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 8,801–8,900 of 14,752
Improved Squeeze and Excitation-Based YOLOv8-SE for Object Detection
Chauhan, R., Deshmukh, M., & Singh, A. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10725047 · Cited by 4
“This method’s benefits include cost-effectiveness, quick detection times, durability against low-altitude clutter [17] interference, and real-time and dynamic recording of successive target images.”
BackgroundLi, X., Hu, T., Li, Z., Long, M., Ye, Z., Huang, J., Yalikun, Y., Liu, S., Liu, Y., Wang, D., et al. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3487630 · Cited by 4
Performance Assessment of Feature Detection Methods for 2-D FS Sonar Imagery*
Kyatham, H., Negahdaripour, S., Xu, M., Lin, X., Yu, M., & Aloimonos, Y. (2024) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans55160.2024.10754482 · Cited by 4
Evaluation of Highly Compressed Semantic Features for Efficient Image Representation
Łażewski, S., & Cyganek, B. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-70518-2_52 · Cited by 4
Multimodal Fusion SLAM With Fourier Attention
Zhou, Y., Mei, G., Wang, Y., Wan, Y., & Poiesi, F. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3512252 · Cited by 4
“Indirect methods often start with front-end modules for feature extraction and matching: they first extract features using algorithms such as SURF [17] or ORB [18], which are then matched to establish correspondences across frames.”
Detecting Duplicate Products in E-Commerce Images Using Siamese Networks
Teper, E., Eseoğlu, F., & Keskin, M. (2024) · doi:10.1109/ubmk63289.2024.10773496 · Cited by 3
Necipsoy, M. E., & Ergüzen, A. (2024) · International Scientific and Vocational Studies Journal · doi:10.47897/bilmes.1501078 · Cited by 3
Wang, Z., & Dong, W. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3532699 · Cited by 3
“…the runtime of the proposed dual-channel method with other popular feature association methods, including the original SuperPoint [14] with SuperGlue [5] (called SS), ORB [12] with NN match [15] and RANSAC filter [30] (called ORB_NR), and SURF [31] with NN match and RANSAC filter (called SURF_NR).”
SiamYOLOv8: a rapid conditional detection framework for one-shot object detection
Desmarescaux, M., Kaddah, W., Alfalou, A., et al. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06513-2 · Cited by 3
“Notable examples include ORB [10] (Oriented FAST and Rotated BRIEF), BRISK [11] (Binary Robust Invariant Scalable Keypoints), SIFT [12, 13] (Scale Invariant Feature Transform), and SURF [14] (Speeded-Up Robust Features).”
PIPE: Privacy-preserving 6DoF Pose Estimation for Immersive Applications
Wu, N., Cheng, R., Chen, S., & Han, B. (2025) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3715014.3722069 · Cited by 5
Geometric constraints and semantic optimization SLAM algorithm for dynamic scenarios
Liu, Y., Wang, Y., Zhang, H., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-16714-x · Cited by 3
CNSv2: Probabilistic Correspondence Encoded Neural Image Servo
Chen, A., Yu, H., Li, S., et al. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128608 · Cited by 3
“• We validate CNSv2 both in simulation and real-world, demonstrating its ability to handle textureless scenes and illumination variations, while preserving the generalization and real-time ability of CNS.”
Performances of Invariant Feature Detectors in Real-Time Video Applications
Hedayati, M., Diyana, W. M., Zaki, W. M. D. W., Hussain, A., & Zulkifley, M. A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-319-02958-0_19 · Cited by 3
“[4], is an improvement over SIFT in terms of processing speed [23].”
BackgroundMethodInfluentialGlobal Pose Estimation from Aerial Images : Registration with Elevation Models
Grelsson, B. (2014) · Linköping University Electronic Press eBooks · doi:10.3384/lic.diva-108213 · Cited by 3
Evaluation of Feature Detectors for KLT based Feature Tracking using the Odroid U3
Barnes, B., Abeywardena, D., Kodagoda, S., et al. (2014) · UTS ePRESS (University of Technology Sydney) · Cited by 3
Knuckle Recognition for Human Identification
Choraś, M., & Kozik, R. (2011) · Advances in intelligent and soft computing · doi:10.1007/978-3-642-20320-6_7 · Cited by 3
A Robust Tracking Algorithm Based on HOGs Descriptor
Miramontes-Jaramillo, D., Kober, V. I., & Díaz-Ram, V. H. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-12568-8_7 · Cited by 3
Binarization with the Local Otsu Filter: Integral Histograms for Document Image Analysis
Nicolaou, A., Ingold, R., & Liwicki, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-44854-0_14 · Cited by 3
Multi-level scene understanding via hierarchical classification
Clouse, H. S., Bian, X., Gentimis, T., et al. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025194 · Cited by 3
“( 9 ) A feature set, f l , for each background subset B l is constructed following the SURF-128[9] algorithm.”
MethodInfluentialPreliminary field trials of autonomous path following
King, P., Anstey, B., & Vardy, A. (2014) · IEEE/OES Autonomous Underwater Vehicles · doi:10.1109/auv.2014.7054412 · Cited by 3
“The SURF keypoint extractor and descriptor [6] was chosen due to its promising results in offline tests.”
MethodFeature matching of fancy weft knitted stitch based on modified SURF algorithm
Lv, T. J., & Long, H. (2014) · Textile Research Journal · doi:10.1177/0040517514551465 · Cited by 3
Quality visual landmark selection based on distinctiveness and repeatability
Shimoda, M., & Yamazaki, K. (2015) · ROBOMECH Journal · doi:10.1186/s40648-015-0036-9 · Cited by 3
Development of a PC-based markerless augmented reality
Yee, T. S., Arshad, H., & Abdullah, A. (2015) · doi:10.1109/iceei.2015.7352468 · Cited by 3
Mansouri, J., Seddik, B., Gazzah, S., et al. (2015) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2015.7367165 · Cited by 3
“An improvement using the computationally efficient image contents SURF descriptor [7] is applied in [8] to attribute localization information to images coming from a wearable camera (placed in a person’s chess).”
MethodBuilding temporal consistent semantic maps for indoor scenes
Zhao, Z., & Chen, X. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353359 · Cited by 3
Stereo visualisation of historical aerial photos - a valuable digital heritage research tool
Hast, A., & Marchetti, A. (2015) · 2015 Digital Heritage · doi:10.1109/digitalheritage.2015.7419593 · Cited by 3
Evaluation of Image Feature Descriptors for Marker-Less AR Applications
子安, 大., Nozaki, K., & Maekawa, H. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14364-4_30 · Cited by 3
“We first selected SIFT[9] and SURF[3], which are well used descriptors.”
MethodBLAID: Boundaries from Locally Adaptive Isotropic Detection
Niroshika, U. A. A., & Meegama, R. G. N. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.04.006 · Cited by 3
“Nevertheless, the overall performance of the proposed BLAID is best when compared to SUSAN, FAST and SURF.”
BackgroundMethodInfluentialA Mobile System for Scene Monitoring and Object Retrieval
Birkas, D., Birkas, K., & Popa, T. (2016) · Computer Animation (CA) · doi:10.1145/2915926.2915933 · Cited by 3
“The breakthrough of Lowe [8] in robust scale and rotation invariant features has open a new wave of feature based methods [9, 10, 11, 12].”
BackgroundEffects of noise and relative overlap on image mosaicing using SURF features
Monali, R., Moonka, S., Priya, A., & Tripathy, S. S. (2016) · IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology · doi:10.1109/rteict.2016.7807931 · Cited by 3
Design of efficient shape feature for object-based watermarking technology
Kim, B., Hong, G.-S., & Psannis, K. E. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4344-3 · Cited by 3
Deformable Object Matching Algorithm Using Fast Agglomerative Binary Search Tree Clustering
Jeong, J., Won, I.-S., Yang, H.-J., Lee, B., & Jeong, D.-S. (2017) · Symmetry · doi:10.3390/sym9020025 · Cited by 3
“The typical algorithms of the extraction method include D. Lowe’s SIFT (Scale-Invariant Feature Transform) [1], which is robust to size and angle change, H. Bay’s SURF (Speeded Up Robust Features) [2], which is faster than SIFT, J. Matas’s region-based MSER (Maximally Stable Extremal Regions) [3], and K. Mikolajczyk’s…”
BackgroundOrdinal pyramid coding for rotation invariant feature extraction
Wang, G., Fan, B., Zhou, Z., et al. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.02.071 · Cited by 3
GVoS: A General System for Near-Duplicate Video-Related Applications on Storm
Jiang, J., Tong, Y., Lu, H. C., Cui, B., Lei, K., & Yu, L. (2017) · ACM Transactions on Information Systems · doi:10.1145/3041657 · Cited by 5
“SURF is an efficient method claimed to approximate or even outperform previously proposed schemes with respect to repeatability, distinctiveness, and robustness yet can be computed and compared much faster [Bay et al. 2006].”
MethodImproved Descriptors for Patch Matching and Reconstruction
Mitra, R., Zhang, J., Narayan, S., Ahmed, S., Chandran, S., & Jain, A. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.125 · Cited by 3
Feature Optimization of Whitefly Detection Algorithm using Image Segmentation and Feature Analysis
Walid, H.-A., Tanjim-Al-Akib, M., & Islam, N. (2017) · Communications on Applied Electronics · doi:10.5120/cae2017652610 · Cited by 3
An integration of minimum local feature representation methods to recognize large variation of foods
Razali, M. N., Manshor, N. B., Halin, A. B. A., et al. (2017) · AIP conference proceedings · doi:10.1063/1.5005456 · Cited by 3
Mobile Robot for Exploration and Manipulation Inside a Nuclear Power Plant
Ritzberger, N., Emenshuber, S., Schubert, G., et al. (2017) · Annals of DAAAM for ... & proceedings of the ... International DAAAM Symposium · doi:10.2507/28th.daaam.proceedings.012 · Cited by 3
“The program uses SIFT, Scale Invariant Feature Transform [9], and SURF, Speeded-Up Robust Features [1], for Feature detection in the RGB pictures.”
Baby mentor: Learning through images
Samuel, J., Patil, S., Solanki, S., et al. (2017) · International Conference on Innovations in Information, Embedded and Communication Systems · doi:10.1109/iciiecs.2017.8276128 · Cited by 3
“There are several algorithms for identifying and recognizing features such as: SURF [19], SIFT [10], HOG [20], FAST [21].”
MethodTracking of Miniature-Sized Objects in 3D Endoscopic Vision
Khanam, Z., & Raheja, J. L. (2018) · Smart innovation, systems and technologies · doi:10.1007/978-981-10-8102-6_6 · Cited by 3
Photogrammetric visual odometry with unmanned ground vehicle using low cost sensors
Dabove, P., Lingua, A. M., & Piras, M. (2018) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans.2018.8373410 · Cited by 3
“In order to exclude the presence of outliers [23], a particular algorithm for data snooping has been implemented.”
MethodKavallieratou, E., & Likforman-Sulem, L. (2018) · MDPI eBooks · doi:10.3390/books978-3-03897-106-1 · Cited by 3
Navigation Method of AUV to Target Point by Optical and Acoustic Sensor Switching Strategy
Song, S., & Yu, S. (2018) · International Conference on Ubiquitous Robots (UR) · doi:10.1109/urai.2018.8441786 · Cited by 3
“We acquired the field data by using the hovering-type AUV Cyclops, and developed our method with Speeded Up Robust Features (SURF) detection algorithm [7].”
BackgroundMethodPang, B., Yu, Q., Sun, H., et al. (2018) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.12.036012 · Cited by 3
Vision-Based Yaw Bias Estimation For a Quadrotor UAV In Indoor Environment
Zhang, L., Deng, F. Y., & Chen, J. (2018) · International Conference on Control and Automation · doi:10.1109/icca.2018.8444185 · Cited by 3
“It is assumed that the marker is identified and traced frame to frame using a feature-tracking algorithm [11,12].”
MethodEvaluation of Objects Recognition Efficiency on Mapes by Various Methods
Furgala, Y., Mochulsky, Y., & Rusyn, B. (2018) · IEEE International Conference on Data Stream Mining & Processing (DSMP) · doi:10.1109/dsmp.2018.8478435 · Cited by 3
“The most commonly used methods for solving such problems are SURF (Speeded Up Robust Features), SIFT (Scale-Invariant Feature Transform) and ORB (Oriented Features from Accelerated Segment Test and Rotated Binary robust independent elementary features) [1-7].”
MethodFusion of Interest Point/Image based descriptors for efficient person re-identification
Khedher, M. I., Jmila, H., & El‐Yacoubi, M. A. (2018) · doi:10.1109/ijcnn.2018.8489111 · Cited by 3
“CMC (from rank 1 to rank 30) on PRID-2011 of two SURF versions: 1) Standard SURF proposed in [15] and 2) Modified SURF using adapted descriptive regions.”
BackgroundMethodInfluentialA Stereo Vision Method for IMU-based Motion Tracking Systems Calibration
Daponte, P., Vito, L. D., Lamonaca, F., Mazzilli, G., Picariello, F., & Tudosa, I. (2018) · IEEE International Symposium on Medical Measurements and Applications (MeMeA) · doi:10.1109/memea.2018.8438815 · Cited by 3
“RGB to gray scale, then for each of them the Speeded-Up Robust Features (SURFs) are extracted according to the algorithm presented in [8].”
MethodAvoiding to Face the Challenges of Visual Place Recognition
Mihankhah, E., & Wang, D. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-01054-6_52 · Cited by 3
Industry 4.0, Intelligent Visual Assisted Picking Approach
Arbulú, M. R., Abaunza, P. A. M., Wagner, M., Beltran-Hernandez, C. C., & Harada, K. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-05918-7_18 · Cited by 3
Enhacing Image Mosaicing with Adaptive Local Homographies
Pan, F., & Shang, H. (2018) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/icdsp.2018.8631702 · Cited by 3
“Featurebased method has acquired most focus due to tremendous advances in feature extraction algorithm, such as SIFT [3], SURF [4], ORB [5], etc.”
MethodA Polarized Light Compass Aided Place Recognition System
Guo-liang, H., He, X., Hu, X., Zhang, L., Fan, C., Mao, J., Li, X., & Wu, X. (2019) · IEEE International Conference on Robotic Computing (IRC) · doi:10.1109/irc.2019.00050 · Cited by 3
“Local feature descriptors, such as SIFT[1], SURF[2] and ORB[3] have been widely used in place recognition.”
MethodAgileSLAM: A Localization Approach for Agile Head Movements in Augmented Reality
Williamson, B. M., Vargas, A. N., Garrity, P., Sottilare, R. A., & LaViola, J. J. (2018) · IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct) · doi:10.1109/ismar-adjunct.2018.00025 · Cited by 3
“If a keyframe is present we match the SURF features between the current color image and the keyframe’s composite RGB image.”
MethodVisual Odometry Based on K-Nearest Neighbor Matching and Robust Motion Estimation
Pudchuen, N., & Deelertpaiboon, C. (2018) · International Electrical Engineering Congress (iEECON) · doi:10.1109/ieecon.2018.8712323 · Cited by 3
“This is because ORB has binary descriptor which is different from floating-point descriptor like SIFT or Speed Up Robust Feature (SURF) [15].”
MethodA Crystal/Clear Pipeline for Applied Image Processing
Watkins, C. J. C. H., Rosa, N., Carroll, T., Ratcliffe, D., Ristic, M., Russell, C., Li, R., Fazio, V. J., & Newman, J. M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-18645-6_2 · Cited by 3
Sujata, Trivedi, M., & Mitra, S. K. (2018) · IEEE Applied Signal Processing Conference (ASPCON) · doi:10.1109/aspcon.2018.8748418 · Cited by 3
“Inspired by the SIFT, [3] introduced Speed Up Robust Features (SURF).”
MethodJiang, D., & Kim, J. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07985-4 · Cited by 3
“(SURF) [2], Affine SIFT (ASIFT) [25], Oriented FAST and Rotated BRIEF (ORB) [28], Maximally Stable Extremal Region (MSER) [23], Fast Retina Keypoint (FREAK) [1] and”
MethodPeriocular Region Based Biometric Identification Using SIFT and SURF Key Point Descriptors
Kamarajugadda, K. K., & Pavani, M. (2019) · IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) · doi:10.1109/iemcon.2019.8936271 · Cited by 3
Restricted Boltzmann machine as an aggregation technique for binary descriptors
Sobczak, S., Kapela, R., McGuinness, K., Świetlicka, A., Pazderski, D., & O'Connor, N. E. (2019) · The Visual Computer · doi:10.1007/s00371-019-01782-8 · Cited by 3
“Binary image descriptors, such as BRIEF [1], BRISK [2], FREAK[3] andORB[4], are a popular alternative to themore common dense real-valued local descriptors like SIFT [5], SURF [6], HOG [7] and even features extracted from convolutional layers of pretrained deep neural networks [8] (CNN features).”
BackgroundAlvarez, A. B., Ponnusamy, G., & Alioto, M. (2020) · IEEE Access · doi:10.1109/access.2020.2968576 · Cited by 3
Prominent Structures for Video Analysis and Editing
Wang, M., Fang, X., Yang, G., et al. (2020) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2020.2970045 · Cited by 3
“Previous alignment approaches [3] mainly focus on matching the same scene based on low-level local features such as SIFT [4] and SURF [5], which do not define the structure of the scene well and cannot work if the scenes are totally different.”
BackgroundMethodInfluentialFake News Detection by Image Montage Recognition
Steinebach, M., Liu, H., & Gotkowski, K. (2020) · Journal of Cyber Security and Mobility · doi:10.13052/jcsm2245-1439.921 · Cited by 3
Ito, I., & Pižurica, A. (2020) · Journal of Imaging · doi:10.3390/jimaging6020004 · Cited by 3
“In this sense, it is different from some common image descriptors such as scale-invariant feature transform (SIFT) [5] and speed-up robust features (SURF) [6], which extract features robust to deformation.”
BackgroundRodrigues, J. M. F., Cardoso, P. J. S., Monteiro, J., et al. (2020) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-7998-2112-0.ch001 · Cited by 3
Image plane interference co-phasing technology for synthetic digital holography
Yang, F., Zhu, L., Li, Y., et al. (2020) · Optik · doi:10.1016/j.ijleo.2020.164568 · Cited by 3
Peeling off image layers on topographic architectures
Radványi, M., & Karacs, K. I. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.04.023 · Cited by 3
Are You Watching Closely? Content-based Retrieval of Hand Gestures
Parian, M. A., Rossetto, L., Schuldt, H., & Dupont, S. (2020) · International Conference on Multimedia Retrieval · doi:10.1145/3372278.3390723 · Cited by 3
“Early feature extractors were based on hand crafted features such as color histograms [11, 15, 30], Local Binary Patterns [15, 29, 39] or key-point descriptors (like SIFT [40] and SURF [2]).”
MethodMotion Correction in Multimodal Intraoperative Imaging
Chen, F., Müller, J., Müller, J., et al. (2020) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2020.3005891 · Cited by 3
Camera motion estimation algorithm for IoT devices based on optimized feature tracking method
Meng, Z., Meng, L., & Tomiyama, H. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.06.051 · Cited by 3
Reconstruction of the Shape of a Tumbling Target from a Chaser in Close Orbit
Volpe, R., Sabatini, M., & Palmerini, G. B. (2020) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero47225.2020.9172529 · Cited by 3
Copy-Move Forgery Detection and Performance Analysis of Feature Detectors
Koshy, L., & PraylaShyry, S. (2020) · International Conference on Communications and Signal Processing (ICCSP) · doi:10.1109/iccsp48568.2020.9182066 · Cited by 3
Hardware-Software Co-Design for Face Recognition on FPGA SoCs
Wang, H., Cao, S. C., Xu, S., et al. (2020) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas45731.2020.9180922 · Cited by 3
Possibilistic BRISK method for an efficient registration (PBRISK)
Marzouka, W. B., Solaiman, B., Hammouda, A., et al. (2020) · International Conference on Advanced Technologies for Signal and Image Processing · doi:10.1109/atsip49331.2020.9231632 · Cited by 3
Neural road semantic segmentation in driving scenarios
Iancu, D.-T., Sorici, A., & Florea, A. M. (2020) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai50035.2020.9223197 · Cited by 3
“The first approaches regarding object detection and segmentation involved classical computer vision algorithms such as Histogram of Gradients (HOG) [3], Scale Invariant Feature Transform (SIFT) [4], Speeded Up Robust Features (SURF) [5] or Corner Detectors [6].”
MethodA Particle Filtering Framework for Integrity Risk of GNSS-Camera Sensor Fusion
Mohanty, A., Gupta, S., & Gao, G. (2020) · Proceedings of the Satellite Division's International Technical Meeting (Online)/Proceedings of the Satellite Division's International Technical Meeting (CD-ROM) · doi:10.33012/2020.17660 · Cited by 4
“Although we experimented with other feature extraction methods such as SIFT [29], SURF [30], and AKAZE [31], ORB was found most effective for extracting descriptors from highly blurred images.”
MethodTraffic Intersection Re-Identification Using Monocular Camera Sensors
Xiong, L., Deng, Z., Huang, Y., Du, W., Zhao, X., Lu, C., & Tian, W. (2020) · Sensors · doi:10.3390/s20226515 · Cited by 3
Multiple View Relations Using the Teaching and Learning-Based Optimization Algorithm
López-Martínez, A., & Cuevas, F. J. (2020) · Computers · doi:10.3390/computers9040101 · Cited by 3
Accelerated High-Level Synthesis Feature Detection for FPGAs Using HiFlipVX
Kalms, L., & Göhringer, D. (2020) · Springer eBooks · doi:10.1007/978-3-030-53532-2_7 · Cited by 5
Combining LiDAR Scan Matching with Stereo Visual Odometry Using Curvefusion
Du, S., Li, X., Lauterbach, H., Borrmann, D., & Nüchter, A. (2021) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr49711.2021.9349385 · Cited by 2
A distributed source autoencoder of local visual descriptors for 3D reconstruction
Milani, S. (2021) · Pattern Recognition Letters · doi:10.1016/j.patrec.2021.03.019 · Cited by 3
Wang, R., Zeng, L., Cao, W., & Wong, K. K. L. (2021) · Measurement · doi:10.1016/j.measurement.2021.109379 · Cited by 3
Literature Survey: Application of Machine Learning Techniques on Static Sign Language Recognition
Robert, Y., Nigudkar, Y., Kulkarni, A., et al. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-73603-3_16 · Cited by 3
Yamashita, Y., & Wakahara, T. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413054 · Cited by 3
“They are used not only for smoothing of an image but also for a variety of research topics: feature extraction [1], [2], [3], [4], image matching [5], [6], [7], pattern recognition [8], [6], scale space method [9], and so on.”
BackgroundPA-FlowNet: Pose-Auxiliary Optical Flow Network for Spacecraft Relative Pose Estimation
Chen, Z., Chen, P.-H., Kuan-Wen, C., & Chan, C.-Y. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413201 · Cited by 7
“First, extract keypoints from the images by SIFT [15], SURF [1], or other methods for feature matching.”
MethodClassification of Rail Welding Defects Based on the Bag of Visual Words Approach
Molefe, M. E., & Tapamo, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77004-4_20 · Cited by 4
Simons, T., & Lee, D.-J. (2021) · Electronics · doi:10.3390/electronics10131511 · Cited by 3
A novel privacy-preserving outsourcing computation scheme for Canny edge detection
Li, B., He, F., & Zeng, X. (2021) · The Visual Computer · doi:10.1007/s00371-021-02307-y · Cited by 7
A Mask-RCNN based object detection and captioning framework for industrial videos
Namjoshi, M., & Khurana, K. (2021) · International Journal of Advanced Technology and Engineering Exploration · doi:10.19101/ijatee.2021.874394 · Cited by 4
“Other feature detection methods include Scale-Invariant Feature Transform (SIFT) [15], Speeded Up Robust Features (SURF) [28].”
MethodNear Infrared and Visible Image Registration Using Whale Optimization Algorithm
Saxena, S., & Pohit, M. (2021) · International Journal of Applied Metaheuristic Computing · doi:10.4018/ijamc.2022010109 · Cited by 3
At the Pulse of Time: Machine Vision in Retinal Videos
Hamann, T., Wiest, M. R. J., Mislēvičs, A., Бондаренко, А. Л., & Zweifel, S. A. (2021) · Acta neurochirurgica. Supplementum · doi:10.1007/978-3-030-85292-4_34 · Cited by 3
Chathoth, S. V., Mishra, A. K., Mishra, D., & Sai, S. G. R. K. (2021) · Advances in Computational Intelligence · doi:10.1007/s43674-021-00023-7 · Cited by 3
“Scale invariant feature transform (SIFT), speeded up robust features (SURF), Fourier Mellin moments are some examples of rotational invariant features of images.”
MethodImage Key Point Matching by Phase Congruency
Protsenko, M. А., & Pavelyeva, E. A. (2021) · Computational Mathematics and Modeling · doi:10.1007/s10598-021-09532-z · Cited by 3
“The classical algorithms for the construction of key-point descriptors is the Scale-Invariant Feature Transform algorithm (SIFT) [10], its modifications [11, 12], and the Speeded Up Robust Features (SURF) method [13].”
MethodSupervised Machine Learning Approaches for Moving Object Tracking: A Survey
Mondal, A. (2022) · SN Computer Science · doi:10.1007/s42979-022-01040-0 · Cited by 4
“However, it cannot encode the object’s precise information, such as size, orientation, and pose. surf Bay et al. proposed a novel scale and rotation invariant detector and descriptor, called surf (Speeded-Up Robust Features) [45, 46].”
BackgroundCO-REGISTRATION OF VIDEO-GRAMMETRIC POINT CLOUDS WITH BIM – FIRST CONCEPTUAL RESULTS
Kaiser, T., Clemen, C., & Block-Berlitz, M. (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-xlvi-5-w1-2022-141-2022 · Cited by 6
Mery, D., & Pieringer, C. (2020) · Springer eBooks · doi:10.1007/978-3-030-56769-9_9 · Cited by 4
Bouaziz, Y., Royer, E., Bresson, G., & Dhome, M. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11870-4 · Cited by 4
“The first detectors and descriptors such as SIFT [30] or SURF [2] were hand crafted.”
MethodGoel, P., Dayal, P., Patra, T. K., et al. (2022) · International Mobile and Embedded Technology Conference (MECON) · doi:10.1109/mecon53876.2022.9752107 · Cited by 3
Hu, H., Li, B., Yang, W., et al. (2022) · Remote Sensing · doi:10.3390/rs14163857 · Cited by 3
Application and Analysis of Recurrent Convolutional Neural Network in Visual Odometry
Xu, D., & Zhang, Z. (2022) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma54519.2022.9856336 · Cited by 4
ExpertosLF: dynamic late fusion of CBIR systems using online learning with relevance feedback
Alarcão, S. M., Mendonça, V., Maruta, C., & Fonseca, M. J. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13119-0 · Cited by 5
“Other binary descriptors are Binary Robust Independent Elementary Features (BRIEF) [16], Binary Robust Invariant Scalable Keypoints (BRISK) [53], Fast Retina KeyPoint (FREAK) [4], Scale-Invariant Feature Transform (SIFT) [66], and Speeded Up Robust Features (SURF) [12].”
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.