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 4,701–4,800 of 14,752
Fast Full-Search-Equivalent Pattern Matching Using Asymmetric Haar Wavelet Packets
Ouyang, W., Zhao, T., Cham, W.-K., & Wei, L. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2629621 · Cited by 12
Concealed weapon detection from images using SIFT and SURF
Kaur, A., & Kaur, L. (2016) · Online International Conference on Green Engineering and Technologies · doi:10.1109/get.2016.7916679 · Cited by 12
“Therefore, in this paper, proposed algorithms overcome the limitation of SIFT [16] and SURF [17] by detecting multiple guns from single image.”
MethodTHE EFFECT OF IMAGE ENHANCEMENT METHODS DURING FEATURE DETECTION AND MATCHING OF THERMAL IMAGES
Akçay, Ö., & Avşar, E. Ö. (2017) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlii-1-w1-575-2017 · Cited by 11
“After image filtering, object features were detected using different parameters of two detection algorithms Maximally Stable Extremal Regions (MSER) and Speeded Up Robust Features (SURF) algorithms (Matas et al. 2002, Nister et al. 2008, Bay et al. 2008).”
MethodMinija, S. J., & Emmanuel, W. R. S. (2017) · The Imaging Science Journal · doi:10.1080/13682199.2017.1356610 · Cited by 12
“Here, the scale-invariant features transform (SIFT) [19] and speeded up robust features (SURF) [20] feature descriptors are used to detect the local feature information.”
MethodInostroza, F., Díaz, S., Cárdenas, J., Godoy, S. E., & Figueroa, M. E. (2017) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2017.09.006 · Cited by 12
“Other algorithms are based on image features, such as Scale Invariant Feature Transform (SIFT) [9,10] or Speeded-Up Robust Features (SURF) [11].”
MethodFlexible Stereo: Constrained, Non-Rigid, Wide-Baseline Stereo Vision for Fixed-Wing Aerial Platforms
Hinzmann, T., Taubner, T., & Siegwart, R. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8461085 · Cited by 13
Efficient Indoor Positioning with Visual Experiences via Lifelong Learning
Wen, H., Clark, R., Wang, S., Lu, C. X., Du, B., Hu, W. S., & Trigoni, N. (2018) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2018.2852645 · Cited by 12
An Image Processing Approach to Machine Fault Diagnosis Based on Visual Words Representation
Zhang, J., Wang, P. E., Gao, R. X., & Yan, R. (2018) · Procedia Manufacturing · doi:10.1016/j.promfg.2018.01.007 · Cited by 15
Real-time ball-position measurement using multi-view cameras for live football broadcast
Takahashi, M., Yokozawa, S., Mitsumine, H., & Mishina, T. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5694-1 · Cited by 12
A Human–Robot Collaborative System for Robust Three-Dimensional Mapping
Du, J., Sheng, W., & Liu, M. (2018) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2018.2854544 · Cited by 13
“Compared to traditional methods, we use the visual features [28] instead of the whole point set to ensure real-time processing and the motion information from the robot is utilized to improve the accuracy.”
MethodMulti-Scale Context Attention Network for Image Retrieval
Lou, Y., Bai, Y., Wang, S., & Duan, L. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240602 · Cited by 14
“Early image retrieval methods rely on handcrafted local features, such as SIFT [19], SURF [6], ORB [30], which are all equipped with the invariance properties in terms of scale and rotation to some extent.”
MethodAutomatic Panoramic UAV Image Mosaic Using ORB Features and Robust Transformation Estimation
Chen, J., Luo, L., Wang, S., et al. (2018) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2018.8483513 · Cited by 12
“First, we evaluate SIFT, SURF, and ORB to demonstrate the superiority of ORB, which achieves the highest performance and the shortest processing time.”
BackgroundMethodInfluentialBruno, P., Zaffino, P., Scaramuzzino, S., Rosa, S. D., Indolfi, C., Calimeri, F., & Spadea, M. F. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03840-3_5 · Cited by 13
The Study of Preprocessing and Postprocessing Techniques of Image Stitching
Vaidya, O., & Gandhe, S. T. (2018) · 2018 International Conference On Advances in Communication and Computing Technology (ICACCT) · doi:10.1109/icacct.2018.8529642 · Cited by 12
“COMPARISON OF FEATURE EXTRACTION ALGORITHM BASED ON QUANTITATIVE PARAMETERS [3], [11], [12], [14], [15]”
MethodA vague set approach for identifying shot transition in videos using multiple feature amalgamation
Bhaumik, H., Bhattacharyya, S., & Chakraborty, S. (2018) · Applied Soft Computing · doi:10.1016/j.asoc.2018.10.053 · Cited by 12
Motion Estimation Made Easy: Evolution and Trends in Visual Odometry
Poddar, S., Kottath, R., & Karar, V. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-03000-1_13 · Cited by 58
Robust UAV Visual Teach and Repeat Using Only Sparse Semantic Object Features
Toudeshki, A. G., Shamshirdar, F., & Vaughan, R. (2018) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2018.00034 · Cited by 19
FVGNN: A Novel GNN to Finger Vein Recognition from Limited Training Data
Li, J., & Fang, P. (2019) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic.2019.8785512 · Cited by 13
An Approach for Semantic Segmentation of Tree-like Vegetation
Digumarti, S. T., Schmid, L., Rizzi, G. M., Nieto, J. I., Siegwart, R., Beardsley, P. A., & Cadena, C. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793576 · Cited by 17
“Similarly camera pose estimation techniques that rely on correspondence matching [9], [10], [11] again fail due to the lack of distinctive salient points in these regions.”
BackgroundClosed Form Word Embedding Alignment
Dev, S., Hassan, S., & Phillips, J. M. (2019) · Knowledge and Information Systems · doi:10.1007/s10115-020-01531-7 · Cited by 16
Seamless 3D Surround View with a Novel Burger Model
Zhang, L., Chen, J., Liu, D., Shen, Y., & Zhao, S. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803453 · Cited by 12
“In our implementation, the SURF feature detector [10] serves as the feature detection algorithm.”
MethodBELID: Boosted Efficient Local Image Descriptor
Suárez, I., Sfeir, G., Buenaposada, J. M., & Baumela, L. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-31332-6_39 · Cited by 12
IoT Devices Recognition through Object Detection and Classification Techniques
Mavrogiorgou, A., Kiourtis, A., & Kyriazis, D. (2019) · World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4) · doi:10.1109/worlds4.2019.8903926 · Cited by 13
Nischwitz, A., Fischer, M., Haberäcker, P., et al. (2019) · Springer eBooks · doi:10.1007/978-3-658-28705-4 · Cited by 12
Big Map R-CNN for object detection in large-scale remote sensing images
Wang, L., Tao, D., Wang, R., Wang, R., & Li, H. (2019) · Mathematical Foundations of Computing · doi:10.3934/mfc.2019019 · Cited by 13
Rondao, D., Aouf, N., Richardson, M. A., & Dubois-Matra, O. (2020) · Acta Astronautica · doi:10.1016/j.actaastro.2020.03.049 · Cited by 12
“Descriptor Time [ms] Speed-up ORB 0.1627 103 BRISK 0.2057 81 SURF 0.7676 22 SIFT 9.4847 2 LIOP 14.5418 1 FREAK 16.7328 1 5.4.”
BackgroundMethodInfluentialWeakly supervised learning for image keypoint matching using graph convolutional networks
Pang, S., Du, A., Orgun, M. A., & Chen, H. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.105871 · Cited by 12
Training Data Extraction and Object Detection in Surveillance Scenario
Wilkowski, A., Stefańczyk, M., & Kasprzak, W. (2020) · Sensors · doi:10.3390/s20092689 · Cited by 14
Decorrelated Clustering with Data Selection Bias
Wang, X., Fan, S., Kuang, K., Shi, C., Liu, J., & Wang, B. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/301 · Cited by 14
Object Scale Selection of Hierarchical Image Segmentation Using Reliable Regions
Al‐Huda, Z., Peng, B., Yang, Y. Z., & Ahmed, M. (2019) · International Conference on Intelligent Systems and Knowledge Engineering (ISKE) · doi:10.1109/iske47853.2019.9170333 · Cited by 13
“Our work has investigated features based on size, location color, texture, and edge histograms, including color features (3), texture (65-features), SIF (64 features) [13], and SURF (64 features) [14] in each reliable region.”
Vokhmintcev, A., & Timchenko, M. (2020) · Acta Polytechnica Hungarica · doi:10.12700/aph.17.8.2020.8.7 · Cited by 12
“The most successful feature descriptors such as SIFT (Scale Invariant Feature Transform) [18] and SURF (Speeded-Up Robust Features) [19] are robust to scale and viewpoint changes.”
MethodModelling internal knot distribution using external log features
Zolotarev, F., Eerola, T., Lensu, L. T., et al. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105795 · Cited by 12
Recursive Block Based Keypoint Matching For Copy Move Image Forgery Detection
Narayanan, S. S., & Gopakumar, G. (2020) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt49239.2020.9225658 · Cited by 17
“The two important methods to find the keypoints of the images are Scale Invariant Feature Transform (SIFT) [25] and Speeded Up Robust Features(SURF) [26].”
MethodChu, T., Chen, Y., Huang, L., Xu, Z., & Tan, H. (2020) · Remote Sensing · doi:10.3390/rs12233978 · Cited by 13
“Street view image retrieval methods based on handcrafted local image features such as SIFT [10], SURF [11], and Hesa ff SIFT [12] are usually used in combination with descriptor aggregation methods such as bag-of-words (BoW) [13,14], Fisher vector (FV) [15] and vectors of locally aggregated descriptors (VLAD) [16].”
MethodFang, Y., Wang, K., Cheng, R., & Yang, K. (2020) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv47402.2020.9304612 · Cited by 11
“However, SIFT [24], SURF [28] local descriptors have demonstrated viewpoint invariance, but degrades the robustness on the appearance changing conditions.”
A low-dimensional binary-based descriptor for unknown satellite relative pose estimation
Huang, Y., Zhang, Z., Cui, H., & Zhang, L. (2021) · Acta Astronautica · doi:10.1016/j.actaastro.2021.01.050 · Cited by 14
Weber’s law based multi-level convolution correlation features for image retrieval
Yu, L., Liu, N., Zhou, W., Dong, S., Yu, F., & Abbas, K. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10355-0 · Cited by 12
Model-image registration of a building’s facade based on dense semantic segmentation
Fond, A., Berger, M., & Simon, G. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103185 · Cited by 14
“Unless an adaptive depth blur is applied to the synthetic image, which requires a tedious calibration of the camera response curve, feature points such as SIFT [11] or SURF [32], both based on approximations of Laplacian of Gaussian, prove more repeatable.”
Vision-based adjusting of a digital model to real-world conditions for wire insertion tasks
Hefner, F., Schmidbauer, S., & Franke, J. E. (2021) · Procedia CIRP · doi:10.1016/j.procir.2020.05.248 · Cited by 12
IMPROVING RANSAC FEATURE MATCHING BASED ON GEOMETRIC RELATION
Elashry, A., van der Sluis, B., & Toth, C. K. (2021) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xliii-b2-2021-321-2021 · Cited by 12
Loop Closure Detection based on Image Covariance Matrix Matching for Visual SLAM
Ying, T., Yan, H., Li, Z., Shi, K., & Feng, X. (2021) · International Journal of Control Automation and Systems · doi:10.1007/s12555-020-0730-0 · Cited by 12
“A large number of feature descriptors, such as scale invariant feature transform (SIFT) [17] and speeded up robust features (SURF) [18], are extracted from the training images and clustered.”
MethodFundus Image Registration Technique Based on Local Feature of Retinal Vessels
Ramli, R., Hasikin, K. B., Idris, M. Y. I., et al. (2021) · Applied Sciences · doi:10.3390/app112311201 · Cited by 12
Li, S., Lv, X., Ren, J., et al. (2022) · Remote Sensing · doi:10.3390/rs14030630 · Cited by 12
Qualitative Comparison of Image Stitching Algorithms for Multi-Camera Systems in Laparoscopy
Guy, S., Haberbusch, J.-L., Promayon, E., et al. (2022) · Journal of Imaging · doi:10.3390/jimaging8030052 · Cited by 12
Komuravelli, R., Sinclair, M. D., Alsop, J., et al. (2015) · ACM SIGARCH Computer Architecture News · doi:10.1145/2872887.2750374 · Cited by 12
Automatic compact camera module solder joint inspection method based on machine vision
Peng, Y., Yan, Y., Chen, G., & Feng, B. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/ac769a · Cited by 12
“…this paper are compared with those of the oriented FAST and rotated BRIEF (ORB)-based [22] and pyramid layer speed up robust feature (SURF)-based [23] matching methods, which show that the ORB-based matching method takes longer time and is less resistant to rotational interference, resulting in…”
Unsupervised Spiking Instance Segmentation on Event Data Using STDP Features
Kirkland, P., Manna, D. L., Vicente, Á., & Caterina, G. D. (2022) · IEEE Transactions on Computers · doi:10.1109/tc.2022.3191968 · Cited by 13
Plant Classification Using Firefly Algorithm and Support Vector Machine
Jovanović, L., Bačanin, N., Antonijević, M., et al. (2022) · IEEE Zooming Innovation in Consumer Technologies Conference (ZINC) · doi:10.1109/zinc55034.2022.9840579 · Cited by 12
GIFdroid: an automated light-weight tool for replaying visual bug reports
Feng, S., & Chen, C. (2022) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3510454.3516857 · Cited by 17
“GUI mapping: We adopted Precision@k and compared it with 10 mature image processing baselines, including pixel level (e.g, euclidean distance [17], color histogram [27], fingerprint [8]), and structural level (e.g., SSIM [28], SIFT [21], SURF [10], ORB [23]).”
MethodEffective and Efficient Image Copy Detection Based on GPU
Xie, H., Gao, K., Zhang, Y., Li, J., Liu, Y., & Ren, H. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35740-4_26 · Cited by 12
“In this paper we propose a novel scheme which combines two local features, Harris-Laplace (with SIFT descriptor) [5, 6] and SURF [7], to design an effective and efficient image copy detection system.”
BackgroundMethodInfluentialObject Detection by Keygraph Classification
Hashimoto, M., & Junior, R. M. C. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02124-4_23 · Cited by 12
SenseCam Image Localisation Using Hierarchical SURF Trees
Conaire, C. Ó., Blighe, M., & O'Connor, N. E. (2009) · Lecture notes in computer science · doi:10.1007/978-3-540-92892-8_4 · Cited by 12
“In a similar vein to SIFT and other interest point descriptors (many of which are evaluated in [10]), the recently proposed SURF method [6] locates interest points and extracts an invariant descriptor for each point.”
BackgroundMethodInfluentialTeleoperated Visual Inspection and Surveillance with Unmanned Ground and Aerial Vehicles
Surmann, H., Holz, D., Blumental, S., Linder, T., Molitor, P., & Tretyakov, V. (2008) · International Journal of Online Engineering (iJOE) · doi:10.3991/ijoe.v4i4.699 · Cited by 13
Maier, D., & Bennewitz, M. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386098 · Cited by 12
Pure reactive behavior learning using Case Based Reasoning for a vision based 4-legged robot
Peula, J. M., Urdiales, C., Herrero, I., Sánchez-Tato, I., & Sandoval, F. (2008) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.11.003 · Cited by 14
Nguyen, V. A., Starzyk, J. A., & Goh, W.-B. (2013) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2012.12.004 · Cited by 12
Scale-invariant corner keypoints
Li, B., Li, H., & Söderström, U. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7026161 · Cited by 13
Investigations of Ubicomp in the oil and gas industry
Heyer, C. (2010) · doi:10.1145/1864349.1864360 · Cited by 12
“Object recognition and tracking utilises the SURF algorithm [1] and is currently able to track objects at approximately five frames per second.”
Robust Object Recognition Using Wide Baseline Matching for RoboCup Applications
Loncomilla, P., & Ruíz-del-Solar, J. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-68847-1_46 · Cited by 13
“We are working in this direction using some novel features that can be evaluated in less time, as for example SURF features [16].”
BackgroundMethodHierarchical Latent Dirichlet Allocation models for realistic action recognition
Li, H., Liu, J., & Zhang, S. (2011) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2011.5946649 · Cited by 12
A reduced-reference metric based on the interest points in color images
Nauge, M., Larabi, M., & Fernández-Maloigne, C. (2010) · Picture Coding Symposium · doi:10.1109/pcs.2010.5702578 · Cited by 12
Object-based tag propagation for semi-automatic annotation of images
Ivanov, I., Vajda, P., Lutz Goldmann, A., Lee, J., & Ebrahimi, T. (2010) · Multimedia Information Retrieval · doi:10.1145/1743384.1743471 · Cited by 13
Online video mosaicing through SLAM for ROVs
Caccia, M., Bruzzone, G., Ferreira, F., et al. (2009) · doi:10.1109/oceanse.2009.5278217 · Cited by 12
“In particular, the use of Speeded Up Robust Features (SURF) [8] provided very interesting results.”
MethodDETERMINATION OF UAS TRAJECTORY IN A KNOWN ENVIRONMENT FROM FPV VIDEO
Li-Chee-Ming, J., & Armenakis, C. (2013) · 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-xl-1-w2-247-2013 · Cited by 12
Outlet detection and pose estimation for robot continuous operation
Eruhimov, V., & Meeussen, W. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094910 · Cited by 13
Rapid image retrieval for mobile location recognition
Schroth, G., Al-Nuaimi, A., Huitl, R., et al. (2011) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2011.5946947 · Cited by 12
Path tracking by a mobile robot equipped with only a downward facing camera
Nagai, I., & Watanabe, K. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354239 · Cited by 12
GraphFlow – 6D Large Displacement Scene Flow via Graph Matching
Alhaija, H. A., Sellent, A., Kondermann, D., & Rother, C. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24947-6_23 · Cited by 14
Joint Measurement and Trajectory Recovery in Visible Light Communication
Zheng, D., Chen, G., & Farrell, J. A. (2016) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2016.2554062 · Cited by 15
“D image measurements, various feature detectors and descriptors, including corner (Förstner [15], Harris and Pike [19], Moravec [34], FAST [41], Shi and Tomasi [42]) and blob detectors (CENSURE [2], SURF [7], SIFT [31]), have been developed to find and describe features in images.”
BackgroundKognitive Automobile - Neue Konzepte und Ideen des Sonderforschungsbereiches TR-28
Thuy, M., Althoff, M., BUSS, M. J., Diepold, K. J., Eberspaecher, J., Faerber, G., Goebl, M., Heißing, B., Kraus, S., Nagel, R., et al. (2008) · mediaTUM (Technical University of Munich) · Cited by 14
A comparison of monocular and stereo visual FastSLAM implementations
Giubilato, R., Pertile, M., & Debei, S. (2016) · IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace) · doi:10.1109/metroaerospace.2016.7573217 · Cited by 14
A brief survey of visual odometry for micro aerial vehicles
Shan, M., Bi, Y., Qin, H., Li, J., Gao, Z. Y., Lin, F., & Chen, B. M. (2016) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2016.7793198 · Cited by 18
A stereo and rotating laser framework for UAV navigation in GPS denied environment
Qin, H., Bi, Y., Ang, K. Z. Y., et al. (2016) · Proceedings of the Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon.2016.7793246 · Cited by 12
HOOFR: An enhanced bio-inspired feature extractor
Nguyen, D. D., Elouardi, A., Aldea, E., & Bouaziz, S. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7900090 · Cited by 16
“An alternative named Speed Up Robust Feature (SURF) was proposed in [4].”
MethodApplication‐Specific Tone Mapping Via Genetic Programming
Debattista, K. (2017) · Computer Graphics Forum · doi:10.1111/cgf.13307 · Cited by 14
Uncertainty Model for Template Feature Matching
Zhang, H., Grießbach, D., Wohlfeil, J., & Börner, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-75786-5_33 · Cited by 15
Markiewicz, J. S., & Zawieska, D. (2019) · Applied Sciences · doi:10.3390/app9030509 · Cited by 12
“This reduces the computational complexity [28,29].”
Resource Constrained Multimedia Event Detection
Lan, Z., Yang, Y., Ballas, N., Yu, S.-I., & Haputmann, A. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-04114-8_33 · Cited by 12
Unconstrained Ear Processing: What is Possible and What Must Be Done
Barra, S., Marsico, M. D., Nappi, M., & Riccio, D. (2014) · Lecture notes in electrical engineering · doi:10.1007/978-3-642-54080-6_6 · Cited by 14
“Speeded-Up Robust Features (SURF) [15], which is deemed able to minimize the effect of pose variations and poor image registration.”
BackgroundMosaicing of endoscopic placenta images
Reeff, M. (2011) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-a-006393305 · Cited by 11
Intrinsic statistical techniques for robust pose estimation
Dubbelman, G. (2011) · UvA-DARE (University of Amsterdam) · Cited by 12
Vision-based Pose Estimation for Augmented Reality : A Comparison StudyPreprint
Belghit, H., Bellarbi, A., Zenati, N., & Otmane, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.09316 · Cited by 28
6-PACK: Category-level 6D Pose Tracker with Anchor-Based KeypointsPreprint
Wang, C., Martín-Martín, R., Xu, D., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.10750 · Cited by 12
“Classical methods detect and match keypoints based on handdesigned local features [4, 7, 30, 37, 38].”
MethodLevy, J., Jackson, C. R., Sriharan, A., Christensen, B. C., & Vaickus, L. J. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.01.07.897801 · Cited by 22
“Regardless, we plan to investigate more robust measures of tissue similarity between ground truth and predicted stains (e.g. correspondence in circular objects detected using SURF and SIFT features) (Bay et al., 2006; Lowe, 2004).”
MethodMoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric FusionPreprint
Wada, K., Sucar, E., James, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.04336 · Cited by 12
Frequency learning for image classification
Stuchi, J. A., Boccato, L., & Attux, R. (2020) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · doi:10.48550/arxiv.2006.15476 · Cited by 19
LiDAR Odometry Methodologies for Autonomous Driving: A SurveyPreprint
Jonnavithula, N., Lyu, Y., & Zhang, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.06120 · Cited by 36
“as SIFT [17], SURF [18], ORB [19], or even networks like DCP [20].”
MethodCorrespondence consensus of two sets of correspondences through optimisation functions
Moreno‐García, C. F., & Serratosa, F. (2015) · Pattern Analysis and Applications · doi:10.1007/s10044-015-0486-y · Cited by 12
Shape grammar parsing : application to image-based modeling
Teboul, O. (2011) · theses.fr (ABES) · doi:10.70675/36465d8bz8269z49e7z8f85zedde7e6d6011 · Cited by 16
Zumaya, C. C., Catalano, I., & Queralta, J. P. (2024) · Remote Sensing · doi:10.3390/rs16162974 · Cited by 11
Comparative analysis of Machine Learning approaches for early stage Cervical Spondylosis detection
Sreeraj, M., Joy, J., Jose, M., Varghese, M., & Rejoice, T. J. (2020) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2020.08.010 · Cited by 15
Mejia-Zuluaga, P. A., Dozal, L., & Valdiviezo-N., J. C. (2022) · Remote Sensing · doi:10.3390/rs14030801 · Cited by 10
“Image Registration The registration of the spectral bands was implemented through the Speeded up Robust Features (SURF) algorithm [30], which is designed as a detector and descriptor of local characteristics using box filters for handling scales.”
MethodMSANet: Multi-scale attention networks for image classification
Cao, P., Xie, F., Zhang, S., Zhang, Z., & Zhang, J. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12792-5 · Cited by 13
“For decades, the common methods used for feature extraction include Scale Invariant Feature Transform (SIFT) [33], Histogram of Oriented Gradient (HOG) [14], Local Binary Patterns (LBP) [36], Speed Up Robust Feature (SURF) [7], etc.”
MethodRong, F., Xie, D., Zhu, W. P., et al. (2021) · International Conference on Networking Systems of AI (INSAI) · doi:10.1109/insai54028.2021.00033 · Cited by 11
Li, F., Lu, D., Lu, C., & Jiang, Q. (2022) · Mathematical Problems in Engineering · doi:10.1155/2022/8330985 · Cited by 13
Sui, H., Li, J., Lei, J., Liu, C., & Gou, G. (2022) · Remote Sensing · doi:10.3390/rs14225879 · Cited by 18
From Coarse to Fine: Two-Stage Indoor Localization with Multisensor Fusion
Zhang, L., Bao, J., Xu, Y., Wang, Q., Xu, J., & Li, D. (2022) · Tsinghua Science & Technology · doi:10.26599/tst.2022.9010029 · Cited by 14
A computer vision-based IoT data ingestion architecture supporting data prioritization
Kiourtis, A., Mavrogiorgou, A., & Kyriazis, D. (2023) · Health and Technology · doi:10.1007/s12553-023-00748-0 · Cited by 12
“Thus, the Open Computer Vision (OpenCV) [37] library is being used to identify resemblances among the devices’ images through the Speeded-up Robust Features (SURF) method [38], to finally detect the features and unique characteristics of the input image (i.”
MethodDeep Learning-Based Portable Image Analysis System for Real-Time Detection of Vespa velutina
Jeon, M.-S., Jeong, Y., Lee, J.-S., et al. (2023) · Applied Sciences · doi:10.3390/app13137414 · Cited by 11
Learning Transformation-Predictive Representations for Detection and Description of Local Features
Wang, Z., Wu, C., Yang, Y., & Li, Z. (2023) · 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/cvpr52729.2023.01103 · Cited by 12
“Different from early hand-crafted key-points, e.g. , SIFT[27] and SURF [3], the recent effort has been put into learning key-points through the deep neural networks.”
Method
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.