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 14,001–14,100 of 14,752
Stacked Object Clustering with Adaptive Scanning and Density Centralized Voting
You, H., Xu, F., & Du, J. (2024) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784485224.039
Design of Micro-Aperture Measurement System Based on Image Processing
李, 若. (2024) · Operations Research and Fuzziology · doi:10.12677/orf.2024.141074
An Effective Checkerboard Calibration Technique for a Stereo Camera System
Satushe, V., Vyas, V., Gujar, P., et al. (2023) · IEEE Pune Section International Conference (PuneCon) · doi:10.1109/punecon58714.2023.10450002
Multimodal Attention-Based Feature Fusion for Short Video ClassificationPreprint
Sinclair, C., Callahan, A., Everly, S., & Beckett, J. (2024) · Research Square · doi:10.21203/rs.3.rs-3936566/v1 · Cited by 1
Upkd: Unsupervised Pylon Keypoint Detection from 3d Lidar Data for Autonomous Uav Power InspectionPreprint
Wu, J., Chen, C., Yan, Z., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4758824
Siji, R., & Nithya, S. (2024) · International Journal of Applied Engineering Research · doi:10.37622/ijaer/19.1.2024.41-49
“Similar in concept to SIFT, SURF was created by Bay et al. [24] as a more reliable and speedier extractor than earlier models.”
Loop Closure Detection Based On Semantic Information In Dynamic Scenes
Li, C., Qin, Y., Huang, Y., et al. (2023) · China Automation Congress (CAC) · doi:10.1109/cac59555.2023.10450851
“Traditional hand-crafted local feature methods, such as SIFT [1], SURF [2], and ORB [3], have been widely used in visual SLAM.”
MethodPosition Mapping using Content Based Image Retrieval and Annoy
Dalal, R., Randhawa, S. K., Modi, S., et al. (2023) · International Conference on Modeling, Simulation & Intelligent Computing (MoSICom) · doi:10.1109/mosicom59118.2023.10458815
“Some well-known feature detection methods include the Harris corner detector, SIFT (Scale Invariant Feature Transform)[9], SURF (Speeded Up Robust Features)[10], ORB (Oriented Fast and Rotated Brief)[11], and FAST (Features from Accelerated Segment Test)[12].”
MethodA Keypoint-Based Technique for Detecting the Copy Move Forgery in Digital Images
Rehman, K., & Islam, S. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-9562-2_66
Zhu, H., Dong, A., & Yu, J. (2023) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads60453.2023.00343
“SURF [5] algorithm is used for feature detection and description, while the FLANN library [6] is employed for feature matching.”
MethodAppati, J. K., & Wunake, P. (2024) · Research Square · doi:10.21203/rs.3.rs-4008856/v1 · Cited by 1
DIGITAL IMAGE RESTORATION USING SURF ALGORITHM
Tammineni, S., Rayavarapu, S. M., Gottapu, S. R., et al. (2024) · Informatyka Automatyka Pomiary w Gospodarce i Ochronie Środowiska · doi:10.35784/iapgos.5373
“The performance of SURF is comparable to that of SIFT [1].”
ResultPrecision Face Mask Detection in Crowded Environment using Machine Vision
Alsayaydeh, J. A. J., Yusof, M. F., Lin, C. Y., Al-Andoli, M. N., Herawan, S. G., & Isa, I. S. M. (2024) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2024.0150325
“Feature-based detectors, which include algorithms such as the Cascade Object detector, Barcode detector, and April Tag detector, provide an alternative approach for object detection and classification [19].”
MethodChen, M., Shi, Y., Wu, L., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4782052
Research on Garbage Recognition of Road Cleaning Vehicle Based on Improved YOLOv5 Algorithm
Liu, X., Wen, Z., Kang, K., & Liu, X. (2024) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2024-01-2003
Shilin, D., Vtyurina, S. I., Dey, S., et al. (2024) · International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE) · doi:10.1109/reepe60449.2024.10479935
“…[12, 13, 14], SURF (Speeded Up Robust Features) [12, 13, 15], FREAK (Fast Retina Keypoint), AKAZE и ORB (Oriented FAST and Rotated BRIEF) [16], BRISK (Binary Robust Invariant Scalable Keypoints) [17], BRIEF (Binary Robust Independent Elementary Features) [18], deep neural networks, and…”
BackgroundTechnique to Generate Depth Maps from Real Scenes without Manual Calibration
Casado, R. S., Carvalho, C. W., Fernandes, M. M., et al. (2024) · IEEE Latin America Transactions · doi:10.1109/tla.2024.10500710
“The algorithms considered in this work were BRISK [12], SURF [13], Harris [14], Minimum Eigeen Value (Min8Val) [15], FAST [16], [17] and MSER [18].”
MethodLarge-scale Language-image Model-based Bag-of-Objects Extraction for Visual Place Recognition
Jung, S., & Park, B. (2024) · Journal of Sensor Science and Technology · doi:10.46670/jsst.2024.33.2.78
Copy-Move Forgery Detection Using Regional Density Center ClusteringPreprint
Lin, C., Wu, Y., Huang, K., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4797821
Multi-scale Visual Feature Association Based Long-Term UAV Positioning Algorithm
Xiaozu, L., & Zhao, J. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-1087-4_18
SfM ToAEval: Trade-off Aware Evaluation of Feature Extraction Algorithms in Structure from Motion
Taha, D., El-Mashad, S. Y., & Zayed, H. H. (2024) · Engineering Research Journal · doi:10.21608/erjsh.2024.245661.1242
“…(like AGAST [17], FAST [18], and STAR [19]), feature description only (like BEBLID [20], BRIEF [21], DAISY [22], FREAK [23], LATCH [24], LUCID [25], TEBLID [26], and VGG [27]), or both feature detection and description (like AKAZE [28], BRISK [29], KAZE [30], ORB [31], SIFT [32], and SURF [33]).”
BackgroundNRPerson: A Non-Registered Multi-Modal Benchmark for Tiny Person Detection and Localization
Yang, Y. H., Han, X., Wang, K., Yu, X., Yu, W., Wang, Z., Li, G., Han, Z., & Jiao, J. (2024) · Electronics · doi:10.3390/electronics13091697 · Cited by 1
Airport Pedestrian Target Tracking Algorithm Based on Surf and Improved Correlation Filtering
Wan, H., Xie, Y., Yang, Z., et al. (2023) · International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc59590.2023.10507379
“Inspired by SIFT algorithm, Bay et al. proposed speed up robust features (surf) algorithm in 2006 [5].”
MethodA lightweight network model designed for alligator gar detection
Wang, X., Shi, W., & Chen, R. (2024) · Scientific Reports · doi:10.1038/s41598-024-61016-3 · Cited by 1
Multi-channel and multi-featured extended orb with gabor filter and non-maximum suppression
Kumar, K., Gupta, D., Nayyar, S., et al. (2024) · World Journal of Advanced Engineering Technology and Sciences · doi:10.30574/wjaets.2024.12.1.0183
All-in-Focus Three-Dimensional Reconstruction Based on Edge Matching for Artificial Compound Eye
Wu, S., Ren, L., & Yang, Q. (2024) · Applied Sciences · doi:10.3390/app14114403
RS-YOLO: A YOLO-Based Method for Small Object Detection in Remote SensingPreprint
Ao, D., Zhao, W., Zhang, Y., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-4416811/v1
Towards Generating Authentic Human-Removed Pictures in Crowded Places Using a Few-Second Video
Lee, J., Lee, E., & Kang, S. (2024) · Sensors · doi:10.3390/s24113486
“Note that several feature matching algorithms are considered, such as Orientated FAST and Robust BRIEF (ORB) [39], Speeded Up Robust Feature (SURF) [40], and Scale-Invariant Feature Trans-form (SIFT) [41].”
MethodExploring Sign Language Recognition Methods: An Effective Kernel Approach
Manogna, J. S., Nandini, V., Krishna, B. R., Peddi, A., Satyanarayana, J. V., & Rao, M. V. P. C. S. (2024) · Springer proceedings in mathematics & statistics · doi:10.1007/978-3-031-51167-7_34
Attention-based mechanism for SuperPoint feature point extraction in endoscopy
Zhang, M. (2024) · Advances in Computer Signals and Systems · doi:10.23977/acss.2024.080311
“The first one mainly extracts information by calculating and abstracting images through mathematical formulas, some representative algorithm include SIFT(Scale-invariant Feature Transform) [11], SURF(Speeded Up Robust Features) [12] and ORB(Oriented FAST and Rotated BRIEF) [13], etc.”
MethodAouthu, S., Meenakshi, K., Swaraja, K., et al. (2024) · Cogent Engineering · doi:10.1080/23311916.2024.2345851
Application of intelligent algorithms in the field of computer vision
Huang, H. P., & Hao, Z. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-21758-6.00002-4
RRER: A refined registration method based on contrast minimum for event and RGB cameras
Zhang, S., Tang, T., Sang, F., et al. (2024) · IET Image Processing · doi:10.1049/ipr2.13131
Advanced facial recognition with LBP-URIGL hybrid descriptors
Hendi, S. H., Taher, H. B., & Hussein, K. Q. (2024) · Pollack Periodica · doi:10.1556/606.2024.00972
Object/Scene Recognition based on Directional PixelVoting Descriptor from Edge-based SegmentationPreprint
Aguilar‐González, A., Santiago, A. M., & Osuna-Coutiño, J. A. D. J. (2024) · Research Square · doi:10.21203/rs.3.rs-4464710/v1
Panorama Inspector: A Novel Methodology for Automated Error Detection in Stitched Images
İşlek, İ., & Karaman, Ç. Ç. (2024) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit58233.2024.10540820
“Some methods based on traditional computer vision theories include SIFT [2], SURF [3], FAST [4], BRIEF [5], and ORB [6], published in the 1 https://www.vht360.com/ early 2000s.”
MethodWang, X., Zhang, Z., Zhang, M., et al. (2024) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit58233.2024.10540696
“The classic methods are SIFT [28] , SURF [29] , ORB [30] , and KAZE [31] , all of which have passed the test of time.”
MethodFingerprint Authentication System with Feature Detection using Descriptor Analysis
Imran, M., & Umar, M. S. (2024) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict60155.2024.10544976 · Cited by 1
“The objective of finding the similarity between a pair of images as well as objects or scene from a motion video is often an integral part of any computer vision application[7].”
BackgroundAn Improved Neighborhood-Based Mismatch Removal Algorithm for Consumer Device
Zhang, H., Hou, W., Jia, N., et al. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3409774
“As mentioned before, a variety of methods exploiting neighborhood preservation have been developed for feature matching [15], [16], [17].”
InfluentialJian, H., Wen, G., Fan, X., et al. (2023) · doi:10.1109/iccbd-ai62252.2023.00064
Novel Approaches for Aligning Geospatial Vector Maps
Cherif, M. A., Tripodi, S., Tarabalka, Y., et al. (2024) · 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-xlviii-2-2024-55-2024
“Feature matching involves identifying and aligning key points in images, such as corners or textures, using algorithms like SIFT (Lowe, 1999), SURF (Bay et al., 2006), and ORB (Rublee et al., 2011).”
MethodA Modern Approach to High Dynamic Range Image Processing with Machine Learning Architectures
Kovtun, R. S., Chuprov, S., Gataullin, R. I., et al. (2024) · doi:10.1109/scm62608.2024.10554097
“Therefore, algorithms based on compiling descriptors that are invariant to rotations (but not invariant to exposure) [14], [15] cannot be used in their original form.”
Sharma, T., & Verma, N. K. (2024) · Algorithms for intelligent systems · doi:10.1007/978-981-97-2011-8_1
Remote-Sensing Image Stitching Based on Infinite Homography and Global Seam Finding
Chang, J., Li, Q., Liang, Y., et al. (2024) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126624503079
Aerial Image Matching Algorithm Based on Edge Boxes
Fang, Q., Xu, B., Zhang, C., et al. (2024) · International Conference on Advanced Algorithms and Control Engineering (ICAACE) · doi:10.1109/icaace61206.2024.10548455
“Conventional feature extraction methods (such as SIFT [4], SURF [5], etc.) require downsampling of the entire image.”
MethodVisual Detection System for Industrial Defects
Wang, L., Xu, A., Huang, Z., & Shen, Q. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-3626-3_25
Transformer-Driven Models for Language, Vision, and Multimodality
Luo, M., Gokhale, T., Varshney, N., Yang, Y., & Baral, C. R. (2024) · Synthesis lectures on computer vision · doi:10.1007/978-3-031-57816-8_2
Qingge, 李. L., Xiaogang, 杨. Y., Ruitao, 卢. L., et al. (2024) · Infrared and Laser Engineering · doi:10.3788/irla20240086
A Method of Infrared Image Mosaic Based on Keyframe Matching
Shao, J., Yu, Y. L., Xu, Z., et al. (2023) · doi:10.1109/mvipit60427.2023.00015
Oak Ridge National Laboratory Bundle Adjustment of Maxar WorldView and GeoEye Imagery
Tate, C. G., USDOE, Thomas, O. H., et al. (2024) · doi:10.2172/2394741
Lorentz-modulated multiscale nonlinear diffusion for stitching in near-uniform scenes
Jong, T. K., & Bong, D. B. L. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19704-9
“In search of scale-invariant interest points, we employ Hessian matrix by converting all nonlinear scale spaces into integral images, enabling fast computation to be later implemented using box filters [13, 48].”
InfluentialReliable Cosine Matching via Neighborhood Consensus for Fundus Image Registration
Tang, K., Wang, S., Yang, H., Lai, H., Sun, J., & Luo, Y. (2024) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd61410.2024.10580782
“Traditional image registration methods, like SIFT [3] and SURF [4], utilize feature assessment to compute transformation parameters.”
MethodDesign and Validation of Pipeline Inspection Robot based on Panoramic Vision
Jia, Z., Li, S., & Li, B. (2024) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc62350.2024.10588117
“In 2006, Bay proposed the Speeded-Up Robust Features (SURF) algorithm [11], an advanced version of the SIFT algorithm.”
MethodA lightweight feature point detection model based on feature pyramid and attention
Zhou, Y., Gao, Z., Bu, F., et al. (2024) · IEEE International Conference on Electronic Technology, Communication and Information (ICETCI) · doi:10.1109/icetci61221.2024.10594506
“There are also other representative methods such as SURF [8], KAZE [9], AKAZE [10], and BRISK [11].”
MethodSudhish, D. K., Nair, L. R., & Sivan, S. (2024) · The Journal of Supercomputing · doi:10.1007/s11227-024-06350-z
“The SURF features can be given as follows [31], (3) where X = (x, y) in an image I, L pp ( X , 𝜎 ) , L qq ( X , 𝜎 ) and L pq ( X , 𝜎 ) implies convolution of Gaussian second-order derivative.”
Deformation Estimation of Textureless Objects from a Single Image
Adli, S. E., Pickard, J. K., Sun, G., et al. (2024) · Sensors · doi:10.3390/s24144707
Chen, D., Ju, H. K., & Kang, K. (2024) · AIP conference proceedings · doi:10.1063/5.0220114
Research on Clothing Image Retrieval Combining Topology Features with Color Texture Features
Zhang, X., Sun, H., & Ma, J. (2024) · Mathematics · doi:10.3390/math12152363
SLAM und kartenbasierte Lokalisierung
Sons, M., Theers, M., & Hofstetter, I. (2024) · ATZ/MTZ-Fachbuch · doi:10.1007/978-3-658-38486-9_21
Localizing Scan Targets from Human Pose for Autonomous Lung Ultrasound Imaging
Long, J., Cai, J., Al-Battal, A. F., et al. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-66428-1_38
Estudio de invariabilidad de marcas visuales ante cambios de iluminación
Gutiérrez, M. M., Ballesta, M., Valiente, D., et al. (2024) · Jornadas de Automática · doi:10.17979/ja-cea.2024.45.10809
Enhancing Multi-View Stereo Reconstruction with High Receptive Field ConvolutionPreprint
Eum, S., & Park, U. (2024) · Research Square · doi:10.21203/rs.3.rs-4709825/v1
Joint-Loss Enhanced Self-Supervised Learning for Refinement-Coupled Object 6D Pose Estimation
Mu, F., Sun, S., Huang, R., Zou, C., Li, W., Zhan, H., & Cheng, H. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611061
“Traditional approaches rely on manual descriptors to extract features from 2D images [7][8][20][21] and 3D point clouds [9][10][22].”
MethodTissue Block and Digital Slide Registration Method for Microscopic Samples
Paulik, R., Kozlovszky, M., & Molnar, B. A. (2024) · IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI) · doi:10.1109/saci60582.2024.10619739
“Classic feature-based algorithms, such as the Scale Invariant Feature Transform (SIFT) [9] and Speeded Up Robust Features (SURF) [10] techniques, are highly effective for detecting, describing, and matching .”
MethodSRSP: Sub-Random SuperPoint Based on Reprojection Error and Randomized Round Encoding
Tian, X., Li, L., & Cao, H. (2024) · IEEE Access · doi:10.1109/access.2024.3443093
“In 2008, Bay et al. [3] proposed the speeded-up robust features algorithm called SURF, an improved version of the SIFT algorithm.”
MethodPlangger, J. (2024) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2024-16051
Structure displacement extraction method based on image feature matching
Chen, X., Wang, Y., & Tan, J. (2024) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma61710.2024.10633029
“At present, there are many image feature matching algorithms, such as SIFT [9], SURF [10] and ORB [11].”
MethodAdaptive Robust Visual Place Recognition via Image Wise Automatic Method Selection
Wickramasinghe, H. (2024) · Queensland University of Technology · doi:10.5204/thesis.eprints.251496
Bildpyramiden, Wavelet-Transformation und Multiskalenanalyse
Beyerer, J., León, F. P., Frese, C., et al. (2024) · Springer eBooks · doi:10.1007/978-3-662-69951-5_16
Zhang, Y., & Du, Y. (2024) · Applied Sciences · doi:10.3390/app14177721
Target Detection Method Based on Joint Matching of Edge and Region Features
He, L., Liu, X., & Shen, A. (2024) · International Conference on Robotics, Control and Automation (ICRCA) · doi:10.1109/icrca60878.2024.10649273
“Bay and Ess et al. proposed a fast and robust feature extraction algorithm (SURF[2]), which perfectly overcomes the shortcomings of the SIFT feature extraction algorithm such as high computational overhead and long operation time.”
MethodSimMolCC: A Similarity of Automatically Detected Bio-Molecule Clusters between Fluorescent Cells
Hattori, S., Miki, T., Sanjo, A., Kobayashi, D., & Takahara, M. (2024) · Applied Sciences · doi:10.3390/app14177958
Sánchez, N., Santos., R. F. D., Vítor, G. B., & Beleño, R. D. H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4949568
Roghani, S. E. S., & Koyuncu, E. (2024) · IEEE Access · doi:10.1109/access.2024.3456909
“The search space for the in-line setup is detailed in 27, and the search space for the 45-degree setup is described in 32 and 33.”
MethodA novel key point based ROI segmentation and image captioning using guidance information
Selvakani, J. L., Ranganathan, B., & Palanisamy, G. (2024) · Machine Vision and Applications · doi:10.1007/s00138-024-01597-1
“The features can either be handcrafted, such as SIFT [17] and SURF [2], or learned from trained deep learning architectureofRNNcalledlongshort-termmemory(LSTM), which solves the vanishing gradient problem of RNNs [1].”
Object/Scene Recognition Based on a Directional Pixel Voting Descriptor
Aguilar‐González, A., Santiago, A. M., & Osuna-Coutiño, J. A. D. J. (2024) · Applied Sciences · doi:10.3390/app14188187
Lu, S., Xu, R. C., Shao, W., et al. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10662177
“Although SURF algorithm has better real-time and robustness compared to SIFT algorithm [11] , there are some issues such as missing detection of some feature points.”
MethodA rotation matching method for heterogeneous images based on invariant feature translation
Tang, B., Yang, X., Lü, R., et al. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10662506
“Traditional heterogenous image matching methods can be categorized into region-based matching methods [5-7] and feature-based matching methods [8, 9].”
BackgroundHuman Skeleton Point Detection Based on Super Resolution
Chen, L., & Zhu, Z. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10661439
“Traditional methods rely on manually designed features and rules, such as HOG-SVM [1] , SURF [2] , The Randomized Hough Transform method [3] , and model-based approaches.”
MethodA Detector-Free Image Matching Method based on Enhanced Feature Fusion
Chen, Z., & Xu, C. Y. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10662731
“For example, LoG [12], SURF [13], KAZE [14].”
Liu, S., Zhu, Y., Aoyama, T., et al. (2024) · Sensors · doi:10.3390/s24186050
“Techniques such as feature extraction using methods like SIFT (Scale-Invariant Feature Transform) [20] and SURF (Speeded Up Robust Features) [22] have shown significant improvements in matching accuracy and robustness in various computer vision applications.”
MethodAsıl, U., & Nasibov, E. N. (2024) · Research Square · doi:10.21203/rs.3.rs-4935014/v1
Slavin, O. (2024) · Studies in systems, decision and control · doi:10.1007/978-3-031-67685-7_9
Huang, D.-Y., Chen, C.-H., Chen, T.-Y., et al. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20222-x
“In general, common feature point detection methods include corner (i.e., feature point) detection such as AKAZE (Accelerated-KAZE), Harris corner [25], SIFT [26], SURF [27], and ORB [28].”
Zuo, G., Liu, H., & Li, J. (2024) · International Journal of Advanced Robotic Systems · doi:10.1177/17298806241279609
“Early methods 3,4 relied on local feature matching, which could handle occlusion to some extent but was limited by viewpoint changes and performed poorly on texture-less objects.”
Detection of Tuberculosis from Chest X-Rays Using Convolutional Neural Network
Bansal, S., Patel, P., & Harjai, A. (2024) · Smart innovation, systems and technologies · doi:10.1007/978-981-97-3690-4_43
Tagami, R., Kobayashi, H., Akizuki, S., et al. (2024) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2024edp7039
“In addition, keypoint matching (KPM) [4]–[6] has low recognition accuracy depending on the frequency of the image.”
BackgroundGesture recognition method based on handicraft features
Miao, Q., Li, Y., Liu, X., et al. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-28959-0.00003-0
A Fast Image Mosaic Algorithm Based on Feature Partition Extraction
Lian, Z., & Ren, J. (2024) · Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC) · doi:10.1109/ipec61310.2024.00019
“This technology refers to the process of removing overlapping areas from two or more images through image preprocessing [5], image registration [6], and image fusion [7], and concatenating them into a wide-angle image containing multiple image information.”
BackgroundResearch on Multi-Granularity Detection and Recognition of Vehicle Faces
Yan, Z., Zhong, X., Liu, C., et al. (2024) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat62382.2024.10695347
“Traditional machine learning techniques for object detection, such as Histogram of Oriented Gradients (HoG) [1], Speeded Up Robust Features (SURF) [2], Support Vector Machines (SVM) [3], and Deformable Part Models (DPM) [4], were hindered by limitations including slow processing times, complex…”
BackgroundVisual SLAM Based on Improved Line Filtering Decision and Weight Optimization
Cao, Y., Luo, Z., & Deng, Z. (2024) · IEEE Access · doi:10.1109/access.2024.3481420
“Early works primarily focused on the extraction and matching of point features, such as Scale-Invariant Feature Transform (SIFT) [16], Speeded Up Robust Features (SURF) [17], Harris corner detection [18], and others.”
BackgroundLarge-scale Image Stitching Algorithm Integrating UAV Position Information and MGFT Model
Liu, Z., Liu, J., Wang, K., et al. (2024) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm62033.2024.10715893
“In 2008, Bay et al. proposed the SURF algorithm [9], which detects and describes feature points in images using a fast image pyramid and box filters.”
MethodFR-SLAM: A SLAM Improvement Method Based on Floor Plan Registration
Feng, J., Li, X., Park, H., Liu, J., & Zhang, Z. (2024) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm62033.2024.10715930 · Cited by 3
“Following the establishment of the mapping, which takes the floor plan as its primary guide, the robot movement follows the predetermined pathway.”
MethodA method of UAV image homography matrix estimation based on deep learning
Mao, Y., Xue, X., Qu, G., et al. (2024) · doi:10.1117/12.3037062
Low-Cost Stereo Vision: A Single-Camera Approach For Precise Robotic Perception
Marx, S., Gusenburger, J., Bashir, A., & Müller, R. (2024) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case59546.2024.10711598 · Cited by 1
“Our stereo matching process is inspired by traditional feature-based matching processes where key features are being located in both images of a stereo pair using feature descriptors such as Scale-Invariant Feature Transform (SIFT) [19] or Speeded-Up Robust Features (SURF) [20].”
MethodGMM-IKRS: Gaussian Mixture Models for Interpretable Keypoint Refinement and Scoring
Santellani, E., Zach, M., Sormann, C., Rossi, M., Kühn, A., & Fraundorfer, F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72980-5_5 · Cited by 5
Scene Measurement Method Based on Fusion of Image Sequence and Improved LiDAR SLAM
Liang, D., Li, D., Yang, K., et al. (2024) · Electronics · doi:10.3390/electronics13214250
An Improved Monocular ORB-SLAM Using Scaled-Invariant Features
Fu, J., Ma, P., & Jia, Z. (2024) · IEEE International Conference on Advanced Information, Mechanical Engineering, Robotics and Automation (AIMERA) · doi:10.1109/aimera59657.2024.10735742
“Such as SIFT (Scale-Invariant Feature Transform)[4], SURF (Speeded-Up Robust Features)[5], and ORB (Oriented FAST and Rotated BRIEF) features[6].”
MethodInterpretable Unsupervised Homography Estimation
Zhou, Z., Zhu, Q. X., Wang, Y., Mo, Y., Chen, L., Huang, J., & Jiang, T. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8490-5_28
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.