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 7,801–7,900 of 14,752
Wan, G., Huang, R., Xu, Y., Ye, Z., Feng, Y., Xie, H., & Tong, X. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3544241 · Cited by 4
“In recent decades, the feature matching of homologous images has been extensively studied, such as SIFT [3], speeded-up robust features (SURFs) [37], and KAZE [38].”
RING#: PR-By-PE Global Localization With Roto-Translation Equivariant Gram Learning
Lu, S., Xu, X., Zhang, D., Wu, Y., Lu, H., Chen, X., Xiong, R., & Wang, Y. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3543267 · Cited by 14
“Traditional methods rely on handcrafted local features, such as scale-invariant feature transform (SIFT) [40], speeded up robust features (SURF) [41], and oriented FAST and rotated BRIEF (ORB) [42], to extract local descriptors, which are then aggregated into global descriptors using aggregation…”
Embedded machine vision sensor with portable imaging device and high durability
Wu, P., Yuan, H., Bai, B., et al. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106143 · Cited by 4
Jung, J., Choi, H., & Lee, Y. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13050828 · Cited by 4
Leveraging Image Matching Toward End-to-End Relative Camera Pose Regression
Khatib, F., Margalit, Y., Galun, M., & Basri, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-85187-2_12 · Cited by 14
“Classical techniques rely on keypoint extraction and matching using descriptors such as SIFT [8, 15, 36, 48, 49], followed by robust estimation of the essential matrix using, e.g., RANSAC [23].”
BackgroundMethodMultifeature Fusion for Enhanced Content‐Based Image Retrieval Across Diverse Data Types
Soni, P., Singh, M., Sharma, P., et al. (2025) · Journal of Electrical and Computer Engineering · doi:10.1155/jece/3889925 · Cited by 4
“Te proposed system is tested using the dataset of Corel-1000 [59].”
Herbon, C., Otte, B., Tönnies, K. D., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11752-2_44 · Cited by 4
Towards an Informed Search Behavior for Domestic Robots
Ziegler, L., Siepmann, F., Kortkamp, M., & Wachsmuth, S. (2010) · PUB – Publications at Bielefeld University (Bielefeld University) · Cited by 4
Semantic Analysis of 3D Anatomical Medical Images for Sub-image Retrieval
Venkatraghavan, V., & Ranjan, S. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-28460-1_13 · Cited by 4
Non-rigid Surface Tracking for Virtual Fitting System
Shimizu, N., Yoshida, T., Hayashi, T., et al. (2013) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004303000120018 · Cited by 4
“So if we use matching algorithm based on local features like SIFT (Lowe, 1999), SURF (Bay et al., 2006), many miss-correspondences will occur.”
Markerless Outdoor Localisation Based on SIFT Descriptors for Mobile Applications
Wendt, F. L., Bres, S., Tellez, B., & Laurini, R. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-69905-7_50 · Cited by 4
Development of image error correction system for 3D optical microscope
Yoon, J., Kim, H., & Kim, C. (2015) · doi:10.1109/icctim.2015.7224601 · Cited by 4
Human-robot SLAM in industrial environments
Guerra, E., Bolea, Y., Grau, A., & Munguía, R. (2015) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin.2015.7281766 · Cited by 4
“Inside these areas, SURF-based feature descriptors [18] are matched to produce new stereo features to initialize or add to the EKF state vector.”
MethodAutomated image stitching for enhanced visual inspections of nuclear power stations
Murray, P., West, G. M., Marshall, S., et al. (2013) · Strathprints: The University of Strathclyde institutional repository (University of Strathclyde) · Cited by 4
Approximate and SQP Two View Triangulation
Tossavainen, T. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19318-7_1 · Cited by 4
Ethical Implications Regarding Assistive Technology at Workplaces
Behrendt, H., Funk, M., & Korn, O. (2015) · Springer eBooks · doi:10.1007/978-3-319-15515-9_6 · Cited by 4
Reliable Image Matching with Recursive Tiling
Novák, D., Baltsavias, E., & Schindler, K. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24393-6_5 · Cited by 4
A comparative study of parallel software SURF implementations
Hidalgo‐Paniagua, A., Vega-Rodríguez, M. A., Pavón, N., et al. (2013) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.3163 · Cited by 4
Visual Fuzzy Control for Blimp Robot to Follow 3D Aerial Object
AL-Jarrah, R. A., & Roth, H. (2014) · Communications in computer and information science · doi:10.1007/978-3-319-08201-1_10 · Cited by 4
Automated Mobile System for Accurate Outdoor Tree Crop Enumeration Using an Uncalibrated Camera
Nguyen, T. T., Slaughter, D. C., Hanson, B. D., et al. (2015) · Sensors · doi:10.3390/s150818427 · Cited by 4
Facilitating Ubiquitous interaction Using Intelligent Agents
Campbell, A., Collier, R., Dragone, M., et al. (2012) · Studies in computational intelligence · doi:10.1007/978-3-642-25691-2_13 · Cited by 4
Properties and Structure of Fast Text Search Engine in Context of Semantic Image Analysis
Rygał, J., Najgebauer, P., Nowak, T., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-29347-4_69 · Cited by 4
Pedicle Detection in Planar Radiographs Based on Image Descriptors
Cunha, P., Moura, D. C., & Barbosa, J. G. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-31298-4_33 · Cited by 5
Environment Adaptive Pedestrian Detection using In-vehicle Camera and GPS
Suzuo, D., Deguchi, D., Ide, I., et al. (2014) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004677003540361 · Cited by 4
Keypoint based automatic image orientation and skew investigation on tie points
Altuntaş, C. (2013) · Kybernetes · doi:10.1108/03684921311323725 · Cited by 4
Automatic collection of Web video shots corresponding to specific actions using Web images
Nga, D. H., & Yanai, . (2012) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2012.6239255 · Cited by 4
“To evaluate the similarity between a video shot and given set of action images, we first extract SURF local features from all action images of selected set and each one frame per five consecutive frames of all the shots.”
MethodInfluentialKeypoint Reduction for Smart Image Retrieval
Yuasa, K., & Wada, T. (2013) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2013.67 · Cited by 4
“Through many researches, local image features (e.g., SIFT, SURF, LBP) are proved to be effective for fast and occlusion-robust image retrieval.”
MethodInfluentialComparing region-based and feature-based methods for ROV vision-based motion estimation
Ferreira, F., Veruggio, G., Caccia, M., & Bruzzone, G. (2012) · IFAC Proceedings Volumes · doi:10.3182/20120919-3-it-2046.00016 · Cited by 4
Ferreira, F., Orsenigo, F., Veruggio, G., et al. (2010) · IFAC Proceedings Volumes · doi:10.3182/20100915-3-de-3008.00010 · Cited by 4
Underwater man-made object prediction using line detection technique
Hussain, S. S., & Zaidi, S. S. H. (2014) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai.2014.7090215 · Cited by 4
“SIFT and SURF generates false matches if number of feature keys are high, either image is matched with right or wrong object these technique totally depend upon database of images of object.”
BackgroundMethodInfluentialValenzuela, R. E. G., Schwartz, W. R., & Pedrini, H. (2014) · Journal of Electronic Imaging · doi:10.1117/1.jei.23.3.033017 · Cited by 4
“Precision 1⁄4 True Positives True Positives þ False Positives (4)”
BackgroundInfluentialFabián, J., Pires, R., & Rocha, A. D. R. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2013.09.011 · Cited by 3
Multimodal desktop interaction: The face - object - gesture - voice example
Vidakis, N., Vlasopoulos, A., Kounalakis, T., et al. (2013) · doi:10.1109/icdsp.2013.6622782 · Cited by 4
“The gestures were one to one assigned to a command and could not be changed by the user.”
BackgroundPan, H., Zhu, Y., & Xia, L. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738617 · Cited by 4
Madokoro, H., Yamanashi, A., & Sato, K. (2013) · Pattern recognition in physics · doi:10.5194/prp-1-93-2013 · Cited by 4
“SIFT and speeded up robust features (SURF) ( Bay et al. , 2008) are used widely for extraction of local features of objects from scene images. In this approach, improved robustness for environmental changes is a challenging task. Given a wide range of view, the feature points to be detected are fewer because there are…”
BackgroundMethodInfluentialA multi-layer approach for camera-based complex map image retrieval and spotting system
Dang, Q. B., Luqman, M. M., Coustaty, M., et al. (2014) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2014.7001968 · Cited by 4
“We are planning to use other feature like SURF or ORB with hashed-based approach.”
MethodA new algorithm for robot localization using monocular vision and inertia/odometry sensors
Wang, K., Liu, Y., & Li, L. (2012) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2012.6491055 · Cited by 4
Interest points based object tracking via sparse representation
Babu, R. V., & Parate, P. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738610 · Cited by 4
Ratio Voting: A New Voting Strategy for Large-Scale Image Retrieval
Uchida, Y., Takagi, K., & Sakazawa, S. (2012) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2012.156 · Cited by 4
“To date, local feature detectors/descriptors have been investigated quite well in the literature [8, 1, 2, 9].”
BackgroundImprovement of inertial sensor based indoor navigation by video content analysis
Bernoulli, T., Krammer, M., Walder, U., et al. (2011) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2011.6071922 · Cited by 4
“For the first level of correlation in both images SURF feature points [12] are extracted, which are known to be insensitive to lighting and contrast variation and invariant under scaling, rotational and translational operations.”
BackgroundImproving feature based object recognition in service robotics by disparity map based segmentation
Asanza, D., & Wirnitzer, B. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5652662 · Cited by 4
Automatic generated recommendation for movie trailers
Xu, Z., & Zhang, Y. (2013) · IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) · doi:10.1109/bmsb.2013.6621738 · Cited by 4
The influence of image descriptors’ dimensions’ value cardinalities on large-scale similarity search
Semertzidis, T., Rafailidis, D., Strintzis, M. G., & Daras, P. (2014) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-014-0073-9 · Cited by 4
“The CEDD 144d-240K dataset contains global CEDD descriptors [4], of 144-dimensions of integer values∈ {0 - 7} and the SURF 5000d-240K dataset with a 5000-dimensional codebook, to extract global vectors from the local SURF descriptors [3] with normalized real values ∈ [0, 1].”
Multicore Computing for SIFT Algorithm in MATLAB® Parallel Environment
Cao, H., & Chen, J. (2012) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads.2012.152 · Cited by 4
“Some software-based speed-up schemes such as SURF [11] and fast SIFT [12] have also been proposed which tried to reduce the time-consuming by ignoring a certain number of key points, which also lead to sacrifice accuracy and misdetection.”
MethodComponent hashing of variable-length binary aggregated descriptors for fast image search
Wang, Z., Duan, L., Lin, J., Huang, T., Gao, W., & Bober, M. Z. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025449 · Cited by 6
Li, Z., Tomioka, Y., & Kitazawa, H. (2013) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e96.d.1171 · Cited by 4
Panoramic Image Reconstruction using SURF Algorithm
Kim, K.-B. (2013) · Journal of the Korea Society of Computer and Information · doi:10.9708/jksci.2013.18.4.013 · Cited by 4
“이러한문제점을해결하기위 해 Lowe의 스케일 불변 특징을 변환하는 SHFT 알고리즘 (Scale Invariant Feature Transform)과 Bay의 고속의 강인한 특징을 추출하는 SURF 알고리즘(Speeded Up Robust Features) 등이 제안되었다[1,2,3].”
Integrating 3D features and virtual visual servoing for hand-eye and humanoid robot pose estimation
Gratal, X., Smith, C., Björkman, M., & Kragić, D. (2013) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2013.7029982 · Cited by 4
Li, L., Liu, Y., & Wang, K. (2014) · IFAC Proceedings Volumes · doi:10.3182/20140824-6-za-1003.01476 · Cited by 4
Huang, D., Zhu, C., Bichot, C., et al. (2013) · doi:10.1145/2461466.2461500 · Cited by 4
Content-Based Image Retrieval on Reconfigurable Peer-to-Peer Networks
Su, C.-R., Chen, J., & Chang, K.-L. (2013) · International Symposium on Biometrics and Security Technologies · doi:10.1109/isbast.2013.36 · Cited by 4
Using high-speed photography and image processing for fixational eye movements measurement
Li, J., & Zhang, X. (2012) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist.2012.6295506 · Cited by 4
“The displacement of the captured eye images was then recorded using an image-processing algorithm, SURF[8], which can perform these measurements in sub-pixels.”
MethodInfluentialA framework for RF-Visual SLAM
Anwar, S., Zhao, Q., Qadeer, N., et al. (2013) · doi:10.1109/ibcast.2013.6512139 · Cited by 4
Object class and instance recognition on rgb-d data
Seib, V., Christ-Friedmann, S., Thierfelder, S., et al. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2049915 · Cited by 4
“This approach is based on Hough-transform clustering of Speeded-Up Robust Features (SURF) [3] that allows reliable recognition even with partially occluded objects and heteroge-neous backgrounds.”
BackgroundMethodInfluentialCompressing a set of CHoG features
Chandrasekhar, V., Tsai, S. S., Reznik, Y. A., et al. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.895431 · Cited by 4
SURF and RANSAC: A Conglomerative Approach to Object Recognition
Kole, S., Agarwal, C., Gupta, T., & Singh, S. (2015) · International Journal of Computer Applications · doi:10.5120/19174-0645 · Cited by 4
TASC: A Transformation-Aware Soft Cascading Approach for Multimodal Video Copy Detection
Tian, Y., Qian, M., & Huang, T. (2015) · ACM Transactions on Information Systems · doi:10.1145/2699662 · Cited by 5
The Research of SLAM Monocular Vision Based on The Improved SURF Feather
You, Y. (2014) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn.2014.84 · Cited by 4
“A. SURF descriptor SURF (Speeded Up Robust Feature) [2] is a robust detector of the local features, which was proposed by Herbert Bay in 2006.”
MethodUsing monocular depth cues for modeling stereoscopic 3D saliency
Iatsun, I., Larabi, M., & Fernández-Maloigne, C. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6853664 · Cited by 4
“one interest points offers the opportunity of using the model in a real-time processing system [23].”
BackgroundScalable mobile search with binary phrase
Luo, Q., Zhang, S. S., Huang, T., et al. (2013) · International Conference on Internet Multimedia Computing and Service · doi:10.1145/2499788.2499815 · Cited by 4
Validation of Object Recognition Framework on Android Mobile Platform
Tyagi, V., Pandya, A. S., Agarwal, A., et al. (2011) · Proceedings - IEEE International Symposium on High-Assurance Systems Engineering/Proceedings · doi:10.1109/hase.2011.62 · Cited by 4
“We ported a Java based implantation of SURF to the Android platform.”
BackgroundInfluentialCAD-guided inspection of aeronautical mechanical parts using monocular vision
Viana, I., Bugarin, F., Cornille, N., & Orteu, J. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2182922 · Cited by 4
“In image analysis matching techniques include descriptor based methods (SIFT, 12 SURF 14 ), cross correlation based methods (CC, NCC, ZNCC Bounded Partial Correlation 15 ), template matching, 16 shape based matching, model based matching, geometry based matching and hybrid approaches.”
Robust egomotion for large-scale trajectories
Rodriguez, D., & Aouf, N. (2012) · IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) · doi:10.1109/mfi.2012.6343049 · Cited by 4
Recognition of aggressive human behavior based on SURF and SVM
Ouanane, A., Serir, A., & Djelal, N. (2013) · doi:10.1109/wosspa.2013.6602398 · Cited by 4
“Speeded Up Robust Features descriptor [5] is a competitive alternative to the SIFT one in terms of robustness to invariant scaling, translation, and rotation.”
MethodHybrid tracking approach for assistive environments
Lalos, C., Anagnostopoulos, V., Konstanteli, K. G., et al. (2009) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/1579114.1579178 · Cited by 4
Comparison of 3D feature registration techniques for indoor mapping
Latif, D. M. A., Salem, M. A. ‐., Ramadan, H., et al. (2013) · International Conference on Computer Engineering & Systems (ICCES) · doi:10.1109/icces.2013.6707211 · Cited by 4
“SURF proved to be slowest algorithm as its mean time is between 200-293 ms while the other three produce results within the same range 7.8-12.6 ms.”
InfluentialThin plate spline feature point matching for organ surfaces in minimally invasive surgery imaging
Lin, B., Sun, Y., & Qian, X. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2007687 · Cited by 4
Matching of Aerospace Photographs with the use of Local Features
Malashin, R. O. (2014) · Journal of Physics Conference Series · doi:10.1088/1742-6596/536/1/012018 · Cited by 4
Ranft, B., Denninger, O., & Pfaffe, P. (2014) · doi:10.1109/ipdpsw.2014.119 · Cited by 4
Shahbandi, S. G., & Lucidarme, P. (2012) · doi:10.1109/iconscs.2012.6502471 · Cited by 4
Towards a Spatial Model for Humanoid Social Robots
Figueira, D., Lopes, M. C., Ventura, R., et al. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04686-5_24 · Cited by 4
“Many different approaches have been used in computer vision to enable recognition, for instance, eigenspace matching has been used successfully by Schiele [13], others have used Speeded Up Robust Features (SURF) [14], and many have benefited from David Lowe’s Scale Invariant Feature Transform (SIFT) [4].”
MethodSelf-localization based on image features of omni-directional image
Hibino, F., Ii, Y., Takahashi, Y., et al. (2012) · doi:10.1109/scis-isis.2012.6505325 · Cited by 4
“We have studied a self-localization method based on image features, for example, SIFT and SURF, so far.”
MethodFeature Regression for Multimodal Image Analysis
Yang, M. Y., Yong, X., & Rosenhahn, B. (2014) · IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2014.118 · Cited by 4
“Speeded Up Robust Feature (SURF) is an improvement of SIFT, which is first presented by [2].”
Return of the king: The Fourier transform based descriptor for visual object classification
Çevıkalp, H., Kurt, Z., & Onarcan, A. O. (2013) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2013.6531160 · Cited by 4
Trainable estimators for indirect people counting: A comparative study
Acampora, G., Loia, V., Percannella, G., et al. (2011) · Proceedings of ... IEEE International Conference on Fuzzy Systems · doi:10.1109/fuzzy.2011.6007637 · Cited by 4
“in 2006 [9] is adopted in order to detect interest points; in the second step, the detected points are partitioned into clusters corresponding to separated groups of persons, as to be able to compute for each group its distance from the camera and its density; in the last step, a trainable function estimator is exploi…”
MethodVirtual Lock: A Smartphone Application for Personal Surveillance Using Camera Sensor Networks
Yoon, S., Oh, H., Lee, D., et al. (2011) · IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA) · doi:10.1109/rtcsa.2011.79 · Cited by 4
PQ-WGLOH: A bit-rate scalable local feature descriptor
Wang, C., Duan, L., Wang, Y., & Gao, W. (2012) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2012.6288040 · Cited by 4
A robust local descriptor method for registering Māori artefacts using colour images
Cheng, D., Xie, S. Q., & Hämmerle, E. (2009) · International Conference on Information and Automation · doi:10.1109/icinfa.2009.5204985 · Cited by 4
“…many cases that the advantages gained in over-increasing the descriptor dimension is often not worth the extra computation cost involved [7], [11], [2] is one of the early and perhaps the most wellknown local descriptor method, which consists of four steps, first low contrast regions at edges are…”
BackgroundMethodExtended feature-based object tracking in presence of data association uncertainty
Alvarez, M. S., & Regazzoni, C. S. (2011) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2011.6027308 · Cited by 4
“These algorithms usually rely on finding correspondences of features between consecutive frames by means of feature local information like Kanade-Lucas-Tomasi tracker (KLT) [11] or by performing matching between interest point employing local descriptors like SIFT [7] and SURF [3].”
MethodCampoy, P., Ivan, F., Miguel, A., et al. (2010) · InTech eBooks · doi:10.5772/8548 · Cited by 4
A rapid defect detecting algorithm for printed matter on the assembly line
Yang, X., & Wu, S. (2012) · International Conference on Systems and Informatics (ICSAI) · doi:10.1109/icsai.2012.6223405 · Cited by 4
“H. Bay and others [4] had proposed the Surf algorithm in 2006, it was three times faster than before Sift, but it was also hard to meet the requirements of the industrial detect speed for the need to detect larger image.”
A Hash Table Approach for Large Scale Perceptual Anchoring
Persson, A., & Loutfi, A. (2013) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2013.522 · Cited by 4
Arakawa, T., Kasada, K., Narumi, T., et al. (2013) · IEEE Virtual Reality (VR) · doi:10.1109/vr.2013.6549401 · Cited by 4
“To achieve this, we used a SURF-based detection method [2].”
MethodContextual smoothing of image segmentation
Letham, J., Robertson, N. M., & Connor, B. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543910 · Cited by 4
“Registration of the visual cameras is achieved automatically by finding corresponding control points using the Speeded Up Robust Features (SURF) [2].”
MethodRobust Simultaneous 3D Registration via Rank Minimization
Thomas, D., Matsushita, Y., & Sugimoto, A. (2012) · International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission · doi:10.1109/3dimpvt.2012.15 · Cited by 4
“Sparse feature-based methods, like SIFT [16] and its variants [4, 6, 25], are known to be fast and efficient, but with limited accuracy.”
MethodAn affine invariant feature detection method based on SIFT and MSER
Wang, Z., Mo, H., Wang, H., et al. (2012) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2012.6360699 · Cited by 4
Temporal-spatial face recognition using multi-atlas and Markov process model
Gou, G., Shen, R., Wang, Y., & Basu, A. (2011) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2011.6012063 · Cited by 4
“Each matching pair of d� E Di and d� E Dj is found by calculating a similarity score sm,n using the strategy proposed in [10].”
MethodVehicle speeding early warning model using frame feature detection and HMM
Lin, C.-C., & Wang, M. (2011) · IEEE International Symposium on Consumer Electronics (ISCE) · doi:10.1109/isce.2011.5973824 · Cited by 4
“SURF (Speed Up Robust Features) [8] is a powerful image features and the ratio of the detector, so the first time by Herbert Bay made in 2006, can be used in computer vision [3, 4] the theory and applications, such as object recognition or reconstruction.”
MethodATDT: Autonomous Template-Based Detection and Tracking of Objects from Airborne Camera
Sadeghi‐Tehran, P., & Angelov, P. P. (2014) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-11310-4_48 · Cited by 4
On the use of feature tracks for dynamic concept detection in video
Mezaris, V., Dimou, A., & Kompatsiaris, I. Y. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5653867 · Cited by 4
“These include SIFT [1], SURF [2], and techniques introducing color information to the original grey-value SIFT [3].”
MethodNHK STRL at TRECVID 2010: Semantic Indexing and Surveillance Event Detection.
Kawai, Y., Takahashi, M., Fujii, M., Naemura, M., & Satoh, S. (2010) · TRECVID · Cited by 7
RoboCup 2014 - homer@UniKoblenz (Germany)
Seib, V., Memmesheimer, R., Jakowlewa, T., et al. (2014) · Cited by 4
Integrated Scenario for Machine-Aided Inventory Using Ambient Sensors
Schairer, T., Weiß, C., Vorst, P., et al. (2008) · Cited by 4
3D spatial pyramid: descriptors generation from point clouds for indoor scene classification
Romero-González, C., Martínez-Gómez, J., García-Varea, I., & Rodríguez-Ruiz, L. (2016) · Machine Vision and Applications · doi:10.1007/s00138-015-0744-4 · Cited by 4
“Since then, most of the methods for generating descriptors rely on local features, nearly all based on SIFT [27] and SURF [2] descriptors with dense sampling strategies [56].”
MethodLogo Spotting on Document Images using Local Features
Le, V. P., Dang, Q. B., & Tran, C. D. (2015) · International Symposium on Information and Communication Technology · doi:10.1145/2833258.2833292 · Cited by 4
3-D-environment reconstruction for mobile robots using fast- SLAM and feature extraction
Arbeiter, G., Fischer, J., & Verl, A. W. (2022) · Fraunhofer-Publica (Fraunhofer-Gesellschaft) · doi:10.24406/publica-fhg-367030 · Cited by 4
Study of Feature based Image Registration Algorithms for Navigation of Unmanned Aerial Vehicles
Lakshmi, K. D., & Vaithiyanathan, V. (2015) · Indian Journal of Science and Technology · doi:10.17485/ijst/2015/v8i22/79315 · Cited by 4
Model-Based Tracking Initialization in Ship Building Environment
Euranto, A., Lahdenoja, O., Suominen, R., & Lehtonen, T. (2014) · UTUPub (University of Turku) · Cited by 4
An efficient coding framework for compact descriptors extracted from video sequence
Huang, Z., Duan, L., Lin, J., Wang, S., Ma, S., & Huang, T. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351520 · Cited by 4
“The first group is local descriptor, such as SIFT [3], SURF [4].”
MethodVassallo, C., Tabib, W., & Peterson, K. M. (2015) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2015.47 · Cited by 4
“The image was processed using Speeded up robust features (SURF) [20] to detect features in the current frame.”
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.