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 1,801–1,900 of 14,752
Towards an efficient distributed object recognition system in wireless smart camera networks
Naikal, N., Yang, A. Y., & Sastry, S. (2010) · International Conference on Information Fusion (FUSION) · doi:10.1109/icif.2010.5711893 · Cited by 38
“The success of SIFT-type viewpoint invariant feature detectors [13, 14] has led to the development of other improved feature detectors and descriptors, such as SURF [2] and CHoG [5], which are better suited for deployment on mobile camera platforms.”
BackgroundMethodInfluentialEvaluation of registration methods on two-dimensional forward-looking sonar imagery
Hurtós, N., Nagappa, S., Cufí, X., Pétillot, Y., & Salví, J. (2013) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans-bergen.2013.6608124 · Cited by 42
DP-FACT: Towards topological mapping and scene recognition with color for omnidirectional camera
Liu, M., & Siegwart, R. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6225040 · Cited by 39
“Nevertheless, the state-of-art object detection methods [10], [11] are usually computational expensive.”
BackgroundMobile augmented reality based on cloud computing
Huang, B.-R., Lin, C. H., & Lee, C. (2012) · IEEE International Conference on Anti-counterfeiting, Security, and Identification (ASID) · doi:10.1109/icasid.2012.6325354 · Cited by 41
“In order to determine where to render the augmented objects in the real environment, most of the previous works relied on the tracking of feature points, including robust image-based features, such as scareinvariant feature transform (SIFT) [6], speeded up robust feature (SURF) [7], and patch tracking [8].”
Camera-based indoor positioning using scalable streaming of compressed binary image signatures
Opdenbosch, D. V., Schroth, G., Huitl, R., Hilsenbeck, S., Garcea, A., & Steinbach, E. G. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025567 · Cited by 45
“In previous work, VLAD and Fisher Kernels have only been applied in combination with features like SURF [19], SIFT [20] or CHoG [2], which rely on floating point representations.”
MethodInspection of Complex Objects Using Multiple-X-Ray Views
Mery, D. (2014) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2014.2311032 · Cited by 40
Simultaneous Parameter Calibration, Localization, and Mapping
Kümmerle, R., Grisetti, G., & Burgard, W. (2012) · Advanced Robotics · doi:10.1080/01691864.2012.728694 · Cited by 41
“While 2D range scans do not provide highly distinguishable features, camera images allow to extract discriminable features, e.g., SIFT [2] or SURF [3].”
BackgroundMethodThermal 3D mapping for object detection in dynamic scenes
Weinmann, M., Leitloff, J., Hoegner, L., Jutzi, B., Stilla, U., & Hinz, S. (2014) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-ii-1-53-2014 · Cited by 46
Feature group matching for appearance-based localization
Ascani, A., Frontoni, E., Mancini, A., et al. (2008) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2008.4651023 · Cited by 40
Rate-adaptive Compact Fisher Codes for Mobile Visual Search
Lin, J., Duan, L., Huang, Y., Luo, S., Huang, T., & Gao, W. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2013.2296532 · Cited by 42
Real‐time condition monitoring of substation equipment using thermal cameras
Pal, D., Meyur, R., Menon, S., Reddy, M. J. B., & Mohanta, D. K. (2018) · IET Generation Transmission & Distribution · doi:10.1049/iet-gtd.2017.0096 · Cited by 46
Schlag, I., & Arandjelović, O. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.342 · Cited by 48
“Most of these methods are local feature based, employing local feature descriptors such as SIFT [20] or SURF [11].”
MethodSeo, J., Alwasel, A., Lee, S. H., Abdel-Rahman, E. M., & Haas, C. T. (2017) · Robotica · doi:10.1017/s0263574717000571 · Cited by 42
An Evaluation of Deep Learning in Loop Closure Detection for Visual SLAM
Xia, Y., Li, J., Qi, L., Yu, H. L., & Dong, J. (2017) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/ithings-greencom-cpscom-smartdata.2017.18 · Cited by 42
Understanding the Characteristics of Mobile Augmented Reality Applications
Chen, H., Dai, Y., Meng, H., et al. (2018) · IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) · doi:10.1109/ispass.2018.00026 · Cited by 40
Safe Driving : Driver Action Recognition using SURF Keypoints
Jegham, I., Khalifa, A. B., Alouani, I., & Mahjoub, M. A. (2018) · doi:10.1109/icm.2018.8704009 · Cited by 46
Baek, I., Davies, A., Yan, G., & Rajkumar, R. (2018) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2018.8500455 · Cited by 43
A Discriminative Distillation Network for Cross-Source Remote Sensing Image Retrieval
Xiong, W., Xiong, Z., Cui, Y., & Lv, Y. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.2980870 · Cited by 44
“Popularhandcrafted featuresincludeglobalfeaturesconstitutingspectral(colour) [6],[34],texture[7],[35],shape[8],[36]aswellaslocal featuresbasedonscaleinvariantfeaturetransform[9],difference of Gaussian [38], and speeded up robust features [10].”
BackgroundHafiz, R., Haque, M. R., Rakshit, A., & Uddin, M. S. (2020) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2020.08.015 · Cited by 42
“After classification of any soft drink, we again impose color and SURF (Bay et al., 2006) based bag-of-feature (BoF) (O’Hara and Draper, 2011) technique to identify how it is served, i.e. in a glass, can, glass bottle or plastic bottle and the process is shown in Fig.”
CNDesc: Cross Normalization for Local Descriptors Learning
Wang, C., Xu, R., Xu, S., Meng, W., & Zhang, X. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3169331 · Cited by 40
A Review on Methods for Automatic Counting of Objects in Digital Images
Barbedo, J. G. A. (2012) · IEEE Latin America Transactions · doi:10.1109/tla.2012.6362356 · Cited by 40
Non-contact remote estimation of cardiovascular parameters
Fan, Q., & Li, K. (2017) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2017.09.022 · Cited by 51
Soatto, S. (2011) · arXiv · doi:10.48550/arxiv.1110.2053 · Cited by 40
Image Location Estimation by Salient Region Matching
Qian, X., Zhao, Y., & Han, J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2462131 · Cited by 39
“descriptors, such as SIFT [42], SURF [49].”
An Augmented Reality Tourist Guide on Your Mobile Devices
Choubassi, M. E., Nestares, O., Wu, Y., et al. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-11301-7_58 · Cited by 39
“We use 64-dimensional SURF [7] which are fast to compute compared to SIFT [8].”
MethodRobust video stabilization based on motion intention for low-cost micro aerial vehicles
Aguilar, W. G., & Ángulo, C. (2014) · International Multi-Conference on Systems, Signals & Devices (SSD) · doi:10.1109/ssd.2014.6808863 · Cited by 40
Real-time 3D reconstruction techniques applied in dynamic scenes: A systematic literature review
Ingale, A. K., & Udayan, J. D. (2020) · Computer Science Review · doi:10.1016/j.cosrev.2020.100338 · Cited by 49
Rathnayake, N., Rathnayake, U., Dang, T. L., & Hoshino, Y. (2022) · Sensors · doi:10.3390/s22124401 · Cited by 40
“The sixth and seventh descriptors are Scale Invariant Feature Transform (SIFT) [42] and Speeded Up Robust Features (SuRF) [43].”
BackgroundClassification Method of Significant Rice Pests Based on Deep Learning
Li, Z., Jiang, X., Jia, X., Duan, X., Wang, Y., & Mu, J. (2022) · Agronomy · doi:10.3390/agronomy12092096 · Cited by 48
Zhou, W., Liu, Y., Zhao, L., Xu, S., & Wang, C. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3314051 · Cited by 44
Pfingsthorn, M. F., & Birk, A. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364915585395 · Cited by 42
Detection and Recognition of Traffic Signs from Road Scene Images
Malik, Z., & Siddiqi, I. (2014) · International Conference on Frontiers of Information Technology (FIT) · doi:10.1109/fit.2014.68 · Cited by 39
Classifier learning with hidden information
Wang, Z., & Ji, Q. (2015) · 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.2015.7299131 · Cited by 52
“The L1 normalized 2000 dimensional SURF descriptors [25] extracted from the raw images are used as the primary feature x.”
MethodD-Nets: Beyond patch-based image descriptors
Hundelshausen, F. V., & Sukthankar, R. (2012) · 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.2012.6248022 · Cited by 40
An augmented workplace for enabling user-defined tangibles
Funk, M., Korn, O., & Schmidt, A. (2014) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/2559206.2581142 · Cited by 42
Automatically Augmenting Lifelog Events Using Pervasively Generated Content from Millions of People
Doherty, A., & Smeaton, A. F. (2010) · Sensors · doi:10.3390/s100301423 · Cited by 43
Computer-aided detection of exophytic renal lesions on non-contrast CT images
Liu, J., Wang, S., Linguraru, M. G., et al. (2014) · Medical Image Analysis · doi:10.1016/j.media.2014.07.005 · Cited by 39
“, 2013a,b), where manifold diffusion with fixed scales were employed to detect exophytic renal lesions and the sum of the Harr wavelet response from speeded up robust features (Bay et al., 2008) were used as appearance features to classify renal lesions.”
InfluentialInterframe Coding of Feature Descriptors for Mobile Augmented Reality
Makar, M. A., Chandrasekhar, V., Tsai, S. S., et al. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2331136 · Cited by 39
Leroy, L., Fuchs, P., & Moreau, G. (2011) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2011.2171173 · Cited by 39
Dai, F., & Lu, M. (2012) · Journal of Construction Engineering and Management · doi:10.1061/(asce)co.1943-7862.0000655 · Cited by 37
Speeded-up Bag-of-Words algorithm for robot localisation through scene recognition
Botterill, T., Mills, S. J., & Green, R. (2008) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2008.4762067 · Cited by 39
SemSense: Automatic construction of semantic indoor floorplans
Elhamshary, M., & Youssef, M. A. (2015) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2015.7346759 · Cited by 40
Stratified pooling based deep convolutional neural networks for human action recognition
Yu, S., Cheng, Y., Su, S., Cai, G., & Li, S. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3768-5 · Cited by 42
Evaluation of Low-Level Features for Real-World Surveillance Event Detection
Xian, Y., Rong, X., Yang, X., & Tian, Y. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2589838 · Cited by 38
“The SURF detector [26] is first exploited”
Williams, S. B., Pizarro, O. R., Steinberg, D., Friedman, A., & Bryson, M. (2016) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2016.09.010 · Cited by 39
SIFT Matching with CNN Evidences for Particular Object Retrieval
Zhang, G., Zeng, Z., Zhang, S., Zhang, Y., & Wu, W. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.01.081 · Cited by 39
Payá, L., Gil, A., & Reinoso, Ó. (2017) · Journal of Sensors · doi:10.1155/2017/3497650 · Cited by 41
“[76, 77], is inspired in SIFT but presents a lower computational cost and a higher robustness against image transformations.”
BackgroundSequence searching with CNN features for robust and fast visual place recognition
Bai, D., Wang, C., Zhang, B., Yi, X., & Yang, X. (2017) · Computers & Graphics · doi:10.1016/j.cag.2017.07.019 · Cited by 38
Structured Weak Semantic Space Construction for Visual Categorization
Zhang, C., Cheng, J., & Tian, Q. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2728060 · Cited by 38
“Local features [3], [6]–[9] are designed to cope with deformations and can also be computed efficiently.”
Teach Me How! Interactive Assembly Instructions Using Demonstration and In-Situ Projection
Funk, M., Lischke, L., Mayer, S., Shirazi, A. S., & Schmidt, A. (2017) · Cognitive science and technology · doi:10.1007/978-981-10-6404-3_4 · Cited by 39
“In case, the change in depth data is over a threshold of 63%, our algorithm runs the SURF object recognition algorithm [5] to compare the image of the defined zone to the previously recorded reference image of the object (Figure 3c).”
MethodHuman hand recognition from robotic skin measurements in human-robot physical interactions
Albini, A., Denei, S., & Cannata, G. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206300 · Cited by 40
“from the contact images using robust feature extraction algorithms such as SIFT [27] and SURF [28].”
MethodMTBI Identification From Diffusion MR Images Using Bag of Adversarial Visual Features
Minaee, S., Wang, Y., Aygar, A., Chung, S., Wang, X., Lui, Y. W., Fieremans, E., Flanagan, S. R., & Rath, J. F. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2905917 · Cited by 42
Object detection and recognition via clustered features
Woźniak, M., & Połap, D. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.09.003 · Cited by 39
Pham, H., Salmane, H., Khoudour, L., Crouzil, A., Zegers, P., & Velastín, S. A. (2019) · Sensors · doi:10.3390/s19081932 · Cited by 45
Robust Loop Closure Detection based on Bag of SuperPoints and Graph Verification
Yue, H., Miao, J., Yu, Y., Chen, W., & Wen, C. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967726 · Cited by 43
“…methods extract plenty of key points and calculate feature descriptors of these points to describe one image, such as SIFT (Scale-Invariant Feature Transform) [5], HOG (Histogram of Oriented Gradient) [6], SURF (Speeded Up Robust Features) [7], and ORB (Oriented FAST and Rotated BRIEF) [8].”
MethodAutomatic human identification based on dental X-ray radiographs using computer vision
Heinrich, A., Güttler, F. V., Schenkl, S., et al. (2020) · Scientific Reports · doi:10.1038/s41598-020-60817-6 · Cited by 39
Deep Feature Extraction for Panoramic Image Stitching
Hoang, V.-D., Tran, D.-P., Nguyen, G. N., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-42058-1_12 · Cited by 39
HDR Reconstruction Based on the Polarization Camera
Wu, X., Zhang, H., Hu, X., Shakeri, M., Fan, C., & Ting, J. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3005379 · Cited by 39
“SURF [22], Harris corner [23] and FAST [24] detectors are chosen in our experiment.”
Learning the micro deformations by max-pooling for offline signature verification
Zheng, Y., Iwana, B. K., Malik, M. I., Ahmed, S., Ohyama, W., & Uchida, S. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108008 · Cited by 46
“In addition, the proposed method performs better than systems[11, 12, 35, 36, 37, 41, 42, 45] which apply the traditional hand-crafted or computer vision based features to feature extraction procedure.”
MethodDocument image classification: Progress over two decades
Liu, L., Wang, Z., Qiu, T., Chen, Q., Lu, Y., & Suen, C. Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.04.114 · Cited by 48
Color-SURF: A surf descriptor with local kernel color histograms
Fan, P., Men, A., Chen, M., & Yang, B. (2009) · IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC) · doi:10.1109/icnidc.2009.5360809 · Cited by 39
“Speeded-Up Robust Features (SURF) [2,3] is a novel scale- and rotation-invariant detector and descriptor.”
Graph commute times for image representation
Behmo, R., Nikos Paragios, A., & Prinet, V. (2008) · 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.2008.4587840 · Cited by 39
Efficient and secure encrypted image search in mobile cloud computing
Zou, Q., Wang, J., Ye, J., Shen, J., & Chen, X. (2016) · Soft Computing · doi:10.1007/s00500-016-2153-7 · Cited by 39
“2012) and scale-invariant feature transform (SURF) descriptors (Bay et al. 2006).”
BackgroundRecent Advances in Zero-shot RecognitionPreprint
Fu, Y., Xiang, T., Jiang, Y., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.04837 · Cited by 32
“SURF [179], local self-similarity histograms [180] and DeCaf [181].”
MethodRobust Features Extraction for On-board Monocular-based Spacecraft Pose Acquisition
Capuano, V., Alimo, S. R., Ho, A. Q., & Chung, S.-J. (2019) · AIAA Scitech 2019 Forum · doi:10.2514/6.2019-2005 · Cited by 39
Yoon, J., & Raychowdhury, A. (2020) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2020.3028298 · Cited by 47
Yamaguchi, T., & Mizutani, T. (2021) · Automation in Construction · doi:10.1016/j.autcon.2021.103651 · Cited by 42
Non-destructive system for in-wall moisture assessment of cultural heritage buildings
Muradov, M., Kot, P., Markiewicz, J. S., Łapiński, S., Tobiasz, A., Onisk, K., Shaw, A., Hashim, K., Zawieska, D., & Mohiuddin, G. (2022) · Measurement · doi:10.1016/j.measurement.2022.111930 · Cited by 46
Object Tracking Using Computer Vision: A Review
Kadam, P., Fang, G., & Zou, J. J. (2024) · Computers · doi:10.3390/computers13060136 · Cited by 64
Vision + X: A Survey on Multimodal Learning in the Light of Data
Zhu, Y., Wu, Y., Sebe, N., & Yan, Y. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3420239 · Cited by 80
“For example, the scale-invariant feature transform (SIFT) [156] and the histogram of oriented gradients (HOG) [54], and Speeded-Up Robust Feature (SURF) [17] are three examples of popular image feature descriptors largely used for computer vision and image processing.”
SURE: Surface Entropy for Distinctive 3D Features
Fiolka, T., Stückler, J., Klein, D. A., Schulz, D., & Behnke, S. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-32732-2_5 · Cited by 39
“SURF [1] sums Haar wavelet responses as a representation of the local gradient pattern.”
MethodLocal detectors and compact descriptors for visual search: A quantitative comparison
Bianco, S., Mazzini, D., Pau, D. P., & Schettini, R. (2015) · Digital Signal Processing · doi:10.1016/j.dsp.2015.06.001 · Cited by 37
“The other gray-levels algorithms that were considered are: the OpenCV SURF (Speeded-Up Robust Features) [14] implementation; the OpenCV FREAK (Fast Retina Keypoint) [15] implementation which uses SURF as the keypoint detector, and the KAZE [16] and A-KAZE [17] original code.”
MethodA new framework for on-line object tracking based on SURF
Miao, Q., Wang, G., Shi, C., Lin, X., & Ruan, Z. (2011) · Pattern Recognition Letters · doi:10.1016/j.patrec.2011.05.017 · Cited by 40
“…(1998), several approaches to scale-invariant interest point detection have been proposed, such as the detector based on Harris-Laplace and Hessian-Laplace by Mikolajczyk and Schmid (2001), Difference of Gaussians (DoG) in SIFT by Lowe (2004), and Hessians approximated in SURF by Bay et al. (2006).”
MethodEffective and scalable video copy detection
Liu, Z., Liu, T., Gibbon, D. C., & Shahraray, B. (2010) · Multimedia Information Retrieval · doi:10.1145/1743384.1743409 · Cited by 37
“More efficient versions of SIFT, including the SURF (Speeded Up Robust Features) features [14], are also considered in this work.”
MethodUnsupervised Classification of Structurally Similar Document Images
Kumar, J., & Doermann, D. (2013) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2013.248 · Cited by 47
“At the local level, a bag-ofvisual words based on SURF features [5] characterize content type.”
InfluentialWei, L., Cappelle, C., Ruichek, Y., & Zann, F. (2011) · International Journal of Vehicular Technology · doi:10.1155/2011/439074 · Cited by 47
“Therefore in this article, the SURF features [30] are extracted from left and right images, then matched by the descriptors.”
MethodA Novel Rate Control Framework for SIFT/SURF Feature Preservation in H.264/AVC Video Compression
Chao, J., Huitl, R., Steinbach, E. G., & Schroeder, D. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2367354 · Cited by 36
Recognition of Degraded Handwritten Characters Using Local Features
Diem, M., & Sablatnig, R. (2009) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2009.158 · Cited by 39
“[1] designed a new descriptor called Speeded Up Robust Features (SURF) for on-line application focusing on computational speed.”
BackgroundMethodScene Flow from Depth and Color Images
Letouzey, A., Petit, B., & Boyer, E. (2011) · British Machine Vision Conference (BMVC) · doi:10.5244/c.25.46 · Cited by 46
“For infinitesimal displacements, we can then write the following Normal Flow Equation [1] for all pixels in I t where the surface is visible: where the associated 3D displacement of a point in the scene is related to the motion of its projection by the 2 × 3 Jacobian matrix J Π ( p ) = ∂ p ∂ P .”
MethodMedical image registration based on SURF detector
Lukashevich, P., Zalesky, B. A., & Ablameyko, S. (2011) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661811020696 · Cited by 41
MANGO - Mobile Augmented Reality with Functional Eating Guidance and Food Awareness
Waltner, G., Schwarz, M. H., Ladstätter, S., Weber, A., Luley, P., Bischof, H., Lindschinger, M., Schmid, I., & Paletta, L. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23222-5_52 · Cited by 46
Patel, M. I., Thakar, V., & Shah, S. K. (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.07.224 · Cited by 40
Holder, C. J., Breckon, T. P., & Xiong, W. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46604-0_11 · Cited by 39
A novel advanced local binary pattern for image-based coral reef classification
Shakoor, M. H., & Boostani, R. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4394-6 · Cited by 38
A robust pointer meter reading recognition method for substation inspection robot
Gao, J., Xie, H., Zuo, L., et al. (2017) · International Conference on Robotics and Automation Sciences (ICRAS) · doi:10.1109/icras.2017.8071914 · Cited by 38
“Consequently, the subimage of the meter is extracted from the processed image via SURF algorithm [3].”
MethodInfluentialFull-Frame Scene Coordinate Regression for Image-Based Localization
Li, X., Ylioinas, J., & Kannala, J. (2018) · Robotics: Science and Systems · doi:10.15607/rss.2018.xiv.015 · Cited by 49
PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction
Shi, Y., Xu, K., Nießner, M., Rusinkiewicz, S. M., & Funkhouser, T. A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01237-3_46 · Cited by 43
“Example keypoint descriptors include SIFT [21], SURF [22], ORB [23], etc.”
MethodAfra, S., & Alhajj, R. (2019) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2019.123151 · Cited by 47
Sensors, SLAM and Long-term Autonomy: A Review
Zaffar, M., Ehsan, S., Stolkin, R., et al. (2018) · Open Access at Essex (University of Essex) · Cited by 38
Moretti, M., Rossi, A., & Senin, N. (2021) · Additive manufacturing · doi:10.1016/j.addma.2020.101817 · Cited by 40
Wu, B., Zhou, J., Yang, H., Huang, Z., Ji, X., Peng, D., Yin, Y., & Shen, X. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107096 · Cited by 44
Facial Age Estimation Through the Fusion of Texture and Local Appearance Descriptors
Huerta, I., Fernández, C., & Prati, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16181-5_51 · Cited by 36
Robust surface tracking combining features, intensity and illumination compensation
Du, X., Clancy, N. T., Arya, S., et al. (2015) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-015-1243-9 · Cited by 38
“In this study, we used the Speeded-Up Robust Features (SURF) descriptor [2] implemented in the OpenCV library [3] to obtain feature correspondences.”
MethodObject Recognition for the Internet of Things
Quack, T., Bay, H., & Gool, L. V. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-78731-0_15 · Cited by 46
“This choice was motivated by the fast computation times and competitive recognition performance shown in [6].”
BackgroundMethodInfluentialSelf-citationKoutsoudis, A., Ioannakis, G., Vidmar, B., Arnaoutoglou, F., & Chamzas, C. (2015) · Journal of Cultural Heritage · doi:10.1016/j.culher.2015.01.008 · Cited by 41
A Markerless Augmented Reality System for Mobile Devices
Ufkes, A., & Fiala, M. A. (2013) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2013.51 · Cited by 46
“[3] E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, "ORB: An efficient alternative to SIFT or SURF," in Computer Vision (ICCV), 2011 IEEE International Conference on, 2011, pp. 2564-2571.”
MethodInfluentialA real-time implementation of SIFT using GPU
Acharya, K., Babu, R. V., & Vadhiyar, S. S. (2018) · Journal of Real-Time Image Processing · doi:10.1007/s11554-014-0446-6 · Cited by 44
Fast pattern matching using orthogonal Haar transform
Ouyang, W., Zhang, R., & Cham, W.-K. (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.2010.5540058 · Cited by 38
“Rectangle sums and Haar-like features have been widely used for a lot of applications such as object detection [35, 37, 34, 41], object classification [21], pattern matching [26, 33, 30], feature point based image matching [7] and texture mapping [12].”
MethodBuilding 3D semantic maps for mobile robots using RGB-D camera
Zhao, Z., & Chen, X. (2016) · Intelligent Service Robotics · doi:10.1007/s11370-016-0201-x · Cited by 31
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.