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 5,701–5,800 of 14,752
A multi-scale UAV image matching method applied to large-scale landslide reconstruction
Ren, C., Zhi, X., Pu, Y., et al. (2021) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2021115 · Cited by 9
Unknown Radial Distortion Centers in Multiple View Geometry Problems
Brito, J. H., Angst, R., Köser, K., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37447-0_11 · Cited by 9
The analysis of selected orientation methods of architectural objects’ scans
Markiewicz, J. S., Kajdewicz, I., & Zawieska, D. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2184959 · Cited by 9
Sensor fusion for GNSS denied navigation
Krishnaswamy, K., Susca, S., McCroskey, R., et al. (2008) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans.2008.4570062 · Cited by 9
Autonomous Robot Navigation in Cyber and RealWorlds
Jarvis, R. A., Ho, N., & Byrne, J. (2007) · International Conference on Cyberworlds (CW) · doi:10.1109/cw.2007.31 · Cited by 10
Semi-supervised learning for location recognition from wearable video
Dovgalecs, V., Mégret, R., Wannous, H., & Berthoumieu, Y. (2010) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2010.5529903 · Cited by 7
Combining High-Resolution Images With Low-Quality Videos
Schubert, F., & Mikolajczyk, K. (2008) · British Machine Vision Conference (BMVC) · doi:10.5244/c.22.116 · Cited by 9
Animating groups of Socially Intelligent Agents
Grimaldo, F., Lozano, M., Barber, F., & Vigueras, G. (2007) · International Conference on Cyberworlds (CW) · doi:10.1109/cw.2007.20 · Cited by 9
Multi-robot map alignment in visual SLAM
Ballesta, M., Gil, A., Reinoso, Ó., Juliá, M., & Jiménez, L. M. (2010) · WSEAS TRANSACTIONS on SYSTEMS archive · Cited by 10
Specification and Evaluation of a Spanish Conversational System Using Dialogue Models
Meza, I., Salinas, L., Venegas, E., et al. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-16952-6_35 · Cited by 9
Pose estimation for mobile devices and augmented reality
Caarls, J. (2009) · Research Repository (Delft University of Technology) · Cited by 9
Supervised learning algorithms for visual object categorization
Abdullah, A. (2010) · Utrecht University Repository (Utrecht University) · Cited by 10
VISION-BASED NAVIGATION AND MAPPING FOR FLIGHT IN GPS-DENIED ENVIRONMENTS
Wu, A. D. (2010) · SMARTech Repository (Georgia Institute of Technology) · Cited by 12
Fast and Robust Dynamic Hand Gesture Recognition via Key Frames Extraction and Feature FusionPreprint
Tang, H., Liu, H., Wei, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.04622 · Cited by 9
Moving Indoor: Unsupervised Video Depth Learning in Challenging EnvironmentsPreprint
Zhou, J., Wang, Y., Qin, K., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.08898 · Cited by 9
“The sparse matchings are also obtained by SURF [1].”
MethodBuga, R. M., Totu, T., Dumitru, A. V., Costache, M., Floroiu, I., Sladoje, N., & Stanciu, S. G. (2020) · Scientific Data · doi:10.1038/s41597-020-0500-0 · Cited by 10
Content-Based Image Retrieval Based on Late Fusion of Binary and Local DescriptorsPreprint
Ali, N., Mazhar, D. A., Iqbal, Z., Ashraf, R., Ahmed, J., & Khan, F. Z. (2017) · Preprints.org · doi:10.20944/preprints201703.0156.v2 · Cited by 9
A markerless augmented reality system for mobile devices
Ufkes, A. (2021) · doi:10.32920/ryerson.14648931 · Cited by 9
Monocular Visual-Inertial-Pressure fusion for Underwater localization and 3D mapping.
Ferrera, M. (2019) · theses.fr (ABES) · doi:10.70675/0a530b06ze9c8z4a9dzabccz9acc11efeb31 · Cited by 13
Heterogeneous stereo: A human vision inspired method for general robotics sensing
Wang, H., Yuan, S., & Wu, K. (2017) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2017.8227967 · Cited by 12
“The tracking method are also improving from filtering[7] and indirect[3] to semi-direct [10][5] or direct methods [12][6][16][17].”
MethodCharacterization of color normalization methods in digital pathology whole slide imaging
Ziaei, D., Li, W., Lam, S., Cheng, W., & Chen, W. (2020) · SPIE Medical Imaging: Digital and Computational Pathology · doi:10.1117/12.2550585 · Cited by 10
Chen, Z., Huang, M., Lyu, J., Qi, X., He, F., & Li, X. (2023) · Frontiers in Oncology · doi:10.3389/fonc.2023.1174843 · Cited by 8
He, J., Jiang, X., Hao, Z., et al. (2023) · Remote Sensing · doi:10.3390/rs15184548 · Cited by 8
Techniques and methods for managing disasters and critical situations
AlAli, Z. T., & Alabady, S. A. (2024) · Natural Hazards · doi:10.1007/s11069-024-06573-6 · Cited by 11
“Artificial intelligence (AI) and machine learning play a vital role in supporting emer-gencies and managing critical situations (Ordóñez et al. 2018 et al. 2019; Zeiler and Fergus 2014; Bay et al. 2006; Pi et al. 2021; Park and Lee 2024).”
Pose estimation algorithm based on point pair features using PointNet + +
Chen, Y., Li, Z., Li, Q., & Zhang, M. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01508-x · Cited by 8
Refining multi-modal remote sensing image matching with repetitive feature optimization
Liao, Y., Xi, K., Fu, H., et al. (2024) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2024.104186 · Cited by 8
Trajectory-Aligned Space-Time Tokens for Few-Shot Action Recognition
Kumar, P., Padmanabhan, N., Luo, L., Rambhatla, S. S., & Shrivastava, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72764-1_27 · Cited by 20
Extraction of Feature Point Pseudo-Neighborhood for High-Accuracy of Fisheye Image Matching
Zhou, G., Liu, J., Luo, M., et al. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3488209 · Cited by 8
“This phenomenon leads to the fact that many traditional image processing algorithms, such as feature extraction and/or feature point-based matching is no longer appropriate for fisheye images, such as SIFT [13], ORB [14], speeded up robust feature (SURF) [15], D-Net [16].”
Unsupervised Global and Local Homography Estimation With Coplanarity-Aware GAN
Liu, S., Hong, M., Lu, Y., Ye, N., Lin, C., & Zeng, B. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3509614 · Cited by 11
Chen, Z., Liu, J., Lu, Z.-R., et al. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adad91 · Cited by 8
Learning Cross-View Consistent 3D Keypoints for Object 6D Pose Estimation
Zhang, S., Zhao, W., Guan, Z., Zhao, W. Z., Peng, J., & Fan, J. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3538018 · Cited by 11
Efficient CNN architecture with image sensing and algorithmic channeling for dataset harmonization
Kanwal, K., Ahmad, K. T., Shabir, A., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-90616-w · Cited by 8
Distillation of Diffusion Features for Semantic Correspondence
Fundel, F., Schusterbauer, J., Hu, V. T., & Ommer, B. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00658 · Cited by 20
“Traditional methods for geometric correspondence, such as SIFT [58, 59] and SURF [5], involve extracting hand-crafted visual descriptors and matching them across images.”
Cross-domain UAV pose estimation: A novel attempt in UAV visual localization
Lin, W., Liu, T., Ren, K., & Chen, Q. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113449 · Cited by 8
MambaGlue: Fast and Robust Local Feature Matching with Mamba
Ryoo, K., Lim, H., & Myung, H. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128473 · Cited by 18
Detecting Looted Archaeological Sites from Satellite Image Time Series
Vincent, E., Saroufim, M., Chemla, J., Ubelmann, Y., Marquis, P., Ponce, J., & Aubry, M. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00216 · Cited by 12
Generic Face Invariant Model for Face Detection
Taffar, M., & Benmohammed, M. (2011) · Advances in intelligent and soft computing · doi:10.1007/978-3-642-23154-4_5 · Cited by 8
A Hardware Architecture for Difference of Gaussian Calculation in Image Feature Extraction
Bukhari, S. A. A., & Iqbal, S. (2014) · International Conference on Frontiers of Information Technology (FIT) · doi:10.1109/fit.2014.70 · Cited by 8
Vision based autonomous vehicle navigation with self-organizing map feature matching technique
Sharma, K., Jeong, K.-Y., & Kim, S. (2011) · Cited by 8
Graph Mining for Object Tracking in Videos
Diot, F., Fromont, É., Jeudy, B., Marilly, E., & Martinot, O. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33460-3_31 · Cited by 8
Deformed iris recognition using bandpass geometric features and lowpass ordinal features
Zhang, M., Sun, Z., & Tan, T. (2013) · International Conference on Biometrics · doi:10.1109/icb.2013.6612987 · Cited by 8
Multi-resolution local binary patterns for image classification
Liang, P., Shao-fa, L., & Qin, J.-W. (2010) · International Conference on Wavelet Analysis and Pattern Recognition · doi:10.1109/icwapr.2010.5576318 · Cited by 8
“The SURF descriptor is built by the Hessian matrix-base measure for feature detection and Harr wavelet response for feature description [4].”
MethodMulti-sensor localization - Visual Odometry as a low cost proprioceptive sensor
Bak, A., Gruyer, D., Bouchafa, S., & Aubert, D. (2012) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2012.6338771 · Cited by 8
Cloud-Based Object Recognition: A System Proposal
Lorenčík, D., Tarhanicova, M., & Sinčák, P. (2014) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-05582-4_61 · Cited by 8
Energy-saving object detection by efficiently rejecting a set of neighboring sub-images
Pan, J. S., Pang, Y., Zhang, K., et al. (2012) · Signal Processing · doi:10.1016/j.sigpro.2012.08.019 · Cited by 8
“Specifically, an image is represented by a subset of an established visual vocabulary with each visual word being a quantized image feature (representative features are SIFT [4], SURF [5], ASFIT [6], Fair-SURF [7], Brief [8], and ORB [9]).”
BackgroundNowicki, M., & Skrzypczyński, P. (2014) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc.2014.6906342 · Cited by 8
“The SIFT (Scale Invariant Feature Transform) [10] and SURF (Speeded Up Robust Feature) [4] are both based upon the concept of the scale-space, which makes them theoretically the most robust ones with respect to the changing scale, rotation, and viewpoint.”
MethodMura, M., Ciuti, G., Ferrari, V., Dario, P., & Menciassi, A. (2014) · International Journal of Medical Robotics and Computer Assisted Surgery · doi:10.1002/rcs.1603 · Cited by 8
Evaluation of interest point detectors for scenes with changing lightening conditions
Zukal, M., Číka, P., & Bürget, R. (2011) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2011.6043663 · Cited by 8
Rapid Dynamic Target Surface Modeling for Crane Operation Using Hybrid LADAR System
Cho, Y. K., Wang, C., Gai, M., et al. (2014) · ASCE Construction Research Congress (CRC) · doi:10.1061/9780784413517.108 · Cited by 8
“Using a robust local feature detector, Speeded Up Robust Features (SURF) (Bay et al. 2008), image-based target object recognition and tracking algorithms were implemented and as an output of which, dynamic bounding box area was defined and updated simultaneously.”
MethodTruck-face recognition using Semantic Texton Forests
Jog, G., Park, M., & Brilakis, I. (2011) · Cambridge University Engineering Department Publications Database · Cited by 8
Multiple-Hypothesis Affine Region Estimation with Anisotropic LoG Filters
Hasegawa, T., Ambai, M., Ishikawa, K., Koutaki, G., Yamauchi, Y., Yamashita, T., & Fujiyoshi, H. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.74 · Cited by 7
ElTantawy, A., & Shehata, M. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27857-5_25 · Cited by 8
THE USE OF COMPUTER VISION ALGORITHMS FOR AUTOMATIC ORIENTATION OF TERRESTRIAL LASER SCANNING DATA
Markiewicz, J. S. (2016) · 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-xli-b3-315-2016 · Cited by 12
“…searching for corresponding natural points,using algorithms based on detection of corners: BRISK (Leutenegeer, 2011), FAST (Rostem, 2006) and BLOB algorithms: MSER (Matas et al., 2002), SIFT (Lowe, 2004), SURF (Bay et al., 2006), ASIFT (Morel and Yu, 2011), CenSurE (STAR, Agrawal, 2008).”
MethodInfluentialAutomated architectural reconstruction using reference planes under convex optimization
Le, M.-H., Trinh, H.-H., Hoang, V.-D., & Jo, K.-H. (2016) · International Journal of Control Automation and Systems · doi:10.1007/s12555-014-0203-4 · Cited by 9
White Blood Cells Classifications by SURF Image Matching, PCA and Dendrogram
Nazlıbilek, S., Karacor, D., Ertrk, K. L., et al. (2015) · Biomedical Research-tokyo · Cited by 8
Nissler, C., Buttner, S., Márton, Z.-C., Beckmann, L., & Thomasy, U. (2016) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2016.7733711 · Cited by 27
Temporal city modeling using street level imagery
Sakurada, K., Tetsuka, D., & Okatani, T. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.01.012 · Cited by 8
Using FPGAs to perform embedded image registration
White, B. (2009) · Cited by 8
A hybrid feature parametrization for improving stereo-SLAM consistency
Zhang, H., Karunasekera, H., & Wang, H. (2017) · International Conference on Control and Automation · doi:10.1109/icca.2017.8003201 · Cited by 7
“Thanks to the feature property of viewpoint and illumination invariance [1], [2], feature-based SLAM approaches are more accurate”
MethodHuman Detection Using Surf And Sift Feature Extraction Methods In Different Color Spaces
Biglari, O., Ahsan, R., & Rahi, M. (2014) · Journal of Mathematics and Computer Science · doi:10.22436/jmcs.011.02.04 · Cited by 8
“[23], which has been shown to yield comparable or better results to SIFT while having a fraction of the computational cost [23, 24].”
ResultRegion of interest aware compressive sensing of THEMIS images and its reconstruction quality
Chakraborty, S., Banerjee, A., Gupta, S. K. S., & Christensen, P. R. (2018) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero.2018.8396524 · Cited by 9
Estabilización de vídeo en micro vehículos aéreos y su aplicación en la detección de caras
Aguilar, W. G., & Ángulo, C. (2014) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · doi:10.24133/cctespe.v9i1.98 · Cited by 8
“Para llevar a cabo esta tarea se pueden encontrar diversos algoritmos [10] [11], sin embargo, SIFT [12] (Scale Invariant Feature Transform) y SURF (Speed Up Robust Feature) [13] son los algoritmos que se usan con mayor frecuencia en la mayor parte de problemas relativos a visión por computador [14].”
BackgroundObject-Based Probabilistic Place Recognition for Indoor Human Environments
Hernandez, A. C., Gómez, C., Barber, R., & Mozos, Ó. M. (2018) · International Conference on Control, Artificial Intelligence, Robotics & Optimization (ICCAIRO) · doi:10.1109/iccairo.2018.00037 · Cited by 9
“The model uses SURF (Speeded Up Robust Features) that are scale and rotation-invariant interest point detector and descriptors [12].”
MethodReal‐time video mosaicking to guide handheld in vivo microscopy
Yin, C., Wei, L., Köse, K., et al. (2020) · Journal of Biophotonics · doi:10.1002/jbio.202000048 · Cited by 8
Automated sorting of used electronic components
Katti, S., Kulkarni, N., & Shaligram, A. D. (2021) · AIP conference proceedings · doi:10.1063/5.0046374 · Cited by 8
Esfahani, M. A., Wang, H., Bashari, B., Wu, K., & Yuan, S. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107424 · Cited by 11
A Unified Framework of Bundle Adjustment and Feature Matching for High-Resolution Satellite Images
Ling, X., Huang, X., & Qin, R. (2021) · Photogrammetric Engineering & Remote Sensing · doi:10.14358/pers.87.7.485 · Cited by 8
Silhouette Vectorization by Affine Scale-Space
He, Y., Kang, S. H., & Morel, J. (2021) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-021-01053-z · Cited by 8
“c Compared with the SURF detector [13].”
MethodDetection of agglomerate fog based on a shallow convolutional neural network
Li, L., Yang, B., & Chen, S. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11540-5 · Cited by 9
“For instance, they need to design features such as local binary pattern (LBP) [21], histogram of oriented gradients (HOG) [4], speeded-up robust features (SURF) [1], and so on.”
Background3D Landmarks Extraction from a Range Imager Data for SLAM
Wang, J., Hu, G., Huang, S., et al. (2009) · UTS ePRESS (University of Technology Sydney) · Cited by 8
Robot Grasping Based on RGB Object and Grasp Detection Using Deep Learning
Villagomez, R. C., & Ordoñez, J. (2022) · International Conference on Mechatronics and Robotics Engineering (ICMRE) · doi:10.1109/icmre54455.2022.9734075 · Cited by 8
DOES: A Deep Learning-Based Approach to Estimate Roll and Pitch at Sea
Ciaccio, F. D., Russo, P., & Troisi, S. (2022) · IEEE Access · doi:10.1109/access.2022.3158971 · Cited by 8
“Instead of relying on engineered, fixed features (e.g. SIFT [47], SURF [48]), recent algorithms exploit deep networks as powerful features extractors or by directly estimating the pose vector in an end-to-end model, from input images to the output prediction.”
MethodVision-Based Autonomous Landing on Unprepared Field With Rugged Surface
Liu, Z., Wang, C., Chen, K., et al. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3194190 · Cited by 8
A Very Fast Image Stitching Algorithm for PET Bottle Caps
Zhu, X. X., Liu, Z., Zhang, X., et al. (2022) · Journal of Imaging · doi:10.3390/jimaging8100275 · Cited by 8
A Light Field Full-Focus Image Feature Point Matching Method with an Improved ORB Algorithm
Zuo, Y., Guan, H., Duan, F., & Wu, T. (2022) · Sensors · doi:10.3390/s23010123 · Cited by 10
“These include Harris [1], SIFT [2], HOG [3], SURF [4], FAST [5], BRIEF [6], and ORB [7].”
MethodThe methodology of the archival aerial image orientation based on the SfM method
Karwel, A. K., & Markiewicz, J. S. (2022) · Sensors and Machine Learning Applications · doi:10.55627/smla.001.02.0015 · Cited by 8
Fast Feature Matching in Visual-Inertial SLAM
Feng, L., Qu, X., Ye, X., et al. (2022) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv57592.2022.10004220 · Cited by 8
Multispectral Image Matching Using SIFT and SURF Algorithm: A Review
Shaharom, M. F. M., & Tahar, K. N. (2023) · International Journal of Geoinformatics · doi:10.52939/ijg.v19i1.2495 · Cited by 8
Zhai, Y., Niu, J., Liu, Y., Chen, X., Liu, J., & Yang, B. T. (2023) · Advanced Optical Materials · doi:10.1002/adom.202300020 · Cited by 8
EEDD: Edge-Guided Energy-Based PCB Defect Detection
Deng, S., Deng, L., Sun, T., et al. (2023) · Electronics · doi:10.3390/electronics12102306 · Cited by 8
Zhang, L., Cui, H., Sun, J., Li, Z., Wang, H., & Li, D. (2023) · Agronomy · doi:10.3390/agronomy13082091 · Cited by 8
UW Deep SLAM-CNN Assisted Underwater SLAM
Amarasinghe, C. K., Ratnaweera, A., & Maitripala, S. (2023) · Applied Computer Systems · doi:10.2478/acss-2023-0010 · Cited by 8
An Approach for Classification of Diseases on Leaves
Lu, Q. T. (2023) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2023.01410112 · Cited by 8
Fully Unsupervised Domain-Agnostic Image Retrieval
Zheng, Z., Ren, H., Wu, Y., Zhang, W., Lu, H., Yang, Y., & Shen, H. T. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3335147 · Cited by 17
“These methods often involve handcrafted descriptors [36], [37], [38] or learnable feature representations [35], [39].”
MethodAn Incremental Knowledge Learning Framework for Continuous Defect Detection
Sun, C., Gao, L., Li, X., Zheng, P., & Gao, Y. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3343768 · Cited by 17
A Review of Using Visual Odometery Methods in Autonomous UAV Navigation in GPS-Denied Environment
Rostum, H. M., & Vásárhelyi, J. (2023) · Acta Universitatis Sapientiae Electrical and Mechanical Engineering · doi:10.2478/auseme-2023-0002 · Cited by 10
Piccinini, F., Tazzari, M., Tumedei, M. M., Stellato, M., Remondini, D., Giampieri, E., Martinelli, G., Castellani, G., & Carbonaro, A. (2024) · Sensors · doi:10.3390/s24020451 · Cited by 10
A Scene Graph Encoding and Matching Network for UAV Visual Localization
Duan, R., Chen, L., Li, Z., Chen, Z., & Wu, B. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3396168 · Cited by 13
“Localdescriptors [7], [8], [9], [10], [11] are pixel-level descriptions containing detailed local appearance and spatial locations.”
BackgroundMethodAM-MSFF: A Pest Recognition Network Based on Attention Mechanism and Multi-Scale Feature Fusion
Zhang, M., Yang, W., Chen, D., Fu, C., & Wei, F. (2024) · Entropy · doi:10.3390/e26050431 · Cited by 9
“Past studies predominantly employed traditional machine learning methods using manually designed features, such as GIST [5], HOG [6], SIFT [7], and SURF [8].”
MethodZhang, B., Dong, Y., Qi, X., Liu, Q., & Zheng, X. (2024) · Measurement · doi:10.1016/j.measurement.2024.114976 · Cited by 8
Learning Intra-View and Cross-View Geometric Knowledge for Stereo Matching
Gong, R., Liu, W., Gu, Z., Yang, X., & Cheng, J. T. (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/cvpr52733.2024.01961 · Cited by 22
“Traditional interest points detection and description algorithms [1, 19, 34, 39] rely on hand-crafted features.”
Progressive Retinal Image Registration via Global and Local Deformable Transformations
Liu, Y., Yu, B., Chen, T., Gu, Y., Du, B., Xu, Y., & Cheng, J. T. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10821896 · Cited by 8
“Many research focus on how to extract more replicable and reliable keypoints [3], [12], [29], [31].”
[Invited Paper] A Review of Web Image Mining
Yanai, . (2015) · ITE Transactions on Media Technology and Applications · doi:10.3169/mta.3.156 · Cited by 10
Fluorescence-Based Enhanced Reality for Colorectal Endoscopic Surgery
Selka, F., Agnus, V., Nicolau, S., Bessaid, A., Soler, L., Marescaux, J., & Diana, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-08554-8_12 · Cited by 10
Toward an object-based semantic memory for long-term operation of mobile service robots
Dayoub, F., Duckett, T., & Cielniak, G. (2010) · Lincoln Repository (University of Lincoln) · Cited by 10
Visual object tracking by an evolutionary self-organizing neural network
Maia, J. E. B., Barreto, G. A., & Coelho, A. L. V. (2011) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/ifs-2011-0477 · Cited by 8
“The use of relative strengths and orientations of gradients also reduces the effect of photometric changes.”
BackgroundA study of discriminant visual descriptors for sport video shot boundary detection
Tippaya, S., Tan, T., Khan, M. M., & Chamnongthai, K. (2015) · Asian Control Conference (ASCC) · doi:10.1109/ascc.2015.7244609 · Cited by 9
“The ratio of matched keypoints is calculated using SURF with 128-dimension.”
BackgroundMethodInfluentialMatching Planar Features for Robot Localization
Charmette, B., Royer, E., & Chausse, F. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-10331-5_19 · Cited by 9
“Classical descriptors such as the SIFT [1] or the SURF [2] use directly information of one image to generate a set of values”
MethodHybrid-BCI smart glasses for controlling electrical devices
Kim, Y., Kaongoen, N., & Jo, S. (2015) · Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE) · doi:10.1109/sice.2015.7285345 · Cited by 9
Dynamaid, an Anthropomorphic Robot for Research on Domestic Service Applications
Stückler, J., & Behnke, S. (2011) · Automatika · doi:10.1080/00051144.2011.11828422 · Cited by 13
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.