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 11,601–11,700 of 14,752
IEKF based object pose estimation for Augmented Reality
Song, J., Hu, S., & Yang, Y. (2018) · International Conference on Virtual Reality · doi:10.1145/3198910.3198914 · Cited by 1
“SIFT [8] and SURF [9] are famous image features; while VFH [10], ORB [11] are features especially designed for object pose estimation.”
BackgroundSINGLE-SHOT DENSE RECONSTRUCTION WITH EPIC-FLOW
Chen, Q., & Poullis, C. (2018) · 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video · doi:10.1109/3dtv.2018.8478620 · Cited by 1
STRUCTURAL CLASSIFICATION IMAGES USING BAYESIAN DECISION MAKING
Gadetska, S., & Gorokhovatsky, V. A. (2018) · Radio Electronics Computer Science Control · doi:10.15588/1607-3274-2018-2-10 · Cited by 1
Analyzing Periodicity and Saliency for Pornographic Video Detection
Liu, Y., Wu, L., Ouyang, J., & Liao, M. (2018) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2018.8499467 · Cited by 1
“SURF [16] and ROI based visual codebook are respectively applied for pornographic image detection [17, 18].”
MethodNovel Discriminative Method for Illegal Parking and Abandoned Objects
Wang, X., Song, H., Fang, Y., et al. (2018) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2018.p0907 · Cited by 1
DVD: Constructing a Discriminative Video Descriptor by Convolving Frame Features
Yang, B., Chen, Y., He, W., & Xiang, J. (2018) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2018.8499251 · Cited by 1
“…the DVD with other video descriptors, we implement two Near Duplicate Video Detection systems which are adopted hand-craft features (SIFT [15] or SURF [1]) and Convolutional Neural Networks (CNNs) based features (generated by ImageNet dataset [3] pre-trained 16-layer and 19-layer VGGNets [20]).”
MethodSurvey of Important Issues in Multi Unmanned Aerial Vehicles Imaging Systeme Indian Commercial Banks
Deng, C., Liu, G., Qu, F., He, X., & Zhang, S. (2018) · International Journal of Software & Hardware Research in Engineering · doi:10.26821/ijshre.6.10.2018.61005 · Cited by 1
Visual Place Recognition based on Multi-level CNN Features
Bao, Z., Li, A., Cui, Z., & Zhang, J. (2018) · International Conference on Robotics, Control and Automation (ICRCA) · doi:10.1145/3265639.3265684 · Cited by 1
“[9] E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, “ORB: an efficient alternative to SIFT or SURF,” in Proc. of the IEEE Intl. Conf. on Computer Vision (ICCV), volume 13, 2011.”
MethodAutomated Wireless Localization Data Acquisition and Calibration with 6DOF Image Localization
Fürst, J., Chen, K., Solmaz, G., et al. (2018) · doi:10.1145/3267305.3274186 · Cited by 1
“Some points in the 3D model are associated with a visual feature (e.g., SIFT [16], SURF [5]) that describes the appearance around it.”
BackgroundDang, Q. B., Coustaty, M., Luqman, M. M., et al. (2018) · International Conference on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2018.8516532 · Cited by 1
Parameters Optimization Method of the Information-Extreme Object Recognition System on the Terrain
Коробов, А. Г., Москаленко, А. С., Nahornyi, V., et al. (2018) · IEEE International Conference on System Analysis & Intelligent Computing (SAIC) · doi:10.1109/saic.2018.8516771 · Cited by 1
“To form the input mathematical description of the recognition system based on the search for visual words and phrases, it is proposed to use the SURF algorithm for the extraction of local features [4,5].”
BackgroundMethodДу, С., & Ikenaga, T. (2018) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.e101.a.1786 · Cited by 1
Iterative Closest Point Based Volume Analysis on UAV Made Time-Series Large-Scale Point Clouds
Stojcsics, D., Domozi, Z., & Molnár, A. (2018) · IEEE International Symposium on Intelligent Systems and Informatics (SISY) · doi:10.1109/sisy.2018.8524645 · Cited by 1
Region-Based Poisson Blending for Image Repairing
Chen, W.-C., & Tsai, W.-J. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-01054-6_30 · Cited by 1
An Automated System for Image Reconstruction from Distorted Image Fragments
Tewari, M., Jana, S., & Parekh, R. (2017) · International Conference on Computer, Electrical & Communication Engineering (ICCECE) · doi:10.1109/iccece.2017.8526211 · Cited by 1
“Keywords—Fragments; Image Reconstruction; SURF; Histogram Equalization I. INTRODUCTION The task of fragmented image reconstruction deals with the reassembly of multiple fragments into an original complete image [1].”
BackgroundInfluentialVisual Based Fire Detection System Using Speeded Up Robust Feature and Support Vector Machine
Asih, L. C., Sthevanie, F., & Ramadhani, K. N. (2018) · doi:10.1109/icoict.2018.8528752 · Cited by 1
“SURF was proposed by Herbert Bay [5] on 2006 for object detection task.”
MethodCascaded Deep Hashing for Large-Scale Image Retrieval
Lu, J., & Zhang, L. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04224-0_36 · Cited by 1
Photoplethysmography Imaging and Common Optical Hybrid Imaging Modalities
Blažek, V., Dahlmanns, S., Pereira, C. B., Yu, X., Blanik, N., Leonhardt, S. K., & Blazek, C. (2018) · Springer eBooks · doi:10.1007/978-3-319-98974-7_2 · Cited by 2
Takeishi, M., Oguro, D., Kikuchi, H., et al. (2018) · IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) · doi:10.1109/icce-asia.2018.8552118 · Cited by 1
Algorithm of Ground Object Detection with Modified SURF Method by Using Morphological Features
Mukhina, M. P., & Barkalova, I. (2018) · IEEE International Conference on Methods and Systems of Navigation and Motion Control (MSNMC) · doi:10.1109/msnmc.2018.8576292 · Cited by 1
“60 2018 IEEE 5th International Conference on Methods and Systems of Navigation and Motion Control (MSNMC) SURF method [5] searches the feature points using Hessian matrix.”
MethodOnboard Video Stabilization for Low Cost Small RPAS Surveillance Applications
Bernardo, R. M., da Silva, L. C. B., & Rosa, P. F. F. (2018) · Brazilian Conference on Intelligent Systems · doi:10.1109/bracis.2018.00084 · Cited by 1
“For features detection, they compared Harris Corner Detection [8], SIFT [9] and SURF [10] algorithms.”
MethodChizhova, M., Korovin, D., Gurianov, A., Brunn, A., Lühmann, T., & Stilla, U. (2018) · MDPI eBooks · doi:10.3390/books978-3-03842-685-1-4 · Cited by 1
Solis, J., Karlsson, C., Ogenvall, M., et al. (2018) · 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2018.8560534 · Cited by 1
Parallel Image Forgery Detection Using FREAK Descriptor
Srıdevı, M., Aishwarya, S., Amedapu, N., et al. (2018) · Smart innovation, systems and technologies · doi:10.1007/978-981-13-1747-7_61 · Cited by 1
Stereo Visual Odometry for Mobile Robot
Boucheloukh, A., Boudjema, F., Nemra, A., Fethi, D., & Louali, R. (2018) · International Conference on Pattern Analysis and Intelligent Systems (PAIS) · doi:10.1109/pais.2018.8598501 · Cited by 1
Image Hash Minimization for Tamper Detection
Maity, S., & Karsh, R. K. (2017) · International Conference on Advances in Pattern Recognition · doi:10.1109/icapr.2017.8593100 · Cited by 1
Fernandes, D. H. S., Alsina, P. J., de Medeiros, A. A. D., Nascimento, L. B. P., Lins, F. C. A., & Pereira, D. S. (2018) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars/sbr/wre.2018.00055 · Cited by 1
Using Edge Position Difference and Pixel Correlation for Aligning Stereo-Camera Generated 3D Scans
Rajamohan, D., Pickering, M. R., & Garratt, M. (2018) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2018.8615836 · Cited by 1
“Experiments using classical feature based methods [8] [9] for matching high-resolution textured 3D data with lower resolution RGB camera images showed false matches even after RANSAC filtering of outliers.”
MethodKulkarni, P., Stranieri, A., & Jelinek, H. F. (2019) · Australasian Computer Science Week Multiconference (ACSW) · doi:10.1145/3290688.3290726 · Cited by 1
“Scale Invariant Feature Transform (SIFT)[21], Speeded Up Robust Features (SURF) [22], Histogram of Oriented Edges (HOG) [23] and Local Ternary Pattern (LTP) [24] are transformations on visual word feature descriptors that have been used for modelling texture information include.”
MethodReal-time Monocular Dense Mapping of Small Scenes with ORB Features
Ji, B., Cao, Q., & Zhu, X. (2018) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm.2018.8610747 · Cited by 1
Feasibility Study of Hyperspectral Line-Scanning Camera Imagery for Remote Sensing Purposes
Soszyńska, A., Muller-Rowold, M., & Reulke, R. (2018) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2018.8634703 · Cited by 1
An Efficient CBIR System for High Resolution Remote Sensing Images
Bouteldja, S., & Kourgli, A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-13469-3_46 · Cited by 1
Zhang, Y., Li, Z., Zhao, Q., et al. (2018) · International Conference on Communication and Information Processing (ICCIP) · doi:10.1145/3290420.3290463 · Cited by 1
“Among those, people usually use Scale Invariant Feature Transform(SIFT)[3], Speeded Up Robust Features(SURF)[4], Histograms of Oriented Gradients(HOG)[5] and others.”
MethodLang, S. R., Luerssen, M. H., & Powers, D. M. W. (2019) · MATEC Web of Conferences · doi:10.1051/matecconf/201927702032 · Cited by 1
“The IP detectors tested (K) were Harris [6], KLT [8], FAST [22,2], SIFT [13] and SURF [7] as well as Rohr [21], Foerstner [3], Beaudet [1] and a different”
MethodA context-driven privacy enforcement system for autonomous media capture devices
Farinella, G., Napoli, C., Nicotra, G., & Riccobene, S. (2019) · Multimedia tools and applications · doi:10.1007/s11042-019-7376-z · Cited by 2
“The Bag-of-Words feature extractor has been trained to populate a 1024 elements visual vocabulary with k-means clustering for codebook generation representing the features by means of an 8-by-8 Dense-SURF technique, while for the k-NN classifier we used a normal euclidean metrics.”
MethodRecurrent bidirectional visual human pose retrieval
Sun, H., Zhang, C., & Akashi, T. (2019) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.22902 · Cited by 1
“The similarity measure can be based on various classical image features and descriptors, such as sped-up robust features (SURF) [6] and histogram of oriented gradients (HOG) [7].”
BackgroundConsistent video projection on curved displays
Lyu, Y., Lu, S.-P., Bolsée, Q., et al. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.03.006 · Cited by 1
A Novel Feature Detection Algorithm Based on Improved 2DPCA- SIFT
Wang, A., Zhao, Y., Zhao, J., Iwahori, Y., & Wang, X. (2015) · International Journal of u- and e- Service Science and Technology · doi:10.14257/ijunesst.2015.8.6.29 · Cited by 1
Narayanankutty, H., & Srinivasan, C. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-16660-1_2 · Cited by 1
Homography Estimation Based on Error Elliptical Distribution
Mao, L., Zhu, H., & Duan, F. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682180 · Cited by 1
Mohammed, A. D. (2019) · i-manager’s Journal on Image Processing · doi:10.26634/jip.5.3.15689 · Cited by 1
A novel feature fusion based Human Action Recognition in 2D Videos
Prasad, K. R., & Rao, P. S. (2018) · International Journal of Engineering & Technology · doi:10.14419/ijet.v7i2.20.13297 · Cited by 1
Parallel Implementation for Real Time Person Matching System
Abid, N., Ouni, T., Loukil, K., et al. (2018) · doi:10.1109/icm.2018.8704089 · Cited by 1
“Experiment results proved that LBP MSCOV outperforms MSCOV and COV descriptors respectively studied in [6] and[l] and also others well-known descriptors such as SIFT [7], SURF [8] and HOG [9].”
ResultBecker, A.-K., & Vornberger, O. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20205-7_31 · Cited by 1
Hafdhellaoui, S., Boualleg, Y., & Farah, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-18305-9_21 · Cited by 1
Nguyen, T. D. T., & Huh, E. (2019) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-181760 · Cited by 1
“For image representation, researchers have spent many years attempting to identify and design effective feature descriptors for CBIR [3, 4], including global features [5] and local features (e.g., scale-invariant feature transform [6] and bag-of-visual-words representations [7]).”
Feature Coordinate Estimation by Multi-Baseline Method utilizing Monocular Vision/GPS/INS
Lee, Y. D., Yoo, W.-J., Kim, L. W., et al. (2019) · European Navigation Conference (ENC) · doi:10.1109/euronav.2019.8714168 · Cited by 1
“Feature correspondences can be estimated by comparing the descriptors [9].”
MethodMulti-PQTable for Approximate Nearest-Neighbor Search
Yuan, X., Liu, Q., Long, J., et al. (2019) · Information · doi:10.3390/info10060190 · Cited by 1
Bi, F., Lei, M., Yang, Z., Hou, J., & Qin, Y. (2019) · Photonic Sensors · doi:10.1007/s13320-019-0558-5 · Cited by 1
“In contrast with the other methods, we note that the method proposed in [19], which was described the building area neighborhood based on 64-dimensional descriptors, did not perform as well as the classical SIFT 128-dimensional descriptors.”
MethodInfluentialOn Efficiency of Scrambled Image Forensics Service Using Support Vector Machine
Shuja, S. M., Khan, R. F. M., Shah, M. A., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-23381-5_2 · Cited by 1
Influence of Different Descriptors to Enhance Image Registration Techniques Using FREAK: Case Study
Aarathi, M. R., & Raju, J. (2019) · doi:10.1109/iciict1.2019.8741354 · Cited by 1
“In 2008, Bay [6] proposed SURF (Speeded Up Robust Features), similar to SIFT, a performant scale and rotation-invariant interest point detector and descriptor used for image-based matching process.”
MethodKim, T. K. (2019) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126620200030 · Cited by 1
Jaenal, A., Moreno, F.-Á., & González-Jiménez, J. (2019) · Applications Intelligent Systems · doi:10.1145/3309772.3309800 · Cited by 2
“Depending on the visual features extracted from the images we distinguish between two different approaches: those based on local descriptors [4, 9, 21, 26], which represent geometric image features as corners, segments or blobs, and holistic descriptors [6, 14], which encode the appearance of the…”
MethodAn Improved Method for Interest Point Detection in Human Activity Video
Hu, Z., Zhang, H., Yang, Y., & Yang, C. (2019) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1237/2/022089 · Cited by 1
“The two-dimensional SURF feature [20] has been extended to three dimensions by Willems [21], and each cell of these eSURF features contains all Harr-wavelet features.”
MethodLuo, D., Ni, B., Yan, Y., & Yang, X. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/335 · Cited by 1
Discriminative supplementary representation learning for novel-category classification
Liu, Q., Li, Z., & Tang, J. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.03.100 · Cited by 1
Vokhmintcev, A., Melnikov, A. V., Pachganov, S., et al. (2019) · doi:10.2991/itids-19.2019.4 · Cited by 1
Infrared and Visible Image Matching Algorithm Based on SIFT and LDB
Zhang, L., Dai, M., & Tian, J. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9917-6_11 · Cited by 1
Data Augmentation Based on Pixel-level Image Blend and Domain Adaptation
Liu, D., Xiao-Chun, H. O. U., Liu, Y., et al. (2019) · doi:10.5121/csit.2019.90923 · Cited by 1
Development and Testing of Data Reduction Software for Measurements Using Pressure Sensitive Paints
Deitrick, W. J., & Stryczniewicz, W. (2018) · Transactions of the Institute of Aviation · doi:10.2478/tar-2018-0031 · Cited by 1
“The automatic selection first detects various points in each image using a processes called Speeded Up Robust Features (SURF) [13].”
MethodReal-Time Image Matching and Tracking for Autonomous Quadrotor Helicopters
Mueller, K., & Trommer, G. F. (2019) · Saint Petersburg International Conference on Integrated Navigation Systems · doi:10.23919/icins.2019.8769431 · Cited by 1
“Popular keypoint matching algorithms use, amongst others, Scale Invariant Features (SIFT) [2], Speeded Up Robust Features (SURF) [3], or ORB features [4].”
MethodEnvironment Virtualization for Visual Localization and Mapping
Valiente, D., Berenguer, Y., Payá, L., et al. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-26945-6_19 · Cited by 1
AI BOT: An Intelligent Personal Assistant
Shanthini, A., Rao, C. P., & Vadivu, G. (2019) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-030-24643-3_66 · Cited by 1
Bilateral Grid Statistics Combined with BRISK for Robust Matching
Zhang, Y., & Li, X. (2019) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic.2019.8785478 · Cited by 1
“Experiments show that the bilateral grid statistics combined with BRISK forms more effective and correct matches than the traditional SIFT-LIKE [7,8,14,15,20,23] methods, which is more robust and less time consuming.”
BackgroundMethodPark, B., Kim, Y., & Kim, S.-Y. (2019) · Studies in computational intelligence · doi:10.1007/978-3-030-24405-7_9 · Cited by 1
Qiu, S., Yang, X., Shu, Y., et al. (2019) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic.2019.8785523 · Cited by 1
Towards Robust Retrieval for Imperfectly Scanned Point Cloud Objects
Lev, J., Lim, J., Ouarti, N., et al. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803694 · Cited by 1
“The last two are inspired by their 2D version [7, 1].”
BackgroundMultiple-Action Transform of Quaternion for Color Images
Lan, R., Wang, X., Xie, X., et al. (2019) · IEEE Access · doi:10.1109/access.2019.2938346 · Cited by 1
“SURF, an improvement of SIFT, obtains comparable performance with DRLTP.”
BackgroundLeast Squares Consensus for Matching Local Features
Zhang, Q., Shi, B., & Xu, H. (2019) · Information · doi:10.3390/info10090275 · Cited by 2
Allegra, D., Erba, D., Farinella, G. M., Grazioso, G., Maci, P. D., Stanco, F., & Tomaselli, V. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30645-8_57 · Cited by 1
Forero, M. G., Acosta, A. L., Ducuara, A. S., et al. (2019) · doi:10.1117/12.2529293 · Cited by 1
Motion Recognition Based on Angle-reg Network
Yu, Z., Zhang, G., Zhang, W., Shen, J., & Jin, Z. (2019) · International Conference on Artificial Intelligence and Computer Science (AICS) · doi:10.1145/3349341.3349404 · Cited by 1
Intelligent Descriptor of Loop Closure Detection for Visual SLAM Systems
Quan, K., Xiao, B., & Wei, Y. (2019) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2019.8833325 · Cited by 1
Image Forensic Analysis And Recognition In Copy-Move Using Bag Of Features And Svm
Bharat Kumar, R., Srinivas, C. V. V. S., & Shaik, A. R. (2019) · International Journal of Engineering Trends and Technology · doi:10.14445/22315381/ijett-v67i5p201 · Cited by 1
Loop Closure Detection for Visual SLAM Using Simplified Convolution Neural Network
Xu, B., Yang, J., Li, M., et al. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-31967-0_6 · Cited by 1
A Novel Method for Digitalisation of Test Fields by Laser Scanning
Fiedler, S., Knoblach, S., Werthmann, H., et al. (2019) · PFG – Journal of Photogrammetry Remote Sensing and Geoinformation Science · doi:10.1007/s41064-019-00079-8 · Cited by 1
SEMANTIC ROAD SCENE KNOWLEDGE FOR ROBUST SELF-CALIBRATION OF ENVIRONMENT-OBSERVING VEHICLE CAMERAS
Hanel, A., & Stilla, U. (2019) · 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-w16-103-2019 · Cited by 1
Chiaroni, F., Rahal, M.-C., Hueber, N., & Dufaux, F. (2020) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.2977269 · Cited by 24
A Review on Visual Odometry Techniques for Mobile Robots: Types and Challenges
Thapa, V., Sharma, A., Gairola, B., Mondal, A. K., Devalla, V., & Patel, R. K. (2019) · Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering) · doi:10.2174/2352096512666191004142546 · Cited by 1
A Fast Image Matching Approach for Real-Time Embedded Systems
Zhang, H., & Bian, H. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8866437 · Cited by 1
Computable invariants for curves and surfaces
Halimi, O., Raviv, D., Aflalo, Y., & Kimmel, R. (2019) · Handbook of numerical analysis · doi:10.1016/bs.hna.2019.07.004 · Cited by 1
Technique for automated target object search in video stream from UAV in post-processing mode
Приставка, П. О., Гісь, Д. І., & Чирков, А. В. (2019) · Ukrainian Information Security Research Journal · doi:10.18372/2410-7840.21.13767 · Cited by 1
Mosaicing of multiplanar regions through autonomous navigation of off‐the‐shelf quadcopter
Prasad, M. G., Akula, S. P., Vemula, A., et al. (2019) · IET Cyber-Systems and Robotics · doi:10.1049/iet-csr.2019.0016 · Cited by 1
“It gives us a subset of HD images which are within a threshold in SURF feature space from the selected image.”
MethodInfluentialEigenvector Orientation Corrected LeNet for Digit Recognition
Swetha, V. C., Mishra, D., & Gorthi, R. K. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-981-32-9088-4_27 · Cited by 1
Carrasco, M., Toledo, P. A., & Tischler, N. D. (2019) · Biomolecules · doi:10.3390/biom9120809 · Cited by 1
An Augmented Approach for Recognising Sri Lankan Currency Notes
Kogilawanee, B., & Ramanan, A. (2018) · IEEE International Conference on Information and Automation for Sustainability (ICIAfS) · doi:10.1109/iciafs.2018.8913332 · Cited by 1
“Step 1: A gray-scaled reference image for each side of the currency notes (LKR 20, 50, 100, 500, 1000, and 5000) and the SURF descriptors [5] extracted from the corresponding images are recorded.”
MethodBlurred Template Matching Based on Cascaded Network
Peng, J., Sang, N., Gao, C., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-34120-6_39 · Cited by 1
Geometric Verification Method of Best Score Increasing Subsequence for Object Instance Recognition
Kusuma, G. P., Harjono, K. D., & Putra, M. T. D. (2019) · International Conference on Information Technology, Computer, and Electrical Engineering · doi:10.1109/icitacee.2019.8904344 · Cited by 1
“The local features that are used in this experiment are extracted using the SURF feature extractor [3].”
MethodJoint Spectral and Spatial Consistency Priors for Variational Pansharpening
Liu, P. (2019) · IEEE Access · doi:10.1109/access.2019.2957214 · Cited by 1
Mutual-Information-Graph Regularized Sparse Transform for Unsupervised Feature Learning
Ду, С., & Ikenaga, T. (2018) · International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) · doi:10.1109/ispacs.2018.8923407 · Cited by 1
Visual Assistant for Crowdsourced Anomaly Event Recognition in Smart City
Ho, M.-T., Nguyen, T.-T., Dao, H. T., & Tran, M. (2019) · International Symposium on Information and Communication Technology · doi:10.1145/3368926.3369734 · Cited by 1
“Traditionally, one of the ways to classify an image would be to use algorithms such as SIFT or SURF [3, 21].”
MethodFace quality analysis of single-image super-resolution based on SIFT
Hu, X. G., Sun, J., Mai, Z., et al. (2019) · Signal Image and Video Processing · doi:10.1007/s11760-019-01614-1 · Cited by 1
“…the distance a , i satisfies the following rule: 𝜃 a , i 𝜆𝜃 a , j , and 𝜆 1 𝜃 a , i is the smallest, and 𝜃 a , j is the second smallest Later some improved SIFT algorithms, such as CSIFT [22] and SURF [23], are proposed to get more robust SIFT key-points and gain better matching results.”
MethodAction and movements recognition methods
Soldatov, D. (2019) · Electronic and Acoustic Engineering · doi:10.20535/2617-0965.2019.2.3.164709 · Cited by 1
Recreation of 3D Models of Objects Using MAV and Skanect
Srividhya, S., Prakash, S., & Elangovan, K. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-37218-7_29 · Cited by 1
Evaluating image matching methods for book cover identification
Hachemi, R., Achar, I., Wiga, B., et al. (2019) · International Conference on Advanced Electrical Engineering (ICAEE) · doi:10.1109/icaee47123.2019.9015089 · Cited by 1
“, SIFT, SURF, ORB and KAZE [12] [13] [14] [15].”
Enforcing the General Planar Motion Model: Bundle Adjustment for Planar Scenes
Örnhag, M. V., & Wadenbäck, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-40014-9_6 · Cited by 1
Stronger Baseline for Vehicle Re-Identification in the Wild
Hsu, C., Hung, C.-H., Jian, C.-Y., et al. (2019) · IEEE Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip47243.2019.8965867 · Cited by 1
Geometry Augmented SURF with Modified Sobel for Improved Affine Invariance in Image Matching
Khan, S. A., Iftikhar, F., & Akram, U. (2019) · International Conference on Robotics and Automation in Industry (ICRAI) · doi:10.1109/icrai47710.2019.8967349 · Cited by 1
Vinay, A., Singh, A., Anand, N., et al. (2020) · Springer proceedings in mathematics & statistics · doi:10.1007/978-981-15-1338-1_30 · Cited by 1
Logistic regression projection-based feature representation for visual domain adaptation
Hosseinzadeh, H., & Einalou, Z. (2020) · Signal Image and Video Processing · doi:10.1007/s11760-020-01649-9 · Cited by 1
“The features used in the experiments are the SURF features [30] with 800 dimensions and deep learning features [31], DeCAF 6 , with 4096 dimensions.”
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.