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 9,501–9,600 of 14,752
Image Class Ranking using Bag of Features
Kulkarni, S., & Manu, T. M. (2022) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit55038.2022.9848330 · Cited by 2
Object Recognition and Pose Estimation from RGB-D Data Using Active Sensing
Manawadu, U. A., Shishiki, K., & Naruse, K. (2022) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim52237.2022.9863241 · Cited by 2
Zhao, C. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/8937084 · Cited by 2
Maze: A Cost-Efficient Video Deduplication System at Web-scale
Qin, A., Xiao, M., Huang, B., & Zhang, X. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548145 · Cited by 5
“The local features are extracted from an image, describing details of the frames: HSV color histograms [14, 21, 39, 47], local binary patterns (LBP) [21, 48, 53], fuzzy multidimensional histograms of color and motion video segments [10], auto colour correlograms (ACC) [6], and the keypoint descriptors, such as SIFT [1…”
BackgroundMethodMittal, P., Sharma, A., & Singh, R. (2022) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.17.022203 · Cited by 3
Chen, J., Yu, Z., & Cun-jian, Y. (2022) · Open Geosciences · doi:10.1515/geo-2022-0393 · Cited by 2
Open-set Pets Facial Recognition Using Deep Learning and Statistical Learning
Zhang, Z., & Ji, Z. (2022) · International Conference on Data Intelligence and Security (ICDIS) · doi:10.1109/icdis55630.2022.00050 · Cited by 3
A single-stage fashion clothing detection using multilevel visual attention
Shajini, M., & Ramanan, A. (2022) · The Visual Computer · doi:10.1007/s00371-022-02751-4 · Cited by 2
Body Part Detection in Smoky Environments with Thermal Camera Using Deep Learning
Gelfert, S. (2022) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas55662.2022.10003742 · Cited by 2
“[10] investigate the challenge of victim detection by using the histogram of oriented gradients (HOG) feature descriptor, which is well known in the domain of pedestrian detection [11], and the speeded up robust features descriptor (SURF) for object detection by [12] as a comparative analysis.”
MethodPPR-Net: Patch-Based Multi-scale Pyramid Registration Network for Defect Detection of Printed Label
Li, D., Li, Y., Li, J., & Lu, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26284-5_19 · Cited by 2
PairingNet: A Multi-Frame Based Vehicle Trajectory Prediction Deep Learning Network
Chen, G.-W., Sun, M.-T., & İk, T.-U. (2023) · IEEE Access · doi:10.1109/access.2023.3260832 · Cited by 3
“The most widely used object detection methods for computer vision are feature extraction by histogram of oriented gradient (HOG) [21], scale-invariant feature transform (SIFT) [22], and speeded up robust features (SURF) [23].”
MethodYu, Q., Wang, R., Liu, F., et al. (2023) · Drones · doi:10.3390/drones7040230 · Cited by 2
“…methods are used in image stitching, and its basic process can be summarized as feature point extraction, (such as scale invariant features transform (SIFT) [11], sped-up robust features (SURF) [12], oriented FAST, rotated BRIEF (ORB) [13], descriptor construction, and feature-point matching.”
MethodCebollada, S., Payá, L., Peidró, A., Mayol-Cuevas, W. W., & Reinoso, Ó. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08515-y · Cited by 4
Perspectively Equivariant Keypoint Learning for Omnidirectional Images
Zhang, Y., Liu, Y., Liu, J., et al. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3270032 · Cited by 2
“Inspired by SIFT, various subsequent algorithms based on the hand-crafted features are proposed to optimize its efficiency, including Speeded-Up Robust Features (SURF) [16], DAISY [17], KAZE [18], FAST [19], and ORB [20].”
MethodLarge‐scale time‐lapse scanning electron microscopy image mosaic using a smooth stitching strategy
Zhao, B., Zhang, K., Liu, P., & Chen, Y. (2023) · Microscopy Research and Technique · doi:10.1002/jemt.24334 · Cited by 2
“Bay et al. (2006) improved the feature extraction and description, which is the well-known speeded up robust features (SURF) algorithm.”
MethodResearch and Implementation of Fire Warning Algorithm Based on Deep Learning
Li, X., Wang, S., Yu, Z., et al. (2022) · doi:10.1109/isaiam55748.2022.00017 · Cited by 2
Rail profile matching method based on stepped calibration plate and improved SURF algorithm
Xu-ang, C., Han, Y., Heng, D., et al. (2023) · Engineering Research Express · doi:10.1088/2631-8695/acd98d · Cited by 2
Pavel, G., & Evgeny, S. (2023) · Химическая физика и мезоскопия · doi:10.15350/17270529.2023.1.1 · Cited by 2
Netrahitha: Currency Detector Jacket for visually impaired people
Koti, A., Khare, A., & Kumar, J. P. (2023) · Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON) · doi:10.1109/ectidamtncon57770.2023.10139655 · Cited by 2
“[17] Herbert Bay and his colleagues introduced a new approach of interest point identification and description that is both scale-invariant and rotation-invariant.”
BackgroundTRACKING THE URBAN CHAMELEON – TOWARDS A HYBRID CHANGE DETECTION OF GRAFFITI
Wild, B., Verhoeven, G., & Pfeifer, N. (2023) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-x-m-1-2023-285-2023 · Cited by 2
Monte Carlo human identification refinement using joints uncertainty
Cecco, M. D., Luchetti, A., & Tavernini, M. (2023) · ACTA IMEKO · doi:10.21014/actaimeko.v12i2.1423 · Cited by 2
KEYPOINTS ON THE IMAGES: COMPARISON OF DETECTION BY DIFFERENT METHODS
Fesiuk, A., & Furgala, Y. (2023) · Electronics and Information Technologies · doi:10.30970/eli.21.2 · Cited by 2
Federated Deep Feature Extraction-based SLAM for Autonomous Vehicles
Anagnostopoulos, C., Γκίλλας, Α., Piperigkos, N., & Lalos, A. S. (2023) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/dsp58604.2023.10167897 · Cited by 5
“Today, modern VSLAM geometrical systems use feature extraction algorithms like SIFT [2], SURF[3], and ORB [4], which select robust features accompanied by a descriptor that’s used for matching.”
MethodКубицький, В., & Panchenko, T. (2023) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-36115-9_30 · Cited by 6
Three-Dimensional Wound Reconstruction using Point Descriptors: A Comparative Study
Souto, J. R. D. A., Barbosa, F. M. C., & de Carvalho, B. M. (2023) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms58004.2023.00189 · Cited by 2
Automatic Labeling of Natural Landmarks for Wheelchair Motion Planning
Ngo, B.-V., Hải, N. T., & Vu, C. C. (2023) · Electronics · doi:10.3390/electronics12143093 · Cited by 2
Analyzing Classical and LDI Depth-Aware Image Stitching for Enhanced Virtual View Representation
Venjarski, J., Tibenský, Š., & Rozinaj, G. (2023) · International Conference on Systems, Signals and Image Processing · doi:10.1109/iwssip58668.2023.10180238 · Cited by 2
Acquiring 360° Light Field by a Moving Dual-Fisheye Camera
Lo, I.-C., & Chen, H. H. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3299444 · Cited by 2
“Classical feature detectors usually perform well on conventional planar natural images but may fail for dual-fisheye images and cause shape distortions or breakages [36], [37], [38].”
BackgroundVehicle Detection in Indian Traffic Using an Anchor-Free Object Detector
Deshmukh, P., Kadha, V., Rayasam, K. C., et al. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-3250-4_45 · Cited by 2
He, N., Jin, H., Li, H., et al. (2023) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2023772 · Cited by 2
Feature Map Activation Analysis for Object Key-Point Detection
Rush, A., & Wood, S. L. (2023) · IEEE Access · doi:10.1109/access.2023.3315589 · Cited by 3
Donadi, I., Olivastri, E., Fusaro, D., Li, W., Evangelista, D., & Pretto, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44137-0_28 · Cited by 2
Image Feature Extraction and Matching of Augmented Solar Images in Space Weather
Wang, R., Bao, L., & Yanxia, C. A. I. (2023) · Chinese Journal of Space Science · doi:10.11728/cjss2023.05.2022-0064 · Cited by 2
Efficient spatial and channel net for lane marker detection based on self-attention and row anchor
Fan, S., Zhang, Y., Lu, S., & Bi, X. (2023) · Scientific Reports · doi:10.1038/s41598-023-47071-2 · Cited by 4
Key-Part Attention Retrieval for Robotic Object Recognition
Liu, J., Cao, Z., & Tang, Y. (2023) · Tsinghua Science & Technology · doi:10.26599/tst.2023.9010022 · Cited by 2
A visual positioning model for UAV’s patrolling video sequence images based on DOM rectification
Liu, H., Fan, W., & Wu, D. (2023) · Scientific Reports · doi:10.1038/s41598-023-49001-8 · Cited by 2
What to Learn: Features, Image Transformations, or Both?
Chen, Y., Xu, B., Dümbgen, F., & Barfoot, T. D. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342415 · Cited by 2
AENet: attention efficient network for cross-view image geo-localization
Xu, J., Zhu, M., Qi, B., et al. (2023) · Electronic Research Archive · doi:10.3934/era.2023210 · Cited by 2
Design and Fabrication of a Conceptual Model for a Portable Ring Shaped Medical Imaging Apparatus
Nozari, M., Sokot, M., Hasani, A. S., et al. (2023) · RSI International Conference on Robotics and Mechatronics (ICRoM) · doi:10.1109/icrom60803.2023.10412369 · Cited by 2
Attention Mechanism Based CNC Milling Cutter Wear Detection Using Machine Vision
Hu, S., Wen, H., Zhang, Z., et al. (2023) · International Conference on Mechatronics and Machine Vision in Practice (M2VIP) · doi:10.1109/m2vip58386.2023.10413371 · Cited by 2
A Specialized and Fortified Model for Vehicle Brand Detection Based on YOLOv8
Zhang, Y. (2023) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs59936.2023.10435394 · Cited by 2
A Hardware-Aware Network for Real-World Single Image Super-Resolutions
Ma, R., & Du, X. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3368372 · Cited by 2
“4, conventional image registration algorithms such as SIFT [35], SURF [36], and SuperGlue [37] cannot produce accurate results.”
MethodCombining bag of visual words-based features with CNN in image classification
Marzouk, M. A., & Elkholy, M. (2024) · Journal of Intelligent Systems · doi:10.1515/jisys-2023-0054 · Cited by 2
“Any classi fi er that uses the worst features outperforms one that uses random features [43,44].”
Hwang, I., & Lee, Y. (2024) · Journal of Computational Design and Engineering · doi:10.1093/jcde/qwae016 · Cited by 5
Optimal Projection Pattern for Active Visual Servoing (AVS)
Arai, S., Miyamoto, Y., Kobayashi, A., & Kosuge, K. (2024) · IEEE Access · doi:10.1109/access.2024.3382204 · Cited by 4
“The visual feature is a multidimensional vector and can be computed based on the image feature, such as the edges, counters, corners, SIFT [39], SURF [40], AKAZE [41], etc., without using the relative pose of the camera to the manipulator and the intrinsic parameter of the camera.”
MethodNakamura, Y., Sasaki, A., Toda, Y., & Kubota, N. (2024) · SICE International Symposium on Control Systems (SICE ISCS) · doi:10.23919/siceiscs60954.2024.10505755 · Cited by 2
“Representative examples include the Bag-of-Visual-Words model [16] using local image descriptors such as SIFT [17] and SURF [18], and place recognition using global image features such as FABMap [19, 20], GIST [21].”
MethodKe, T., Ye, Z., Zhang, X., et al. (2024) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-x-1-2024-107-2024 · Cited by 2
Hybrid self-supervised monocular visual odometry system based on spatio-temporal features
Yuan, S., Zhang, J., Lin, Y., & Yang, L. (2024) · Electronic Research Archive · doi:10.3934/era.2024163 · Cited by 2
“In 2006, Bay et al. [8] proposed speeded up robust features (SURF), which o ff ers higher computational e ffi ciency.”
GraSS: Graph Neural Networks for Loop Closure Detection with Semantic and Spatial Assistance
Lu, S., Peng, Z., Xiao, Z., Yan, B., Lin, S., Yu, S., & He, D. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10557928 · Cited by 2
“Features are mostly extracted using artificially designed features, such as SIFT [9], ORB [10] and SURF [11].”
MethodDavydko, O., Pavlov, V. A., Biecek, P., & Longo, L. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63803-9_1 · Cited by 2
Strand, L., Brückner, M., Lakshminarasimhan, V., et al. (2024) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv55156.2024.10588435 · Cited by 2
“We detect and match SURF features [23] in both the input and the calibrated reference image, as displayed in Fig.”
Method1/0 Shades of UC: Photonic Side-Channel Analysis of Universal Circuits
Mehta, D. M., Hashemi, M., Forte, D. J., et al. (2024) · IACR Transactions on Cryptographic Hardware and Embedded Systems · doi:10.46586/tches.v2024.i3.574-602 · Cited by 2
“For this purpose, the scale-invariant feature transform (SIFT) algorithm is purposefully chosen as it can extract features for spot detection, whereas popular algorithms like speeded-up robust feature (SURF) algorithm [BTVG06] work better with edge detection.”
MethodXu, Z., Wu, X., Liu, Y., et al. (2024) · IET Science Measurement & Technology · doi:10.1049/smt2.12204 · Cited by 2
Zhong, X., Liang, L. H., Koh, A. S.-M., & Yong, Y. S. (2024) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai59869.2024.00157 · Cited by 2
“Corner Detection [4], SURF [5], and ORB [6], are heavily dependent on domain-specific knowledge and often fall short in capturing intrinsic image features in gastroenterology.”
BackgroundJing, 徐. X., Lidong, 包. B., Ming, 方. F., et al. (2024) · Laser & Optoelectronics Progress · doi:10.3788/lop232611 · Cited by 2
Robust Multi-Robot Global Localization with Unknown Initial Pose based on Neighbor Constraints
Zhang, Y., Luo, H., Wang, W., & Feng, W. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610066 · Cited by 2
“Localization systems that use the Bag-of-Words approach include [9]–[13].”
MethodSong, W., Yan, R., Lei, B., & Okatani, T. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610786 · Cited by 3
“Before the emergence of deep learning, hand-crafted local features, such as SIFT [6], ORB [29], and SURF [30], are widely applied in computer vision fields such as image matching.”
MethodThe Technical use of Mobile Robots in Developing Smart Cities in Integration with Vins
Rathika, S., Chourasia, S., Arunkumar, E., et al. (2024) · International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) · doi:10.1109/icacite60783.2024.10617341 · Cited by 2
Lei, M., He, L., & Li, F. (2024) · Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS) · doi:10.1109/acctcs61748.2024.00064 · Cited by 2
Xiao, J., Zhang, K., Xu, X., Liu, S., Wu, S., Huang, Z., & Li, L. (2024) · Energies · doi:10.3390/en17164068 · Cited by 6
ORBcmfd: Oriented FAST and Rotated BRIEF Keypoints Based Image Copy-Move Forgery Detection
Kaushal, G., & Soni, B. (2024) · IEEE Students Conference on Engineering and Systems (SCES) · doi:10.1109/sces61914.2024.10652370 · Cited by 2
“As a result, these techniques are less suited for addressing tasks involving extensive rotation, scaling, and ] [11], Speeded-Up Robust Features (SURF) [12] [13], and Oriented Fast and Rotated BRIEF (ORB) [14] [15].”
BackgroundLarge-Scale Indoor Visual–Geometric Multimodal Dataset and Benchmark for Novel View Synthesis
Cao, J., Zhao, X., & Schwertfeger, S. (2024) · Sensors · doi:10.3390/s24175798 · Cited by 5
“Traditional 3D reconstruction algorithms like COLMAP [8,9] have relied heavily on feature extraction and matching techniques, such as SIFT [10] or SURF [11] feature matching, followed by Structure from Motion (SfM) and Multi-View Stereo (MVS) for scene reconstruction.”
MethodUncooperative Spacecraft Pose Estimation With Normalized Segmentation Coordinate Space
Zhong, L., Chen, S., Wang, W., Yang, W., Yuan, G., Guo, P., Yang, X., & Zhang, X. (2024) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2024.3442570 · Cited by 5
Deformable surface reconstruction via Riemannian metric preservation
Barbany, O., Colomé, A., & Torras, C. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104155 · Cited by 3
FC-GNN: Recovering Reliable and Accurate Correspondences from Interferences
Xu, H., Zhou, J., Yang, H., Pan, R., & Li, C. (2024) · 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/cvpr52733.2024.02382 · Cited by 2
“Traditional methods such as SIFT [27], SURF [3], and ORB [35] are still widely used today.”
Automatic Recognition of Food Ingestion Environment from the AIM-2 Wearable Sensor
Huang, Y., Hassan, M. A., He, J., HIGGINS, J. A., McCrory, M. A., Eicher‐Miller, H. A., Thomas, J. G., Sazonov, E. E., & Zhu, F. M. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00372 · Cited by 3
A unified feature-motion consistency framework for robust image matching
Zhou, Y., Gao, J., & Liu, X. (2024) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2024.09.021 · Cited by 3
Self-Supervised Underwater Caustics Removal and Descattering via Deep Monocular SLAM
Sauder, J. F., & Tuia, D. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72907-2_13 · Cited by 8
“Caustics, in particular, are extremely detrimental for image keypoint matching [25], which forms the basic building block in almost all Simultaneous Localization and Mapping (SLAM) and SfM pipelines [47, 8, 64].”
ADen: Adaptive Density Representations for Sparse-View Camera Pose Estimation
Tang, H., Wang, W., Gleize, P., & Feiszli, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73033-7_7 · Cited by 2
Gartner, C. M., Mathew, J. K., & Bullock, D. M. (2024) · Future Transportation · doi:10.3390/futuretransp4040062 · Cited by 3
“Lisanti proposed a “continuous localization” technique [27], a landmark tracking algorithm utilizing SURF key-point detection [28].”
Adaptive Granularity-Fused Keypoint Detection for 6D Pose Estimation of Space Targets
Gu, X., Yang, X., Liu, H. S., & Yang, D. (2024) · Remote Sensing · doi:10.3390/rs16224138 · Cited by 3
EcoMatcher: Efficient Clustering Oriented Matcher for Detector-Free Image Matching
Chen, P., Yu, L., Wan, Y., Zhang, Y., Wang, J. Z., Zhong, L., Chen, J., & Yan, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73113-6_20 · Cited by 6
ClusVPR: Efficient Visual Place Recognition With Clustering-Based Weighted Transformer
Xu, Y., Shamsolmoali, P., Zareapoor, M., & Yang, J. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3510479 · Cited by 2
“Early VPR approaches [20], [21] relied on classical techniques like SIFT [22] and SURF [23] for detecting keypoints.”
CamPU: A Multi-Camera Processing Unit for Deep Learning-based 3D Spatial Computing Systems
Im, D., & Yoo, H. (2024) · Proceedings of the ... annual International Symposium on Microarchitecture/Proceedings of the annual International Symposium on Microarchitecture · doi:10.1109/micro61859.2024.00014 · Cited by 2
“Previous works [1], [23], [45] have focused on accelerating feature extraction [6], [32] and feature matching in unknown camera environments.”
Lee, J., Choi, D.-G., Kim, G., Song, M., & Yoon, J. (2024) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2024.3505960 · Cited by 2
“In contrast, the indirect SLAM extracting the features from the input images estimates the movement of agents based on the displacement of the features between the consecutive images [10], [11], [12], [13], [14], [15], [16], [17].”
Automatic stitching of panoramas for geological images of polished sections
Nikolaev, G., Korshunov, D. M., & Khvostikov, A. V. (2024) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-x-2-w1-2024-39-2024 · Cited by 2
“Despite this, methods based on key point detection, such as SIFT (Lowe, 1999) and SURF (Bay et al., 2006), remain relevant in this field.”
Ullah, F., Hayajneh, M., Abuali, N. A., Asad, H., Malik, F. S., & Mon, B. F. (2024) · International Conference on Advanced Communication Technologies and Networking (CommNet) · doi:10.1109/commnet63022.2024.10793296 · Cited by 7
Visual and Inertial Sensor Fusion Approach for Visual Inertial Odometry Used in Vehicle Localization
Jo, H., & Yoon, S. W. (2024) · Proceedings of IEEE Sensors/Proceedings of IEEE Sensors ... · doi:10.1109/sensors60989.2024.10785070 · Cited by 2
“Over the past few decades, hand-crafted feature extractors (SIFT [17], SURF [18] and ORB [19]) have been widely used, but deep learning-based methods like SuperPoint have shown superior performance.”
Multispectral image fusion technique based on decoupling of information
Yu, W., Wang, H., Liu, J., et al. (2024) · IET Image Processing · doi:10.1049/ipr2.13296 · Cited by 2
Yu, Z. (2024) · Applied Intelligence · doi:10.1007/s10489-024-06120-7 · Cited by 3
“…of fact, even the state-of-the-art feature detection and matching algorithms, e.g. Scale Invariant Feature Transform (SIFT) [19, 20], or Speeded-Up Robust Features (SURF) [21], have been shown to produce a number of false matches that sig-nificantly lead to incorrect estimates of robot trajectory.”
VRTNet: Vector Rectifier Transformer for Two-View Correspondence Learning
Yang, M., Chen, J., Tian, X., Wei, L., & Ma, J. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3521696 · Cited by 2
Yin, Z., Liu, B., Wang, J., et al. (2024) · IEEE Asia Pacific Conference on Circuits and Systems (APCCAS) · doi:10.1109/apccas62602.2024.10808227 · Cited by 2
Chen, Y., Zhang, L. B., Zhan, H., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-024-03794-x · Cited by 3
“At present, in the field of printed images registration, the main-stream registration methods are SIFT [6], SURF [16] and other registration methods based on feature extraction.”
SLFRM: A Novel Signature Local Feature Reconstruction Module for Offline Signature Verification
Zheng, L., Wu, D. Y., Zhang, M., et al. (2024) · International Conference on Computing and Pattern Recognition (ICCPR) · doi:10.1145/3704323.3704360 · Cited by 2
Zhao, Y., Chen, D., & Gong, J. (2025) · Remote Sensing · doi:10.3390/rs17020184 · Cited by 2
Inclined Aerial Image and Satellite Image Matching Based on Edge Curve Direction Angle Features
Wang, H. H., Liu, C., Ding, Y., et al. (2025) · Remote Sensing · doi:10.3390/rs17020268 · Cited by 2
LoCS-Net: Localizing convolutional spiking neural network for fast visual place recognition
Akcal, M. U., Raikov, I., Gribkova, E., Choudhuri, A., Kim, S. H., Gazzola, M., Gillette, R., Soltész, I., & Chowdhary, G. V. (2025) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2024.1490267 · Cited by 2
“These key-points can be marked by the descriptions generated through the application of methods including SIFT [31], RootSIFT [32], SURF [33], and BRIEF [34].”
Currency Detection Application for Visually Impaired People using Tensorflow Lite
Bhakhar, R., Mandal, R., Goyal, A., et al. (2024) · doi:10.1109/smart63812.2024.10882163 · Cited by 2
“SURF, developed by Herbert Bay et al. [16], is a scale-and rotation-invariant method that surpasses previous techniques in terms of robustness, distinctiveness, and computational speed.”
Single and Multi-Spectral Methods for Pedestrian Detection: A Comprehensive Review
Gupta, J., & Sharma, S. (2025) · International Conference on Multi-Agent Systems for Collaborative Intelligence (ICMSCI) · doi:10.1109/icmsci62561.2025.10894351 · Cited by 2
“Some of these are Histogram of oriented gradients technique (HOG) [4], Scale Invariant Feature Transform technique (SIFT) [5], Local Binary Pattern technique (LBP) [13], Speed Up Robust Features (surf) [6] and Haar method [14].”
Liu, Q., Liu, Z., Wu, Q., Xia, P., & Yao, Y. (2025) · The Photogrammetric Record · doi:10.1111/phor.70002 · Cited by 2
Multimodal Remote Sensing Sparse Registration With a Global-Local Descriptor
Zhang, Y., Lei, Y., Zhu, Y., et al. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3554190 · Cited by 2
“3) Corner Points’ Detection: The corner points, which invariant to rotation and scale [11], are obtained by applying the integral scale space (ISS) for corner detection to the linearly enhanced minimum moment map, addressing the stability issues associated with the corner points detected by the…”
SD-YOLOv5: Implementation of Real-Time Staircase Detection on Jetson Nano Board
Fataniya, B. D., Mecwan, A., Shah, D., Chauhan, M. M., & Dave, J. M. (2025) · SN Computer Science · doi:10.1007/s42979-025-03890-w · Cited by 2
“Histogram of Oriented Gradients (HOG) [6], Deformable Part-based Model (DPM) [7], Scale Invariant Fourier Trans-form (SIFT) [8], Speeded Up Robust Features (SURF) [1, 9] etc.”
Generalizable Single-View Object Pose Estimation by Two-Side Generating and Matching
Sun, Y., Sun, C., Liu, Y., Ma, Y., & Yiu, S. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00063 · Cited by 2
“Then, for a pair with low difficulty, we perform naive matching proposed in E2VG, which can be completed in 150ms.”
Uncertainty Aware Interest Point Detection and Description
Zeng, J., Gu, Z., Liu, W., Cai, L., & Cheng, J. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00215 · Cited by 5
“Early works such as SIFT [38], SURF [5], and others [9, 20, 24, 47, 48] have demonstrated their effectiveness in practical applications.”
Detection of copy-move forgery with deep CNN features using Machine learning Classifier
Rehman, K., & Jain, G. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.564 · Cited by 2
Self-supervised learning with multimodal remote sensed maps for seafloor visual class inference
Liang, C., Cappelletto, J., Massot‐Campos, M., Bodenmann, A., Huvenne, V. A. I., Wardell, C., Bett, B. J., Newborough, D., & Thornton, B. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649251343640 · Cited by 4
“Speeded-Up Robust Features (SURF) were developed to improve the SIFT by using optimised integral operations (Bay et al., 2006).”
A Semianalytical Fourier–Mellin Method for Real-Time Dynamic Star Image Registration
Chen, G., Jiang, L., Zhang, Y., et al. (2025) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2025.3574021 · Cited by 2
“Many scale-invariant and rotation-invariant descriptors include scale-invariant feature transform (SIFT) [7], SURF [8], HOG [9], GLOH [10], FAST [11], ORB [12], and their improved versions, which have been proposed for image registration.”
Zhang, P., Luo, J., & Liang, X. (2025) · Symmetry · doi:10.3390/sym17060832 · Cited by 2
Multiscale Spherical Feature Decoupling Network for Multimodal Image Registration
Li, T., Zhou, Z., Zhu, Q. X., Luo, J., & Wang, Y. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3587800 · Cited by 2
“These methods usually use feature detectors [15], [16], [17] to detect feature points, match corresponding points across images, and then adopt DLT [14] combined with outlier rejection algorithms [18], [19] to estimate the homography.”
Enhancing Lidar Point Cloud Sampling via Colorization and Super-Resolution of Lidar Imagery
Sier, H., Du, H., Yu, X., et al. (2025) · European Conference on Mobile Robots · doi:10.1109/ecmr65884.2025.11163366 · Cited by 2
“Speeded-Up Robust Features (SURF) [25] is a faster alternative to SIFT and uses box filters to approximate DoGs, thus enabling faster computation while maintaining robust performance.”
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.