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 7,001–7,100 of 14,752
A Motion-Insensitive Dissolve Detection Method with SURF
Wang, Y., Yang, Y., Ren, T., et al. (2009) · International Conference on Image and Graphics · doi:10.1109/icig.2009.27 · Cited by 6
“SURF feature is an extension of SIFT, which has better robustness and efficiency than SIFT [15].”
MethodPart-Based High Accuracy Recognition of Serial Numbers in Bank Notes
Feng, B., Ren, M., Zhang, X.-Y., & Suen, C. Y. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11656-3_19 · Cited by 6
“In the training step, we do not need to extract the SURF feature vector and build a dictionary.”
MethodCompact and efficient CBCD scheme based on integrated color features
Roopalakshmi, R., & Reddy, G. R. M. (2011) · International Conference on Recent Trends in Information Technology · doi:10.1109/icrtit.2011.5972370 · Cited by 6
Visual object categorization with new keypoint-based adaBoost features
Bdiri, T., Moutarde, F., & Steux, B. (2009) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2009.5164310 · Cited by 7
“available in the Camellia ( http://camellia.sourceforge.net ) image processing library. These Camellia key-points detection and descriptor functions – named CamKeypoints - implement a variant of SURF [10]. SURF itself is an extremely efficient method (thanks to the use of integral images) inspired from the more classi…”
MethodIntrinsic feature pose measurement for awake animal SPECT imaging
Goddard, J. S., Baba, J. S., Lee, S. J., et al. (2009) · 2006 IEEE Nuclear Science Symposium Conference Record · doi:10.1109/nssmic.2009.5402024 · Cited by 6
Estimation analysis in VSLAM for UAV application
Li, X., Aouf, N., & Nemra, A. (2012) · IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) · doi:10.1109/mfi.2012.6343039 · Cited by 7
Detection of Image Fragments Related by Affine Transforms: Matching Triangles and Ellipses
Paradowski, M., & Sluzek, A. S. (2010) · International Conference on Information Science and Applications · doi:10.1109/icisa.2010.5480532 · Cited by 6
Uchiyama, H., Saitô, H., Nivesse, V., et al. (2008) · Cited by 6
3D SLAM in texture-less environments using rank order statistics
Yousif, K., Bab‐Hadiashar, A., & Hoseinnezhad, R. (2015) · Robotica · doi:10.1017/s0263574715000831 · Cited by 6
Temporally Robust Global Motion Compensation by Keypoint-Based Congealing
Safdarnejad, S. M., Atoum, Y., & Liu, X. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46466-4_7 · Cited by 6
Terrain Relative Navigation Using Crater Identification in Surface Topography Data
Rohrschneider, R. R. (2011) · AIAA Guidance, Navigation, and Control Conference and Exhibit · doi:10.2514/6.2011-6490 · Cited by 6
AUTONOMOUS NAVIGATION OF A 5 GRAM CRAWLING MILLIROBOT IN A COMPLEX ENVIRONMENT
Mathis, A., Russell, J., Moore, T., Cohen, J., Satterfield, B., Kohut, N. J., Fu, X., & Fearing, R. S. (2012) · WORLD SCIENTIFIC eBooks · doi:10.1142/9789814415958_0019 · Cited by 9
Mapari, S. A., & Dani, A. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-47952-1_12 · Cited by 6
Localized Harris-FAST interest point detector
Karthik, O. S., Varun, D., & Ramasangu, H. (2016) · IEEE India Conference · doi:10.1109/indicon.2016.7839107 · Cited by 6
“SURF is further improved to upright form of our descriptor (U-SURF) that is not invariant to image rotation and thusly speedier to figure and more qualified for applications where the camera stays more or less horizontal [8].”
BackgroundDirectcha: A proposal of spatiometric mental rotation CAPTCHA
Sano, A., Fujita, M., & Nishigaki, M. (2016) · Conference on Privacy, Security and Trust · doi:10.1109/pst.2016.7907021 · Cited by 6
An effective fusion model for image retrieval
Mansourian, L., Abdullah, M. T., Abdullah, L. N., et al. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5192-x · Cited by 6
Reliable Monocular Ego-Motion Estimation System in Rainy Urban Environments
Huang, H., Sun, Y., & Liu, M. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8916977 · Cited by 6
“Given a sequential image pair I k ; I k +1 , the global-based approach utilizes distinctive features [28], [29], [30] as sparse representation for a single image.”
MethodCNN Based Handwritten Character Recognition
Wang, S., Chen, L., Wu, C., Fan, W., Sun, J., & Naoi, S. (2017) · WORLD SCIENTIFIC eBooks · doi:10.1142/9789813143685_0003 · Cited by 6
The SmartVision Navigation Prototype for the Blind
du Buf, J. M. H., Barroso, J., Rodrigues, J. M. F., Paredes, H., Farrajota, M., Fern, H., José, J., -, V. T., & Saleiro, M. (2010) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · Cited by 6
Learning, Modeling, and Understanding Vehicle Surround Using Multi-Modal Sensing /
Sivaraman, S. (2013) · eScholarship (California Digital Library) · Cited by 9
Human Pose Recognition Using Neural Networks, Synthetic Models, And Modern Features
Kruis, M. (2010) · SHAREOK (University of Oklahoma; Oklahoma State University; Central Oklahoma University) · Cited by 6
Sensing for HOV/HOT Lanes Enforcement
Morris, T., Morellas, V., Canelon-Suarez, D., et al. (2017) · University of Minnesota Digital Conservancy (University of Minnesota) · Cited by 6
High-Precision Localization Using Ground TexturePreprint
Zhang, L., Finkelstein, A., & Rusinkiewicz, S. M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.10687 · Cited by 6
“While SIFT [30] has been popular since its introduction more than a decade ago, more recent alternatives such as SURF [35], ORB [36] have been shown to achieve similar performance at lower computational cost.”
MethodBaek, I., Davies, A., Yan, G., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.06077 · Cited by 6
Instance Search via Instance Level Segmentation and Feature RepresentationPreprint
Yu, Z., & Zhao, W. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03576 · Cited by 6
“All these approaches are built upon image local features such as SIFT [21], Root-SIFT [22], SURF [23].”
MethodAn Overview of Perception Methods for Horticultural Robots: From Pollination to HarvestPreprint
Ahn, H. S., Dayoub, F., Popović, M., MacDonald, B. A., Siegwart, R., & Sa, I. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.03124 · Cited by 11
“…such as the shape, color, texture, or spatial orientation of the fruit using various feature representations such as the local binary pattern (LBP, texture features) [32] and a histogram of gradients (HoG, geometry and structure features) [33], SIFT [34] or SURF [35] (key-points features).”
Method2nd Place and 2nd Place Solution to Kaggle Landmark Recognition andRetrieval Competition 2019Preprint
Chen, K., Cui, C., Du, Y., Meng, X., & Ren, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.03990 · Cited by 6
Domain-Size Pooling in Local Descriptors: DSP-SIFTPreprint
Dong, J., & Soatto, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.8556 · Cited by 6
“However, similar considerations holds for scale and domain-size sampling.”
BackgroundAccelerating Large-Kernel Convolution Using Summed-Area TablesPreprint
Zhang, L., Halber, M., & Rusinkiewicz, S. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.11367 · Cited by 11
Deep learning based monocular visual-inertial odometry
Esfahani, M. A. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/152280 · Cited by 6
Human inspired robotic path planning and heterogeneous robotic mapping
Williams, H. A. (2016) · Open Access Victoria University of Wellington | Te Herenga Waka (Figshare) · doi:10.26686/wgtn.17014175 · Cited by 6
“Common feature finding approaches such as SIFT [63] and SURF [4] can handle scaling and rotations of images, enabling pose invariance.”
MethodVisual Place Recognition for Simultaneous Localization and Mapping
Tsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2022) · Wiley eBooks · doi:10.1002/9781394152636.ch4 · Cited by 7
User localisation using visual sensing and RF signal strength
Conaire, C. Ó., Fogarty, K., Brennan, C., et al. (2008) · Arrow@dit (Dublin Institute of Technology) · Cited by 6
Simultaneous Localization and Mapping (SLAM) : towards an autonomous search and rescue aiding drone
Heukels, F. R. (2015) · Cited by 6
Route Positioning System for Campus Shuttle Bus Service Using a Single Camera
An, J. (2024) · Electronics · doi:10.3390/electronics13112004 · Cited by 5
Multidirectional Enhancement Model Based on SIFT for GPR Underground Pipeline Recognition
Chen, H., Yang, X., Gong, J., et al. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3458452 · Cited by 5
“Currently, variants of this method, such as SURF, have emerged [29].”
MethodSCPNet: Unsupervised Cross-Modal Homography Estimation via Intra-modal Self-supervised Learning
Zhang, R., Ma, J., Cao, S.-Y., Luo, L., Yu, B., Chen, S., Li, J., & Shen, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73337-6_26 · Cited by 17
Geo‐spatial traffic behaviour analysis and anomaly detection for ITS applications
Akdag, E., D’Amicantonio, G., Vijverberg, J. A., Stajan, D., Beers, B. J., de With, P. H. N., & Bondarev, E. (2024) · IET Intelligent Transport Systems · doi:10.1049/itr2.12591 · Cited by 7
Benmabrouk, Y., Djaffal, S., Gasmi, M., et al. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107700 · Cited by 5
OS-CycleGAN: Modified CycleGAN-Based Descriptors for Optical and SAR Image Matching
Liaghat, A., Helfroush, M. S., Norouzi, J., Danyali, H., & Guerrero, J. M. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3575193 · Cited by 9
“To improve the SIFT performance, many methods such as PCA-SIFT [14], ASIFT [15], SURF [16], FAST [17], KAZE [18], accelerated KAZE [19], and SAR-SIFT [13] were presented.”
Singh, J., Kashyap, R., Bansal, K., Das, R., Sandhu, K. S., Singh, G., & Saini, D. K. (2025) · Journal of Plant Pathology · doi:10.1007/s42161-025-01983-2 · Cited by 7
Coding mode decision algorithm for binary descriptor coding
Monteiro, P., & Ascenso, J. (2014) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · Cited by 5
A design of a GP-GPU based stream processor for an image processing
Lee, K.-Y., Kyung, G., Park, T.-R., et al. (2015) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2015.7296320 · Cited by 5
Using the Microsoft Kinect to Model the Environment of an Anthropomimetic Robot
Devereux, D., Mitra, B. K., Holland, O. E., et al. (2011) · Biomechanics / 752: Robotics · doi:10.2316/p.2011.752-061 · Cited by 5
Fast method for reconstruction of 3D coordinates
Bolecek, L., Říčný, V., & Slanina, M. (2012) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2012.6256395 · Cited by 5
Robust facial expression tracking based on composite constraints AAM
Feng, X., Shen, X., Zhou, M., et al. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6116306 · Cited by 5
THE REGISTRATION OF POINT CLOUD DATA FROM RANGE IMAGING CAMERA
Altuntaş, C., & Yıldız, F. (2013) · Geodesy and Cartography · doi:10.3846/20296991.2013.840358 · Cited by 5
Two-Edge-Corner Image Features for Registration of Geospatial Images with Large View Variations
Saeedi, P., & Mao, M. (2014) · International Journal of Geosciences · doi:10.4236/ijg.2014.511109 · Cited by 5
“Comparison with the State of the Art In order to compare the quality of 2EC features with that of the state of the art, three popular features including SIFT [25], SURF [26], and ASIFT [27] were utilized.”
MethodA similarity measure for analyzing human activities using human-object interaction context
Amiri, S., Pourazad, M. T., Nasiopoulos, P., & Leung, V. C. M. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025480 · Cited by 5
“Implementation details In this work, we use the SURF (Speeded Up Robust Features) [19] feature as implemented in the OpenCV library for extracting features from still images.”
MethodInfluentialCompression of 2D and 3D navigation video sequences using skip mode masking of static areas
Springer, D., Simmet, F., Niederkorn, D., et al. (2012) · Picture Coding Symposium · doi:10.1109/pcs.2012.6213352 · Cited by 5
“SURF and other accelerated feature transforms have the benefit of reduced complexity compared to SIFT [2], but come at some costs: when used for navigation, we noticed increased affinity for features in static areas, like white-on-black letters or sharp T-junctions.”
MethodInfluentialNew framework for Simultaneous Localization and Mapping: Multi map SLAM
Herath, D. C., Kodagoda, S., & Dissanayake, G. (2008) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2008.4543483 · Cited by 5
A visual compass for robot soccer
Aşık, O., & Akın, H. L. (2014) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2014.6830651 · Cited by 5
Tracking multiple people in real time based on their trajectory
Hdioud, B., Rachid, O. H. T., & Tirari, M. E. H. (2013) · International Conference on Intelligent Systems: Theories and Applications · doi:10.1109/sita.2013.6560801 · Cited by 5
Learning Robot Vision for Assisted Living
Yan, W., Torta, E., van der Pol, D., Meins, N., Weber, C., Cuijpers, R. H., & Wermter, S. (2012) · IGI Global eBooks · doi:10.4018/978-1-4666-2672-0.ch015 · Cited by 7
Exploring visual dictionaries: A model driven perspective
Aslan, S., Akgül, C. B., Sankur, B., & Tunalı, E. T. (2017) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2017.09.009 · Cited by 4
Adversarial Training for Adverse Conditions: Robust Metric Localisation Using Appearance Transfer
Porav, H., Maddern, W., & Newman, P. M. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8462894 · Cited by 108
4D Reconstruction of Cultural Heritage Sites
Rodríguez‐Gonzálvez, P., Muñoz, Á. L. F., Pozo, S. D., Sánchez-Aparicio, L. J., Mills, J. P., Fieber, K. D., Haynes, I. P., Guidi, G., Micoli, L. L., & Barsanti, S. G. (2018) · MDPI eBooks · doi:10.3390/books978-3-03842-685-1-6 · Cited by 7
A Method of Robust Pedestrian Tracking in Video Sequences Based on Interest Point Description
An, M.-S., & Kang, D.-S. (2015) · International Journal of Multimedia and Ubiquitous Engineering · doi:10.14257/ijmue.2015.10.10.04 · Cited by 5
“For bounding the minimum box for ROI, we applied the feature selection with the SURF algorithm, which was proposed by Bay [15], to improve the speed of the feature detection process compared with the SIFT algorithm.”
MethodLicence Plate Recognition System for Intelligence Transportation Using BR-CNN
Pattanaik, A., & Balabantaray, R. C. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-16-8403-6_60 · Cited by 6
Semantic embedding: scene image classification using scene-specific objects
Parseh, M. J., Rahmanimanesh, M., Keshavarzi, P., & Azimifar, Z. (2022) · Multimedia Systems · doi:10.1007/s00530-022-01010-9 · Cited by 5
“Some local visual descriptors, which have been widely used in patch feature extraction are: Local Binary Pattern (LBP) [12], Scale Invariant Feature Transform (SIFT) [13], Histogram of Oriented Gradients (HOG) [14], Speeded Up Robust Features (SURF) [15], and Oriented Texture cures (OTC) [16].”
MethodMeasurement Error Detection for Stereo Visual Odometry Integrity
Fu, Y., Wang, S., Zhai, Y., Zhan, X., & Zhang, X. (2022) · NAVIGATION Journal of the Institute of Navigation · doi:10.33012/navi.542 · Cited by 5
Matching method for mutated veneer sheet images using gray-level co-occurrence matrix features
Savolainen, J. (2023) · European Journal of Wood and Wood Products · doi:10.1007/s00107-023-01946-3 · Cited by 6
“In this work, SIFT, SURF, and ORB were tested for the data as an initial guess for the whole images.”
MethodInfluentialAn Improved Image Enhancement Method for Underwater Robot SLAM
Liu, Y., Wang, Y., Xie, C., et al. (2023) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma57826.2023.10215743 · Cited by 5
“Currently, the mainstream feature point extraction algorithms applied in SLAM technology, such as SIFT features[5], SURF features[6], and ORB features[7], all extract feature points based on image grayscale values or their changes.”
MethodZhao, H., Zhang, X., Jiang, D., et al. (2023) · Sensors · doi:10.3390/s23239582 · Cited by 5
Hybrid time-spatial video saliency detection method to enhance human action recognition systems
Gharahbagh, A. A., Hajihashemi, V., Ferreira, M. C., Machado, J. J. M., & Tavares, J. M. R. S. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18126-x · Cited by 8
“Many algorithms have been proposed for image registration, and one of the most common and effective is Speeded Up Robust Features (SURF), which is similar to the scale-invariant feature transform (SIFT) but is faster and less complex in computing [63].”
Photovoltaic Power Forecasting Using Sky Images and Sun Motion
Berresheim, A., & Agudo, A. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448183 · Cited by 5
“A more complex approach is seen in [13], combining block matching, optical flow and SURF [14] feature matching algorithms for cloud recognition, classification and motion prediction.”
MethodAdaptive traffic light control using vision-based deep learning for vehicle density estimation
Karoon, W., Chuasuai, P., Thipprasert, P., et al. (2024) · Asia Pacific Information Technology Conference (APIT) · doi:10.1145/3651623.3651629 · Cited by 5
Multimodal Absolute Visual Localization for Unmanned Aerial Vehicles
Liu, Z., Li, H., Zhang, Z., Lyu, Y., & Xiong, J. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3426538 · Cited by 6
Shape-Adaptive Modality Independent Region Descriptor for Multimodal Remote Sensing Image Matching
Liu, X., Teng, X., Bian, Y., et al. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3447219 · Cited by 5
“ClassicalfeaturematchingmethodsareSIFT[24],SURF [25],KAZE[26],AKAZE[27],ORB[28],andBRISK[29].”
Hardness-Aware Metric Learning With Cluster-Guided Attention for Visual Place Recognition
Guan, P., Cao, Z., Fan, S., Yang, Y., Yu, J., & Wang, S. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3465520 · Cited by 7
“Traditional methods often rely on handcrafted features such as scale-invariant feature transform (SIFT) [8], speeded up robust features (SURF) [9], oriented FAST and rotated BRIEF (ORB) [10].”
Sharma, R., Sharma, K., & Bala, M. (2024) · Scientific Reports · doi:10.1038/s41598-024-75842-y · Cited by 6
RoSe: Rotation-Invariant Sequence-Aware Consensus for Robust Correspondence Pruning
Liu, Y., Zhou, W., Li, Y., & Zhao, S. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681124 · Cited by 8
“We utilize SIFT [29], SURF [5], and ORB [38] descriptors to create initial correspondences, and report the results in Table 2.”
PRIOR-SLAM: Enabling Visual SLAM for Loop Closure Under Large Viewpoint Variations
Wang, Y., Bai, W., Zhang, Z., Wang, H., Sun, H. X., & Cao, Q. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3508193 · Cited by 6
“2) Experimental Setup and Metrics: We compare PRIOR with not only classical features SIFT [53], SURF [54], and ORB [44] from their default OpenCV implementations, but also learned features SuperPoint [39] and R2D2 [40], using the pretrained models provided by their authors.”
A versatile real-time vision-led runway localisation system for enhanced autonomy
Tsapparellas, K., Jelev, N., Waters, J., Shrikhande, A. M., Brunswicker, S., & Mihaylova, L. S. (2024) · Frontiers in Robotics and AI · doi:10.3389/frobt.2024.1490812 · Cited by 6
“Bay et al. introduced Speeded-Up Robust Features (SURF) (Bay et al., 2006), an efficient image descriptor that outperforms state-of-the-art methodologies.”
InfluentialAn Experimental Comparison of Image Feature Detectors and Descriptors applied to Grid Map Matching
Blanco, J., Gonzàlez, J., & Fernández‐Madrigal, J. (2010) · Cited by 5
A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval
Zhang, Y., Chen, J., Huang, X., & Wang, Y. (2015) · PLoS ONE · doi:10.1371/journal.pone.0131721 · Cited by 6
Effectively compressing Near-Duplicate Videos in a joint way
Wang, H., Ma, M., & Tian, T. (2015) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2015.7177385 · Cited by 5
“First, SURF [14] is used to fast detect local features of 𝐼𝑑 and 𝐼𝑏.”
MethodInfluentialAccompanist detection and following for wheelchair robots with fuzzy controller
Wu, B., Jen, C.-L., Tsou, T.-Y., et al. (2012) · International Conference on Advanced Mechatronic Systems · Cited by 5
Tracking image features with PCA-SURF descriptors
Pancham, A., Withey, D., & Bright, G. (2015) · doi:10.1109/mva.2015.7153206 · Cited by 5
“Ke et al. [4] applied PCA to the normalized gradient patch of Scale-Invariant Feature Transform (SIFT).”
InfluentialBin picking for the objects of non-Lambertian reflectance without using an explicit object model
Lee, J., Kim, T., Kang, S., et al. (2014) · International Conference on Ubiquitous Robots and Ambient Intelligence · doi:10.1109/urai.2014.7057466 · Cited by 5
Visual place recognition for multi-robots maps merging
Zhao, L., Jafri, S. R. U. N., & Chellali, R. (2012) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr.2012.6523870 · Cited by 5
“across different images [10] [11] [12].”
Fowers, S. G., Lee, D.-J., Ventura, D. A., & Tippetts, B. J. (2013) · Journal of Aerospace Information Systems · doi:10.2514/1.i010028 · Cited by 5
“For example, SIFT uses 128-element descriptors that require 1024 bytes per descriptor [19], and SURF uses 64-element descriptors that require 512 bytes per descriptor [20].”
MethodCH-SIFT: A local kernel color histogram SIFT based descriptor
Jalilvand, A., Boroujeni, H. S., & Charkari, N. M. (2011) · doi:10.1109/icmt.2011.6001949 · Cited by 5
“The goal of local kernel e drawbacks while keeping the the similarity matching with different 6269 978-1-61284-774-0/11/$26.00 ©2011 IEEE The results of the method show the improvement in the accuracy of point matching in comparison with the SIFT, SURF and CSIFT.”
BackgroundInfluentialLearning Receptive Fields for Pooling from Tensors of Feature Response
Xu, C., & Vasconcelos, N. M. (2014) · 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.2014.112 · Cited by 5
RGB-D fusion: Real-time robust tracking and dense mapping with RGB-D data fusion
Lee, S.-O., Lim, H., Kim, H.-G., & Ahn, S. C. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942938 · Cited by 6
A robust edge based corner detector
Nachar, R. A., Inaty, E., Bonnin, P. J., et al. (2014) · IEEE Mediterranean Electrotechnical Conference (MELECON) · doi:10.1109/melcon.2014.6820539 · Cited by 5
Mobile manipulation: a challenge in integration
Anderson, C. D., Axelrod, B., Case, J. P., et al. (2008) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.777329 · Cited by 5
Learning visual forward models to compensate for self-induced image motion
Ghadirzadeh, A., Kootstra, G., Maki, A., & Björkman, M. (2014) · IEEE RO-MAN · doi:10.1109/roman.2014.6926400 · Cited by 5
“The first method uses Speeded Up Robust Features (SURF) [17] to find matches between two consecutive images.”
MethodInfluentialSpeeding up multi-class texture classification by one-pass vocabulary design and decision tree
Ramanan, A., Ranganathan, P., & Niranjan, M. (2011) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciinfs.2011.6038076 · Cited by 5
Keyframe Selection Framework Based on Visual and Excitement Features for Lifelog Image Sequences
Ratsamee, P., Mae, Y., Jinda-apiraksa, A., Horade, M., Kamiyama, K., Kojima, M., & Arai, T. (2015) · International Journal of Social Robotics · doi:10.1007/s12369-015-0306-y · Cited by 5
“There are 4 similarity criteria used in evaluation process: the number of speeded up robust features (SURF) [4] matching points, the average of the SURF matching error,the color histogram intersection, and the frame number distance.”
MethodInfluentialSeifi, S., Rafighi, A., & Meruvia-Pastor, O. (2014) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1145/2683405.2683447 · Cited by 5
Automatic Generation of Canonical Views for CAD Models
Hu, K., Wang, B., Yuan, B., et al. (2011) · International Conference on Computer-Aided Design and Computer Graphics (CAD/Graphics) · doi:10.1109/cad/graphics.2011.25 · Cited by 5
Mobile phone-based mixed reality: the Snap2Play game
Chin, T.-J., You, Y., Coutrix, C., et al. (2008) · The Visual Computer · doi:10.1007/s00371-008-0283-3 · Cited by 5
Real-time reconstruction of underwater environments: From 2D to 3D
Rossi, M., Scaradozzi, D., Drap, P., et al. (2015) · doi:10.23919/oceans.2015.7404506 · Cited by 5
“The Speeded Up Robust Features (SURF [24]) feature detector and descriptor is used to find and describe salient points in both images.”
MethodLocal Sparse Representation Based Interest Point Matching for Person Re-identification
Khedher, M. I., & El‐Yacoubi, M. A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-26555-1_28 · Cited by 7
ARTOD: Autonomous Real Time Objects Detection by a Moving Camera Using Recursive Density Estimation
Sadeghi‐Tehran, P., & Angelov, P. P. (2016) · Studies in computational intelligence · doi:10.1007/978-3-319-14194-7_7 · Cited by 5
Detection of Region-duplication Forgery in Image Based on Key Points' Binary Descriptors
Zheng, J. (2014) · Journal of Information and Computational Science · doi:10.12733/jics20104208 · Cited by 5
A New Evaluation Framework and Image Dataset for Keypoint Extraction and Feature Descriptor Matching
Barandiarán, Í., Cortes, C. A., Nieto, M., et al. (2013) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004211502520257 · Cited by 5
“, 2007) and for feature description (Bay et al., 2006; Heikkilä et al., 2009; Bellavia et al., 2010; Leutenegger et al., 2011) were tested against their dataset and evaluated with their corresponding scripts, which are freely available online at www.”
MethodOpen source structure-from-motion for aerial video
Leotta, M. J., Smith, E., Dawkins, M., et al. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477659 · Cited by 5
Matching Affine Features with the SYBA Feature Descriptor
Desai, A., Lee, D.-J., & Ventura, D. A. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14364-4_43 · Cited by 5
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.