109/icdsc.2008.4635704 · Cited by 6
“Algorithms such as SIFT [20] and SURF [24] employ operations such as the Laplacian of Gaussian (LoG), Difference of Gaussians (DoG), and Determinant of Hessian (DoH) to detect blobs, which include interest points and edges.”
MethodTracking Based on SURF and Superpixel
Liu, Y., Zhou, W., Yin, H., & Yu, N. (2011) · International Conference on Image and Graphics · doi:10.1109/icig.2011.60 · Cited by 7
A Part-Based Skew Estimation Method
Shiraishi, S., Feng, Y., & Uchida, S. (2012) · IAPR International Workshop on Document Analysis Systems (DAS) · doi:10.1109/das.2012.7 · Cited by 5
“As the extraction and the description of local parts, we will use Speeded-Up Robust Features (SURF) detector [2], while we can use another local feature extraction method.”
MethodAdaptive similarity search in large databases - application to image/video copy detection
Gengembre, N., Berrani, S.-A., & Lechat, P. (2008) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2008.4564988 · Cited by 5
“In image applications, local descriptors can be computed around interest points (obtained for instance by a Harris detector [14, 15], a fast hessian [16] or a ”difference of gaussian” approach [17], etc.”
MethodInfluentialWang, T., Gu, I. Y., Khan, Z. H., & Shi, P. (2009) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2009.5202758 · Cited by 5
“The proposed scheme is realized by integrating SURF and RANSAC [8, 9] for estimating consensus point correspondences, and modify an existing particle filter-based eigen-tracking [4].”
MethodInfluentialSemantic Linking between Video Ads and Web Services with Progressive Search
Wang, B., Wang, J., Chen, S., et al. (2009) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2009.43 · Cited by 5
Tracking Salient Keypoints for Human Action Recognition
Wang, H., & Yi, Y. (2015) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2015.530 · Cited by 5
“Second, the good-features-totrack criterion [10] and SURF [18] are used to estimate the homographic transformation using RANSAC [19].”
MethodAn Analysis of the Factors Affecting Keypoint Stability in Scale-Space
Rey-Otero, I., Morel, J., & Delbracio, M. (2016) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-016-0657-5 · Cited by 6
Image registration research based on SUSAN-SURF algorithm
Huiqing, Z., & Gao, L. (2014) · doi:10.1109/ccdc.2014.6852208 · Cited by 5
“The SURF(Speed up Robust Feature)algorithm([4]), proposed by Bay, computing the integral image and Fast Hessian raised the speed of the feature point detection.”
BackgroundRetinal image registration feature descriptors-a survey
Christy, B. M. D., & Moses, C. (2014) · International Conference on Electronics, Circuits, and Systems · doi:10.1109/ecs.2014.6892684 · Cited by 3
Joint geometric graph embedding for partial shape matching in images
Mukhopadhyay, A., Kumar, A., & Bhandarkar, S. M. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477728 · Cited by 5
“We evaluated the results of the proposed JGGE technique and compared them with those obtained using shape matching techniques that use standard features such as SIFT [20], speeded up robust features (SURF) [6], features from accelerated segment test (FAST) [25], oriented FAST and oriented BRIEF (ORB) [26] and GB [8] i…”
MethodHUMAN ACTION RECOGNITION USING CONTINUOUS HMMS AND HOG/HOF SILHOUETTE REPRESENTATION
Khedher, M. I., El‐Yacoubi, M. A., & Dorizzi, B. (2012) · International Conference on Pattern Recognition Applications and Methods · doi:10.5220/0003695905030508 · Cited by 5
Salach, A., Markiewicza, J. S., & Zawieska, D. (2016) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xli-b5-399-2016 · Cited by 5
Improving Robustness of Slow Feature Analysis Based Localization Using Loop Closure Events
Metka, B., Franzius, M., & Bauer-Wersing, U. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-44781-0_58 · Cited by 5
CoMaL: Good Features to Match on Object Boundaries
Ravindran, S. K., & Mittal, A. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.43 · Cited by 6
Perfect Accuracy with Human-in-the-Loop Object Detection
Brenner, R., Priyadarshi, J., & Itti, L. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48881-3_25 · Cited by 6
Karmaker, D., Schiffner, I., Strydom, R., & Srinivasan, M. V. (2016) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2016.7838650 · Cited by 5
Progressive image stitching algorithm for vision based automated inspection
Aliakbar, M., Qidwai, U. A., Jahanshahi, M. R., et al. (2016) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc.2016.7860924 · Cited by 5
Free Form Object Recognition Module using A-KAZE and GCS
Flores-Rodrıguez, K. L., & Trujillo-Romero, F. (2016) · Research in Computing Science · doi:10.13053/rcs-118-1-2 · Cited by 5
“The most popular of them are Scale Invariant Feature Transform [9] (SIFT) and Speeded Up Robust Feature [10] (SURF).”
Mobile Augmented Reality: Evolving Human-Computer Interaction
Sánchez-Acevedo, M. A., Moxo, B. A. S., & Márquez-Domínguez, J. A. (2017) · Advances in e-business research series · doi:10.4018/978-1-5225-2469-4.ch010 · Cited by 5
Advances in visual concept detection
Viitaniemi, V., Sjöberg, M., Koskela, M., Ishikawa, S., & Laaksonen, J. T. (2015) · Elsevier eBooks · doi:10.1016/b978-0-12-802806-3.00012-9 · Cited by 7
“Histograms of robust, scale-invariant local descriptors—such as ScaleInvariant Feature Transform (SIFT) [37] and the Speeded Up Robust Features (SURF) [5]—and later their Fisher Vector encodings provided the state-of-the-art image descriptors between 2008 and 2013.”
BackgroundEdge-Aware Spatial Denoising Filtering Based on a Psychological Model of Stimulus Similarity
Mathew, J., Zollanvari, A., & James, A. P. (2017) · IEEE Access · doi:10.1109/access.2017.2745903 · Cited by 5
Obstacle detection technique using multi sensor integration for small unmanned aerial vehicle
Ramli, M. F., Shamsudin, S. S., & Legowo, A. (2017) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v8.i2.pp441-449 · Cited by 5
“Therefore, the invariant feature based detection technique that is known as SURF [22-24] will be employed in this project.”
MethodRobot Pose Estimation Based on Visual Information and Particle Swarm Optimization
López-Franco, C., Avila, J. E. G., Arana‐Daniel, N., et al. (2018) · Intelligent Automation & Soft Computing · doi:10.31209/2018.100000000 · Cited by 5
A novel approach for scale and rotation adaptive estimation based on time series alignment
Zhao, D., & Du, F. (2018) · The Visual Computer · doi:10.1007/s00371-018-1598-3 · Cited by 5
“A variety of different feature descriptors with low-level data insensitive to RST have been proposed, such as Moravec [12, 13], Harris [14], scale-invariant feature transform (SIFT) [15, 16], very fast SIFT (VF-SIFT) [17], speeded-up robust features (SURF) [18], and ORiented Brief (ORB) [19].”
Background
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.