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 10,001–10,100 of 14,752
Information Theoretic Rotationwise Robust Binary Descriptor Learning
Rhabi, Y. E., Simon, L., Brun, L., Lladós, J., & Lumbreras, F. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-49055-7_33 · Cited by 2
“Due to this important economical and societal repercussions, the design of ever improving descriptors has drawn a strong interest [4,14].”
GPU-accelerated abrupt shot boundary detection
Zheng, Y., & Zhang, Y. (2016) · International Symposium on Communications and Information Technologies · doi:10.1109/iscit.2016.7751609 · Cited by 2
EXPERIENCES WITH USING SIFT FOR MULTIPLE IMAGE DOMAIN MATCHING
Toth, C. K., & Grejner‐Brzezinska, D. A. (2010) · Cited by 2
Special object extraction from medieval books using superpixels and bag-of-features
Yang, Y., & Rushmeier, H. (2016) · Journal of Electronic Imaging · doi:10.1117/1.jei.26.1.011008 · Cited by 2
“(SURF) feature.(38) To build a visual vocabulary, clustering techniques, such as K-means, are generally used.”
BackgroundFast-Gaussian SIFT for Fast and Accurate Feature Extraction
Ke, L., Wang, J., & Ye, Z. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48896-7_35 · Cited by 2
A Cross-Domain Lifelong Learning Model for Visual Understanding
Qing, C., Huang, Z., & Xu, X. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48890-5_43 · Cited by 2
Optimal space subdivision for parallel approximate nearest neighbour determination
Feng, H., Mills, S. J., Eyers, D. M., et al. (2015) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2015.7761548 · Cited by 2
Low-power and real-time computer vision on-chip
Pang, W., Huang, H., An, F., & Yu, H. (2016) · International SoC Design Conference · doi:10.1109/isocc.2016.7799731 · Cited by 2
Mosaicing deep underwater imagery
Purohit, K., Vasu, S., Rajagopalan, A. N., Jyothi, V. B. N., & Raju, R. (2016) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/3009977.3010029 · Cited by 3
Estimation of View Transformations in Images
Cuevas, E., Osuna-Enciso, V., & Oliva, D. A. (2016) · Studies in computational intelligence · doi:10.1007/978-3-319-51109-2_9 · Cited by 2
Utilising Augmented Reality to create a Brand Interaction Application on Mobile Devices
Wong, E. (2011) · Cited by 2
RGB-D Object Recognition from Hand-Held Object Teaching
Qiao, L., Li, X., & Jiang, S. (2016) · International Conference on Internet Multimedia Computing and Service · doi:10.1145/3007669.3007713 · Cited by 2
“To learn feature representation, conventional methods use hand-crafted features, such as SIFT[12], SURF[2]and HOG[17] to describe images from distinct sides such as color, texture, edge, shape, etc.”
MethodLi, C., Zhou, L., & Chen, W. (2016) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi5120244 · Cited by 2
“The first step was to find the point features using the SIFT [63] or the SURF [64] Figure 5.”
MethodTowards 3D pipe reconstruction employing affine transformations from video information
Reyes-Acosta, A. V., López-Juárez, I., Osorio-Comparán, R., et al. (2016) · doi:10.1109/ica-acca.2016.7778430 · Cited by 2
“La correspondencia se realiza mediante detectores y descriptores comúnmente utilizados en el campo como SIFT [5] y SURF [6] como se muestra en la Fig.”
BackgroundComparison of clustering methods for tracking features in RGB-D images
Pancham, A., Withey, D., & Bright, G. (2016) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2016.7793050 · Cited by 2
“This work focused on the evaluation of methods for clustering SURF features from RGB-D images for tracking objects in a dynamic environment.”
MethodInfluentialModelling of feature matching performance on correlated speckle images
Wang, V., & Hayes, M. (2016) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2016.7804419 · Cited by 2
Evolution Strategy Sampling Consensus for Robust Estimator
Toda, Y., & Kubota, N. (2016) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2016.p0788 · Cited by 2
A BRIEF-Gist based efficient place recognition for indoor home service robots
Jeon, Y., Lee, T., Kim, C., Yi, D.-H., & Cho, D. (2016) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.1109/iccas.2016.7832506 · Cited by 2
A distributed bug analyzer based on user-interaction features for mobile apps
Méndez-Porras, A., Méndez-Marín, G., Tablada-Rojas, A., et al. (2017) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-016-0435-7 · Cited by 2
“Bay et al. (2006) proposed SURF (Speed Up Robust Features), an is scale and rotation invariant interest point detector and descriptor.”
MethodTracking Patterns with Particle Swarm Optimization and Genetic Algorithms
Tavares, Y. M., Nedjah, N., & Mourelle, L. D. M. (2017) · International Journal of Swarm Intelligence Research · doi:10.4018/ijsir.2017040103 · Cited by 2
Camera-based document image spotting system for complex linguistic maps
Dang, Q. B., Coustaty, M., Luqman, M. M., et al. (2016) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2016.7844734 · Cited by 2
“This section describes the camera-based document image retrieval systems used to compare the performances of the proposed approach (SIFT - Lowe (2004), SURF - Bay et al. (2006) and ORB - Rublee et al. (2011)).”
MethodInfluentialHigh resolution non-rigid dense matching based on optimized sampling
Zhang, Q., & Tu, C. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.07.076 · Cited by 2
Trainable Siamese keypoint descriptors for real-time applications
Fedorenko, F., Ivanova, A. A., Limonova, E. E., & Konovalenko, I. A. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2266351 · Cited by 2
Heck, V., Stivanello, M. E., & Stemmer, M. R. (2017) · Journal of Signal Processing Systems · doi:10.1007/s11265-017-1228-8 · Cited by 2
“For comparison purposes, a SURF [1] based sparse stereo matching method was used.”
MethodInfluentialAn unsupervised approach for traffic sign recognition based on bag-of-visual-words
Supriyanto, C., Luthfiarta, A., & Zeniarja, J. (2016) · doi:10.1109/iciteed.2016.7863253 · Cited by 2
Robust Feature Extraction Based Watermarking Method Using Spread Transform Dither Modulation
Li, M., & Yuan, X. (2017) · doi:10.1109/cmvit.2017.11 · Cited by 2
Passive image tamper detection based on Fast Retina Key Point Descriptor
Thirunavukkarasu, V., & Kumar, J. S. (2016) · IEEE International Conference on Advances in Computer Applications (ICACA) · doi:10.1109/icaca.2016.7887966 · Cited by 2
THE FOURIER TRANSFORM BASED DESCRIPTOR FOR VISUAL OBJECT CLASSIFICATION
Çevıkalp, H., & Kurt, Z. (2017) · Anadolu University Journal of Science and Technology-A Applied Sciences and Engineering · doi:10.18038/aubtda.300419 · Cited by 2
“It is followed by the proposed FT descriptor and LTP. SURF is the worst performing descriptor.”
MethodInfluentialA 3D Map Reconstruction Algorithm in Indoor Environment Based on RGB-D Information
Yuan, B., & Zhang, Y. (2016) · International Symposium on Parallel and Distributed Computing · doi:10.1109/ispdc.2016.59 · Cited by 2
Qin, X., Jägersand, M., Yang, X., et al. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7900154 · Cited by 2
“6, the performance of our method is much better than SURF [15] in extracting facade features, especially for extracting long structures.”
MethodThe Teleoperation System of Service Robot Based on Cloud Services
Li, J., & Zhang, L. (2017) · Cited by 2
Tracking skeletal fusion feature for one shot learning gesture recognition
Xuejiao, L., & Su, Y. (2017) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc.2017.7984545 · Cited by 2
Design and Calibration of a Specialized Polydioptric Camera Rig
Mazhar, O., Jamaluddin, A. Z., Jiang, C., David Fofi, B., Seulin, R., & Morel, O. (2017) · Frontiers in ICT · doi:10.3389/fict.2017.00019 · Cited by 3
Fazli, S., & Moeini, M. (2015) · Cited by 2
Local appearance modeling for objects class recognition
Taffar, M., & Miguet, S. (2017) · Pattern Analysis and Applications · doi:10.1007/s10044-017-0639-2 · Cited by 2
Visual Odometry for Pedestrians Based on Orientation Attributes of SURF
Marouane, C., Gutschale, R., & Linnhoff–Popien, C. (2017) · Lecture notes in networks and systems · doi:10.1007/978-3-319-56991-8_13 · Cited by 2
Normal direction local binary pattern for fragment reconstruction
Zhang, L., Sun, J., Song, H., et al. (2017) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2017.8019439 · Cited by 2
“However, fragment matching is a different scenario where SIFT and SURF are not applicable due of lack of the overlaps.”
2DIGH: a polar invariant local image descriptor based on joint histogram
Sadeghi, B., Jamshidi, K., Vafaei, A., et al. (2017) · The Visual Computer · doi:10.1007/s00371-017-1433-2 · Cited by 2
“By applying integral image and filter size change instead of image size change, the number of calculations and processing time, compared to the original SIFT algorithm, is reduced [13].”
MethodInfluentialRobust Underwater Image Stitching Based on Graph Matching
Yang, X., Liu, Z., Li, C., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67777-4_46 · Cited by 2
Robust synthetic basis feature descriptor
Raven, L. A., Lee, D.-J., & Desai, A. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296540 · Cited by 2
“Both SIFT and SURF perform well on intensity images with rotation and scaling variations, but their complexity and robustness require extensive computations and storage.”
MethodInfluentialExtraction of specific data from a sound sample by removing additional distortion
Połap, D. (2017) · Annals of Computer Science and Information Systems · doi:10.15439/2017f182 · Cited by 2
“In the next step, we find key points in these images using SURF (Speeded Up Robust Features) algorithm [11].”
MethodDynamic Environments Localization via Dimensions Reduction of Deep Learning Features
Zhang, H., Wang, X., Du, X., Liu, M., & Chen, Q. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68345-4_22 · Cited by 5
“[8– 10,25,26] proved that ConvNets have been demonstrated outperforms traditional hand-crafted features [3,3,16,23].”
BackgroundTowards Automated Optimization of Web Interfaces and Application to E-commerce
Lutfi, A., & Fasciani, S. (2017) · International Conference on Computer and Applications (ICCA) · doi:10.1109/comapp.2017.8079735 · Cited by 6
“Although faster pattern recognition algorithms exist, such as Speeded-Up Robust Features (SURF) [15], which is more suitable for real-time applications, SIFT provides higher accuracy, which is the key selection criteria.”
MethodFeature matching for underwater image via superpixel tracking
Zhang, S., Dong, J., & Yu, H. L. (2017) · International Conference on Automation and Computing (ICAC) · doi:10.23919/iconac.2017.8081988 · Cited by 2
A REVIEW: RECOGNIZING CLOTHES PATTERNS AND COLOURS FOR BLIND PEOPLE USING NEURAL NETWORK
Joshi, S. K. (2017) · International Journal of Advanced Research in Computer Science · doi:10.26483/ijarcs.v8i8.4630 · Cited by 2
Gupta, N., & Rohil, M. K. (2017) · Thematic Workshops of ACM Multimedia · doi:10.1145/3126686.3126759 · Cited by 3
“In last two decades, many feature detectors [12,15,16,17,18] and feature descriptors [7,8,19,20] have been proposed and studied in various combinations.”
BackgroundMethodColor enhanced local binary patterns in covariance matrices descriptors (ELBCM)
Gouiffès, M., y Terán, A. R. M., & Lacassagne, L. (2017) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2017.09.012 · Cited by 2
“To solve the problem, integral images are used to store all the accumulations computed from the origin of the image to each possible point, then the covariance values are obtained fastly by only four readings in these images [25,3].”
BackgroundA blobs detection algorithm based on a simplified form of the fast radial symmetry transform
Πουλόπουλος, Ν., & Psarakis, E. Ζ. (2017) · doi:10.1109/icdsp.2017.8096117 · Cited by 2
Bentaieb, S., Ouamri, A., Keche, M., et al. (2017) · International Conference on Bio-engineering for Smart Technologies (BioSMART) · doi:10.1109/biosmart.2017.8095327 · Cited by 2
POINTO - A LOW COST SOLUTION TO POINT CLOUD PROCESSING
Houshiar, H., & Winkler, S. (2017) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlii-2-w8-111-2017 · Cited by 2
“to the problem of solving the estimation of 3D structure from a stereo vision the SFM method utilizes the feature detection methods such as Scale Invariant Feature Transform (SIFT) (Lowe, 1999; Lowe, 2004) and Speeded Up Robust Features (SURF) (Bay et al., 2006; Bay et al., 2008) for the detection of correspondences”
MethodInfluentialCoordinate multi-robotic system for image taking and visualization via photogrammetry
de Souza, A. R., Raad, R., Batista, M. R., et al. (2017) · Latin American Robotics Symposium and Brazilian Symposium on Robotics (LARS-SBR) · doi:10.1109/sbr-lars-r.2017.8215328 · Cited by 2
“To extract information from the image set, SIFT (Scale-invariant feature transform) [14] or SURF [15] is used, which detects and describes local information from the images.”
MethodImage invariant description based on local Fourier-Mellin transform
Lehiani, Y., Maïdi, M., Preda, M., et al. (2017) · IEEE International Conference on Signal and Image Processing Applications (ICSIPA) · doi:10.1109/icsipa.2017.8120598 · Cited by 2
Object retrieval in past video using bag-of-words model
Nguyen-Hoang, M.-T., Le, T.-K., Ninh, V.-T., Che, Q.-H., Nguyen, V.-T., & Tran, M. (2017) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais.2017.8217565 · Cited by 2
“There are two important steps in this section: 1) Features Extraction: There are many methods to extract features of an image such as Speed Up Robust Features (SURF) [18], Haar wavelets, color histogram, Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG) [19], 2017 International Conference on Control,…”
MethodInfluential3D object tracking using disparity map
Khan, W. A., Pant, D. R., Adhikari, B., et al. (2017) · International Conference on Computing, Communication and Automation · doi:10.1109/ccaa.2017.8229982 · Cited by 2
“A pair has good match [8] if its distance is closer than 0.”
BackgroundMethodInfluentialFused pose estimation using geometric and texture information
Wang, L., Zhang, Q., Wang, Z., et al. (2017) · Chinese Automation Congress · doi:10.1109/cac.2017.8243520 · Cited by 2
“In the 2D image domain, as the RGB images are rich in texture information and have high resolutions, researchers have presented many discriminative descriptors, such as SIFT [2] and SURF [3].”
MethodSegmentation algorithm on smartphone dual camera: application to plant organs in the wild
Bertrand, S., Cerutti, G., & Tougne, L. (2018) · International Conference on Machine Vision · doi:10.1117/12.2314731 · Cited by 2
Dealing with the structured scene in visual odometry(VO): Incomplete SURF
Chenxing, S., Zhang, H., & Xia, Q. (2017) · International Conference on Robotics and Automation Engineering (ICRAE) · doi:10.1109/icrae.2017.8291425 · Cited by 2
A Fast Local Image Descriptor Based on Patch Quantization
Tian, T., Yang, F., Zheng, K., Yao, H., & Gao, Q. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-74521-3_8 · Cited by 2
Comparative analysis of motion based and feature based algorithms for object detection and tracking
Vaidya, B., & Paunwala, C. N. (2017) · doi:10.1109/icsoftcomp.2017.8280088 · Cited by 2
“For that different feature based techniques like Scale invariant feature transform (SIFT) [7], Speeded up robust features (SURF) [8], Haar Cascade [9], Harris [19] and SUSAN corner detectors, Features from Accelerated Segment test (FAST) [10] are used.”
BackgroundMethodInfluentialStitching Pathological Tissue Images using DOP Feature Tracking
Bergler, M., Weiherer, M., Bergen, T., et al. (2018) · Informatik aktuell · doi:10.1007/978-3-662-56537-7_84 · Cited by 2
Online domain adaptation by exploiting labeled features and pro-active learning
Krishnapuram, R. J., Rajkumar, A., Acharya, A., et al. (2018) · doi:10.1145/3152494.3152507 · Cited by 2
Silva, C., Welfer, D., & Dornelles, C. (2018) · INTELIGENCIA ARTIFICIAL · doi:10.4114/intartif.vol21iss61pp1-13 · Cited by 2
Feature based inter prediction optimization for non-translational video coding in cloud
Xuelin, S., Wang, J., Yang, Q. X., et al. (2017) · IEEE Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip.2017.8305066 · Cited by 2
Dense matching for multi-scale images by propagation
Laraqui, M., Saaidi, A., Mouhib, A., & Abarkan, M. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5644-y · Cited by 2
“The objective of this step is to link each point of interest of the left image with its correspondent in the right image by comparing the descriptors of each of the points previously obtained by the SURF detector.”
MethodEffective Parallelization of a High-Order Graph Matching Algorithm for GPU Execution
Lee, C., & Lee, H. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2797992 · Cited by 2
“SIFT [1], SURF [6], and BRIEF [7] descriptors are typically used to represent”
MethodOLED panels inspection using SURF algorithm
Kwon, S., Kwon, T.-G., Lee, Y., et al. (2017) · International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip.2017.8313712 · Cited by 2
“Since the number of dimensions of SURF is smaller than the number of dimensions of 128 in SIFT, the amount of computation is reduced, but the performance is almost similar.”
MethodInfluentialCT-ultrasound registration for electromagnetic navigation of cardiac intervention
Liu, X., Gu, L., Xie, H., & Zhang, S. (2017) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei.2017.8302189 · Cited by 2
Image matching for structured scenes based on ASIFT and homography constraint
Zhai, Y., Yu, G., Wang, H., et al. (2017) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/compcomm.2017.8322914 · Cited by 2
Uncalibrated Vision-Based Control and Motion Planning of Robotic Arms in Unstructured Environments
Shademan, A. (2012) · doi:10.7939/r3035s · Cited by 2
Embedded learning for computerized production of movie trailers
Sheng, J., Chen, Y., Li, Y., et al. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5943-3 · Cited by 2
Combining Feature Extraction and Clustering for Better Face Recognition
Afra, S., & Alhajj, R. (2018) · Lecture notes in social networks · doi:10.1007/978-3-319-78196-9_11 · Cited by 2
PALMPRINT, FINGER KNUCKLE PRINT AND FACE FEATURES FOR THE HUMAN RECOGNITION SYSTEM
Wincy, J. A. (2018) · International Journal of Advanced Research in Computer Science · doi:10.26483/ijarcs.v9i2.5557 · Cited by 2
Towards Automated Transcription of Label Text from Pinned Insect Collections
Agarwal, N., Ferrier, N., & Hereld, M. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00027 · Cited by 3
“We compute correspondences between images using scale invariant SURF features and descriptors [5] and subsequently remove any outliers using RANSAC.”
MethodA Fast and Deterministic Algorithm for Consensus Set Maximization
Xing, Z., & Shi, Z. (2018) · IEEE Access · doi:10.1109/access.2018.2835302 · Cited by 2
Geometrical coding of color images
Nosovskiy, G. V. (2018) · Publications de l Institut Mathematique · doi:10.2298/pim1817159n · Cited by 2
Abadi, I. N., Moussa, A., & El‐Sheimy, N. (2018) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans.2018.8373478 · Cited by 2
“The results obtained in [6] points out that SIFT and Speeded Up Robust Features (SURF) [7] algorithms fail when experiencing a considerable variation in the image orientations more than 45-degree and to compensate, ASIFT [8] (Affine-SIFT) is used.”
MethodGlobal Localization Using Low-frequency Image-based Descriptor and Range Data-based Validation
Park, C.-S., & Song, J. (2018) · International Journal of Control Automation and Systems · doi:10.1007/s12555-016-0491-y · Cited by 2
Object detection on deformable surfaces using local feature sets
Kaleli, F., & Aydın, N. (2017) · IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI) · doi:10.1109/icpcsi.2017.8392069 · Cited by 2
“transform) [1] and SURF(speeded up robust features)[2] have been developed.”
BackgroundMethodInvariant image descriptors and affine morphological scale-space
Sur, F. (2007) · Cited by 2
Sources of uncertainty in feature-based image registration algorithms
Sundlie, P. O., Taylor, C. N., & Fernando, J. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2180628 · Cited by 2
“The method chosen for this study was to employ the SURF algorithm for 2D image registration.(1) The projective transform computed from the corresponding feature locations is termed a homography.”
MethodThe Dark Side of the Face: Exploring the Ultraviolet Spectrum for Face Biometrics
Samatzidis, T., Siegmund, D., Goedde, M., et al. (2018) · International Conference on Biometrics · doi:10.1109/icb2018.2018.00036 · Cited by 2
“Three different feature types are used in our experiments: LBP (Local Binary Patterns) [22], SURF (Speed Up Robust Features) [2] and CSLBP (Center Symmetric LBP) [12].”
Image Processing at Your Fingertips: The New Horizon of Mobile Imaging
Li, X. S. (2014) · Academic press library in signal processing · doi:10.1016/b978-0-12-396501-1.00008-x · Cited by 2
KLASIFIKASI EKSPRESI WAJAH MENGGUNAKAN BAG OF VISUAL WORDS
Muhathir, M. (2018) · InfoTekJar (Jurnal Nasional Informatika dan Teknologi Jaringan) · doi:10.30743/infotekjar.v2i2.181 · Cited by 2
Video denoising for security and privacy in fog computing
Zhang, H., Yang, Y. F., Yuan, D., Sun, D. W., Zhang, J., Li, G., & Sun, M. (2018) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.4763 · Cited by 2
Target Aware Network Adaptation for Efficient Representation Learning
Zhong, Y., Li, V., Okada, R., & Maki, A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11018-5_38 · Cited by 5
Lovagnini, L., Zhang, W., Bijarbooneh, F. H., et al. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240697 · Cited by 2
“In particular, CIRCE uses: SURF: proposed by Bay et al. [3].”
MethodDeep learning performance for digital terrain model generation
Knyaz, V. A. (2018) · doi:10.1117/12.2325768 · Cited by 2
A SAR Image Fast Stitching Algorithm Based on Machine Learning
Yao, H., Wang, H., & Lin, X. (2018) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-00557-3_55 · Cited by 2
Fast Two-Level Image Indexing Based on Local Interest Points
Najgebauer, P., Grycuk, R., & Scherer, R. (2018) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2018.8485831 · Cited by 2
“As aforementioned, the SURF algorithm [8], [18] is a feature extractor designed to search the exact similar content of the entire image or its fragments.”
MethodApplication of Multi-Column Heterogeneous Convolutional Neural Networks in image classification
Wang, G. (2018) · Journal of Computational Methods in Sciences and Engineering · doi:10.3233/jcm-180871 · Cited by 2
“The extraction of features mainly focuses on features such as texture [13,15], color [11], and shape of the image [6,16], using classifiers such as decision tree [5], support vector machine (SVM) [14], and artificial neural network [7] to classify images.”
Acceleration of Image Stitching Using Embedded Graphics Processing Unit
Abughalieh, K. M., Bataineh, O. M., & Alawneh, S. G. (2018) · IEEE International Conference on Electro Information Technology · doi:10.1109/eit.2018.8500187 · Cited by 2
“[2] H. Bay, T. Tuytelaars and L. V. Gool, "SURF: Speeded Up Robust Features," in Computer Vision – ECCV 2006, Springer Berlin Heidelberg, 2006, pp. 404-417.”
MethodAutomating the Optimization of Web Interfaces for E-Commerce
Lutfi, A., & Fasciani, S. (2018) · Springer eBooks · doi:10.1007/978-3-319-89914-5_13 · Cited by 2
Tiwari, V., & Jain, S. C. (2018) · Recent Advances in Computer Science and Communications · doi:10.2174/2213275912666181127120030 · Cited by 2
Video Stitching with Extended-MeshFlow
Chen, K., Yao, J., Xiang, B., et al. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545663 · Cited by 2
Potgieter, M., & van Niekerk, J. (2013) · SAIEE Africa Research Journal · doi:10.23919/saiee.2013.8531868 · Cited by 2
Content-Based Image Retrieval Using Multiresolution Feature Descriptors
Srivastava, P., & Khare, A. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-03000-1_9 · Cited by 2
Video Similarity Measurement and Search
Bekhet, S., Hassaballah, M., Ahmed, A. A., & Ahmed, A. H. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-03000-1_4 · Cited by 3
Bolodurina, I. P., Shardakov, V. M., Вячеславовна, З. В., et al. (2018) · Global Smart Industry Conference (GloSIC) · doi:10.1109/glosic.2018.8570145 · Cited by 2
ORB Algorithm Applied to Detection, Location and Grasping Objects
Conceição, A. G. S., de Oliveira, D. M., & Carvalho, M. P. (2018) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars/sbr/wre.2018.00040 · Cited by 2
“Oriented FAST and Rotated BRIEF (ORB) [8] is an alternative to SIFT [6] and SURF [7].”
MethodAutomated Volume Analysis of Open Pit Mining Productions Based on Time Series Aerial Survey
Stojcsics, D., Domozi, Z., & Molnár, A. (2018) · UKSim-AMSS International Conference on Computer Modelling and Simulation (UKSim) · doi:10.1109/uksim.2018.00027 · Cited by 2
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.