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 5,401–5,500 of 14,752
Review on image registration methods for the quality control in additive manufacturing
Chand, K., Fritsch, T., Oster, S., Ulbricht, A., & Bruno, G. (2025) · Progress in Additive Manufacturing · doi:10.1007/s40964-024-00932-2 · Cited by 17
“Common algorithms for feature detection include Harris corner detection, Scale-Invariant Feature Transform (SIFT) [80, 81], and Speeded-Up Robust Features (SURF) [82].”
A Multihierarchy Flow Field Prediction Network for Multimodal Remote Sensing Image Registration
Wang, W., Mu, K., & Liu, H. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3532939 · Cited by 10
Automatic 3D inspection method for AR-assisted assembly based on virtual-to-real registration
Yan, Z., Fu, H., Xinyuan, J., Qi, X., Cui, E., & Zhang, L. (2025) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2025.04.013 · Cited by 13
Xiao, Y., Zhang, C., Jiang, B., et al. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3576290 · Cited by 9
“Some classical methods for feature detection and description include SIFT [29], SURF [30], RIFT [31], the Canny detector [32], and Laplacian of Gaussian-based detectors [33].”
Savelonas, M. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9100255 · Cited by 13
“…methods that combine traditional handcrafted features, such as scale-invariant feature transform (SIFT) [146] and speeded-up robust features (SURF) [147], with DL architectures; and (3) methods that incorporate expert-defined heuristics or thresholds, as well as domain knowledge and rule-based…”
Fast PDE-Based Image Analysis in Your Pocket
Luxenburger, A., Zimmer, H., Gwosdek, P., & Weickert, J. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-24785-9_46 · Cited by 10
“Also sparse feature matching approaches based on SIFT or SURF features [12] have been considered on mobile platforms.”
MethodA novel biologically inspired local feature descriptor
Zhang, Y., Tian, T., Tian, J., Gong, J., & Ming, D. (2014) · Biological Cybernetics · doi:10.1007/s00422-013-0583-1 · Cited by 11
SP‐SIFT: enhancing SIFT discrimination via super‐pixel‐based foreground–background segregation
Navarro, F., Escudero-Viñolo, M., & Bescós, J. (2014) · Electronics Letters · doi:10.1049/el.2013.3949 · Cited by 11
“Owing to a combination of reasonable performance and publicly available implementations, the scale invariant feature transform (SIFT) [1], speeded up robust features [2] and DAISY [3] are the most popular description techniques in this fi eld.”
MethodTraffic sign recognition using a novel permutation-based local image feature
Tian, T., Sethi, I. K., & Patel, N. V. (2014) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2014.6889629 · Cited by 9
Object Recognition by Combining Binary Local Invariant Features and Color Histogram
Phan, D., Oh, C.-M., Kim, S.-H., et al. (2013) · IAPR Asian Conference on Pattern Recognition (ACPR) · doi:10.1109/acpr.2013.103 · Cited by 9
“Bay [11] in 2006 because it produces smaller descriptor as well as speeds up matching step.”
BackgroundA new method for combined face detection and identification using interest point descriptors
Stein, S., & Fink, G. A. (2011) · doi:10.1109/fg.2011.5771452 · Cited by 9
Local visual words coding for low bit rate mobile visual search
Wu, Y., Lu, S., Mei, T., et al. (2012) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2393347.2396364 · Cited by 9
“We adopt SURF as the local descriptor, which is fast to compute and can achieve similar performance to SIFT [1].”
BackgroundMethodAn experimental study on the universality of visual vocabularies
Hou, J., Liu, W., Xu, E., Xia, Q., & Qi, N. (2013) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2013.08.002 · Cited by 10
Estabilización Robusta de Vídeo basada en Diferencia de Nivel de Gris
Aguilar, W. G., & Ángulo, C. (2013) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · doi:10.24133/cctespe.v8i1.110 · Cited by 9
“[11] H. Bay, T. Tuytelaars, and L. Van Gool, "Surf: Speeded Up Robust Features," European Conference on Computer Vision, pp. 1:404-417, 2006.”
BackgroundCommonality Preserving Image-Set Clustering Based on Diverse Density
Fukui, T., & Wada, T. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14249-4_25 · Cited by 9
Performance evaluation for feature extractors on street view images
Güzel, M. S. (2015) · The Imaging Science Journal · doi:10.1080/13682199.2015.1109783 · Cited by 11
A general framework for image feature matching without geometric constraints
Arnfred, J. T., & WINKLER, S. S. (2016) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.12.017 · Cited by 9
“With SIFT and SURF this is the Euclidean distance of the feature vectors (Lowe, 2004; Bay et al., 2006), whereas BRIEF, BRISK, and FREAK use the Hamming distance (Leutenegger et al., 2011; Calonder et al., 2010; Alahi et al., 2012).”
MethodMulti-run 3D Streetside Reconstruction from a Vehicle
Zeng, Y., & Klette, R. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40261-6_70 · Cited by 9
“The speeded-up robust feature detector (SURF), see [2], is used to extract feature points in the first frame.”
MethodDense Correspondence and Optical Flow Estimation Using Gabor, Schmid and Steerable Descriptors
Baghaie, A., D’Souza, R. M., & Yu, Z. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27857-5_37 · Cited by 9
Makita, K., Vincent, T., Ebisuno, S., et al. (2016) · Springer eBooks · doi:10.1007/978-4-431-55861-3_8 · Cited by 9
Remote feature learning for mobile re-identification
Vernier, M., Martinel, N., Micheloni, C., et al. (2013) · International Conference on Distributed Smart Cameras · doi:10.1109/icdsc.2013.6778221 · Cited by 9
“Scale Invariant Feature Transform (SIFT) [12] and Speed-up Robust Feature (SURF) [4] are two well-known feature detector algorithms that achieve great performance under a variety of image transformations.”
BackgroundExtreme learning machine for structured output spaces
Maliha, A., Yusof, R. B., & Shapiai, M. I. (2016) · Neural Computing and Applications · doi:10.1007/s00521-016-2754-1 · Cited by 9
“Each determined location is represented by a local descriptor, SURF [38].”
MethodGarain, J., Shah, A., Kumar, R. K., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54526-4_28 · Cited by 9
ElTantawy, A., & Shehata, M. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7900243 · Cited by 9
“In case of aerial imagery, matching the candidate moving objects among the frames using features, such as SURF [1], FAST [16], etc., is very difficult as these objects appear very small.”
MethodAn Anthropomorphic Hand with Five Fingers Controlled by a Motion Leap Device
Moldovan, C. C., & Starețu, I. (2017) · Procedia Engineering · doi:10.1016/j.proeng.2017.02.436 · Cited by 9
Probabilistic Combination of Noisy Points and Planes for RGB-D Odometry
Proença, P. F., & Gao, Y. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-64107-2_27 · Cited by 9
“Image points are detected by relying on SURF features [1].”
MethodFlaspohler, G., Roy, N., & Girdhar, Y. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202130 · Cited by 9
Optimized Filtering With Binary Descriptor for Blind Image Quality Assessment
Oszust, M. (2018) · IEEE Access · doi:10.1109/access.2018.2860127 · Cited by 9
“A more advanced image descriptor, Speeded-Up Robust Features (SURF) [33], calculated on images convolved with Prewitt filters is used in [34].”
MethodReal-Time RGB-D SLAM with Points and Lines
Cheng, Z., & Wang, G. (2018) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec.2018.8469424 · Cited by 9
“Compared with SIFT [7] and SURF [8], ORB is much more efficient and can be computed in real time, which is important in a real time system.”
MethodMadhu, G. (2020) · Algorithms for intelligent systems · doi:10.1007/978-981-15-3689-2_8 · Cited by 9
Goshin, Y. V., Петрович, К. А., & RAS, I. R. –. B. O. T. F. “. A. P. (2020) · Computer Optics · doi:10.18287/2412-6179-co-683 · Cited by 9
Wu, W., Zhao, D., & Zhao, J. (2020) · Optik · doi:10.1016/j.ijleo.2020.165952 · Cited by 9
Improving Visual Place Recognition Performance by Maximising Complementarity
Waheed, M., Milford, M. J., McDonald-Maier, K. D., & Ehsan, S. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3088779 · Cited by 17
Coarse-to-Fine UAV Image Geo-Localization Using Multi-stage Lucas-Kanade Networks
Wu, S., Du, C., Chen, H., & Jing, N. (2021) · Information Communication Technologies Conference (ICTC) · doi:10.1109/ictc51749.2021.9441503 · Cited by 10
“There are many methods used in image matching like Scale Invariant Feature Features (SIFT) [7], Speed Up Robust Feature (SURF) [8], Harris operator [9].”
MethodEffect of Parameter Optimization on Classical and Learning-based Image Matching Methods
Efe, U., İnce, K. G., & Alatan, A. A. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00283 · Cited by 13
Deep Global Feature-Based Template Matching for Fast Multi-Modal Image Registration
Lei, R., Yang, B., Quan, D., et al. (2021) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss47720.2021.9553820 · Cited by 9
“The mainstream ones are Harris corner, Susan corner, SIFT [5] feature point, SURF [6] feature point, etc. SIFT-like methods have been widely used due to their scale-invariant.”
BackgroundAppearance-based Loop Closure Detection via Bidirectional Manifold Representation Consensus
Zhang, K., Li, Z., & Ma, J. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561704 · Cited by 9
van Rensburg, S. K. J. (2021) · Journal of Global Information Management · doi:10.4018/jgim.293290 · Cited by 13
Pre-trained CNNs as Feature-Extraction Modules for Image Captioning: An Experimental Study
Al-Malla, M. A., Jafar, A., & Ghneim, N. (2022) · ELCVIA Electronic Letters on Computer Vision and Image Analysis · doi:10.5565/rev/elcvia.1436 · Cited by 13
Hauswald, J., Laurenzano, M. A., Zhang, Y., et al. (2015) · ACM SIGARCH Computer Architecture News · doi:10.1145/2786763.2694347 · Cited by 9
EXTENSION AND EVALUATION OF THE AGAST FEATURE DETECTOR
Zhang, H., Wohlfeil, J., & Grießbach, D. (2016) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-iii-4-133-2016 · Cited by 9
Evaluation of fisheye-camera based visual multi-session localization in a real-world scenario
Mühlfellner, P., Furgale, P., Derendarz, W., & Philippsen, R. (2013) · IEEE Intelligent Vehicles Symposium Workshops (IV Workshops) · doi:10.1109/ivworkshops.2013.6615226 · Cited by 11
AFM Tip Localization and Efficient Scanning Method for MEMS Inspection
Chen, H.-C., Liu, Y.-L., Huang, C.-C., et al. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3175250 · Cited by 9
Defect Detection for a Vertical Shaft Surface Based on Multimodal Sensors
Chu, X., Tang, L., Sun, F., et al. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3195977 · Cited by 9
Mechanical Particle Filter-Based Active Vision System for Fast Wide-Area Multiobject Detection
Long, X., Ma, L., Jiang, H. Z., Li, Z., Chen, Y., & Gu, Q. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3201949 · Cited by 9
“To increase the repeatability and robustness 168 of SIFT, Bay et al. [28] proposed the speeded up robust fea-169 tures (SURFs) while reducing the processing time.”
BackgroundOn-board Absolute Localization Based on Orbital Imagery for a Future Mars Science Helicopter
Brockers, R., Proença, P. F., Delaune, J. H., Todd, J. E., Matthies, L. H., Tzanetos, T., & Balaram, J. B. (2022) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero53065.2022.9843673 · Cited by 14
Non-rigid point set registration: recent trends and challenges
Yuan, X., & Maharjan, A. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10292-4 · Cited by 11
“In general, putative correspondence set is computed using feature descriptors such as SIFT (Lowe 1999), Shape Context (SC) (Belongie et al. 2002), SURF (Bay et al. 2006), FPFH (Rusu et al. 2009), Spin Image (Johnson and Hebert 1999), IDSC (Ling and Jacobs 2007), 3DSC (Frome et al. 2004), etc.”
MethodSILA: a system for scientific image analysis
Moreira, D., Cardenuto, J. P., Shao, R., Baireddy, S., Cozzolino, D., Gragnaniello, D., AbdAlmageed, W., Bestagini, P., Tubaro, S., Rocha, A. D. R., et al. (2022) · Scientific Reports · doi:10.1038/s41598-022-21535-3 · Cited by 14
Detail-Aware Deep Homography Estimation for Infrared and Visible Image
Luo, Y., Wang, X., Wu, Y., & Shu, C. (2022) · Electronics · doi:10.3390/electronics11244185 · Cited by 9
Learning Soft Estimator of Keypoint Scale and Orientation with Probabilistic Covariant Loss
Yan, P., Tan, Y., Xiong, S., Tai, Y., & Li, Y. (2022) · 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/cvpr52688.2022.01880 · Cited by 11
“SURF [3] and KAZE [1] design different scale spaces.”
BackgroundMethodInfluentialLNC Assisted Localization and Mapping in Pipe Environment
Zhang, H., Yuan, J., Guo, S., et al. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981563 · Cited by 9
“Raising acceptable thresholds of image matching methods (SIFT [14], ORB [15], SURF [16], SuperPoint [17]) provides more true matches while the false correspondences are also increased.”
MethodMallis, D., Sánchez, E., Bell, M., & Tzimiropoulos, G. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3234212 · Cited by 9
Accuracy evaluations of real-time LiDAR-based indoor localization system
Nimura, M., Kanai, K., & Katto, J. (2023) · International Conference on Consumer Electronics · doi:10.1109/icce56470.2023.10043573 · Cited by 13
“This method uses image feature detection algorithms such as SIFT (Scale-Invariant Feature Transform) [6], SURF (Speeded-Up Robust Features) [7], and ORB (Oriented FAST and Rotated BRIEF) [8].”
MethodA Robust Indoor Localization Method Based on DAT-SLAM and Template Matching Visual Odometry
Zeng, Q., Ou, B., Wang, R., Yu, H., Yu, J., & Hu, Y. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3253570 · Cited by 9
“Early image feature extraction methods include scale invariant feature transform (SIFT) [7] and Speeded Up Robust Features (SURF) [8].”
MethodGorokhovatskyi, V., Peredrii, O., Tvoroshenko, I., et al. (2023) · Advanced Information Systems · doi:10.20998/2522-9052.2023.1.01 · Cited by 9
Image Matching and Localization Based on Fusion of Handcrafted and Deep Features
Song, X., Zou, Y., Shi, Z., & Yang, Y. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3305677 · Cited by 9
Local Topology Constrained Point Cloud Registration in Building Information Modeling
Liu, Y., Jiang, H., Nader, G., Wu, Z., Tanasnitikul, T., & Lasang, P. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3341218 · Cited by 10
Lim, H., Oh, M., Lee, S., Ahn, S., & Myung, H. (2024) · International Journal of Control Automation and Systems · doi:10.1007/s12555-023-0826-4 · Cited by 15
“In contrast, traversable regions are more likely to vary depending on the maneuverability of the robot platforms.”
Chen, J., Li, Q., Zhang, W., Wang, B., & Zhang, D. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3365794 · Cited by 11
“Various feature detection techniques, including SIFT [17], FAST [18], speeded up robust features (SURFs) [32], BRIEFs [19], and others, are frequently utilized in literatures.”
MethodZolfaghari, S., Kristoffersson, A., Folke, M., Lindén, M., & Riboni, D. (2024) · Sensors · doi:10.3390/s24051381 · Cited by 8
“SURF is a fast and robust feature detection algorithm in image processing and computer vision, designed for efficiently identifying key points in images [30].”
BackgroundMethodInfluentialDesign Space Exploration of Low-Bit Quantized Neural Networks for Visual Place Recognition
Grainge, O., Milford, M. J., Bodala, I. P., Ramchurn, S. D., & Ehsan, S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3386459 · Cited by 18
“Previously this has been achieved by lightweight handcrafted feature extraction techniques such as those utilizing keypoint descriptors [4], [5], [6] or whole image holistic descriptors [7], [8].”
MethodVisible/Infrared Image Registration Based on Region-Adaptive Contextual Multifeatures
Zhao, Q., Dong, L., Liu, M., Kong, L., Chu, X., Hui, M., & Zhao, Y. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3385088 · Cited by 14
“Traditional approaches of image matching typically rely on feature descriptors based on image gradients or intensities, such as SIFT [38], SURF [39], and DAISY [40].”
MethodNasser, S. A., Gupte, N., & Sethi, A. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00760 · Cited by 27
“Traditional keypoint detection algorithms, such as Harris corner detector [32], SIFT [25] and SURF [9], have been widely used in computer vision applications for decades.”
MethodQiao, H., Yang, X., Liang, Z., et al. (2024) · Applied Sciences · doi:10.3390/app14156403 · Cited by 9
Benchmarking Pretrained Vision Embeddings for Near- and Duplicate Detection in Medical Images
Truong, T., Jush, F. K., & Lenga, M. (2024) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi56570.2024.10635550 · Cited by 14
“The most common handcrafted embeddings are SIFT [1] and SURF [2] features.”
MethodYang, A. Y., Maji, S., Hong, K., et al. (2009) · Cited by 9
Object recognition by effective methods and means of computer vision
Dorner, J., Kozák, Š., & Dietze, F. (2015) · International Conference on Process Control · doi:10.1109/pc.2015.7169962 · Cited by 9
“Therefore another approach was applied [9], in which not only the first but also the second most similar descriptors was searched for.”
MethodPlantNet Participation at LifeCLEF2014 Plant Identification Task
Goëau, H., Joly, A., Yahiaoui, I., et al. (2014) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 9
Probabilistic matching pair selection for SURF-based person re-identification
Khedher, M. I., El‐Yacoubi, M. A., & Dorizzi, B. (2012) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 9
Using Recognition to Guide a Robot's Attention
Thomas, A., Ferrari, V. D., Leibe, B., et al. (2008) · doi:10.15607/rss.2008.iv.032 · Cited by 9
“[12, 1]) to determine continuous scale coordinates and orientations from discrete values.”
BackgroundSelf-citationBFROST: binary features from robust orientation segment tests accelerated on the GPU
Cronje, J. (2011) · Cited by 9
2D and 3D visualization methods of endoscopic panoramic bladder images
Behrens, A., Heisterklaus, I., Müller, Y., et al. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.877630 · Cited by 9
Trace Transform Based Method for Color Image Domain Identification
Olaizola, I. G., Quartulli, M., Flórez, J., & Sierra, B. (2014) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2014.2300843 · Cited by 9
Word Spotting Using Radial Descriptor
Kassis, M., & El‐Sana, J. (2014) · International Conference on Frontiers in Handwriting Recognition · doi:10.1109/icfhr.2014.71 · Cited by 9
Crowdsourcing as a methodology to obtain large and varied robotic data sets
de Croon, G., Gerke, P. K., & Sprinkhuizen-Kuyper, I. G. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942768 · Cited by 9
Memory‐efficient SURF architecture for ASIC implementation
Lee, S., Jang, S., Kim, J., et al. (2014) · Electronics Letters · doi:10.1049/el.2013.4102 · Cited by 9
Ultra-wide Baseline Aerial Imagery Matching in Urban Environments
Altwaijry, H., & Belongie, S. (2013) · British Machine Vision Conference (BMVC) · doi:10.5244/c.27.15 · Cited by 9
Fast online learning and detection of natural landmarks for autonomous aerial robots
Villamizar, M., Sanfeliu, A., & Moreno-Noguer, F. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907591 · Cited by 10
“One obvious solution for this is based on algorithms that first extract points of interest from the input and target images, represent them with a potentially complex descriptor [1], [14], and match them using a robust algorithm for outlier rejection [13], [20], [25].”
MethodRobust segment-based object tracking using generalized hyperplane approximation
Choi, H., & Oh, S. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.02.008 · Cited by 9
Visual words sequence alignment for image classification
Drozda, P., Górecki, P., Sopyła, K., & Artiemjew, P. (2013) · IEEE International Conference on Cognitive Informatics · doi:10.1109/icci-cc.2013.6622273 · Cited by 9
Image Mosaic using ORB descriptor and improved blending algorithm
Tian, F., & Shi, P. A. (2014) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2014.7003867 · Cited by 9
“SURF is several times faster than SIFT and robust against image transformations, but remains time-consuming on account of its floating point eigenvectors [7].”
Jäger, B., Mair, E., Brand, C., Stürzl, W., & Suppa, M. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696612 · Cited by 8
Logo and Trademark Recognition
Kesidis, A. L., & Karatzas, D. (2014) · Springer eBooks · doi:10.1007/978-0-85729-859-1_16 · Cited by 9
“[3 9] 20 01 Pa rt -b as ed Fo ur ie r”
BackgroundInfluentialA NOVEL IMAGE ACQUISITION AND PROCESSING PROCEDURE FOR FAST TUNNEL DSM PRODUCTION
Roncella, R., Umili, G., & Forlani, G. (2012) · 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/isprsarchives-xxxix-b5-297-2012 · Cited by 9
Case-Based Reasoning for planning turn-taking strategy with a therapeutic robot playmate
Park, H. W., & Howard, A. M. (2010) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob.2010.5626917 · Cited by 8
“Popular object recognition techniques like ScaleInvariant Feature Transform [19] or Speeded Up Robust Features [20] extracts interesting features to provide feature description of the objects.”
BackgroundImproving visual SLAM algorithms for use in realtime robotic applications
Benavidez, P. J., Muppidi, M., & Jamshidi, M. M. (2014) · World Automation Congress (WAC) · doi:10.1109/wac.2014.7084333 · Cited by 9
DENSE sampling of features for image retrieval
Sicre, R., & Gevers, T. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025618 · Cited by 9
Liu, M., Alper, B. T., & Siegwart, R. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630629 · Cited by 9
“PTAM [6] uses mainly FAST corners[7]; FAB-MAP [8] uses mainly SIFT [9] or SURF [10].”
MethodFerreira, F., Veruggio, G., Caccia, M., et al. (2009) · IFAC Proceedings Volumes · doi:10.3182/20090916-3-br-3001.0048 · Cited by 9
Schachter, B. J. (2012) · Optical Engineering · doi:10.1117/1.oe.52.4.041102 · Cited by 10
“A similar approach is speeded-up robust feature (SURF).(26) Let IðxÞ denote the input image.”
MethodPerformance evaluation of DTM area-based matching reconstruction of Moon and Mars
Re, C., Cremonese, G., Dall’Asta, E., et al. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.974524 · Cited by 9
“An initial disparity map can be computed using feature based matching (SURF [13]) followed by interpolation of the accepted disparities on a regular grid using a Delaunay triangulation.”
MethodEfficient visual odometry estimation using stereo camera
Mou, W., Wang, H., & Seet, G. (2014) · International Conference on Control and Automation · doi:10.1109/icca.2014.6871128 · Cited by 11
Relative orientation and scale for improved feature matching
Mills, S. J. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738719 · Cited by 9
Mono-spectrum marker: an AR marker robust to image blur and defocus
Toyoura, M., Aruga, H., Turk, M., & Mao, X. (2013) · The Visual Computer · doi:10.1007/s00371-013-0910-5 · Cited by 9
Object segmentation and key-pose based summarization for motion video
Tian, Z., Xue, J., Lan, X., et al. (2013) · Multimedia Tools and Applications · doi:10.1007/s11042-013-1488-7 · Cited by 9
Efficient Tree-Based Feature Descriptor and Matching Algorithm
Fowers, S. G., Desai, A., Lee, D. J., et al. (2014) · Journal of Aerospace Information Systems · doi:10.2514/1.i010173 · Cited by 9
Chaudhary, K., Mae, Y., Kojima, M., & Arai, T. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907585 · Cited by 9
“Note in this section for validation of acquired object models, the features were computed using SURF and RGB color histogram descriptors.”
MethodInfluentialAn automatic image fusion algorithm for unregistered multiply multi-focus images
Liu, Y., & Yu, F. (2014) · Optics Communications · doi:10.1016/j.optcom.2014.12.015 · Cited by 9
Funk, M., Schmidt, A., & Holmquist, L. E. (2013) · doi:10.1145/2494091.2494149 · Cited by 9
Robust Harris-SURF features for robotic vision based navigation
Rodríguez, D., & Aouf, N. (2010) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2010.5625280 · Cited by 9
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.