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 1,701–1,800 of 14,752
UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering
Banani, M. E., Gao, L., & Johnson, J. (2021) · 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/cvpr46437.2021.00705 · Cited by 68
ExtriDeNet: an intensive feature extrication deep network for hand gesture recognition
Bhaumik, G., Verma, M., Govil, M. C., & Vipparthi, S. K. (2021) · The Visual Computer · doi:10.1007/s00371-021-02225-z · Cited by 47
“The traditional approaches for handcrafted features extraction include SURF [1], SIFT [2], EXTRA [3], XKin [4], etc.”
MethodShahzad, A., Raza, M., Shah, J. H., Sharif, M. I., & Nayak, R. S. (2021) · Complex & Intelligent Systems · doi:10.1007/s40747-021-00564-x · Cited by 50
Self-Supervised Equivariant Learning for Oriented Keypoint Detection
Lee, J., Kim, B., & Cho, M. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00480 · Cited by 64
“The keypoint loss uses the window sizes Nl ∈ [8, 16, 24, 32, 40] with λl ∈ [256, 64, 16, 4, 1] same as [3], and the loss balancing parameter β is 100.”
BackgroundMethodPVNet: Pixel-wise Voting Network for 6DoF Pose EstimationPreprint
Peng, S., Liu, Y., Huang, Q., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.11788 · Cited by 43
“For objects of rich textures, traditional methods [24, 32, 1] detect local keypoints robustly, so the object pose is estimated both efficiently and accurately, even under cluttered scenes and severe occlusions.”
MethodAnalysis of Skin Marks Through the Use of Intelligent Things
Połap, D. (2019) · IEEE Access · doi:10.1109/access.2019.2947354 · Cited by 46
Single-view robot pose and joint angle estimation via render & compare
Labbé, Y., Carpentier, J., Aubry, M., & Šivic, J. (2021) · 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/cvpr46437.2021.00170 · Cited by 77
SEAR: Scaling Experiences in Multi-user Augmented Reality
Zhang, W., Han, B., & Hui, P. (2022) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3150467 · Cited by 48
Feature Matching via Motion-Consistency Driven Probabilistic Graphical Model
Ma, J., Fan, A., Jiang, X., & Xiao, G. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01644-2 · Cited by 42
“The matching images are of different modalities, and we use SURF (Bay et al., 2006) to construct putative correspondences.”
MethodInfluentialRobust Texture-Aware Local Adaptive Image Watermarking With Perceptual Guarantee
Huang, Y., Guan, H., Liu, J., Zhang, S., Niu, B., & Zhang, G. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3245650 · Cited by 47
Deep Learning on Image Stitching With Multi-viewpoint Images: A Survey
Yan, N., Mei, Y., Xu, L., Yu, H., Sun, B., Wang, Z., & Chen, Y. (2023) · Neural Processing Letters · doi:10.1007/s11063-023-11226-z · Cited by 40
Pishhesari, A. K., Moniri-Morad, A., & Sattarvand, J. (2024) · Technologies · doi:10.3390/technologies12030040 · Cited by 49
“Surf generates vectors using Haar-wavelet responses [78].”
Dusha, D., & Mejías, L. (2012) · The International Journal of Robotics Research · doi:10.1177/0278364911433777 · Cited by 42
Active Classification: Theory and Application to Underwater Inspection
Hollinger, G. A., Mitra, U., & Sukhatme, G. S. (2016) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-29363-9_6 · Cited by 42
Combining Geometric and Appearance Priors for Robust Homography Estimation
Serradell, E., Özuysal, M., Lepetit, V., Fua, P., & Moreno-Noguer, F. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15558-1_5 · Cited by 41
“However, our approach can use other state-of-the-art keypoint descriptors such as SIFT [19] or SURF [20], provided that we can assign a similarity score to each hypothetical correspondence.”
MethodReal time object scanning using a mobile phone and cloud-based visual search engine
Zhong, Y., Garrigues, P. J., & Bigham, J. P. (2013) · Proceedings of the 15th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/2513383.2513443 · Cited by 42
BRAND: A robust appearance and depth descriptor for RGB-D images
Nascimento, E. R., Oliveira, G. L., Campos, M. F. M., Vieira, A. W., & Schwartz, W. R. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385693 · Cited by 46
Automated map generation from aerial images for precise vehicle localization
Pink, O., & Stiller, C. (2010) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2010.5625276 · Cited by 42
Combining Local Features for Offline Writer Identification
Jain, R., & Doermann, D. (2014) · International Conference on Frontiers in Handwriting Recognition · doi:10.1109/icfhr.2014.103 · Cited by 52
“For each interest point, a 64-dimensional SURF feature vector is extracted by splitting the patch into a 4x4 grid and extracting (∑Dx, ∑Dy, ∑ |Dx|, ∑|Dy|), where Dx and Dy are the Haar wavelet response in the x and y directions.”
MethodInfluentialProbabilistic place recognition with covisibility maps
Stumm, E., Mei, C., & Lacroix, S. (2013) · 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2013.6696952 · Cited by 42
Hough Voting for 3D Object Recognition under Occlusion and Clutter
Tombari, F., & Stefano, L. D. (2012) · IPSJ Transactions on Computer Vision and Applications · doi:10.2197/ipsjtcva.4.20 · Cited by 47
A Compressive Sensing Approach to Describe Indoor Scenes for Blind People
Mekhalfi, M. L., Melgani, F., Bazi, Y., & Alajlan, N. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2372371 · Cited by 42
Cross-spectral visual simultaneous localization and mapping (SLAM) with sensor handover
Magnabosco, M., & Breckon, T. P. (2012) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2012.09.023 · Cited by 41
Ma, R., Chen, J., & Su, Z. (2010) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1816041.1816076 · Cited by 42
“SURF: Speeded up robust features.”
BackgroundMethodInfluentialFinding the Best Feature Detector-Descriptor Combination
Dahl, A. L., Aanæs, H., & Pedersen, K. S. (2011) · International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission · doi:10.1109/3dimpvt.2011.47 · Cited by 47
Song, Z. L., & Zhang, J. (2010) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2009.2039917 · Cited by 42
“Among them, the scale-invariant feature transform (SIFT) algorithm is to detect, describe, and match such local features [6].”
MethodInfluentialGeneralized Unsupervised Manifold Alignment
Cui, Z. (2016) · Cited by 58
Cross-Indexing of Binary SIFT Codes for Large-Scale Image Search
Liu, Z., Li, H., Zhang, L., et al. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2312283 · Cited by 42
“Some commonly used descriptors include SIFT, SURF [5], [27] and some recently developed descriptors [28]–[30].”
N3M: Natural 3D Markers for Real-Time Object Detection and Pose Estimation
Hinterstoißer, S., Benhimane, S., & Navab, N. (2007) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2007.4409004 · Cited by 42
Regularized local metric learning for person re-identification
Liong, V. E., Lu, J., & Ge, Y. (2015) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.05.001 · Cited by 42
Rapid building detection using machine learning
Cohen, J., Ding, W., Kuhlman, C., Chen, A., & Di, L. (2016) · Applied Intelligence · doi:10.1007/s10489-016-0762-6 · Cited by 46
Multiplier-Less Stream Processor for 2D Filtering in Visual Search Applications
Licciardo, G. D., Cappetta, C., Benedetto, L. D., et al. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2603068 · Cited by 42
“However, for the fulfillment of severe constrains, HW implementations also need a number of simplifications that give rise to less complex alternatives to Gaussian filtering [9], [10].”
BackgroundResultOn Realistic Target Coverage by Autonomous Drones
Saeed, A., Abdelkader, A., Khan, M., Neishaboori, A., Harras, K. A., & Mohamed, A. M. S. (2019) · ACM Transactions on Sensor Networks · doi:10.1145/3325512 · Cited by 44
“2008a), the accuracy of object matching and point matching between two images drop significantly for rotations larger than 45◦ (Bay et al. 2006).”
BackgroundInfluentialA brief review of the application of machine vision in livestock behaviour analysis
Banhazi, T. M., & Tscharke, M. (2016) · Journal of Agricultural Informatics · doi:10.17700/jai.2016.7.1.279 · Cited by 50
“Spatial scale can be handled using rotation and scale invariant techniques such as ‘Scale Invariant Feature Transform’ (SIFT) and ‘Speed-up Robust Features’ (SURF) (Lowe, 2004; Lowe, 1999; Bay et al., 2006). doi: 10.17700/jai.2016.7.1.279 31 Matthew Tscharke, Thomas M. Banhazi: A brief review of the application of mac…”
MethodInfluentialMULTISPECTRAL IMAGING IN CULTURAL HERITAGE CONSERVATION
Pozo, S. D., Rodríguez‐Gonzálvez, P., Sánchez-Aparicio, L. J., et al. (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-2-w5-155-2017 · Cited by 42
“158 points and tie-points of unknown position measured automatically in the images by SIFT (Scale-Invariant Feature Transform, Lowe, 1999) or SURF (Speeded Up Robust Features, Bay et al., 2006) algorithms.”
MethodKernelized Subspace Pooling for Deep Local Descriptors
Wei, X., Zhang, Y., Gong, Y., & Zheng, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00200 · Cited by 40
“[23, 5, 8, 35, 28, 39], while more recent works adopted machine learning methods to learn high-quality feature descriptors from large image datasets [6, 36, 33, 10, 31, 4].”
BackgroundMethodKestrel: Video Analytics for Augmented Multi-Camera Vehicle Tracking
Qiu, H., Liu, X., Rallapalli, S., Bency, A. J., Chan, K., Urgaonkar, R., Manjunath, B. S., & Govindan, R. (2018) · IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi.2018.00015 · Cited by 49
Application of Artificial Intelligence in Capsule Endoscopy: Where Are We Now?
Hwang, Y., Park, J., Lim, Y. J., & Chun, H. J. (2018) · Clinical Endoscopy · doi:10.5946/ce.2018.173 · Cited by 43
Thai, V.-P., Zhong, W., Pham, T. H., et al. (2019) · Integrated Communications, Navigation and Surveillance Conference (ICNS) · doi:10.1109/icnsurv.2019.8735240 · Cited by 42
“Spatial-based features such as SIFT [25], SURF [26], HOG [27] or even ConvNet [28] face difficulty in classifying objects when their pixel dimensions are too small.”
BackgroundVein Biometric Recognition on a Smartphone
Garcia-Martin, R., & Sánchez-Reillo, R. (2020) · IEEE Access · doi:10.1109/access.2020.3000044 · Cited by 42
LodoNet: A Deep Neural Network with 2D Keypoint Matching for 3D LiDAR Odometry Estimation
Zheng, C., Lyu, Y., Li, M., & Zhang, Z. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413771 · Cited by 64
“Other feature extraction methods include SURF [2] and ORB [24], however, they cannot generate robust feature vectors on LiDAR frames.”
MethodUAV-Based Heating Requirement Determination for Frost Management in Apple Orchard
Yuan, W., & Choi, D. D. (2021) · Remote Sensing · doi:10.3390/rs13020273 · Cited by 48
Połap, D., Włodarczyk-Sielicka, M., & Wawrzyniak, N. (2021) · ISA Transactions · doi:10.1016/j.isatra.2021.04.003 · Cited by 42
Automatic Object Tracking and Segmentation Using Unsupervised SiamMask
Noor, S., Waqas, M., Saleem, M. I., & Minhas, H. N. (2021) · IEEE Access · doi:10.1109/access.2021.3101054 · Cited by 51
Dynamic Image-to-Class Warping for Occluded Face Recognition
Wei, X., Li, C., Lei, Z., Yi, D., & Li, S. Z. (2014) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2014.2359632 · Cited by 42
Transforming 3D Coloured Pixels into Musical Instrument Notes for Vision Substitution Applications
Bologna, G., Deville, B., Pun, T., & Vinckenbosch, M. (2007) · EURASIP Journal on Image and Video Processing · doi:10.1155/2007/76204 · Cited by 42
Compact and Discriminative Descriptor Inference Using Multi-Cues
Han, Y., Yang, Y., Wu, F. Q., & Hong, R. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2479917 · Cited by 41
Cross-Domain Object Recognition Via Input-Output Kernel Analysis
Guo, Z., & Wang, Z. J. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2259836 · Cited by 40
A Coding Framework and Benchmark Towards Low-Bitrate Video Understanding
Tian, Y., Lu, G. S., Yan, Y., Zhai, G., Chen, L., & Gao, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3367879 · Cited by 66
“In addition to AI models, there are also many applications relying on traditional interest points detection algorithms such as SIFT [15] and SURF [16].”
MethodADRNet: Affine and Deformable Registration Networks for Multimodal Remote Sensing Images
Xiao, Y., Zhang, C., Chen, Y., Jiang, B., & Tang, J. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3373568 · Cited by 65
“Specifically, feature-based methods, such as SIFT [2], SURF [3], ORB [4], detect and match feature points in two images to estimate the geometric transformation parameters (TPs) between different images.”
MethodSuperpixel-Based Interest Points for Effective Bags of Visual Words Medical Image Retrieval
Haas, S., Donner, R., Burner, A., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-28460-1_6 · Cited by 41
“, SIFT [8], or derivatives such as SURF [4]) are insensitive to small perturbations in the interest points, fine-grained, repetitive structures like those encountered in microscopic images [2] or lung CTs [6] prove difficult for repeatable interest point identification.”
BackgroundNovel Method of Monocular Real-Time Feature Point Tracking for Tethered Space Robots
Huang, P., Cai, J., Meng, Z., Hu, Z., & Wang, D. (2013) · Journal of Aerospace Engineering · doi:10.1061/(asce)as.1943-5525.0000367 · Cited by 42
Co-Segmentation Guided Hough Transform for Robust Feature Matching
Chen, H., Lin, Y., & Chen, B. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2420556 · Cited by 41
A new global alignment approach for underwater optical mapping
Elibol, A., García, R., & Gracias, N. (2011) · Ocean Engineering · doi:10.1016/j.oceaneng.2011.05.013 · Cited by 41
Envisor: Online Environment Map Construction for Mixed Reality
DiVerdi, S., Wither, J., & Höllerer, T. (2008) · Proceedings of the IEEE Virtual Reality Annual International Symposium · doi:10.1109/vr.2008.4480745 · Cited by 41
Place recognition using straight lines for vision-based SLAM
Lee, J. H., Zhang, G., Lim, J., & Suh, I. H. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631111 · Cited by 41
Large-Scale Image Phylogeny: Tracing Image Ancestral Relationships
Dias, Z., Goldenstein, S., & Rocha, A. (2013) · IEEE MultiMedia · doi:10.1109/mmul.2013.17 · Cited by 41
Implementation and optimization of image processing algorithms on handheld GPU
Singhal, N., Park, I. K., & Cho, S. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5651740 · Cited by 41
Object Localization with Global and Local Context Kernels
Blaschko, M. B., & Lampert, C. H. (2009) · British Machine Vision Conference (BMVC) · doi:10.5244/c.23.63 · Cited by 41
Rapid multimodality registration based on MM-SURF
Zhao, D., Yang, Y., Ji, Z., & Hu, X. (2013) · Neurocomputing · doi:10.1016/j.neucom.2013.10.037 · Cited by 43
Efficient and accurate face detection using heterogeneous feature descriptors and feature selection
Pan, H., Zhu, Y., & Xia, L. (2012) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2012.09.003 · Cited by 42
“and SURF [34,35] have been successfully used in generic object detection and recognition.”
BackgroundMethodComparison of local feature descriptors for mobile visual search
Chandrasekhar, V., Chen, D. M., Lin, A., Gabriel Takacs, A., Tsai, S. S., Cheung, N. M., Reznik, Y. A., Grzeszczuk, R., & Girod, B. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5649937 · Cited by 41
Long, T., Jiao, W., He, G., & Wang, W. (2013) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2013.2273871 · Cited by 43
Towards appearance-based methods for lidar sensors
McManus, C., Furgale, P., & Barfoot, T. D. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980098 · Cited by 44
AERIAL IMAGES FROM AN UAV SYSTEM: 3D MODELING AND TREE SPECIES CLASSIFICATION IN A PARK AREA
Gini, R., Passoni, D., Pinto, L., et al. (2012) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsarchives-xxxix-b1-361-2012 · Cited by 41
“…by EyeDEA, software developed by the DICATeA department of University of Parma (Roncella et al., 2011a, 2011b) and based on SURF feature descriptor (Bay et al., 2008, Fischler et al.,1981); 2) 181 TPs manually selected, modified (if needed) and verified on the Wallis-filtered images: they derived…”
MethodA novel system for object pose estimation using fused vision and inertial data
Li, J., Besada, J. A., Bernardos, A. M., Tarrío, P., & Casar, J. R. (2016) · Information Fusion · doi:10.1016/j.inffus.2016.04.006 · Cited by 44
“Many robust local descriptors including SIFT (Scale-Invariant Feature Transform) [33] and SURF (Speeded-Up Robust Features) [34] are stable under different view points and lighting conditions and can be used to detect features existing in the scenes to build a markerless method.”
BackgroundRobust single-view instance recognition
Held, D., Thrun, S., & Savarese, S. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487365 · Cited by 41
“However, the performance drops off quickly as the angular difference between the training and test 1.9 3.5 1.3 SURF [8] 3.4 5.3 2.6 BOLD [39] 5.2 5.9 4.9 SIFT [7] 6.3 12.6 3.9 Line-2D [14] 5.5 0.3 7.4 Color Histogram Intersection [40] 12.4 23.3 8.2 HMP (Depth) [5] 33.0 37.7 31.2 HMP (RGB) [5] 42.3…”
BackgroundInfluentialA non-cooperative target grasping position prediction model for tethered space robot
Chen, L., Huang, P., Cai, J., Meng, Z., & Liu, Z. (2016) · Aerospace Science and Technology · doi:10.1016/j.ast.2016.09.009 · Cited by 41
Sufficient Image Appearance Transfer Combining Color and Texture
Song, Z., & Liu, S. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2631123 · Cited by 40
“Otherwise, SIFT [29] and SURF [30] are good at solving image-scaling problem, but their extractions of feature points are not stable.”
BackgroundMarani, R., Palumbo, D., Galietti, U., et al. (2016) · IEEE International Conference on Intelligent Systems · doi:10.1109/is.2016.7737471 · Cited by 41
Real-time pedestrian crossing lights detection algorithm for the visually impaired
Cheng, R., Wang, K., Yang, K., Long, N., Bai, J. Y., & Liu, D. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5472-5 · Cited by 44
Reliable Multi-View Clustering
Tao, H., Hou, C., Liu, X., Liu, T., Yi, D., & Zhu, J. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11621 · Cited by 45
Firuzi, K., Vakilian, M., Darabad, V. P., et al. (2017) · IEEE Transactions on Dielectrics and Electrical Insulation · doi:10.1109/tdei.2017.006758 · Cited by 41
Real-time 3D Traffic Cone Detection for Autonomous Driving
Dhall, A., Dai, D., & Gool, L. V. (2019) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2019.8814089 · Cited by 52
Self-citationDiatom identification including life cycle stages through morphological and texture descriptors
Sánchez, C., Cristóbal, G., & Bueno, G. (2019) · PeerJ · doi:10.7717/peerj.6770 · Cited by 48
“We did 167 some experiments with SURF features (Bay et al., 2006) but the results did not improve the final 168 performance.”
MethodUnsupervised feature learning with C-SVDDNet
Wang, D., & Tan, X. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.06.001 · Cited by 48
Woźniak, M., & Połap, D. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2951089 · Cited by 45
“We find key-points using the speeded up robust features (SURF) algorithm [18].”
MethodRecognition of Indian Sign Language Using ORB with Bag of Visual Words by Kinect Sensor
Gangrade, J., Bharti, J., & Mulye, A. (2020) · IETE Journal of Research · doi:10.1080/03772063.2020.1739569 · Cited by 44
“Speed Up Robust Features (SURF) another scale and rotation invariant method, which gives similar key points like SIFT [39].”
MethodMulti-view Optimization of Local Feature Geometry
Dusmanu, M., Schönberger, J. L., & Pollefeys, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58452-8_39 · Cited by 49
Predicting human complexity perception of real-world scenes
Nagle, F., & Lavie, N. (2020) · Royal Society Open Science · doi:10.1098/rsos.191487 · Cited by 42
Spatio-temporal visual attention modelling of standard biometry plane-finding navigation
Cai, Y., Droste, R., Sharma, H., Chatelain, P., Drukker, L., Papageorghiou, A. T., & Noble, J. A. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101762 · Cited by 41
Choi, J., & Myung, H. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341682 · Cited by 60
S2DNet: Learning Image Features for Accurate Sparse-to-Dense Matching
Germain, H., Bourmaud, G., & Lepetit, V. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58580-8_37 · Cited by 83
“For feature description, methods using histograms of local gradients [7, 10,27,39] or learning-based patch description [4, 11,34,58,59,65] have been widely used.”
MethodUsing Machine Learning to Develop a Fully Automated Soybean Nodule Acquisition Pipeline (SNAP)
Jubery, T. Z., Carley, C. N., Singh, A., Sarkar, S., Ganapathysubramanian, B., & Singh, A. K. (2021) · Plant Phenomics · doi:10.34133/2021/9834746 · Cited by 44
“Our earlier iterations to approach this problem included segmentation and detection using classical SURF and SIFT methods [65] and a deep learning-based Faster-RCNN approach [66].”
Multisource Heterogeneous Domain Adaptation With Conditional Weighting Adversarial Network
Yao, Y., Li, X., Zhang, Y., & Ye, Y. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3105868 · Cited by 47
“To avoid such leakage, a possible solution is to utilize various preprocessed features (e.g., SURF [20], DeCAF 6 [21], and ResNet 50 [22]) provided by different participants rather than the raw samples (e.g., photographs) for training.”
MethodRobust feature matching via neighborhood manifold representation consensus
Ma, J., Li, Z., Zhang, K., Shao, Z., & Xiao, G. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.11.004 · Cited by 42
Hauswald, J., Laurenzano, M. A., Zhang, Y., Li, C., Rovinski, A., Khurana, A., Dreslinski, R., Mudge, T., Petrucci, V., Tang, L., et al. (2015) · ACM SIGPLAN Notices · doi:10.1145/2775054.2694347 · Cited by 46
Integrity of Visual Navigation—Developments, Challenges, and Prospects
Zhu, C., Meurer, M., & Günther, C. G. (2022) · NAVIGATION Journal of the Institute of Navigation · doi:10.33012/navi.518 · Cited by 47
Object detection and tracking for autonomous underwater robots using weighted template matching
Kim, D., Lee, D., Myung, H., et al. (2012) · doi:10.1109/oceans-yeosu.2012.6263501 · Cited by 41
“Since the objects have a few of features, the template matching technique [16] has been employed instead of featurebased image matching algorithms such as SIFT [14] or SURF [15].”
MethodRobust 3D face recognition based on resolution invariant features
Zhang, G., & Wang, Y. (2011) · Pattern Recognition Letters · doi:10.1016/j.patrec.2011.02.004 · Cited by 41
Classification of archaeological ceramic fragments using texture and color descriptors
Smith, P. J., Bespalov, D., Shokoufandeh, A., et al. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543523 · Cited by 41
Closing Loops With a Virtual Sensor Based on Monocular SLAM
Munguía, R., & Grau, A. (2009) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2009.2016377 · Cited by 44
“) and to extract n speeded-up-robustfeature (SURF) descriptors di from a p × p patch centered in the point detected by the saliency operator [19].”
HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual RecognitionPreprint
Yan, Z., Zhang, H., Piramuthu, R., Jagadeesh, V., DeCoste, D., Wei, D., & Yu, Y. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1410.0736 · Cited by 40
Moghimi, A., Çelik, T., Mohammadzadeh, A., & Kusetoğulları, H. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3069919 · Cited by 42
Towards AI-Based Traffic Counting System with Edge Computing
Dinh, D.-L., Nguyen, H.-N., Thai, H.-T., & Le, K.-H. (2021) · Journal of Advanced Transportation · doi:10.1155/2021/5551976 · Cited by 48
“In [19, 20], scale-invariant feature 2 Journal of Advanced Transportation”
BackgroundA loosely-coupled EMD-denoised stereo VO/INS/GPS integration system in GNSS-denied environments
Nezhadshahbodaghi, M., & Mosavi, M. R. (2021) · Measurement · doi:10.1016/j.measurement.2021.109895 · Cited by 40
Masked Motion Encoding for Self-Supervised Video Representation Learning
Sun, X., Chen, P., Chen, L., Li, C., Li, T. H., Tan, M., & Gan, C. (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/cvpr52729.2023.00222 · Cited by 76
3D point cloud-based place recognition: a survey
Luo, K., Yu, H., Chen, X., Yang, Z., Wang, J., Cheng, P., & Mian, A. S. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10713-6 · Cited by 53
“Since the camera is the most commonly used sensor for this purpose, conventional image feature extraction algorithms such as SIFT (Lowe 2004), SURF (Bay et al. 2006), BRIEF (Calonder et al. 2010) and ORB (Rublee et al. 2011) have been conveniently applied to VPR.”
Influential3D-Assisted Feature Synthesis for Novel Views of an Object
Su, H., Wang, F., Yi, E., & Guibas, L. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.307 · Cited by 37
“View-invariant Image Comparison Many papers in literature attempt to achieve view-invariance by designing robust features [16, 3, 22].”
BackgroundRobust vision-based robot localization using combinations of local feature region detectors
Arnau Ramisa, A., Tapus, A., Aldavert, D., Toledo, R., & de Mántaras, R. L. (2009) · Autonomous Robots · doi:10.1007/s10514-009-9136-9 · Cited by 40
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.