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 9,601–9,700 of 14,752
Efficient Lightweight CNN and 2D Visualization for Concrete Crack Detection in Bridges
Wang, X., Zhang, F., & Zou, X. (2025) · Buildings · doi:10.3390/buildings15183423 · Cited by 2
SeFENet: Robust Deep Homography Estimation via Semantic-Driven Feature Enhancement
Shi, Z., Zhang, Z., Cui, K., et al. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3612762 · Cited by 2
“Common feature extraction methods include SIFT [22], SURF [23], ORB [24], GMS [25], BEBLID [26], SuperPoint [27].”
FNon R-CNN: A multi-scale ground object detection and recognition network
Yan, Z., Zhu, W., Zhong, X., et al. (2025) · High-Confidence Computing · doi:10.1016/j.hcc.2025.100359 · Cited by 2
Cross-View Geo-Localization via 3D Gaussian Splatting-Based Novel View Synthesis
Ding, X., Zhang, X., Song, S., Li, B., Hui, L., & Dai, Y. (2025) · Remote Sensing · doi:10.3390/rs17223673 · Cited by 3
Hierarchical Neural Semantic Representation for 3D Semantic Correspondence
Du, K., Hu, J., Li, H., Xu, H., Huang, H., Fu, C., & Liu, S. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763921 · Cited by 14
Tan, Y. Z., Cheng, H., Ng, K. W., Ngiam, K. Y., Gao, Y., & Khoo, E. T. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3621335 · Cited by 2
GPU-Based Multi-resolution Image Analysis for Synthesis of Tileable Textures
Eibner, G., Fuhrmann, A. L., & Purgathofer, W. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33191-6_47 · Cited by 2
Description of Interest Regions
Pietikäinen, M., Hadid, A., Zhao, G., & Ahonen, T. (2011) · Computational imaging and vision · doi:10.1007/978-0-85729-748-8_5 · Cited by 2
Semantic Query Answering in Digital Libraries
Kollia, I., Rapantzikos, K., Stamou, G. B., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-30448-4_3 · Cited by 2
Biological inspired system for Localization and Mapping in underwater environments
Silveira, L., Guth, F., Fisher, D., et al. (2013) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.23919/oceans.2013.6741356 · Cited by 2
Under vehicle perception for high level safety measures using a catadioptric camera system
Şahin, C., & Ünel, M. (2013) · Proceedings of the Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon.2013.6699827 · Cited by 2
Intelligent object anchoring using relative anchors
Heyer, T., & Gräser, A. (2012) · International Conference on Optimization of Electrical and Electronic Equipment · doi:10.1109/optim.2012.6231775 · Cited by 2
Robust Detection and Tracking of Long-range Target in a Compound Framework
Sun, K., & Li, X. (2013) · Journal of Multimedia · doi:10.4304/jmm.8.2.98-105 · Cited by 2
Study of Stored Product Insects Identification Based on near Infrared Spectroscopy (NIRS)
Zhao, W. C., Chi, X. Y., & Zhang, C. (2014) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.513-517.2706 · Cited by 2
Visual perception system for a social robot
Bandera, J. P., Marfil, R., Palomino, A. J., Bandera, A. J., & Vázquez-Martín, R. (2010) · IEEE Conference on Robotics, Automation and Mechatronics (RAM) · doi:10.1109/ramech.2010.5513182 · Cited by 2
Research of Medical Image Non-Rigid Registration Based on TPS-SEMISURF Algorithm
Dong, A. S., Yang, B. Q., Zhao, D. Y., et al. (2013) · Advanced materials research · doi:10.4028/www.scientific.net/amr.791-793.2112 · Cited by 2
“As a feature detection description algorithm, SURF (Speed-up robust features) [5] successfully improved SIFT algorithm.”
MethodFast verification via statistical geometric for mobile visual search
Zhang, M., Li, S., Lin, X., et al. (2015) · Multimedia Systems · doi:10.1007/s00530-015-0452-y · Cited by 2
Park, J., Bahn, W., Lee, C.-H., et al. (2011) · International Conference on Ubiquitous Robots and Ambient Intelligence · doi:10.1109/urai.2011.6145950 · Cited by 2
Vision-based distance and position estimation of nearby objects for mobile spatial interaction
Holzmann, C., & Hochgatterer, M. (2011) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/1943403.1943460 · Cited by 2
Permutation estimation and minimax matching thresholds
Collier, O., & Dalalyan, A. S. (2013) · Cited by 2
Bauaufnahme, Gebäudeerfassung und BIM
Blankenbach, J. (2017) · Springer Reference Naturwissenschaften · doi:10.1007/978-3-662-47188-3_36 · Cited by 2
Optical flow based guidance system design for semi-strapdown image homing guided missiles
Huang, L., Song, J., Zhang, M., et al. (2016) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2016.08.011 · Cited by 2
“A variety of algorithms have been used to calculate optical flow, the most popular of which are Lucas Kanade (LK),(15) Horn Schunck (HS),(16) Pyramid LK (PLK),(17) Scale Invariant Feature Transform (SIFT)(18) and Speed Up Robust Features (SURF).(19) Mammarella et al.”
MethodA structural similarity assessment for generating hybrid images
Takahashi, K., Hasegawa, M., Tanaka, Y., et al. (2011) · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/acssc.2011.6189993 · Cited by 2
“We used the ratio of the uncovered objects in the foreground image obtained by the SURF interest points and its scales for the metric.”
MethodInfluential3D shape template generation from RGB-D images capturing a moving and deforming object
Takehara, H., Nakashima, Y., Sato, T., & Yokoya, N. (2016) · Electronic Imaging · doi:10.2352/issn.2470-1173.2016.21.3dipm-407 · Cited by 2
“, [16, 17, 18]) loosely associate the point trajectories in different frames to reduce registration errors.”
BackgroundA Binary Representation for Real-Valued, Local Feature Descriptors
Oszust, M. (2017) · Journal of Automation Mobile Robotics & Intelligent Systems · doi:10.14313/jamris_1-2017/1 · Cited by 2
Stiching large images by enhancing SURF and RANSAC Algorithm
Nithya, R., Priya, K., & Vigneshwari, S. (2017) · International Conference on Electrical, Computer and Communication Technologies (ICECCT) · doi:10.1109/icecct.2017.8117868 · Cited by 3
“[12] H.”
Efficient line matching with homography
Yan, S., Dai, Y., & Zhu, Z. (2017) · Measurement Science and Technology · doi:10.1088/1361-6501/aaa210 · Cited by 2
Stereo Odometry Based on Careful Frame Selection
Fan, H., & Zhang, S. (2017) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid.2017.88 · Cited by 3
“At present, there are many characterizes of featuredetection, for example, SIFT [11], SURF [12], ORB [13], Harris [14], FAST [15].”
Rapid Relevance Feedback Strategy Based on Distributed CBIR System
Liao, J., Li, B., Wang, J., et al. (2018) · International Journal on Semantic Web and Information Systems · doi:10.4018/ijswis.2018040101 · Cited by 2
Rapid image retrieval with binary hash codes based on deep learning
广伟, 邓., Xu, C. L., Tu, X., Li, T., & Gao, N. (2018) · International Workshop on Pattern Recognition (IWPR) · doi:10.1117/12.2502072 · Cited by 3
1D Signals Descriptors for 3D Shape Recognition
Baibai, K., Emharraf, M., Mrabti, W., Ech-Choudany, Y., Hachami, K., & Bellach, B. (2018) · Smart innovation, systems and technologies · doi:10.1007/978-3-030-03577-8_75 · Cited by 2
An Optimal Threshold Registration Algorithm of UAV Color Images Based on SURF
Yao, Y., Zhang, K., & Wang, X. (2018) · International Conference on Vision, Image and Signal Processing (ICVISP) · doi:10.1145/3271553.3271567 · Cited by 2
“SURF [3] was proposed based on the SIFT by Bay et al. in 2006.”
MethodSaliency-Guided Feature Matching for Self-Driving Systems
Cha, A. H., & Kim, W. (2018) · IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) · doi:10.1109/icce-asia.2018.8552102 · Cited by 2
Scene Matching-based Localization of Unmanned Aerial Vehicles in Unstructured Environments
Ebadi, K., & Wood, S. L. (2018) · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/acssc.2018.8645277 · Cited by 2
“In this work we rely on the Speeded-up Robust Features (SURF) [7] for feature detection and description, as it has a high computational speed and is invariant to rotation and scale variation.”
MethodA Color Mask and Trained Image Set for the Creation of New Technique for Indoor Robotic Navigation
Warnakulasooriya, K., Sudantha, B. H., & Premachandra, C. (2018) · International Conference on Information Technology Research (ICITR) · doi:10.1109/icitr.2018.8736147 · Cited by 2
Multifeature Image Indexing for Robot Localization in Textureless Environments
Dung, T. D., Hossain, D., Kaneko, S.-I., & Capi, G. (2019) · Robotics · doi:10.3390/robotics8020037 · Cited by 2
Stitching video streams captured by multi-UAVs with stabilization
He, Q., Wu, H., Wang, X., et al. (2019) · International Conference on Graphics and Image Processing (ICGIP) · doi:10.1117/12.2524245 · Cited by 2
Human tracking by using multiple methods and weighted products
Utaminingrum, F., Cahyaningrum, W., Wihandika, R. C., et al. (2019) · Signal Image and Video Processing · doi:10.1007/s11760-019-01478-5 · Cited by 2
“It shows that the proposed method achieves highest compared to several methods such as Utaminingrum [22], BRISK [4], SIFT [8] and SURF [3].”
MethodHeated Metal Mark Attribute Recognition Based on Compressed CNNs Model
Yin, H., Mao, K., Zhao, J., Chang, H., Dazhi, E., & Tan, Z. (2019) · Applied Sciences · doi:10.3390/app9091955 · Cited by 2
Learning local feature representation from matching, clustering and spatial transform
Mei, J., Jiang, X., & Cai, J. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.102601 · Cited by 2
Ruggiero, F., Kim, J., Gutiérrez–Giles, A., et al. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-3-030-31993-9_4 · Cited by 2
“Typically, object tracking is based on local feature detection, (i.e., the traditional Harris’ corner detector [14], SIFT [15], SURF [16] or FAST [17]).”
MethodResearch on Visual and Inertia Fusion Odometry Based on PROSAC Mismatched Culling Algorithm
Deng, L., Li, X., & Zhang, Y. (2019) · doi:10.1145/3366715.3366725 · Cited by 2
An IMU/Visual Odometry Integrated Navigation Method Based on Measurement Model optimization
Luo, W. H., Xiong, Z., Xing, L., Duan, S., Liu, J., & Yu, Y. (2018) · IEEE CSAA Guidance, Navigation and Control Conference (CGNCC) · doi:10.1109/gncc42960.2018.9019061 · Cited by 2
“sides of the road so the quantity of features is abundant [13].”
BackgroundFröhlich, H. B., Grozmani, N., Wolfschläger, D., Gonçalves, A. A., & Schmitt, R. H. (2020) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-020-05253-6 · Cited by 1
“…Invariant Feature Transform (SIFT) proposed by Lowe [14, 15], Binary Robust Invariant Scalable key points (BRISK) developed by Leutenegger et al. [12], Oriented FAST and Rotated BRIEF [3, 21] (ORB) proposed by Rublee et al. [23] and Speeded Up Robust Features (SURF) developed by Bay et al. [2].”
MethodAlgorithm For Stabilizing Video Images
Sotnikov, A. V., Shipatov, A. V., Myo, A. K., et al. (2020) · Wave Electronics and its Application in Information and Telecommunication Systems (WECONF) · doi:10.1109/weconf48837.2020.9131516 · Cited by 2
“To highlight special points in the image, instead of the SIFT [3] and SURF [4] algorithms, the BRISK detector [5] was used, which has an order of magnitude greater performance with the same, and in some cases, higher quality detection of key features.”
MethodAccurate estimation of feature points based on individual projective plane in video sequence
Liu, H., Tang, S., Lei, D., et al. (2020) · The Visual Computer · doi:10.1007/s00371-020-01928-z · Cited by 2
“Variant kinds of matching methods are based on feature point detection approaches, such as SIFT [23], speeded-up robust features (SURF) [3], ORB [28], binary robust inde-”
MethodPoint-Based Registration for Multi-stained Histology Images
Zhang, J., Li, Z., & Yu, Q. (2020) · IEEE International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc50857.2020.9177486 · Cited by 2
Optimal Feature Subset Selection and MSVM Classification Based CBIR for Medical Images
Ganesh, S. S. (2020) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2020/81942020 · Cited by 2
Cross-Resolution Deep Features Based Image Search
Massoli, F. V., Falchi, F., Gennaro, C., & Amato, G. M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60936-8_27 · Cited by 2
Classifier Belief Optimization for Visual Categorization
Yang, G., & Li, X. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-67832-6_46 · Cited by 2
Chen, J., Wu, Q., & Sun, K. (2021) · IEEE Access · doi:10.1109/access.2021.3071425 · Cited by 2
He, K., Zhao, Y. L., Liu, Z., Li, D., & Ma, X. (2021) · The Visual Computer · doi:10.1007/s00371-021-02107-4 · Cited by 3
“The traditional algorithms for feature extraction, like SIFT [3] and SURF [4] utilized the linear Gaussian pyramids and multi-scale decomposition to eliminate noise and extract features.”
MethodMei, F., Gao, T., & Lyu, Y. (2021) · Security and Communication Networks · doi:10.1155/2021/6688393 · Cited by 2
“To improve SIFTperformance, Bay et al. [12] initially proposed the speeded-up robust features (SURF) technique.”
MethodResearch on the Construction Method of 3D Dense Map Based on Visual Slam
Sun, T., & Shi, X. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1871/1/012083 · Cited by 2
“Endres et al. [2] proposed the RGBD-SLAM[3] (RGB-Depth SALM) algorithm to use iterative closest point ICP[4] (Iterative Closest Point) for pose estimation.”
MethodResearch on Workpiece Image Mosaic Technology of Groove Cutting Robot
Chu, H.-H., Xue, B., & Li, N. (2021) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-021-05734-0 · Cited by 2
“In terms of feature point extraction, Bay [12] followed Lowe’s idea and proposed the SURF algorithm that replaces convolution with image integration.”
MethodUTR: Unsupervised Learning of Thickness-Insensitive Representations for Electron Microscope Image
Tong, X., Chen, B., Chen, X., & Han, H. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506597 · Cited by 5
“3(a), the matching performance of UTR is far superior to other descriptors[9, 10, 11, 12, 5].”
BackgroundKiểm thử giải thuật AI trong nhận diện bệnh tôm qua hình ảnh
Quach, L.-D., Phan, T. N., Hùng, T. T., & Ngôn, N. C. (2021) · Can Tho University Journal of Science · doi:10.22144/ctu.jvn.2021.078 · Cited by 2
Learning to Predict Repeatability of Interest Points
Doan, A.-D., Turmukhambetov, D., Latif, Y., Chin, T.-J., & Bae, S. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561383 · Cited by 3
Research on Monocular SLAM of Indoor Mobile Robot Based on Semi-direct Method
Tian, M., & Chen, W. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-7213-2_5 · Cited by 2
A Convolutional Neural Network Pipeline For Multi-Temporal Retinal Image Registration
Ho, C., Wang, Y., Zhang, J., et al. (2021) · International SoC Design Conference · doi:10.1109/isocc53507.2021.9613906 · Cited by 2
Efficient Approach for Autonomous Facility Inspection Using UAV Images
Lin, Y.-T., Kan, Y.-H., & Han, J.-Y. (2022) · Journal of Infrastructure Systems · doi:10.1061/(asce)is.1943-555x.0000676 · Cited by 2
Yan, Y., Wang, W., Su, N., et al. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3144474 · Cited by 2
Measurement algorithm of notch length of plastic parts based on video
Tao, J., Wei, H., & Zhang, K. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/ac61c3 · Cited by 2
Hokmabadi, I. A. S., & El-Sheimy, N. (2022) · 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-xliii-b2-2022-343-2022 · Cited by 2
A Novel Biologically Inspired Structural Model for Feature Correspondence
Lu, Y., Yang, X., Li, Y., Yu, Q., Liu, Z., & Qiao, H. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2022.3188333 · Cited by 2
“These methods for comparison include famous SIFT [4], SURF [6] for feature description evaluation, and the spectral matching (SM) [11], the probabilistic GM Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
BackgroundMethodPruning Deep Feature Networks Using Channel Importance Propagation
Chen, H., & Li, C. (2021) · International Conference on Computer Science and Management Technology (ICCSMT) · doi:10.1109/iccsmt54525.2021.00080 · Cited by 2
Jiang, P., Liu, J., Xiao, D., et al. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-13832-4_38 · Cited by 2
Siqueira, H. L., Ruhkamp, P., Halfaoui, I., Karmann, M., & Urfalıoǧlu, O. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892803 · Cited by 2
Towards Accurate Image Matching by Exploring Redundancy Between Multiple Descriptors
Yu, J., Sun, K., Li, K., Tang, C. Y., & Feng, R. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3274225 · Cited by 4
“[14] proposed a light-weighted descriptor called SURF, which is much faster than SIFT.”
MethodImage Stitching in Dynamic Scene for Computer Vision Project-Base Learning
Lao, Y., Cao, Y., Zhang, H., & Zhang, Y. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-2449-3_33 · Cited by 2
Traffic sign recognition by the use of speed up robust features
Shahbaz, S. J., Al-Zuky, A. A. D., & Al-Obaidi, F. E. M. (2023) · AIP conference proceedings · doi:10.1063/5.0170840 · Cited by 2
Sign Detection Based Text Localization in Mobile Device Captured Scene Images
Zhang, J., & Kasturi, R. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-05167-3_6 · Cited by 2
Mery, D. (2015) · Springer eBooks · doi:10.1007/978-3-319-20747-6_8 · Cited by 2
Feature Point Matching with Matching Distribution
Ratanasanya, S., Polvichai, J., & Sirinaovakul, B. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-19024-2_2 · Cited by 2
Fast Feature Extractors for Palmprint Biometrics
Choraś, M., & Kozik, R. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-27245-5_16 · Cited by 2
Resolving Conflicts in Object Tracking in Video Stream Employing Key Point Matching
Szwoch, G. (2012) · Communications in computer and information science · doi:10.1007/978-3-642-30721-8_33 · Cited by 2
Towards Condition-Invariant Sequence-Based Route Recognition
Milford, M. J. (2011) · QUT ePrints (Queensland University of Technology) · Cited by 2
Development of Novel Endoscope with NIR Camera Using Real-time Video Composite Method
Watanabe, M., Takemura, H., Mizoguchi, H., et al. (2013) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-319-02913-9_33 · Cited by 2
“Generally, to image compositing and matching, image feature descriptors such as SIFT [4], SURF [5] and FAST [6] etc.”
MethodAn adaptive spherical view representation for navigation in changing environments
Dayoub, F., Duckett, T., & Cielniak, G. (2009) · QUT ePrints (Queensland University of Technology) · Cited by 2
Motion Optimization Scheme for Cooperative Mobile Robots
Franklin, S. J., Finn, A., Pattison, J., & Jain, L. C. (2010) · Studies in computational intelligence · doi:10.1007/978-3-642-14084-6_6 · Cited by 2
INSTREET - Application for Urban Photograph Localization
Grega, M., Łach, S., & Cyganek, B. (2012) · Communications in computer and information science · doi:10.1007/978-3-642-30721-8_13 · Cited by 2
Puerto-Souza, G. A., Castaño-Bardawil, A., & Mariottini, G.-L. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-38085-3_15 · Cited by 2
A bag-of-regions representation for video classification
Choi, M.-K., Wang, Z., Lee, H.-G., et al. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2876-y · Cited by 2
Automatic Alignment System in Simple Planes for Projection Mapping
Kaneda, T., Mitsukura, Y., & Hamada, N. (2015) · Journal of Signal Processing · doi:10.2299/jsp.19.151 · Cited by 2
Geometry-aware Video Registration
Palma, G., Callieri, M., Dellepiane, M., et al. (2010) · ISTI Open Portal · doi:10.2312/pe/vmv/vmv10/107-114 · Cited by 2
Common Representational Format
Mitchell, H. B. (2010) · Springer eBooks · doi:10.1007/978-3-642-11216-4_3 · Cited by 2
3D human behavior recognition based on spatiotemporal texture features
Fan, C., Tian, L., Wang, G., Ming, Y., Shi, J., & Jin, Y. (2015) · Conference on Human System Interactions · doi:10.1109/hsi.2015.7170692 · Cited by 2
A depth-incorporated 2D descriptor for robust and efficient 3D environment reconstruction
Zhang, K., Zheng, S., Yu, W., et al. (2015) · International Conference on Computer Science & Education (ICCSE) · doi:10.1109/iccse.2015.7250334 · Cited by 2
“propose a new 2D image descriptor called SURF [25].”
BackgroundMethodReal-Time Feature Acquisition and Integration for Vision-Based Mobile Robots
Hübner, T., & Pajarola, R. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-10331-5_18 · Cited by 2
New Approaches to Data Classification in DLP Systems
Pshehotskaya, E., Sokolova, T. N., & Ryabov, S. A. (2014) · International Conference on Computing Technology and Information Management · Cited by 2
Iterative three-dimensional rigid object pose estimation with contour correspondence
Leng, D., & Sun, W. (2012) · IET Image Processing · doi:10.1049/iet-ipr.2010.0435 · Cited by 2
Support system for handwriting using projector
Yamada, K., & Takahashi, M. (2011) · Society of Instrument and Control Engineers of Japan · Cited by 2
Revisiting the PnP Problem with a GPS
Pylvänäinen, T., Fan, L., & Lepetit, V. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-10331-5_76 · Cited by 2
Automatic Stabilization of Infrared Images Using Frequency Domain Methods
Dios, J. R. M., & Ollero, A. (2012) · Automation · doi:10.5772/48054 · Cited by 2
Improved face recognition algorithm employing SURF descrpitors
Kang, M., Choo, W., & Moon, S. B. (2010) · Society of Instrument and Control Engineers of Japan · Cited by 2
Mosaicing of Fibered Fluorescence Microscopy Video
Backer, S. D., Cornelissen, F. W., Lemeire, J., Nuydens, R., Meert, T. F., Schelkens, P., & Scheunders, P. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88458-3_83 · Cited by 3
“, found by algorithms like SIFT [4], SURF [5], MSER [6], etc.”
MethodA Genetic Programming Approach to Geometrical Digital Content Modeling in Web Oriented Applications
Palaghiţă, D. (2011) · RePEc: Research Papers in Economics · Cited by 2
An Improved Algorithm for Image Mosaic Based on Speeded-Up Robust Features
Lu, X., Jun-ben, W., & He, Z. (2010) · International Conference on Management and Service Science (MASS) · doi:10.1109/icmss.2010.5575648 · Cited by 2
“Bay [7] proposed box filters to approximate the second order Gaussian derivatives.”
BackgroundReal-Time Object Segmentation Using a Bag of Features Approach
Aldavert, D., Arnau Ramisa, A., Ramon, L. D. M., & Toledo, R. (2010) · Frontiers in artificial intelligence and applications · doi:10.3233/978-1-60750-643-0-321 · Cited by 2
Approaches to Door Identification for Robot Navigation
Jauregi, E., Lazkano, E., & Sierr, B. (2010) · InTech eBooks · doi:10.5772/8976 · Cited by 3
“This chapter compares several approaches developed for door identification based on handle recognition, from specific methods based on colour segmentation techniques to more general ones that focus on feature extraction methods, like SIFT (Lowe, 2004) and (U)SURF (Bay et al., 2008).”
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.