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 7,201–7,300 of 14,752
Quaero at TRECVID 2013: Semantic Indexing and Instance Search
Safadi, B., Derbas, N., Hamadi, A., et al. (2013) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 5
Cloud-Based Image Recognition for Robots
Lorenčík, D., Ondo, J., Sinčák, P., et al. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-16841-8_71 · Cited by 5
“We are using the SIFT (Scale invariant feature transform) [9] ad SURF (Speeded-Up Robust Features) [10] for features extraction and Membership function ArtMap [11]–[13] and Gaussian classifier for the classification of objects.”
MethodAdvertisement Image Recognition for a Location-Based Reminder System
Liu, S., Li, Y., Guo, A., et al. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-17829-0_40 · Cited by 5
Augmenting RatSLAM using FAB-MAP-based visual data association
Maddern, W., Glover, A., Milford, M. J., & Wyeth, G. F. (2009) · Cited by 5
Optimizing Visual Vocabularies Using Soft Assignment Entropies
Kuang, Y., Åström, K., Kopp, L., Oskarsson, M., & Byröd, M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19282-1_21 · Cited by 8
“SIFT or SURF [11, 2, 15] are computed at each interest point.”
MethodFESID: Finite Element Scale Invariant Detector
Kerr, D., Coleman, S., & Scotney, B. W. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04146-4_10 · Cited by 5
The Use of a Graphic Processing Unit (GPU) in a Real Time Visual Odometry Application
Vargas, J. A. D., & Kurka, P. R. G. (2015) · doi:10.1109/dsn-w.2015.32 · Cited by 5
A novel unsupervised approach for minimally-invasive video segmentation
Sepehri, M. M., Khatibi, T., & Shadpour, P. (2014) · Journal of Medical Signals & Sensors · doi:10.4103/2228-7477.128438 · Cited by 5
Wu, X., Housden, R. J., Ma, Y., Rueckert, D., & Rhode, K. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-36961-2_23 · Cited by 7
“The features we use are Speed Up Robust Features [8], also known as SURF, which is based on the integral image.”
MethodCV-SLAM using line and point features
Choi, H., Jo, S., & Kim, E. (2012) · Cited by 5
Papliński, A. P. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39065-4_63 · Cited by 5
Manifold Diffusion for Exophytic Kidney Lesion Detection on Non-contrast CT Images
Liu, J., Wang, S., Yao, J., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40811-3_43 · Cited by 5
“Mean and standard deviation of intensity values as well as speeded up robust feature (SURF) descriptor[1] are used to describe the lesion appearance.”
MethodReal-Time Robust Image Feature Description and Matching
Thomas, S. J., MacDonald, B. A., & Stol, K. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19309-5_26 · Cited by 5
SPEEDED UP IMAGE MATCHING USING SPLIT AND EXTENDED SIFT FEATURES
Alhwarin, F., Ristić–Durrant, D., & Gräser, A. (2010) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0002820102870295 · Cited by 5
Autonomous Robot Navigation Based on Clustering across Images
Vintr, T., Pastorek, L., & Řezanková, H. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-21975-7_27 · Cited by 5
On the detection of systematic errors in terrestrial laser scanning data
Wang, J., Kutterer, H., & Fang, X. (2012) · Journal of Applied Geodesy · doi:10.1515/jag-2012-0025 · Cited by 9
A method of infrared/visible image matching based on edge extraction
Zhao, Z., & Wang, R. (2010) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2010.5646877 · Cited by 5
EMOVIS: An Efficient Mobile Visual Search System for Landmark Recognition
Li, D., & Chuah, M. C. (2013) · doi:10.1109/msn.2013.45 · Cited by 5
MVSS: Mobile Visual Search Based on Saliency
Du, Y., Li, Z., Qu, W., et al. (2013) · doi:10.1109/hpcc.and.euc.2013.131 · Cited by 5
“There are also some other low-bit rate descriptors such as: Speeded-Up Robust Features (SURF) [10], Gradient Location and Orientation Histogram (GLOH) [11] and Compressed Histogram of Gradients (CHoG) [12].”
BackgroundGeometrical distortion integrated performance index for vision-based navigation system
Won, D. H., Chun, S., Lee, S., et al. (2013) · International Journal of Control Automation and Systems · doi:10.1007/s12555-012-0194-y · Cited by 5
Geometric constraints for robot navigation using omnidirectional camera
Wang, M.-L., Wu, H., He, C.-H., Huang, W.-T., & Lin, H. (2012) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2012.6377986 · Cited by 5
A novel affine attack robust blind watermarking algorithm
Yang, S., Song, Z., Fang, Z., et al. (2010) · Procedia Engineering · doi:10.1016/j.proeng.2010.11.038 · Cited by 5
Pareto-optimal dictionaries for signatures
Calonder, M., Lepetit, V., & Fua, P. (2010) · 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/cvpr.2010.5540050 · Cited by 5
Karakaya, F., Altun, H., & Çavuşlu, M. A. (2009) · IEEE Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2009.5136444 · Cited by 5
Ta, D.-N., Ok, K., & Dellaert, F. (2014) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.03.010 · Cited by 6
Pan/Tilt Camera Control for Vision Tracking System Based on the Robot Motion and Vision Information
Park, J., Hwang, W., Bahn, W., et al. (2011) · IFAC Proceedings Volumes · doi:10.3182/20110828-6-it-1002.01781 · Cited by 5
Adaptive Euclidean maps for histograms: generalized Aitchison embeddings
Le, T., & Cuturi, M. (2014) · Machine Learning · doi:10.1007/s10994-014-5446-z · Cited by 7
Camera-based navigation for service robots using pictographs on the crossing point
Chugo, D., Hirose, K., Nakashima, K., Yokota, S., Kobayashi, H., & Hashimoto, H. (2012) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2012.6389224 · Cited by 6
Traffic sign detection and identification using SURF algorithm and GPGPU
Ding, D., Yoon, J. H., & Lee, C. (2012) · International SoC Design Conference · doi:10.1109/isocc.2012.6406907 · Cited by 5
Data association and map management for robot SLAM using local invariant features
Wang, Y.-T., & Feng, Y.-C. (2013) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2013.6618068 · Cited by 5
“The modified SURF method is described in three aspects, including feature detection, description and matching, in the following subsections.”
MethodPerformance characterization and acceleration of Optical Character Recognition on handheld platforms
Srinivasan, S., Zhao, L., Sun, L., et al. (2010) · IEEE International Symposium on Workload Characterization · doi:10.1109/iiswc.2010.5648852 · Cited by 5
Android-Based Visual Tag Detection for Visually Impaired Users
Dong, H., Kang, J., Schafer, J. M., et al. (2014) · International Journal of E-Health and Medical Communications · doi:10.4018/ijehmc.2014010104 · Cited by 5
Grasping objects localized from uncertain point cloud data
Saut, J.-P., Ivaldi, S., Sahbani, A., et al. (2014) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.07.011 · Cited by 5
“2D features (SURF [32]) are then extracted in the segmented images.”
MethodInspección visual subacuática mediante robótica submarina
Carreras, M., Ridao, P., García, R., Ribas, D., & Palomeras, N. (2012) · Revista Iberoamericana de Automática e Informática Industrial RIAI · doi:10.1016/j.riai.2011.11.011 · Cited by 5
AN EMPIRICAL EVALUATION OF INTEREST POINT DETECTORS
Barandiarán, Í., Graña, M., & Nieto, M. (2013) · Cybernetics & Systems · doi:10.1080/01969722.2013.762232 · Cited by 5
Detection of Façade Regions in Street View Images from Split-and-Merge of Perspective Patches
Liu, F., & Seipel, S. (2014) · Journal of Image and Graphics · doi:10.12720/joig.2.1.8-14 · Cited by 5
“Some of those systems rely on motion vector tracking [2] and [3], while others, such as the well-known SIFT [4], SURF [5], or CHoG [6] methods, retrieve local feature points based on histograms of gradients.”
MethodGeometric and colorimetric error compensation for multi-view images
Jung, J.-I., & Ho, Y. (2013) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2013.04.008 · Cited by 5
Wan, T., Bloch, B., Danish, S. F., & Madabhushi, A. (2014) · Neurocomputing · doi:10.1016/j.neucom.2013.11.051 · Cited by 5
“A speeded up robust features (SURF)-based landmark detection method [35] employed the SURF features, which are robust local descriptors, to identify informative landmarks.”
MethodAdaptive Pipeline Parallelism for Image Feature Extraction Algorithms
Chen, P., Yang, D., Zhang, W., et al. (2012) · Proceedings of the International Conference on Parallel Processing · doi:10.1109/icpp.2012.14 · Cited by 5
Pose tracking using motion state estimation for mobile augmented reality
Kobayashi, T., Kato, H., & Yanagihara, H. (2015) · International Conference on Consumer Electronics · doi:10.1109/icce.2015.7066298 · Cited by 5
“The tracking rates for all sequences of SURF, [2] and our method are on average 87.8%, 99.3% and 99.2%, respectively.”
MethodInfluentialReal time image de-blurring and image stitching for muscle inspired camera orientation system
Kilbride, S. A., Kim, M. D., & Ueda, J. (2014) · doi:10.1109/arso.2014.7020985 · Cited by 5
Evaluation of Feature Extraction Methods for Face Recognition
Liu, Y., Li, C., Su, B., et al. (2013) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid.2013.192 · Cited by 5
SIFT vs. FREAK: Assessing the usefulness of two keypoint descriptors for 3D face verification
Križaj, J., Štruc, V., Dobrišek, S., et al. (2014) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro.2014.6859775 · Cited by 5
“Image descriptors, such as the SIFT [2], the SURF [3] or the HOG [4] descriptor, established themselves as state-of-the-art tools for solving various vision-related problems ranging from object detection, recognition and tracking to image stitching and retrieval.”
MethodTarget follwing with a vision sway compensation for robotic fish Fibo
Na, K., Jeong, I., Han, S.-B., et al. (2011) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2011.6181604 · Cited by 5
A More Robust Feature Correspondence for more Accurate Image Recognition
El-Mashad, S. Y., & Shoukry, A. (2014) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2014.32 · Cited by 6
Low-rank SIFT: An affine invariant feature for place recognition
Yang, H., Cai, S., Wang, J., & Quan, L. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7026159 · Cited by 5
Appearance‐based approach to hybrid metric‐topological simultaneous localisation and mapping
Fernández, L., Payá, L., Reinoso, Ó., et al. (2014) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2013.0086 · Cited by 5
Vision-based pose estimation for autonomous outdoor navigation of aerial vehicles
Samadzadegan, F., & Abdi, G. (2011) · International Conference on Control, Instrumentation, and Automation · doi:10.1109/icciautom.2011.6356778 · Cited by 5
Accurate off-line query expansion for large-scale mobile visual search
Gao, K., Zhang, Y., Zhang, D., & Lin, S. (2012) · Signal Processing · doi:10.1016/j.sigpro.2012.10.011 · Cited by 5
The effectiveness of detector combinations
Li, Z., Gong, W., Nee, A. Y. C., et al. (2009) · Optics Express · doi:10.1364/oe.17.007407 · Cited by 5
Zhao, J., Tao, W., Zhang, H., et al. (2010) · OCEANS'10 IEEE SYDNEY · doi:10.1109/oceanssyd.2010.5603809 · Cited by 5
“Such as the second order Gaussian filter is replaced by a mean filter [8], as shown in Fig.”
BackgroundMethodInfluentialA fast integral image generation algorithm on GPUs
Dang, Q., Yan, S., & Wu, R. (2014) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/padsw.2014.7097862 · Cited by 6
SAIL-MAP: Loop-closure detection using saliency-based features
Birem, M., Quinton, J., Berry, F., & Mezouar, Y. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6943206 · Cited by 5
“In [1], [2], [3] the features used are SIFT [18] or SURF [19].”
MethodVideo-based vehicle detection method
Кустикова, В. Д., Meyerov, I. B., & Zolotykh, N. Y. (2014) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661814040117 · Cited by 5
Efficient Modern Description Methods by Using SURF Algorithm for Recognition of Plant Species
Kazerouni, M. F., Schlemperz, J., & Kuhnert, K.-D. (2015) · Advances In Image and Video Processing · doi:10.14738/aivp.32.1151 · Cited by 5
“A widely used keypoint based detector and descriptor is SURF [9].”
MethodMultiple 3D object position estimation and tracking using double filtering on multi-core processor
Park, J.-H., Rho, S., Jeong, C., et al. (2012) · Multimedia Tools and Applications · doi:10.1007/s11042-012-1029-9 · Cited by 5
“SIFT has high accuracy.”
MethodInfluentialUsing Local-Based Harris-PHOG Features in a Combination Framework for Human Action Recognition
Hemati, R., & Mirzakuchaki, S. (2013) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-013-0816-6 · Cited by 5
“Scale-Invariant Feature Transform (SIFT) [13], Speed Up Robust Feature (SURF) [14] and Harris-PHOG [15–17] are the highly successful algorithms for detecting many interest points and describing them.”
BackgroundMethodFundus image mosaic generation for large field of view
Usmani, D., Ahmad, T., Akram, M. U., et al. (2014) · International Conference on Hybrid Intelligent Systems (HIS) · doi:10.1109/his.2014.7086170 · Cited by 5
Evaluating classifier combination in object classification
Hou, J., Xu, E., Xia, Q., & Qi, N. (2014) · Pattern Analysis and Applications · doi:10.1007/s10044-014-0366-x · Cited by 5
Visual detection of vehicles using a bag-of-features approach
Pinto, P., Tomé, A. M., & Santos, V. M. F. (2013) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/robotica.2013.6623539 · Cited by 5
“The algorithm presented in this paper distinguishes itself by following a bag-of-features approach and also combining SURF features with a Support Vector Machine for vehicle classification.”
MethodInfluentialFast planar object detection and tracking via edgel templates
Lee, T., & Soatto, S. (2012) · doi:10.1109/wacv.2012.6163024 · Cited by 5
LSGP: Line-SIFT Geometric Pattern for wide-baseline image matching
Liu, H., Chen, X., Zhang, J., et al. (2013) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2013.6571948 · Cited by 5
“For example,SIFT [5], SURF [6], MSER [7], etc.”
Comparison of different feature detectors and descriptors for car classification in UAV images
Moranduzzo, T., & Melgani, F. (2013) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2013.6721127 · Cited by 8
“• SURF algorithm performs the detection of the points by using determinants of Hessian matrices and describes them by summing Haar wavelet responses inside a region of interest extracted around the considered point.”
MethodInfluentialAugmenting 3D urban environment using mobile devices
Wu, Y., Choubassi, M. E., & Kozintsev, I. V. (2011) · IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2011.6092396 · Cited by 5
“In this paper, we chose SURF for its trade-off between speed and accuracy.”
BackgroundInfluentialHarris feature vector descriptor (HFVD)
Wang, X. G., Wu, F., & Wang, Z. H. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4760977 · Cited by 5
“From then, a lot of similar work has been done, such as the Shape Context [2], GLOH [10] and SURF [1].”
MethodA non-linear multi-scale blending algorithm for fluorescence bladder images
Behrens, A., Guski, M., Stehlé, T., et al. (2010) · Computer Science - Research and Development · doi:10.1007/s00450-010-0144-y · Cited by 5
Training Binary Descriptors for Improved Robustness and Efficiency in Real-Time Matching
Akhoury, S. S., & Laganière, R. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41184-7_30 · Cited by 5
“Interestingly, SIFT is more optimized than SURF in the current OpenCV implementation, hence it yields smaller computational times compared to SURF.”
BackgroundMethodInfluentialTomašev, N., & Mladenić, D. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40994-3_44 · Cited by 5
Being in Two Places at Once: Smooth Visual Path Following on Globally Inconsistent Pose Graphs
van Es, S. K., & Barfoot, T. D. (2015) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2015.17 · Cited by 6
Carlo, S. D., Prinetto, P., Rolfo, D., Sansonne, N., & Trotta, P. (2014) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/1687-6180-2014-147 · Cited by 6
Automatic target prediction and subtle gaze guidance for improved spatial information recall
Sridharan, S., & Bailey, R. (2015) · doi:10.1145/2804408.2804415 · Cited by 5
An interactive system of stereoscopic video conversion
Zhang, Z., Zhou, C., Xin, B., Wang, Y., & Gao, W. (2012) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2393347.2393374 · Cited by 5
“Given the segmented foreground object, we extract SURF(Speeded Up Robust Features) [2] as feature points for feature tracking and warp contour using KLT tracking [18] method, which is a fast, efficient, scale-and rotation-invariant interest point detector.”
MethodDesign and Detection of Local Geometric Features for Deformable Marker Fields
Horváth, Z., Herout, A., Szentandrási, I., et al. (2013) · Spring Conference on Computer Graphics · doi:10.1145/2508244.2508254 · Cited by 5
“SURF: Speeded up robust features.”
BackgroundInfluentialMoving object detection using keypoints reference model
Zaki, W. M. D. W., Hussain, A., & Hedayati, M. (2011) · EURASIP Journal on Image and Video Processing · doi:10.1186/1687-5281-2011-13 · Cited by 5
“An almost real-time computation can be gained without any loss in performance [15].”
BackgroundMethodInfluentialMulti-level trajectory modeling for video copy detection
Chen, S., Wang, J., Ouyang, Y., et al. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5496165 · Cited by 5
Semantic browsing of video surveillance databases through Online Generic Indexing
Marraud, D., Cépas, B., & Reithler, L. (2009) · ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC) · doi:10.1109/icdsc.2009.5289366 · Cited by 5
Service robots navigation using pictographs detection for indoor environment
Hirose, K., Chugo, D., Yokota, S., & Takase, K. (2011) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2011.6119644 · Cited by 6
Direct perception and action system for unknown object grasping
Masuta, H., Lim, H., Motoyoshi, T., et al. (2015) · IEEE RO-MAN · doi:10.1109/roman.2015.7333637 · Cited by 5
Scale Invariant Metrics of Volumetric Datasets
Raviv, D., & Raskar, R. (2015) · SIAM Journal on Imaging Sciences · doi:10.1137/140987675 · Cited by 5
Location-Based Large-Scale Landmark Image Recognition Scheme for Mobile Devices
Kim, D., Hwang, E., & Rho, S. (2012) · doi:10.1109/music.2012.16 · Cited by 5
Incremental 3D Body Reconstruction Framework for Robotic Telepresence Applications
Almeida, L., Menezes, P. J., Seneviratne, L. D., & Dias, J. M. M. (2011) · Biomechanics / 752: Robotics · doi:10.2316/p.2011.752-068 · Cited by 5
Towards Vision-Based Pose- and Condition-Invariant Place Recognition along Routes
Pepperell, E., Corke, P., & Milford, M. J. (2014) · QUT ePrints (Queensland University of Technology) · Cited by 5
Look Inside the World of Parts of Handwritten Characters
Song, W., Uchida, S., & Liwicki, M. (2011) · Proceedings of the International Conference on Document Analysis and Recognition · doi:10.1109/icdar.2011.161 · Cited by 5
“In [1]–[4], scale-invariant feature transform [5] (SIFT) or speeded-up robust features [6] (SURF) descriptors were employed, instead.”
MethodInfluentialA speeded-up affine invariant detector
Zhou, H., Pan, Y., & Zhang, Z. (2012) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2012.6469986 · Cited by 5
A Feature-Based Object Tracking Method Using Online Template Switching and Feature Adaptation
Fan, L. (2011) · International Conference on Image and Graphics · doi:10.1109/icig.2011.102 · Cited by 5
Camera-based localization for indoor service robots using pictographs
Hirose, K., Chugo, D., Yokota, S., & Takase, K. (2011) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2011.6027131 · Cited by 6
People counting with image retrieval using compressed sensing
Foroughi, H., Ray, N., & Zhang, H. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854424 · Cited by 5
“WI-SIFT (Whole Image SIFT) and WI-SURF are the global versions of the corresponding famous local normalized descriptors SIFT [18] and SURF [19].”
MethodAn efficient automatic geo-registration technique for high resolution spaceborne SAR image fusion
Lee, W.-K., & Kim, A.-L. (2011) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2011.6049992 · Cited by 5
“Haarwavelet is used in each divided sub-domain to construct 64dimension Descriptor vector, thus enabling fast and accurate characteristic point extraction [5].”
MethodExtraction of object features from high resolution SAR images based on SURF features
Tian, X., Wang, C., & Zhang, H. (2011) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2011.6049471 · Cited by 5
“SURF approximates or evens outperform previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster[3-4].”
Video face recognition via combination of real‐time local features and temporal–spatial cues
Gou, G., Huang, D., & Wang, Y. (2014) · IET Computer Vision · doi:10.1049/iet-cvi.2013.0025 · Cited by 5
“Moreover, SURF is also robust to the variations of scales, rotations and poses [12].”
BackgroundMethodInfluentialA New Approach to Satellite Time-series Co-registration for Landslide Monitoring
Barazzetti, L., Gianinetto, M., & Scaioni, M. (2015) · Springer eBooks · doi:10.1007/978-3-662-45931-7_12 · Cited by 5
Image registration method based on SURF and FREAK
Yanhai, W., Zhang, C., Wang, J., et al. (2015) · IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) · doi:10.1109/icspcc.2015.7338825 · Cited by 5
Fixed Homography-Based Real-Time SW/HW Image Stitching Engine for Motor Vehicles
Suk, J.-H., Lyuh, C., Yoon, S., et al. (2015) · ETRI Journal · doi:10.4218/etrij.15.0113.1120 · Cited by 5
“Descriptor-based features such as SIFT [18] and SURF [19] improve the performance of automatic panorama synthesis.”
MethodPlanar Object Detection using Local Feature Descriptors
Kottman, M. (2011) · Cited by 5
Nanni, L., Ghidoni, S., & Menegatti, E. (2013) · Padua Research Archive (University of Padova) · Cited by 5
SORTING LOCAL DESCRIPTORS FOR LOW BIT RATE MOBILE VISUAL SEARCH
Yao, H., & Gao, W. (2011) · Cited by 5
Vision-Controlled Micro Flying Robots
Scaramuzza, D., Achtelik, M. C., Doitsidis, L., Fraundorfer, F., Kosmatopoulos, E. B., Martinelli, A., Achtelik, M., Chli, M., Chatzichristofis, S. A., Kneip, L., et al. (2014) · Cited by 6
Euclidean auto calibration of camera networks: Baseline constraint removes scale ambiguity
Vupparaboina, K. K., Raghavan, K., & Jana, S. (2016) · National Conference on Communications · doi:10.1109/ncc.2016.7561098 · Cited by 5
A Web Portal for Effective Multi-model Exploration
Grošup, T., Čech, P., Lokoč, J., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14442-9_37 · Cited by 5
3D Line Segment Based Model Generation by RGB-D Camera for Camera Pose Estimation
Nakayama, Y., Saitô, H., Shimizu, M., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16634-6_34 · Cited by 5
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.