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 10,301–10,400 of 14,752
Analysis, Recognition, and Classification of Biological Membrane Images
Kulbacki, M., Segen, J., & Bąk, A. (2017) · Advances in anatomy, embryology and cell biology · doi:10.1007/978-3-319-56895-9_8 · Cited by 2
Ramasamy, V., Nandagopal, D., Tran, M. D.-J., et al. (2017) · Procedia Computer Science · doi:10.1016/j.procs.2017.09.018 · Cited by 2
Pose Measurement Based on Vision Perception
Huang, P., Meng, Z., Guo, J., & Zhang, F. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-812309-6.00003-8 · Cited by 3
Matsuda, H., & MAKANAE, K. (2017) · Journal of Japan Society of Civil Engineers Ser F3 (Civil Engineering Informatics) · doi:10.2208/jscejcei.73.i_347 · Cited by 2
Store products recognition and counting system using computer vision
Algburi, M. H., & Albayrak, S. (2017) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn.2017.8319389 · Cited by 2
“Net wrapper to the OpenCV [15] image processing library, for the SURF detection.”
MethodInfluentialA fast near-duplicate keyframe detection method based on local features
Luan, X., Xie, Y., Guo, Y., et al. (2017) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct.2017.8359890 · Cited by 2
“Other descriptors, such as SURF [5], GLOH [8], PCA-SIFT [9] and so on, are improved on the basis of the method of using this descriptor.”
BackgroundMethodInfluentialJana, S., & Bhat, M. S. (2018) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2018.05.032 · Cited by 2
UAV-aided Large-scale Map Building and Road Extraction for UGV
Meiling, W., Yu, H., Guoqiang, F., et al. (2017) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2017.8446253 · Cited by 2
“Bay[4] presented a new algorithm, based on SIFT, called SURF which used box filters to approximate the Gaussian, resulting in a faster computation compared to SIFT.”
MethodMulti-Camera Matching of Spatio-Temporal Binary Features
Xompero, A., Lanz, O., & Cavallaro, A. (2018) · International Conference on Information Fusion (FUSION) · doi:10.23919/icif.2018.8455444 · Cited by 2
Multimodal Image Registration between SWIR and LWIR Images in an Embedded System
Cárdenas, J., & Figueroa, M. E. (2018) · Euromicro Conference on Digital System Design (DSD) · doi:10.1109/dsd.2018.00029 · Cited by 2
“Multimodal image registration algorithms, such as MI, SIFT, and SURF are computationally very intensive, and therefore require long execution times and large amounts of memory.”
MethodSolar Panels Frames Quality Assessment
Tribak, H., & Zaz, Y. (2017) · International Renewable and Sustainable Energy Conference (IRSEC) · doi:10.1109/irsec.2017.8477360 · Cited by 2
Brief Introduction to Statistical Machine Learning
Angelov, P. P., & Gu, X. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-02384-3_2 · Cited by 2
Study of RGB-D point cloud registration method guided by color information
Lin, Y., Liu, H., & Ye, Q. (2018) · Tenth International Conference on Information Optics and Photonics · doi:10.1117/12.2505869 · Cited by 2
Real-time monocular 3D perception with ORB-Features
Ji, B., & Cao, Q. (2018) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-06-2018-0115 · Cited by 2
SeFM: A Sequential Feature Point Matching Algorithm for Object 3D Reconstruction
Fang, Z., Ma, H., Zhu, X., et al. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-0115-6_28 · Cited by 2
RETRACTED ARTICLE: A method for spectral image registration based on feature maximum submatrix
Wang, K., Wang, H., Wu, M., et al. (2018) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-018-0377-4 · Cited by 2
RetractedFire detection of Unmanned Aerial Vehicle in a Mixed Reality-based System
Esfahlani, S. S., Cirstea, S., Sanaei, A., et al. (2018) · Proceedings of the Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon.2018.8592764 · Cited by 2
Evaluation of IGFTT Keypoints Detector in Indoor Visual SLAM
Zacarkim, V. L., Todt, E., & Bombardelli, F. G. (2018) · doi:10.1109/lars/sbr/wre.2018.00025 · Cited by 2
“SIFT [6] and SURF [7] are classic in the literature because they are robust and vastly tested.”
BackgroundMulti-scale FAST feature extraction heterogeneous design based on FPGA
Ding, R., Sun, H., & Ye, P. (2018) · International Conference on Systems and Informatics (ICSAI) · doi:10.1109/icsai.2018.8599455 · Cited by 2
“y Scale y v j x Scale x u _ * _ * i = + = + (6)”
Active Descriptor Learning for Feature Matching
Koçanaoğulları, A., & Ataer-Cansızoğlu, E. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11018-5_49 · Cited by 2
Planar Motion Bundle Adjustment
Örnhag, M. V., & Wadenbäck, M. (2019) · International Conference on Pattern Recognition Applications and Methods · doi:10.5220/0007247700240031 · Cited by 2
“The inter-image homographies were estimated using the MSAC algorithm (Torr and Zisserman, 2000) from four point correspondences by extracting SURF keypoints and applying a KNN algorithm to establish the matches.”
MethodRotation-Invariant Approach Using Mask to Content-Based Image Retrieval
Chifa, N., Badri, A., & Ruichek, Y. (2019) · International Conference on Computer and Technology Applications (ICCTA) · doi:10.1145/3323933.3324066 · Cited by 2
“Other CBIR look to find the a specific object in images, for that many researchers proposed the local features who focus mainly on key points [10], the most popular ones: SIFT [11], SURF [12], HOG [13].”
BackgroundHu, Z., & Zhao, B. C. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7666-5 · Cited by 2
Feature Detector-level Fusion Methods in Food Recognition
Razali, M. N., & Manshor, N. B. (2019) · International Conference on Communication Engineering and Technology (ICCET) · doi:10.1109/iccet.2019.8726897 · Cited by 2
“Hessian matrix has a good performance in term of computation time and accuracy [19].”
BackgroundA Novel Image Mosaic Method Based on Improved ORB and its Application in Police-UAV
Wang, S., Zhang, Y., Wang, W., et al. (2018) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/cybermatics_2018.2018.00285 · Cited by 2
“The quality of the mosaic image and the time cost are two main parameters to measure the stitching performance [22], so we use the feature matching rate and registration time as the quantitative indicators to evaluate the quality of image registration, and compare with SIFT, SURF and ORB algorithm.”
MethodInfluentialORB-Based Multiple Fixed Resolution Approach for On-Board Visual Recognition
Phillips, D., Pooransingh, A., & Güven, S. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-23367-9_5 · Cited by 2
Garcia, R. G., Paglinawan, C. C., Paglinawan, A. C., et al. (2019) · International Conference on Biomedical Engineering and Technology (ICBET) · doi:10.1145/3326172.3326194 · Cited by 2
Benabdelaziz, R., Gaceb, D., & Haddad, M. (2019) · International Journal of Computer Vision and Image Processing · doi:10.4018/ijcvip.2019070103 · Cited by 2
An Effective Fusion Enhancing Approach for Single Underwater Degraded Image
Zou, S., Li, Q., Ren, Y., Tang, D., & Ge, X. (2019) · doi:10.1145/3339363.3339391 · Cited by 2
“Finally, the SURF [19] algorithm is applied to the underwater degraded image and the corresponding enhanced image proposed by our method to match the local feature points of these images (see Fig.7).”
MethodSURF-Based Image Matching Method for Landing on Small Celestial Bodies
Chen, Y.-L., & Gao, J. (2019) · doi:10.2991/masta-19.2019.68 · Cited by 2
Metode Pengenalan Tempat Secara Visual Berbasis Fitur CNN untuk Navigasi Robot di Dalam Gedung
Afrisal, H. (2019) · Jurnal Teknologi dan Sistem Komputer · doi:10.14710/jtsiskom.7.2.2019.47-55 · Cited by 3
Online Panorama Image Generation for a Disaster Rescue Vehicle
Sovetov, K., Kim, J., & Kim, D. (2019) · International Conference on Ubiquitous Robots (UR) · doi:10.1109/urai.2019.8768497 · Cited by 2
Content-based image retrieval using local ternary wavelet gradient pattern
Srivastava, P., & Khare, A. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08039-5 · Cited by 2
Explicit Learning of Feature Orientation Estimation
Dai, J., Zhang, J., & Nguyen, T. Q. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803644 · Cited by 3
“SURF [4] applies guassian weights to the wavelet responses in horizontal and vertical directions, and from which, determines the orientation for the patch.”
BackgroundMethodInfluential3D Optical Reconstruction of Building Interiors for Game Development
Szwoch, M., & Bartoszewski, D. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-31254-1_15 · Cited by 2
Fuzzy tissue detection for real-time focal control in corneal confocal microscopy
Bartschat, A., Allgeier, S., Scherr, T., et al. (2019) · at - Automatisierungstechnik · doi:10.1515/auto-2019-0034 · Cited by 2
Qiu, Y. J., Li, X., Ding, S., et al. (2019) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2019.8868352 · Cited by 2
“Firstly, the feature points are extracted and matched using Speeded Up Robust Features (SURF) algorithm.”
Outdoor Mapping Framework: from Images to 3D Model
Skuratovskyi, S., Gorovyi, I. M., Vovk, V., et al. (2019) · Signal Processing Symposium (SPSympo) · doi:10.1109/sps.2019.8882019 · Cited by 2
“Such algorithms as scale-invariant feature transform (SIFT) [17] and speeded-up robust features (SURF) [18] are good tools of choice due to high robustness to extremal viewing angles and varying illumination.”
MethodSystem of Feature Extraction for Video Pattern Recognition on FPGA
Sergiyenko, A., Serhiienko, P. A., Orlova, M., et al. (2019) · IEEE Ukraine Conference on Electrical and Computer Engineering (UKRCON) · doi:10.1109/ukrcon.2019.8879958 · Cited by 2
“Among them DSIFT method has much less complexity [4], SURF method utilizes the integer calculations instead of floating point ones, as well as the wavelet functions and Haar transform [5], the descriptors of the HOG method represent the image gradient sets in the Pavlo Serhiienko Department of System Programming and S…”
Method3D Indoor Mapping Based on Camera Visual Odometry Using Point Cloud
Syahputra, K. A., Dewantara, B. S. B., & Pramadihanto, D. (2019) · International Electronics Symposium (IES) · doi:10.1109/elecsym.2019.8901563 · Cited by 2
“From the image captured before, feature detection is performed using SURF (Speeded Up Robust Feature) Method [16], [17] and feature matching to”
MethodVideo Data Hierarchical Retrieval via Deep Hash Method
Suo, Y., Zhang, C. G., Xi, X., Wang, X., & Zou, Z. (2019) · IEEE International Conference on Communication Software and Networks · doi:10.1109/iccsn.2019.8905258 · Cited by 2
“There are some representative approaches such as SIFT, Speeded Up Robust Features (SURF) [12] and Histogram of Oriented Gradient (HOG) [13].”
MethodSpatial Aggregation of Visual Features for Image Data Search in a Large Geo-Tagged Image Dataset
Alfarrarjeh, A., Kim, S. H., Bright, A., Hegde, V., Akshansh, A., & Shahabi, C. (2019) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2019.00-43 · Cited by 2
The Application of Image Processing in UAV Reconnaissance Information Mining System
Pan, Q., Wang, J., Yu, H., et al. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-3-030-30825-4_4 · Cited by 2
Learning Local Feature Descriptor with Motion Attribute For Vision-based Localization
Song, Y., Zhu, D., Li, J., Tian, Y., & Li, M. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967749 · Cited by 2
Laser-Supported Monocular Visual Tracking for Natural Environments
Chahine, G., & Pradalier, C. (2019) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar46387.2019.8981604 · Cited by 2
A Fast Method for Image Matching and Registration Based on SIFT Algorithm and Image Pyramid
Chuang, G., Jia, F., Tang, W., et al. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1449/1/012119 · Cited by 2
“The SIFT algorithm has the characteristics of scale and rotation invariance, strong anti-noise performance, etc., but SIFT algorithm calculation speed is slow, large amount of data, high complexity, long time consumption [7].”
Rodriguez, J., & Castaño-Cano, D. (2019) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar46387.2019.8981626 · Cited by 2
Reliability Validation of Learning Enabled Vehicle Tracking
Sun, Y., Zhou, Y., Maskell, S. R., et al. (2020) · Research Portal (Queen's University Belfast) · doi:10.48550/arxiv.2002.02424 · Cited by 2
Combining Local Binary Pattern and Speeded-Up Robust Feature for Content-Based Image Retrieval
Srivastava, P., Khare, M., & Khare, A. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-3380-8_32 · Cited by 2
Similarity Metric for Millions of Unlabeled Face Images
Salman, H., & Zhan, J. (2020) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc47524.2020.9031220 · Cited by 2
Stereo Vision Based Speed Estimation for Autonomous Driving
Umamaheswaran, S., Malavika Nair, M., Joseph, A. Z., et al. (2019) · doi:10.1109/icit48102.2019.00042 · Cited by 2
“Also from literature it was identified that SIFT outperforms [9] other image matching algorithms like ORB [10] and SURF [11] in most of the scenarios.”
MethodAutomated Iris Segmentation and Robust Features Extraction Based on Parallel SURF Feature Model
Rahmani, V., & Narouei, M. A. (2020) · International Computer Conference, Computer Society of Iran (CSICC) · doi:10.1109/csicc49403.2020.9050083 · Cited by 2
“The Speed Up Robust Features extraction (SURF) is one of the most popular and robust feature extractor method in computer vision [9].”
MethodA Low-Cost, Wide-Range and Multi-Functional Vision Backend of Sailboat Research Testbed
Yu, X., Qi, W., Sun, Q., et al. (2019) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar47638.2019.9044018 · Cited by 2
“Since each image contains plenty of features and two adjoining images have at least 30% overlap, therefore, we then use SURF [8] or SIFT [9] feature extractor to extract features and conduct pair-wise matching for each pair of images.”
MethodA Sensor Suite for Toeboard Three-Dimensional Deformation Measurement During Crash
Song, M., Chen, C., Furukawa, T., et al. (2020) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2019-22-0014 · Cited by 2
Perspective template matching by differential evolution introducing the group remaking
Sato, J., Yamada, T., Ito, K., et al. (2020) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.23134 · Cited by 2
“In order to avoid this problem, feature point-based meth-ods such as scale invariant feature transform [1] and speed up robust feature [2] are often used.”
MethodA framework for automated bone age assessment from digital hand radiographs
Simu, S., & Lal, S. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08816-7 · Cited by 2
“Speeded Up Robust Features (SURF) uses box filters as an approximation of Laplacian of Gaussian (LoG) [1].”
BackgroundMethodLEDCOM: A Novel and Efficient LED Based Communication for Precision Agriculture
Vineeth, K. V. S., Prasad, Y. R. V., Dubey, S. R., et al. (2019) · IEEE Conference on Information and Communication Technology (CICT) · doi:10.1109/cict48419.2019.9066177 · Cited by 2
“There are several other feature detectors like SIFT [19] and SURF [20] that describe features at different scales by approximating a Gaussian scale space of an image.”
MethodTriangular road signs detection and recognition algorithm and its embedded system implementation
Chou, T., Chang, S. Y., Vinay, M., et al. (2017) · Cited by 2
Machine Learning-based Diffractive Imaging with Subwavelength Resolution
Ghosh, A., Roth, D. J., Nicholls, L. H., et al. (2020) · Conference on Lasers and Electro-Optics · doi:10.1364/cleo_qels.2020.fw3b.7 · Cited by 2
“Conventional techniques, built with computer vision in mind, call for image segmentation, edge identification, and analysis of edge distribution within the image[27-29].”
IMRL: An Improved Inertial-Aided KLT Feature Tracker
Quan, M., Mu, B., & Chai, Z. (2019) · IEEE Conference on Cybernetics and Intelligent Systems · doi:10.1109/cis-ram47153.2019.9095829 · Cited by 3
“Feature tracking algorithms can be divided into two categories: intensity-based [1][2][3] and descriptor-based [4][5] [6][7] approaches.”
BackgroundTri-level optimization-based image rectification for polydioptric cameras
Lee, S., An, G. H., Kim, J., Yun, K., Cheong, W., & Kang, S. (2020) · Signal Processing Image Communication · doi:10.1016/j.image.2020.115884 · Cited by 2
Homography estimation along short videos by recurrent convolutional regression network
Mi, Y., Zheng, K., & Wang, S. (2020) · Mathematical Foundations of Computing · doi:10.3934/mfc.2020014 · Cited by 2
Multi-Directional Projection Transformations for Machine Learning based Object Matching
Kertész, G., Szénási, S., & Vámossy, Z. (2019) · IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI) · doi:10.1109/saci46893.2019.9111566 · Cited by 2
Robust Adaptable Segmentation-Based Copy Move Forgery Detection Method
Dhanya, R., & Kalaiselvi, R. (2020) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-3992-3_61 · Cited by 2
AFM Tip Localization on Large Range Sample Using Particle Filter for MEMS Inspection
Liu, Y., Huang, K., Huang, C.-C., et al. (2020) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc45564.2020.9147562 · Cited by 2
Microscale Precision of 6DOF Localization Rectification of Low-End Stereo Vision Using Deep Learning
Farag, R., Saad, M., Emara, H., & Bahgat, A. K. (2020) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie45063.2020.9152567 · Cited by 2
Yang, Z., Wang, Y., Zhang, C., et al. (2020) · Journal of Fusion Energy · doi:10.1007/s10894-020-00251-8 · Cited by 2
Iraqi license plate recognition system using (YOLO) with SIFT and SURF Algorithm
Jasem, N. H. (2020) · JOURNAL OF MECHANICS OF CONTINUA AND MATHEMATICAL SCIENCES · doi:10.26782/jmcms.2020.08.00048 · Cited by 4
Visual SLAM Location Methods Based on Complex Scenes: A Review
Zhang, H., & Peng, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-57881-7_43 · Cited by 2
Blur-Countering Keypoint Detection via Eigenvalue Asymmetry
Zhang, C., Lu, X., & Akashi, T. (2020) · IEEE Access · doi:10.1109/access.2020.3020561 · Cited by 2
Research on the Technology of Searching for Fashion Trend Image Based on ResNet50 Model
Tian, Y., Zheng, Z., Li, G., et al. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1642/1/012011 · Cited by 2
“The local features commonly used in images are Harris corner [3], SURF feature [4], SIFT feature [5], and Msers region of maximum stable extreme value region [6].”
MethodFuzzy Granule Manifold Alignment Preserving Local Topology
Li, W., Xue, J., Chen, Y., et al. (2020) · IEEE Access · doi:10.1109/access.2020.3027311 · Cited by 2
“In this paper, we used Histogram of Oriented Gradients (HOG) [56] and Speeded Up Robust Features (SURF) [57] as image features.”
MethodPerceptual Modelling of Unconstrained Road Traffic Scenarios with Deep Learning
Nidamanuri, J., Karri, A. P., & Venkataraman, H. (2020) · International Conference on Advanced Computer Information Technologies (ACIT) · doi:10.1109/acit49673.2020.9208871 · Cited by 2
“On the other hand, Scale-Invariant Feature Transform (SIFT) [10] were proposed to detect rear faces of vehicles with partial occlusions and Speeded-up Robust features (SURF) [11] was used for vehicle detection in blind spots.”
MethodRodriguez, M. P., Facciolo, G., von Gioi, R. G., et al. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9191245 · Cited by 2
“SIFT has inspired numerous variations over the past 15 years [3, 4, 5].”
BackgroundPhenotypic evaluation of Brown Swiss dairy cattle using images processing
Alatrista-Salas, H., Lopez, J. M. A., Fuentes, E., et al. (2020) · IEEE Latin America Transactions · doi:10.1109/tla.2020.9398641 · Cited by 2
“…modelos basados en t´ecnicas de apariencia, como Histogram of Oriented Gradients (HOG) [9], caracter´ısticas de Wavelet , caracter´ısticas de color, algo-ritmo de Tamura, algoritmo de Speeded Up Robust Features (SURF) [10], Local Binary Patterns (LBP) [11] y Fuzzy Local Binary Patterns (Fuzzy-LBP).”
BackgroundUIScreens: extracting user interface screens from mobile programming video tutorials
Alahmadi, M. D., Tayeb, A. J., Malkadi, A., Parra, E., & Haiduc, S. (2020) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3368089.3417935 · Cited by 2
“The script uses the Speeded Up Robust Features (SURF) algorithm [2] to extract and compare the feature vectors of pairs of UI screens using Euclidean distance.”
MethodClassification of Neuroblastoma Histopathological Images Using Machine Learning
Panta, A., Khushi, M., Naseem, U., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63836-8_1 · Cited by 2
“Bay et al.[10] has also shown that the SURF feature extraction method can outperform SIFT on multiple occasions.”
MethodDog Noseprint Identification Algorithm
Cho, S., Paeng, J., Kim, T., et al. (2021) · International Conference on Information Networking · doi:10.1109/icoin50884.2021.9333973 · Cited by 2
“We used three matching algorithms, namely, SIFT [6], speeded up robust features (SURF) [8], and oriented FAST and rotated BRIEF (ORB) [9].”
MethodCity-Scale Point Cloud Stitching Using 2D/3D Registration for Large Geographical Coverage
Yao, S., Aliakbarpour, H., Seetharaman, G. S., et al. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68793-9_3 · Cited by 2
Efficient Outlier Removal Combining REPPnP and the Levenberg-Marquardt Method
Aizono, K., & Matsushima, K. (2020) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc51575.2020.9345016 · Cited by 3
Non-negative discriminative collective target nearest-neighbor representation
Sun, Y., Zhou, J., Sun, Y., Zhou, Y., Yu, Y., & Sun, Z. (2021) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-021-00169-0 · Cited by 2
“Hence, the SURF feature is adopted to filter noise.”
BackgroundInfluentialLeveraging attention‐based visual clue extraction for image classification
Cui, Y., Du, Y., Wang, X., Wang, H., & Su, C. (2021) · IET Image Processing · doi:10.1049/ipr2.12280 · Cited by 2
“Some representative human-designed features, such as the histogram of oriented gradients (HOG) [4], local binary pattern (LBP) [5], the scale invariant feature transform (SIFT) [6] and speeded up robust feature (SURF) [7], have been proposed.”
BackgroundA Preliminary Study for Identification of Additive Manufactured Objects with Transmitted Images
Yamamoto, K., Kawamura, R., Takazawa, K., et al. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77772-2_29 · Cited by 2
“In this experiment, the SURF algorithm[34] was used to perform feature extraction.”
MethodDeep Learning Based Formation Control of Drones
Kaboré, K., & Güler, S. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-77939-9_11 · Cited by 2
Inserting and tracking a plane object in a three-dimensional scene
Oufqir, Z., Abderrahmani, A. E., & Satori, K. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11536-1 · Cited by 2
“The second one presents the markerless methods, these methods are the most used in augmented reality [42], they detect the characteristic points of a scene without any prior knowledge of the environment by using descriptors such as SIFT [33], SURF [10], BRIEF [24].”
MethodAnalysis on Texture Feature Extraction Methods for Face Recognition in New Born
Rahamathunnisa, U., & Sudhakar, K. S. (2021) · International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT) · doi:10.1109/rteict52294.2021.9573777 · Cited by 2
“Principal Component Analysis (PCA) is provides better accuracy than Linear Discriminant Analysis (LDA) [27] and Speeded Up Robust Features (SURF) [28] methods.”
MethodNatural Scene Text Recognition Using Convolutional Recurrent Neural Network
Wang, Y., & Ha, J.-E. (2021) · International Conference on Computer Science & Education (ICCSE) · doi:10.1109/iccse51940.2021.9569296 · Cited by 2
A Texture Features-Based Robust Facial Expression Recognition
Goswami, J. K., Jalal, S., Negi, C. S., & Jalal, A. S. (2021) · International Journal of Computer Vision and Image Processing · doi:10.4018/ijcvip.2022010103 · Cited by 2
A Noise-robust Feature Fusion Model Combining Non-local Attention for Material Recognition
Zhou, C., Yang, Y., Lu, Z., Liu, D., & Yang, Y. (2022) · International Conference on Image and Graphics Processing (ICIGP) · doi:10.1145/3512388.3512450 · Cited by 3
“Initially, researchers proposed a variety of handcraft classic feature descriptors, such as SIFT [23], SURF [2] and so on, in order to reduce or eliminate the influence of factors such as illumination, rotation, and viewing angle.”
BackgroundXie, H., Chen, W., & Wang, J. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-030-95892-3_1 · Cited by 2
Fundamentals of Machine Vision
Stiller, C., Bachmann, A., & Geiger, A. (2015) · Springer eBooks · doi:10.1007/978-3-319-09840-1_21-1 · Cited by 2
Mookerjee, M., Chan, M. A., Gil, Y., Gill, G., Goodwin, C., Pavlis, T. L., Shipley, T. F., Swain, T., Tikoff, B., & Vieira, D. (2022) · Geological Society of America eBooks · doi:10.1130/2022.2558(01 · Cited by 2
Simultaneous Localization and Mapping
Sünderhauf, N. (2023) · Springer tracts in advanced robotics · doi:10.1007/978-3-031-24017-1_2 · Cited by 2
Robust and Accurate Visual Odometry by Stereo
Cumani, A., & Guiducci, A. (2009) · Lecture notes in electrical engineering · doi:10.1007/978-0-387-85437-3_48 · Cited by 2
Continuous Visual Codebooks with a Limited Branching Tree Growing Neural Gas
Kortkamp, M., & Wachsmuth, S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15825-4_24 · Cited by 2
“An example for a local image description is the SURF feature [1].”
BackgroundMethodInfluentialParallel algorithms for iris biometrics
Panda, A. C. (2011) · Cited by 3
Robotic Goal-Based Semi-Autonomous Algorithms Improve Remote Operator Performance
Hunt, S. D. (2010) · Human Biology · Cited by 2
Image Background Matching for Identifying Suspects
Fogg, P. N., Peterson, G. L., & Veth, M. J. (2008) · IFIP International Federation for Information Processing/IFIP · doi:10.1007/978-0-387-84927-0_24 · Cited by 2
“The average recognition rates or accuracy of detecting repeat locations for SURF, SURF-128 and SIFT are 82.6%, 85.7% and 78.1%, respectively [2].”
BackgroundMethodInfluentialEfficient Random Sampling for Nonrigid Feature Matching
Fan, L., & Pylvänäinen, T. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-10331-5_43 · Cited by 2
Quantization of Discrete Probability DistributionsPreprint
Reznik, Y. A. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1008.3597 · Cited by 3
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.