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 13,201–13,300 of 14,752
A spatiotemporal warping-based video synchronization method for video stitching
Zhou, X. S., Zhou, Z. O., & Cao, S. (2018) · IEEE Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip.2018.8698679
CREAK descriptor evaluation for visual odometry
Smulders, D., Uren, K. R., van Schoor, G., et al. (2019) · Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) · doi:10.1109/robomech.2019.8704807
Trajectories and Camera Motion Compensation in Aerial Videos
Beumier, C., & Neyt, X. (2018) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis.2018.00037
“Acronyms such as FAST [11], SIFT [12] or SURF [13] are now common in the literature [7, 14].”
Reading Contents Estimation from an Indoor Surveillance Camera
Kawanishi, Y., Murase, H., Xu, J., et al. (2019) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.85.463
Khethisa, J. A. (2017) · Open University of Cape Town (University of Cape Town)
Detection of face spoofing using low-level features and shape analysis
Arini, D., Ramadhani, K., & Sthevanie, F. (2019) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1192/1/012002
“In SURF [3], determinant Hessian obtained from Hessian matrix which defined as follows where L xx ( x, σ ) is the convolution of the Gaussian second order derivative with the image I ( x, y ), and similarly for L xy ( x, σ ) and L yy ( x, σ ).”
BackgroundMethodInfluentialA Semi-local Method for Image Retrieval
Karamti, H. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-16660-1_16
Real-Time Face Recognition System Using Software Agent
Al-Bakry, A. M., Al‐Mamory, S. O., & Alfartosy, H. H. (2017) · doi:10.1109/aic-mitcsa.2017.8723018
Vocabulary Trees with OSS Detectors
Vinay, A., Acharya, H. R., Singh, H., et al. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.05.015
An algorithm of search of key point pairs strong correspondences in images and depth maps
Dashkevich, A., Vorontsova, D., & Skorobogatko, N. (2019) · Bulletin of the National Technical University «KhPI» Series New solutions in modern technologies · doi:10.20998/2413-4295.2019.05.11
Autonomous Pick-and-Place of Pneumatically Attachable Flexible Rails
Ettorre, C. D., Stilli, A., Dwyer, G., et al. (2019) · The Hamlyn Symposium on Medical Robotics · doi:10.31256/hsmr2019.10
Similarity Search in Large Collections of Biometric Data
Zezula, P., Batko, M., Dohnal, V., et al. (2009)
Unifying Multi-Domain Multi-Task Learning: Tensor and Neural Network PerspectivesPreprint
Yang, Y., & Hospedales, T. M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.09345
Recovering affine features from orientation- and scale-invariant onesPreprint
Baráth, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.03503
“An approach is proposed for recovering affine correspondences from orientation- and scale-invariant features obtained by, for instance, SIFT or SURF detectors.”
BackgroundTowards Learning free Naive Bayes Nearest Neighbor-based Domain AdaptationPreprint
Saeedan, F., & Caputo, B. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.07783
Image Processing with Virtual Pencil and Virtual Mouse using Webcam Recognition for Drawing
Ginanjar, R., & Carnelius, S. I. (2016) · IT for Society · doi:10.33021/itfs.v1i1.17
Orientation covariant aggregation of local descriptors with embeddingsPreprint
Tolias, G., Furon, T., & Jégou, H. (2014) · doi:10.48550/arxiv.1407.2170
A Survey of Appearance Models in Visual Object TrackingPreprint
Li, X., Hu, W., Shen, C., et al. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1303.4803
Nordin, N. F., Setumin, S., Radman, A., & Suandi, S. A. (2019) · IntechOpen eBooks · doi:10.5772/intechopen.86473
“Indeed, there is a collection of face descriptors proposed over the years such as scale-invariant feature transform (SIFT) [5], speeded up robust feature (SURF) [6], local binary pattern (LBP) [7], and histogram of oriented gradient (HOG) [8].”
BackgroundTrace transform based method for color image domain identificationPreprint
Olaizola, I. G., Quartulli, M., Flórez, J., et al. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1208.3901
Graphical Representation for Heterogeneous Face RecognitionPreprint
Peng, C., Gao, X., Wang, N., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.00488
Mobile Multi-View Object Image SearchPreprint
Çalışır, F., Baştan, M., Ulusoy, Ö., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1507.08861
Detekcja obiektów z wykorzystaniem probabilistycznych modeli grafowych
Wietrzykowski, J. (2016) · Prace Naukowe Politechniki Warszawskiej. Elektronika
Efficient Media Retrieval from Non-Cooperative QueriesPreprint
Shih, K. J., Wei, D., Jagadeesh, V., & Piramuthu, R. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.5307
Image-Based Geo-Localization Using Satellite ImageryPreprint
Hu, S., & Lee, G. H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.00159
“This causes cross-view matching with traditional handcrafted features like SIFT (Lowe 2004) and SURF (Bay et al. 2006) fail.”
MethodDo We Need Binary Features for 3D Reconstruction?Preprint
Fan, B., Kong, Q., Sui, W., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.04502
Affine Subspace Representation for Feature DescriptionPreprint
Wang, Z., Fan, B., & Wu, F. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1407.4874
SConE: Siamese Constellation Embedding Descriptor for Image MatchingPreprint
Trzcinski, T. P., Komorowski, J., Dąbała, Ł., Czarnota, K., Kurzejamski, G., & Lynen, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.11054
Feature Selection for Unsupervised Domain Adaptation using Optimal TransportPreprint
Gautheron, L., Redko, I., & Lartizien, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.10861
DASC: Robust Dense Descriptor for Multi-modal and Multi-spectral Correspondence EstimationPreprint
Kim, S., Min, D., Ham, B., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.07944
SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel PatchesPreprint
Giraud, R., Ta, V., Bugeau, A., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.07169
“They have progressively proven their efficiency for several applications such as texture synthesis [36] and image denoising [37], and in the design of computer vision descriptors [38], [39] that include spatial information.”
Loss Switching Fusion with Similarity Search for Video Classification
Wang, L., Huynh, D. Q., & Mansour, M. R. (2019) · UWA Profiles and Research Repository (University of Western Australia) · doi:10.48550/arxiv.1906.11465
Improved Descriptors for Patch Matching and ReconstructionPreprint
Mitra, R., Zhang, J., Narayan, S., Ahmed, S., Chandran, S., & Jain, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.06854
Petrov, D., Rumyantsev, K. E., & Polikarpov, S. (2019) · International Conference on Multimedia Systems and Signal Processing (ICMSSP) · doi:10.1145/3330393.3330420
SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching TasksPreprint
Schuster, R., Wasenmüller, O., Unger, C., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.03076
“Robustness is also a problem for faster hand-crafted feature extractors like SURF [5] and DAISY [38].”
BackgroundChange Detection Method based on Block Similarity Measure
Yu, L., & Sun, T. (2019) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1237/2/022047
“Similar local descriptors include SURF[25], BRIEF[26], LIOP[27], etc. Pooling technology, in fact, imitates human visual system.”
BackgroundSOM-VLAD Based Feature Aggregation for Face Recognition Using Keypoint Fusion
Vinay, A., Cholin, A. S., Bhat, A. D., et al. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9184-2_46
Building a Versatile Deduplication System
Yan, Z. (2018)
Video-Surveillance System for Fall Detection in the Elderly
Yano, K., Manabe, Y., Hirano, M., et al. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-23528-4_45
Generation of magnifying endoscopic images of gastric neoplasms based on an all‐in‐focus algorithm
Matsui, K., Funasaka, K., Miyahara, R., Furukawa, K., Matsushita, M., Yamamura, T., Ishikawa, T., Ohno, E., Nakamura, M., Kawashima, H., et al. (2019) · Journal of Gastroenterology and Hepatology · doi:10.1111/jgh.14792
A Fast Interest Points Feature Descriptors Algorithm for Mobile Image Retrieval Applications
Saber, H.-A., М.А., М., & Omar, R. (2018) · International Journal of Computer Applications · doi:10.5120/ijca2018916149
KLASIFIKASI KATEGORI CITRA DIGITAL DENGAN METODE BAG OF VISUAL WORDS
Tanjung, M. A. P. (2019) · JURTEKSI (Jurnal Teknologi dan Sistem Informasi) · doi:10.33330/jurteksi.v5i2.359
Detector and Descriptor Based Recognition and Counting of Objects in Real Time Environment
Singh, H. V., & Verma, S. K. (2019) · Springer eBooks · doi:10.1007/978-3-030-15887-3_26
Let Vehicles Talk with Images for Smart Vehicular Communication System
Santosh, K. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9181-1_2
Learning Local Feature Descriptor with Motion Attribute for Vision-based LocalizationPreprint
Song, Y., Zhu, D., Li, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.01180
Rotation and scale invariant three-dimensional recognition using optical scanning holography
Lee, J., Kim, T. W., Im, D. H., et al. (2019) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie.2019.8781423
Local Feature Detection Based on Image Block Discrete Scale Space
Leng, J., Li, T.-H., & Xu, W. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-25128-4_69
Unsupervised Learning Framework of Interest Point Via Properties OptimizationPreprint
Yan, P., Tan, Y., Yuan, X. H., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.11375
Sohn, K., & Murshid, M. M. (2019) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2019.8797890
Douglas-Quaid -- Open Source Image Matching LibraryPreprint
Falconieri, V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.04014
Camera Pose Estimation Method Based on Deep Neural Network
Qing, T. X., Wu, F., & Tao, Z. Y. (2019) · International Conference on Deep Learning Technologies (ICDLT) · doi:10.1145/3342999.3343014
Removing Spinning Motion from Spherical Video Using a Rotationally Invariant Feature Extractor
Slevin, M., & Cuffe, P. (2019) · Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon.2019.8926884
“It should be noted that ORB was chosen over SIFT [15] and SURF [16] for the purposes of this project because the latter two methods are patented algorithms, which hinders the availability and reproducibility of the algorithm.”
MethodCarl-Hauser -- Open Source Image Matching Algorithms Benchmarking FrameworkPreprint
Falconieri, V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.03449 · Cited by 1
Research on stereo matching methods for long distance sea surface image
Yang, Y., Lu, C., & Chen, C.-H. (2019) · International Conference on Engineering, Applied Sciences, and Technology (ICEAST) · doi:10.1109/iceast.2019.8802587
“Common stereo matching algorithm including SIFT, SURF, HARRIS [5-7] and so on put large effort on finding out feature points which are invariable to scale and orientation, but the features extracted out used to match these points are focus on matching the obvious unusual points, they are not effective on matching sea…”
MethodAn IMU-aided Visual Odometry with Loop-closure Optimization
Mei, Y., Wang, Z., & Cai, B. (2018) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2018.8812403
“The descriptors of the feature points are obtained by various feature point detection algorithm, such as SIFT, SURF and ORB [18-20].”
MethodIdentificação automática do comportamento do tráfego a partir de imagens de vídeo
Marcomini, L. A. (2018) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.18.2018.tde-01102018-102649 · Cited by 1
Blanco, G. (2019) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.55.2019.tde-10062019-162252 · Cited by 1
Unified Underwater Structure-from-MotionPreprint
Ichimaru, K., Taguchi, Y., & Kawasaki, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.03583
“Then, image features are extracted from the images, and correspondences are computed across frames (We used SURF [4] as the feature).”
MethodSaliency based Semi-supervised Learning for Orbiting Satellite TrackingPreprint
Li, P., Sun, Y., & Wan, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.03656
“Popular algorithms for edge and key point extraction includes Harris[13], Canny[14], SIFT [15] and SURF [16].”
MethodLarge Scale Objects Recognition by using GIFTS Image Feature and its Evaluation in Practical use
NAKANO, H., Mori, Y., Morita, C., et al. (2015) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.81.1107
Duman, F., & Düven, E. (2019) · Uludağ University Journal of The Faculty of Engineering · doi:10.17482/uumfd.560127
Saleem, S. (2019) · Journal of Electronic Imaging · doi:10.1117/1.jei.28.5.053004
A Histogram and GLCM-based Approach for Image Copy-Move Forgery Detection
Teerakanok, S., & Uehara, T. (2019) · Journal of Information Processing · doi:10.2197/ipsjjip.27.574
“[13] to provide a much faster and computationally efficient alternative to SIFT.”
BackgroundMethodSunwayImg: A Parallel Image Processing Library for the Sunway Many-Core Processor
Liu, R., Liu, Y., Zhao, M., Song, K., & Qian, D. (2019) · IEEE Access · doi:10.1109/access.2019.2939940
Reinforcement Learning-based Traffic Control to Optimize Energy Usage and Throughput (CRADA report)
Karnowski, T. P., Office of Sustainable Transportation. Vehicle Technologies Office (VTO) USDOE Office of Energy Efficiency and Renewable Energy (EERE), Eicholtz, M., Elwasif, W. R., Ferrell, R., Naughton, T. J., Oesch, S., Patton, R. M., Rose, D. C., Tokola, R., et al. (2019) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.2172/1560460
“Left: vehicle with SURF points identified......................................................................................7 Figure 6.”
Optimal Image-Aided Inertial Navigation
Gopaul, N. S. (2018) · YorkSpace (York University) · Cited by 2
Горбачев, В. А., & Osokin, I. (2019) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661819030064
Mobile User Re-authentication Using Clothing Information
Nguyen, H. M., Rattani, A., & Derakhshani, R. R. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-26972-2_13
Content Based Image retrieval system using machine learning
Dalvi, N. (2019) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2019.6095
Dense point cloud generation of urban scenes from nadir RGB images in a remote sensing system
Schreyvogel, N. S., Mispelhorn, J., & Middelmann, W. (2019) · doi:10.1117/12.2531839
Identification of stereo rig alignment error based on vertical disparity ma
Katragadda, S. (2019) · Journal of WSCG · doi:10.24132/jwscg.2019.27.2.8
A bag of features approach for human attribute analysis on face images
de Araujo, R. W. M. (2019) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.45.2019.tde-07102019-213618
A Global Extraction Method of High Repeatability on Discretized Scale-Space Representations
Zhang, Q., & Shi, B. (2019) · Information · doi:10.3390/info10120376
“In comparison with SIFT and SURF, except the score being close to SIFT under the scene of JPEG compression (cf. Figure 7a), GPE acquires Information 2019, 10, 376 10 of 12 prominent advantage in all other cases.”
MethodInfluentialBi, F., Lei, M., Qin, Y., et al. (2019) · The Journal of Engineering · doi:10.1049/joe.2019.0711
DOAFT: Infrared And Visual Image Registration Based on Dominant Orientation Align Feature Transform
Wang, S., Xi, P., & Cai, Y. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8865405
“We use the speed up robust feature(SURF)[1] detector for feature detection.”
BackgroundMethodInfluentialImage-Based Copy-Paste Tamper Detection Technology Based on Improved Surf
Hu, Y., Wang, Y., & Ai, X. (2019) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/612/5/052017
“Such as SIFT [5] algorithm, SURF [6] algorithm, MIFT algorithm and ORB [7] algorithm.”
MethodVideo Logo Retrieval based on local FeaturesPreprint
Guan, B., Ye, H., Liu, H., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.03735
Zhou, Y., & Maskell, S. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.01727
“The feature points can be generated by, for example, Harris corner or SIFT-like [19] detectors.”
MethodFuzzy Control Reversing System Based on Visual Information
Liu, S., Fan, Y., Tang, Y., Jing, X., Yao, J., & Han, H. W. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-31726-3_21
Motion Statistic Based Local Homography Transformation Estimation for Mismatch Removal
Ду, С., & Ikenaga, T. (2019) · doi:10.1145/3348488.3348496
“With the keypoints detected by these algorithms, many local feature descriptors which are designed for extracting informative features from the keypoints are proposed [4, 9, 10, 11, 12, 13].”
MethodBackNet: An Enhanced Backbone Network for Accurate Detection of Objects with Large Scale Variations
Hossain, M. T., Teng, S. W., & Lu, G. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-34879-3_5 · Cited by 1
Robust and Accurate Global Motion Estimation Using the Student-t DistributionPreprint
Zhou, Y., & Maskell, S. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.01734
Saliency Assessment Using Selective Features Based on Entropy and Wavelet Transform
Kaddar, B., Fizazi, H., & Mansouri, D. E. K. (2019) · International Conference on Information Systems and Technologies (ICIST) · doi:10.1145/3361570.3361583
“[Bay et al. 2006] proposed an algorithm based on the points generated by the SURF algorithm, this being fast, having a robust descriptor and having a high coincidence with visually salient regions [Harding and Robertson 2009].”
MethodImproving Human Annotation in Single Object TrackingPreprint
Pang, Y., Li, X., Yuan, L., & Ling, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.02807
Image Processing Techniques to Improve Deep 6DoF Detection in RGB Images
Felix, H. D. C., Simões, F., Cunha, K., & Teichrieb, V. (2019) · Symposium on Virtual and Augmented Reality (SVR) · doi:10.5753/svr_estendido.2019.8457
“Traditionally in computer vision, the most common 6DoF object detection techniques focus on textured objects [4], [5], due to the possibility of creating efficient and robust descriptors for various transformations and challenges as the object’s scale, lighting, rotation, and other changes, etc.”
BackgroundMenéndez, J. C. G. (2019) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.3.2019.tde-19112019-100543
Chandrasekhar, S., & Mhala, N. N. (2019) · International Conference on Intelligent Sustainable Systems (ICISS) · doi:10.1109/iss1.2019.8908056
Skorohod, B. A., Statsenko, A. V., & Фатеев, С. И. (2019) · Monitoring systems of environment · doi:10.33075/2220-5861-2019-2-30-36
Model Quality Aware RANSAC: A Robust Camera Motion EstimatorPreprint
Yeh, S.-H., & Song, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.11884
Authentication of Surveillance Video using Video Fingerprinting
Sirigeri, V. J., & Giri, G. L. (2014) · IJSRD : international journal for scientific research and development
UAV-Based Motion Target Detection and Tracking Method in Dynamic Scenes
Yang, G., Zhang, J., Zhu, L. H., et al. (2019) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc.2019.00098
“We use Speeded Up Robust Features (SURF) feature points to describe the features of each frame, and Fast Library for Approximate Nearest Neighbors (FLANN) feature matching method to match the two adjacent frames[10,11].”
Method3D city scale reconstruction using wide area motion imagery
Viguier, R. (2018) · doi:10.32469/10355/69879
Software for Detection of Objects while Video Sequences Handling
Korovin, I., Khisamutdinov, M., & Ivanov, D. Y. (2019) · doi:10.2991/mmsta-19.2019.41
Image-Driven Automated End-to-End Testing for Mobile Applications
Fritz, C. (2019) · Journal of the Arkansas Academy of Science
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.