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 9,901–10,000 of 14,752
Bifocal Matching Using Multiple Geometrical Solutions
Carrasco, M., & Mery, D. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25346-1_18 · Cited by 2
“This process was performed with the SURF [3] algorithm, from which we selected the best k sets with the least projection error according to the MLESAC estimator.”
MethodYin, S., Ouyang, P., Liu, L., et al. (2015) · IEEE Custom Integrated Circuits Conference (CICC) · doi:10.1109/cicc.2015.7338481 · Cited by 2
A Computational Model for Landmarks Acquisition in Positioning
Zhou, Y., Wu, D., Du, J. Y., et al. (2015) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-015-0276-1 · Cited by 2
Concentration analysis by detecting face features of learners
Cha, S., & Kim, W. (2015) · IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM) · doi:10.1109/pacrim.2015.7334807 · Cited by 2
Bayes pooling of visual phrases for object retrieval
Jiang, W., Zhao, Z., & Su, F. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2939-0 · Cited by 2
“We extract 128-dimension RootSIFT descriptors [1] on Hessian detectors [2] from images.”
MethodBrno University of Technology at TRECVid 2010 SIN, CCD
Hradiš, M., Řezníček, I., Barina, D., et al. (2010) · TRECVID · Cited by 2
Spatial-temporal correlation for trajectory based action video retrieval
Shen, X., Zhang, L., Wang, Z., et al. (2015) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2015.7340811 · Cited by 2
A Sub-Harris Operator Coupled with SIFT for Fast Images Matching in Low-altitude Photogrammetry
He, H., Chen, X., Liu, B., et al. (2014) · International Journal of Signal Processing Image Processing and Pattern Recognition · doi:10.14257/ijsip.2014.7.3.32 · Cited by 2
CEA LIST at Trecvid 2012: Semantic Indexing and Instance Search
Ballas, N., Labbé, B., Borgne, H. L., et al. (2012) · Cited by 2
Boosting Binary Image Descriptors
Trzcinski, T. P., & Christoudias, C. M. (2012) · Cited by 3
AN EFFICIENT HYBRID REAL TIME FACE RECOGNITION ALGORITHM IN JAVA ENVIRONMENT
Abdou, M. A., & Fathy, M. (2015) · Cited by 2
Online Kernel-Based Multimodal Similarity Learning with Application to Image Retrieval
Zhang, W., & Zhang, H. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-22053-6_24 · Cited by 4
Underwater floor pattern matching with an unmanned underwater vehicle
Kim, J., Kang, H., Kim, M.-K., et al. (2015) · International Conference on Ubiquitous Robots and Ambient Intelligence · doi:10.1109/urai.2015.7358874 · Cited by 2
Improving Camera Pose Estimation for Indoor Marker-less Augmented Reality
Sudirman, S., & El-Rhalibi, A. (2015) · doi:10.1109/cit/iucc/dasc/picom.2015.150 · Cited by 2
“One of the first corner detectors is Harris detector [20] in 1988 and since there are numerous more developed including GFTT [21], FAST [22], ORB [23], MSER [24], SIFT [25] and SURF [26].”
MethodAutomatic structural matching of 3D image data
Ponomarev, S. V., Lutsiv, V. R., & Malyshev, I. A. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2194312 · Cited by 2
“[12] Bay, H.”
Dewanti, F., & Sumiharto, R. (2015) · IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) · doi:10.22146/ijeis.7640 · Cited by 2
“3D quadratic menggunakan ekspansi Taylor terhadap fungsi scale-space, D(x,y,σ), yang digeser sedemikian rupa sehingga titik origin-nya digunakan sebagai titik uji menggunakan persamaan (2) berikut :”
BackgroundMSURF: A new image matching algorithm which combines homography and SURF algorithm
Zhong, S., Yifu, C., Zhang, M., Zhong, X., & Liu, C. (2015) · International Conference on Geoinformatics · doi:10.1109/geoinformatics.2015.7378709 · Cited by 3
PerLoc: Enabling Infrastructure-Free Indoor Localization with Perspective Projection
Feng, P., Zhang, L., Liu, K., et al. (2015) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass.2015.47 · Cited by 2
“With this typical setting, a SURF feature descriptor can be represented as a vector with 64 dimensions.”
MethodInfluentialEvaluation of Clustering Configurations for Object Retrieval Using SIFT Features
Fernández-Robles, L., Castejón‐Limas, M., Alfonso‐Cendón, J., et al. (2015) · Lecture notes in management and industrial engineering · doi:10.1007/978-3-319-12754-5_21 · Cited by 2
“Later, Bay, Tuytelaars and Van Gool [3] outperformed previously proposed schemes with respect to repeatability, distinctiveness, robustness and speed.”
BackgroundMethodModeling Relationship between Visual Impression of Products and Their Graphical Features
Niwa, S., & Kato, T. (2013) · Communications in computer and information science · doi:10.1007/978-3-642-39473-7_140 · Cited by 2
“2 Shape Features As the shape graphical features, we calculated SURF (Speeded Up Robust Features) [4].”
MethodDynamic Hand Localization and Tracking using SURF and Kalman Algorithm
Golash, R., & Jain, Y. K. (2014) · International Journal of Computer Applications · Cited by 2
Inter-Concept Distance Measurement with Adaptively Weighted Multiple Visual Features
Nakamura, K., & Babaguchi, N. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16634-6_5 · Cited by 2
Efficiently Scaling Edge Detectors
Kerr, D., Coleman, S., & Scotney, B. (2011) · Cited by 2
Savchenko, A., Milov, V. R., & Belova, N. S. (2015) · Communications in computer and information science · doi:10.1007/978-3-319-26123-2_2 · Cited by 2
Imbalanced Learning Ensembles for Defect Detection in X-Ray Images
Díez-Pastor, J.-F., García‐Osorio, C., Barbero-García, V., & Álamo, A. B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-38577-3_68 · Cited by 4
Increase Efficiency of SURF using RGB Color Space
Wafy, M. H., & M., A. (2015) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2015.060810 · Cited by 2
“SURF (Speeded Up Robust Features) algorithm was adopted by Bay et al. [1].”
MethodBag-of-Visual-Words, its Detectors and Descriptors; A Survey in Detail
Faraji, M., & Shanbehzadeh, J. (2015) · Cited by 2
State-of-the-Art: Transformation Invariant Descriptors
Sreeraj, M., & Asha, S. (2013) · Dyuthi Digital Repository (Cochin University of Science and Technology) · Cited by 2
Sun, M., Yang, S., Jiang, J., et al. (2015) · Bio-Medical Materials and Engineering · doi:10.3233/bme-151421 · Cited by 2
“The strategy adopted in SURF algorithm [12] is an integral image, in which the image is iterated only once.”
Multi-users Real-Time Interaction with Bacterial Biofilm Images Using Augmented Reality
Hosseini, M. K., Bednarz, T. P., & Sowmya, A. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-07464-1_28 · Cited by 2
“Scale-invariant feature transform [5], Speeded Up Robust Features [6] and Harris [7] corner detector methods have been used widely in the literature to detect features but heavy mathematical computation involved in any of these methods may slow down an application significantly.”
MethodMatsui, T., Katagiri, Y., Katagiri, H., et al. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.08.160 · Cited by 2
A real-time tracking method based on SURF
Wang, W., Zhou, Y., Zhu, X., et al. (2015) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2015.7407898 · Cited by 2
“Gao et al.[7] make use of SIFT, SURF[6] , RANSAC[8] to form a mobile vehicle detection method, greatly enhance the precision of detection.”
MethodMap fusion in an independent multi-robot approach
Ballesta, M., Gil, A., Reinoso, Ó., Payá, L., & Jiménez, L. M. (2010) · WSEAS TRANSACTIONS on SYSTEMS archive · Cited by 2
Object contour detecting using pseudo zernike moment and multi-layer perceptron
Borzue, N., & Karim Faez, A. (2015) · National and International Iranian Conference on Biomedical Engineering (ICBME) · doi:10.1109/icbme.2015.7404160 · Cited by 3
“Table 1 compares the results of PZM with two different feature extractors of Scale-Invariant Feature Transform (SIFT) [27] and Speeded Up Robust Features (SURF) [28] on the task of object contour detection.”
ResultEvaluation of Keypoint Descriptors for Gender Recognition
Iglesias, F. S., Buemi, M. E., Acevedo, D. G., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-12568-8_69 · Cited by 2
Olojede, A., & Suleman, H. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27974-9_22 · Cited by 2
“The nearest neighbours are defined as the key points with minimum Euclidean distance from the given descriptor vector [9].”
BackgroundMethodMulti-frame Feature Integration for Multi-camera Visual Odometry
Chien, H.-J., Geng, H., Chen, C., & Klette, R. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-29451-3_3 · Cited by 3
Improving surf interest point detection for defocus blur robustness
Saad, E., & Hirakawa, K. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351359 · Cited by 2
Tapping motion blur for robust normal estimation of planar scenes
Vasu, S., Rajagopalan, A. N., & Seetharaman, G. S. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351305 · Cited by 1
KIDS Lab at ImageCLEF 2012 Personal Photo Retrieval
Ku, C.-W., Chien, B.-C., Chen, G., et al. (2012) · CLEF (Online Working Notes/Labs/Workshop) · Cited by 2
An improved averaging combination method for image and object recognition
Yingli, W., Wang, W., & Wang, R. (2015) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew.2015.7169751 · Cited by 2
Object transparent vision combining multiple images from different views
Judvaitis, J., Hermanis, A., Nesenbergs, K., et al. (2015) · Automatic Control and Computer Sciences · doi:10.3103/s0146411615050053 · Cited by 2
“There are several existing algorithms for keypoint detection: SURF [16] SIFT [17] ORB [18], etc.”
MethodBoF based Action Recognition using Spatio-Temporal 2D Descriptor
Kim, J.-O. (2015) · Journal of Internet Computing and services · doi:10.7472/jksii.2015.16.3.21 · Cited by 2
MRSL: Autonomous Neural Network-Based 3-D Positioning System
Hedayati, H., & Tabrizi, N. (2015) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci.2015.88 · Cited by 2
A novel semi-blind video watermarking using KAZE-PCA-2D Haar DWT scheme
Prasad, K. L., Rao, T. C. M., & Kannan, V. (2015) · IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) · doi:10.1109/iccic.2015.7435721 · Cited by 2
Image Features and Feature Processing
Xu, L., Lin, W., & Kuo, C. ‐. J. (2015) · Springer briefs in electrical and computer engineering · doi:10.1007/978-981-287-468-9_3 · Cited by 3
Leveraging Human Computations to Improve Schematization of Spatial Relations from Imagery
Rao, H., Huang, S., & Fu, W. (2016) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2873065 · Cited by 1
Lossless Location Coding for Image Feature Points
Choi, G., Jung, H.-I., & Kim, H.-K. (2013) · International Journal of Machine Learning and Computing · doi:10.7763/ijmlc.2013.v3.290 · Cited by 2
EZCam: WYSWYG Camera Manipulator for Path Design
Li, C.-C., Lai, Y., Syu, N.-S., Guo, H.-N., Todorov, D., & Yao, C. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2543018 · Cited by 2
“efficient without the need of expensive feature detection such as scale-invariant feature transform [28] and speeded up robust features [29].”
BackgroundStojancic, M., & Eakins, D. (2011) · SMPTE Motion Imaging Journal · doi:10.5594/j18060xy · Cited by 2
Subset Selection for Landmark Modern and Historic Images
Ali, H. K., & Whitehead, A. D. (2015) · doi:10.5121/csit.2015.50607 · Cited by 2
A Novel Keypoint Detection in Wavelet Pyramid Space
Gao, Y., Zhang, H., & Guo, J. H. (2011) · International Journal of Digital Content Technology and its Applications · doi:10.4156/jdcta.vol5.issue6.8 · Cited by 2
A fully visual based business document classification system
Infantino, I., Maniscalco, U., Stabile, D., et al. (2014) · Science and Information Conference · doi:10.1109/sai.2014.6918208 · Cited by 2
Design of Binary Robust Independent Elementary Features through Compressive Sensing View
Zhang, J., Liu, X., & Liu, X. (2015) · International Journal of Applied Physics and Mathematics · doi:10.17706/ijapm.2015.5.1.67-75 · Cited by 2
“So on top of SIFT, people developed Speeded up robust features(SURF) [3] and PCA-SIFT [4].”
MethodRady, S. (2016) · Studies in computational intelligence · doi:10.1007/978-3-319-14194-7_12 · Cited by 2
Planar Object Recognition Using Local Descriptor Based On Histogram Of Intensity Patches.
Jakab, M. (2013) · Cited by 2
Kernel Visual Keyword Description for Object and Place Recognition
Ali, A. M., & Rashid, T. A. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-28658-7_3 · Cited by 2
Development of a system for practical skill training of maintenance personnel
Yu, Y., Yamasaki, Y., Kajihara, Y., et al. (2015) · Innovation and supply chain management · doi:10.14327/iscm.9.83 · Cited by 2
Estimating deformation factors of planar patterns in spherical panoramic images
Kim, B.-S., & Park, J.-S. (2016) · Multimedia Systems · doi:10.1007/s00530-016-0513-x · Cited by 2
“[9, 10] proposed SURF which is a speedup version of SIFT.”
Using Apache Lucene to Search Vector of Locally Aggregated Descriptors
Amato, G. M., Bolettieri, P., Falchi, F., Gennaro, C., & Vadicamo, L. (2016) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0005722503830392 · Cited by 2
A Method of Acceleration Applied in Symmetric-SIFT and SIFT
Zhao, D., Wang, Q., Sun, H., et al. (2013) · Lecture notes in electrical engineering · doi:10.1007/978-3-642-38466-0_64 · Cited by 2
Image based reconstruction for cystoscopy
Brischwein, M., Wittenberg, T. C., & Bergen, T. (2015) · Current Directions in Biomedical Engineering · doi:10.1515/cdbme-2015-0113 · Cited by 2
Poster Abstract: Efficient Visual Positioning with Adaptive Parameter Learning
Wen, H., Wang, S., Clark, R., et al. (2016) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1109/ipsn.2016.7460701 · Cited by 2
Feature Detection and Description using a Harris-Hessian/FREAK Combination on an Embedded GPU
Danielsson, M., Sievert, T., Grahn, H., et al. (2016) · International Conference on Pattern Recognition Applications and Methods · doi:10.5220/0005662005170525 · Cited by 2
“SURF, while based on the same principle, uses Haar wavelets instead of gradients.”
MethodInfluentialCommonality Preserving Multiple Instance Clustering Based on Diverse Density
Fukui, T., & Wada, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16634-6_24 · Cited by 2
Mosaicing scenes with a quadcopter
Prasad, M. G., Chandran, S., & Brown, M. S. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477634 · Cited by 2
Tampering Detection in Low-Power Smart Cameras
Gaibotti, A., Marchisio, C., Sentinelli, A., et al. (2015) · Communications in computer and information science · doi:10.1007/978-3-319-23983-5_23 · Cited by 2
“Background estimates and block matching in [5] enable the displacement detection, while the number of SURF [6] keypoints is used to detect blurring.”
Marker-Less Augmented Reality for Human Robot Interaction
Košnar, K., Vick, A., Přeučil, L., & Krüger, J. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-22383-4_14 · Cited by 2
Fast Stitching Algorithm by using Feature Tracking
Park, S.-Y., Kim, J.-H., & Yoo, J. (2015) · Journal of Broadcast Engineering · doi:10.5909/jbe.2015.20.5.728 · Cited by 2
F-Hessian SIFT-Based Railroad Level-Crossing Vision System
Lim, H.-S., Yoon, H.-S., Kim, C.-H., et al. (2010) · The Journal of the Korea institute of electronic communication sciences · Cited by 2
Cloning Localization Based on Feature Extraction and K-means Clustering
Alfraih, A. S., Briffa, J. A., & Wesemeyer⋆, S. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19321-2_31 · Cited by 2
“The two most commonly used features for cloning detection are (SIFT) [10], (SURF) [3].”
MethodFAB: Fast Angular Binary Descriptor for Matching Corner Points in Video Imagery
Tahir, M., Kanwal, N., & Anjum, F. (2016) · Journal of Robotics · doi:10.1155/2016/3458207 · Cited by 2
How many bits do I need for matching local binary descriptors?
Alcantarilla, P. F., & Stenger, B. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487369 · Cited by 2
“Traditional vectorbased descriptors in floating-point representation such as SIFT [1], SURF [2] and KAZE [3] achieve good performance in most applications.”
InfluentialHYBRID-BASED DENSE STEREO MATCHING
Chuang, T., Ting, H.-W., & Jaw, J. (2016) · 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-xli-b3-495-2016 · Cited by 2
“Moreover, to shrink the potential disparity errors and to enhance the quality of depth estimation at image edges (object boundaries), this study manipulates the USURF descriptor (Bay et al., 2008) to simultaneously recover the edge disparities, and weights both values derived from the stereo and U-SURF matching to fin…”
MethodRobust matching algorithm based on SURF
Luo, Y., & Chen, Y. (2015) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip.2015.7493896 · Cited by 3
“A good number of local feature descriptors have been widely used recently, including SIFT [I], SURF [2], BRIEF [3], ORB [4], DAISY [5], etc.”
BackgroundMethodA low-cost camera-based transducer tracking system for freehand three-dimensional ultrasound
Baba, M. M., Mohamed, O. A., Awwad, F. R., & Daoud, M. I. (2016) · IEEE International New Circuits and Systems Conference (NEWCAS) · doi:10.1109/newcas.2016.7604825 · Cited by 3
“The proposed system extracts local feature keypoints using the Speeded Up Robust Features (SURF) method which is considered fast and robust against different image transformations [16].”
Method3D Scene Reconstruction from Depth Camera Data
Zanuttigh, P., Marin, G., Mutto, C. D., Dominio, F., Minto, L., & Cortelazzo, G. M. (2016) · Springer eBooks · doi:10.1007/978-3-319-30973-6_7 · Cited by 3
Perception in Autonomous Vehicles
Kala, R. (2016) · Elsevier eBooks · doi:10.1016/b978-0-12-803729-4.00003-9 · Cited by 3
Feature Extraction in Content-Based Image Retrieval
Foley, J. J., & Kwan, P. (2014) · Advances in information quality and management · doi:10.4018/978-1-4666-5888-2.ch583 · Cited by 2
Novel Image Descriptor Based on Color Spatial Distribution
Najgebauer, P., Korytkowski, M., Barranco, C. D., et al. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-39384-1_63 · Cited by 2
Detection and matching of object using proposed signature
Elsalamony, H. A. (2014) · Elsevier eBooks · doi:10.1016/b978-0-12-802045-6.00038-7 · Cited by 2
“The determinant of Hessian matrix is where w is recommended as 0.9, that is the relative weight of the filter responses [17,18].”
BackgroundMethodInfluentialNew learning approach for computer-aided diagnostic
Bourass, Y., Zouaki, H., & Bahri, A. (2015) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa.2015.7507201 · Cited by 2
How to Teach Young Kids New Concepts with Interactive Videos and Visual Recognition
To, Q. H., Tran, B.-H., & Tran, M. (2016) · Communications in computer and information science · doi:10.1007/978-3-319-40542-1_46 · Cited by 2
COMMERCIAL VIDEO RETRIEVAL WITH VIDEO-BASED BAG OF WORDS
Wang, J., Lu, H., DUAN, L., et al. (2007) · WORLD SCIENTIFIC eBooks · doi:10.1142/9789812709677_0213 · Cited by 2
Multimedia Interfaces for People Visually Impaired
Dingli, A., & Mercieca, I. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-41962-6_43 · Cited by 2
Scale invariant feature transform evaluation in small dataset
Hassan, A. M. (2015) · International Conference on Sciences and Techniques of Automatic Control and Computer Engineering · doi:10.1109/sta.2015.7505105 · Cited by 2
Fast 2D-to-3D matching with camera pose voting for 3D object identification
Bao, R., & Iwamoto, K. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532440 · Cited by 2
RETOP: A retinal topography keypoint descriptor
Huang, J.-Y., Tsai, H.-Y., & Tsai, C.-H. (2016) · IEEE/ACIS International Conference on Computer and Information Science (ICIS) · doi:10.1109/icis.2016.7550795 · Cited by 2
“The first one is SIFT-like descriptor [2][7][6] which records the values of all the orientation histogram entries surrounding a keypoint, while the second one is binary descriptor [8][9][10][11] that only uses one bit to denote the difference of selected pairs surrounding a keypoint.”
BackgroundMethodReinforcement learning of visual descriptors for object recognition
Naranjo, M. P. (2014) · TDX (Tesis Doctorals en Xarxa) · Cited by 2
A New Hybrid Face Recognition System via Local Gradient Probabilistic Pattern (LGPP) and 2D-DWT
Dahmouni, A., Aharrane, N., Moutaouakil, K. E., et al. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-46568-5_28 · Cited by 2
A Scalable Patch-Based Approach for RGB-D Face Recognition
Grati, N., Ben-Hamadou, A., & Hammami, M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46681-1_35 · Cited by 2
3D Line Segment Based Model Generation by RGB-D Camera for Camera Pose Estimation
Nakayama, Y., Saitô, H., Shimizu, M., et al. (2015) · The Journal of The Institute of Image Information and Television Engineers · doi:10.3169/itej.69.j148 · Cited by 2
Simultaneous camera pose and correspondence estimation in cornerless images
Lin, W.-Y., Guo, D. M., Tan, P., et al. (2009) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2009.5459339 · Cited by 2
FOMP: A Novel Preprocessing Technique to Speed-Up the Outlier Removal from Matched Points
Ramos, J. S., Watanabe, C. Y. V., & Traina, A. J. M. (2016) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2016.039 · Cited by 2
“The most common approach to match a pair of images is the feature-based methods, which encompasses three steps [7]: (1) interest point detection, in which algorithms such as Scale-Invariant Feature Transform (SIFT) [8] and Speed-Up Robust Features (SURF) [9] have been widely used; (2) feature extraction from each poin…”
MethodInfluentialDepth data assisted structure-from-motion parameter optimization and feature track correction
Recker, S., Gribble, C., Shashkov, M. M., et al. (2014) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2014.7041930 · Cited by 2
“Such tracking can be sparse [6], [7] or dense [8] and consists of computing and linking the pixel coordinates in all images for each scene point, whenever it is visible.”
BackgroundStructured output tracking guided by keypoint matching
Fang, Z., Cao, Z., & Xiao, Y. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2241354 · Cited by 2
Classification based character segmentation guided by Fast-Hessian-Affine regions
Ota, T., & Wada, T. (2011) · Asian Conference on Pattern Recognition · doi:10.1109/acpr.2011.6166546 · Cited by 2
“Our method, Fast-Hessian-Affine, is implemented as an all-integer algorithm based on OpenSURF [15].”
MethodInfluentialA Vision-based System to Help Senior Citizens for Memory Recall of Object-placing
Huang, P. S., Huang, C.-P., Hsieh, C., et al. (2011) · International Conference on Instrumentation and Measurement, Computer, Communication and Control (IMCCC) · doi:10.1109/imccc.2011.96 · Cited by 2
“To increase the matching speed, SURF detector and descriptor [12] were used instead in this paper.”
MethodInfluentialA Sparse and Inlier Based SIFT and SURF Features for Automated Face Recognition
Vinay, A., Shekhar, V. S., kar, V. S. S., et al. (2016) · doi:10.1145/2980258.2982112 · Cited by 2
“SURF has several notable characteristics such as repeatability and distinctiveness, and is capable of being computed swiftly by relying on integral images for image convolutions in order to cut down the computation time by utilizing a Fast Hessian matrix [4][27][28].”
BackgroundMethodInfluentialLocal self similarity-based super-resolution for asymmetric dual-camera
Moon, B., Yu, S., Ko, S., et al. (2016) · IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin) · doi:10.1109/icce-berlin.2016.7684713 · Cited by 2
“using SURF [3] and the outliers are removed by the RANSAC algorithm [4].”
MethodInfluential
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.