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 9,801–9,900 of 14,752
A low complexity image stitching using advanced feature matching in mobile environments
Ahn, H., Lee, Y.-H., Lee, J.-H., et al. (2014) · Journal of Computer Virology and Hacking Techniques · doi:10.1007/s11416-014-0207-x · Cited by 2
Robot Simultaneous Localization and Mapping Using Speeded-Up Robust Features
Wang, Y.-T., Chi, C. T., & Feng, Y. C. (2013) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.284-287.2142 · Cited by 2
Scalable learning for restricted Boltzmann machines
Barshan, E., & Fieguth, P. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025557 · Cited by 2
“Researchers have tried to engineer hand-crafted descriptors to discriminate different components of the image [1, 2, 3, 4], where the best representative of this category is the Scale-Invariant Feature Transform (SIFT) [1].”
BackgroundPart-Based Recognition of Arbitrary Fonts
Wang, S., Uchida, S., & Liwicki, M. (2013) · Proceedings of the International Conference on Document Analysis and Recognition · doi:10.1109/icdar.2013.41 · Cited by 2
“This process can be realized by some feature detection and description method, for example, the speededup robust features (SURF) [9].”
MethodHu, L., Ye, J., Feng, Y. J., et al. (2015) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2015.7326913 · Cited by 2
“SIFT (ScaleInvariant Feature Transform)[2] and SURF (Speeded Up Robust Features)[3] features are invariant to rotation and scaling, widely applied for remote sensing image registration.”
MethodUsing a visual-attention model when solving problems of autonomous navigation of mobile robots
Pimenov, V. (2010) · Journal of Optical Technology · doi:10.1364/jot.77.000684 · Cited by 2
Spatio-temporal modeling of visual attention for stereoscopic 3D video
Iatsun, I., Larabi, M., & Fernández-Maloigne, C. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7026092 · Cited by 3
Visual detection in omnidirectional view sensors
Chong, N. S., Kho, Y. H., & Wong, M. L. D. (2013) · Signal Image and Video Processing · doi:10.1007/s11760-013-0528-0 · Cited by 3
“The SURF descriptor algorithm [8,9] is a partially SIFTinspired algorithm to address the issue on processing speed.”
BackgroundMethodResultInfluentialImprovement of Image Mosaic Algorithm Based on SURF
Long, X., Chen, Q., & Bao, J. W. (2013) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.427-429.1625 · Cited by 2
“…large data volume, high time complexity, poor timeliness existing in the Scale-invariant feature transform (SIFT) algorithm which was proposed by D.G.Lowe [8], H.Bay and others proposed speeded up robust features (SURF) algorithm which is an image matching method based on feature information [9].”
MethodFeature Correspondence with Even Distribution
Tan, X., Sun, C., Sirault, X. R. R., et al. (2012) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2012.6411723 · Cited by 2
Visual words selection based on class separation measures
Górecki, P., Artiemjew, P., Drozda, P., et al. (2013) · IEEE International Conference on Cognitive Informatics and Cognitive Computing · doi:10.1109/icci-cc.2013.6622275 · Cited by 2
Real time mosaicing and change detection system
Sreyas, S. T., Kumar, J. P., & Pandey, S. (2012) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/2425333.2425386 · Cited by 2
“The most popular methods include SIFT by David Lowe [17], an upgrade to that by Herbert Bay named SURF [9] and more recently the one proposed by Stefan Leutenegger, called BRISK [23].”
BackgroundMethodInfluentialOn-the-fly detection of images with gastritis aspects in magnetically guided capsule endoscopy
Mewes, P. W., Neumann, D., Juloski, A. L., et al. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.878803 · Cited by 2
Performance Analysis of Robust Image Features Detection Algorithms
Nikolova, I. (2014) · Information Technologies and Control · doi:10.2478/itc-2013-0011 · Cited by 2
“The correspondence problem refers to the task of finding distinctive image locations (called features, features point, points of interest or key points [1,11,15]) in the images under consideration, and then match these locations based on their local appearance.”
BackgroundMethodAn Improved Face Verification Approach Based on Speedup Robust Features and Pairwise Matching
Moura, E. S., Gomes, H. M., & de Carvalho, J. M. (2013) · doi:10.1109/sibgrapi.2013.57 · Cited by 2
GPU-based real-time trinocular stereo vision
Yao, Y., Linton, R. J., & Padır, T. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2008583 · Cited by 2
“Though new feature descriptors are continuously being developed and researched, most popular and widely used feature descriptors today are SIFT (Scale-Invariant Feature Transform) [10], SURF (Speeded Up Robust Feature) [11], FAST [23] and ORB (Oriented FAST and Rotated BRIEF) [24].”
MethodChatterjee, A., Singh, N., Ray, O., et al. (2011) · International Journal of Intelligent Defence Support Systems · doi:10.1504/ijidss.2011.044806 · Cited by 2
An image registration algorithm based on SIFT and CCH
Gan, L., & Wang, C. (2010) · International Conference on Computer Engineering and Technology · doi:10.1109/iccet.2010.5485535 · Cited by 2
Cross-Spectral Stereo Matching Based on Local Self-Similarities and Image Moments
Mouats, T., & Aouf, N. (2013) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2013.691 · Cited by 2
“[9] M. Teke and A. Temizel, “Multi-spectral Satellite Image Registration Using Scale-Restricted SURF,” 2010 20th International Conference on Pattern Recognition, pp. 2310–2313, Aug. 2010.”
MethodInfluentialEvaluation of point matching methods for wide-baseline stereo correspondence on mobile platforms
Juhasz, E., Tanács, A., & Kató, Z. (2013) · International symposium on image and signal processing and analysis/ISPA ... · doi:10.1109/ispa.2013.6703848 · Cited by 2
“b) SURF: is a more efficient modification of SIFT and it includes both a detector and a descriptor [5].”
MethodNatural Landmark Tracking Method to Support UAV Navigation over Rain Forest Areas
Pinage, F. A., Carvalho, J. R. H., & Neto, J. P. D. Q. (2012) · doi:10.1109/sbesc.2012.28 · Cited by 2
Analysing solution quality of anytime Bag of Words object classification for a service robot
Lotz, A., Steck, A. J., & Schlegel, C. (2012) · IEEE International Conference on Technologies for Practical Robot Applications · doi:10.1109/tepra.2012.6215645 · Cited by 2
“1In our example the SURF [11] algorithm implemented in OpenSURF [12] is used, which is parametrized with 5 octaves and 4 layers.”
MethodMultimedia Content-Based Visual Retrieval
Zhou, W., Li, H., & Tian, Q. (2014) · Academic press library in signal processing · doi:10.1016/b978-0-12-420149-1.00012-0 · Cited by 2
Dynamic Insertion of Virtual Objects in Photographs
Nóbrega, R., & Correia, N. M. R. (2013) · International Journal of Creative Interfaces and Computer Graphics · doi:10.4018/ijcicg.2013070102 · Cited by 2
3D palmprint pose estimation using stereo camera
Bingöl, Ö., & Ekinci, M. (2013) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2013.6531388 · Cited by 2
“edilebilmesi için alan tabanlı lan Bay ve ark.[14] tarafından rbüz Öznitelikler (Speed up du kullanılmıştır.”
Reference Point-Based SIFT Feature Matching
Cao, L., Liao, D., & Xue, B. (2014) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.543-547.2670 · Cited by 2
“Bay[5] proposed a matching algorithm for SURF feature matching that only compares features of same Laplacian response sign.”
MethodInfluentialView synthesis for lightfield displays using region based non-linear image warping
Adhikarla, V. K., Kovács, P. T., Barsi, A., et al. (2012) · International Conference on D Imaging · doi:10.1109/ic3d.2012.6615117 · Cited by 2
A Photo Visualization System Considering Region of Interest
Ryu, D.-S., Kim, S., & Cho, H.-G. (2010) · IEEE International Conference on Computer and Information Technology (CIT) · doi:10.1109/cit.2010.118 · Cited by 2
Robust Duplicate Detection of 2D and 3D Objects
Vajda, P., Ivanov, I., Goldmann, L., et al. (2010) · International Journal of Multimedia Data Engineering and Management · doi:10.4018/jmdem.2010070102 · Cited by 2
Object detection in gray scale images based on invariant polynomial features
Schindler, A., & Maier, G. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5649524 · Cited by 2
“The discriptors for local image contents built in the SIFT framework or in approaches similar to SIFT (like RIFT [3], SURF [4] or PCA-SIFT [5]) are based on gradient orientation histograms with arbitrarily chosen size and quantization techniques.”
MethodGeometric Total Variation for Texture Deformation
Bespalov, D., Dahl, A. B., & Shokoufandeh, A. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.1119 · Cited by 2
Invariant Extended Kalman Filter-based state estimation for MAV in GPS-denied environments
Li, D., Li, Q., Cheng, N., Yang, S. Y., Song, J., & Tang, L. (2014) · International Conference on Advances in Computing, Communications and Informatics (ICACCI) · doi:10.1109/icacci.2014.6968244 · Cited by 2
A novel image matching algorithm using local description
Wu, W., & Zhang, Q. (2014) · doi:10.1109/iccwamtip.2014.7073403 · Cited by 2
A Mobile Camera Calibration Method Using an Environmental Stereo Camera
Tsuru, H., Kitahara, I., & Ohta, Y. (2012) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.133.47 · Cited by 2
Hierarchical fusion of descriptor matching and L-K optical flow
Wang, H., Pan, C., Davoine, F., et al. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6115838 · Cited by 2
“For scale invariance, the Laplacian scale theory can be further integrated [5, 6].”
BackgroundMethodA partially flexible virtual trailer link model for vehicle-following systems
Chen, W., Zhao, C., Dai, G., et al. (2014) · Transactions of the Institute of Measurement and Control · doi:10.1177/0142331214539990 · Cited by 2
“The position of the target found by SURF can be used in Camshift when the target is lost.”
MethodInfluentialHigh-speed Recognition Algorithm Based on BRISK and Saliency Detection for Aerial Images
Teng-jiao, X., Danpei, Z., Jun, S., et al. (2013) · doi:10.1109/isdea.2012.194 · Cited by 2
Robust Hand Gesture Recognition with Feature Selection and Hierarchical Temporal Self-Similarities
Wu, Y., Zhao, L., & Ding, H. (2013) · International Journal of Information and Electronics Engineering · doi:10.7763/ijiee.2013.v3.368 · Cited by 3
Akizuki, S., & Hashimoto, M. (2015) · Electronics and Communications in Japan · doi:10.1002/ecj.11694 · Cited by 2
Learning from mobile contexts to minimize the mobile location search latency
Duan, L., Ji, R., Chen, J., et al. (2012) · Signal Processing Image Communication · doi:10.1016/j.image.2012.05.006 · Cited by 2
“Comparing to the previous works on compact local descriptors e.g. SURF [21], GLOH [22], PCA-SIFT [23], and MSR descriptors [24], works in [17–20] focused on even lower bit rate descriptors specialized for mobile visual search.”
MethodEmergent Semantic Patterns in Large Scale Image Dataset: A Datamining Approach
Khan, U. M., McCane, B., & Trotman, A. (2012) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2012.6411739 · Cited by 2
Image‐based surface deformation for multi‐view three‐dimensional facial reconstruction
Dong, H., & Dong, S. (2014) · IET Computer Vision · doi:10.1049/iet-cvi.2013.0188 · Cited by 2
An Effective Method and Device for Eye Detection with Physical Properties
Quan, D., Zhao, Y. J., Li, J., et al. (2013) · International Conference on Computer Science and Electronics Engineering (ICCSEE) · doi:10.2991/iccsee.2013.190 · Cited by 2
“The one is using SURF [19] descriptor and algorithm to get the matching-matrix M.”
MethodInfluentialAudio-visual large-scale video copy detection
Liu, Y., Xu, C., & Lu, H. (2011) · International Journal of Computer Mathematics · doi:10.1080/00207160.2011.583351 · Cited by 2
PPD: A Robust Low-computation Local Descriptor for Mobile Image Retrieval
Liu, C. (2010) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2010.06.007 · Cited by 3
An integrated system for object tracking, detection, and online learning with real-time RGB-D video
Chen, I.-K., Chi, C.-Y., Hsu, S.-L., & Chen, L. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854868 · Cited by 2
“All feature points methods like SIFT [2] or SURF [3] are only suitable for complex patterns or complex textured targets, which have to be visually complex in order to generate feature points on them [4].”
MethodDetection of scale-invariant key points employing a resistive network
Yasukawa, S., Okuno, H., & Yagi, T. (2012) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2012.6427366 · Cited by 2
A PCA-Based Binning Approach for Matching to Large SIFT Database
Treen, G., & Whitehead, A. D. (2010) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2010.9 · Cited by 2
Visual attention modeling for 3D video using neural networks
Iatsun, I., Larabi, M., & Fernández-Maloigne, C. (2014) · International Conference on D Imaging · doi:10.1109/ic3d.2014.7032602 · Cited by 2
“A new direction for saliency evaluation has been opened by the notion of interest points, like Harris detector [16], SIFT (Scale-Invariant Features Transformation) [27] or SURF (Speeded Up Robust Features) [2].”
BackgroundA survey report on mobile eye-based Human-Computer Interaction
Srinivas, S., & Blustein, J. (2011) · International Conference on Information Society · doi:10.1109/i-society18435.2011.5978526 · Cited by 2
“Realtime object recognition is achieved using SURF [18], face recognition by using functions from “OpenCV library” [19] with time log and location.”
MethodAssessment of interest points detection algorithms in OTB
Lahlou, O., Michel, J., Pichard, D., et al. (2009) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2009.5417485 · Cited by 2
“A variant of SIFT called SURF (Speed-Up Feature Transform) [2] uses a Laplacian approximation instead of the difference of Gaussians, and uses a 64 components descriptor based on the local Haar wavelet response.”
BackgroundMethodInfluentialMay, M., Turner, M. J. L., & Morris, T. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25367-6_17 · Cited by 4
“Although the processes in this paper use SIFT they could be applied to many other feature detectors such as SURF [2], GLOH [15] or FAST [9].”
MethodContinuous piecewise affine transformation for image registration
Lee, Y.-S., Hwang, W.-L., & Tian, X. (2015) · International Journal of Wavelets Multiresolution and Information Processing · doi:10.1142/s021969131550006x · Cited by 2
Automatic scene/DVD chapter extraction in Hollywoodian movies
Țapu, R., Mocanu, B., & Tapu, E. (2013) · International Symposium on Signals, Circuits and Systems · doi:10.1109/isscs.2013.6651209 · Cited by 2
“Concerning the visual similarity measure involved in the above-described process we have considered the number of matched interest points determined based on SURF descriptor [16].”
MethodDiscriminative Feature Points Distribution in Near-Infrared Pedestrian Images
Zhang, X., Chen, G., Saruta, K., & Terata, Y. (2015) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.135.1222 · Cited by 2
RoboBuntu: A Linux distribution for mobile robotics
Mancini, A., Frontoni, E., Ascani, A., et al. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152548 · Cited by 2
Viewpoint normalized images for feature based landmark detection
Kovács, V., & Tevesz, G. (2012) · IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI) · doi:10.1109/saci.2012.6249978 · Cited by 2
“The most common feature extractors such as SIFT [5] (Scale Invariant Feature Transform) and SURF [9] (Speeded Up Robust Feature) provide robust feature detection independently of changes in translation, rotation and also reject small changes in illumination and viewpoint variance.”
MethodUsing Multi-Descriptors for Real Time Cosmetic Image Retrieval
Areeyapinan, J., Kanongchaiyos, P., & Kawewong, A. (2014) · Engineering Journal · doi:10.4186/ej.2014.18.4.97 · Cited by 2
Content based Video Retrieval: A Survey
HPatel, D. (2015) · International Journal of Computer Applications · doi:10.5120/19245-0596 · Cited by 2
A machine learning approach to determining tag relevance in geotagged Flickr imagery
Hughes, M. M., O'Connor, N. E., & Jones, G. J. F. (2012) · International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) · doi:10.1109/wiamis.2012.6226774 · Cited by 2
A fast and effective outlier detection method for matching uncalibrated images
Zhao, F., Wang, H., Chai, X., & Ge, S. (2009) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2009.5414409 · Cited by 2
“[12] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, "SURF: Speeded Up Robust Features", Computer Vision and Image Understanding, vol.110, no.3, pp.346-359, 2008.”
MethodTeleoperierte mobile Roboter warten Prozessanlagen
Arbeiter, G., Bubeck, A., Fischer, J., et al. (2010) · atp magazin · doi:10.17560/atp.v52i05.398 · Cited by 2
Liu, F., & Feng, H. (2014) · International Journal of Multimedia and Ubiquitous Engineering · doi:10.14257/ijmue.2014.9.9.20 · Cited by 2
Non-rigid Face Tracking Using Short Track-Life Features
Lucey, S., & Jang, J.-S. (2010) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2010.51 · Cited by 2
Lang, H., Lei, L., & Wang, Y. (2010) · International Conference on Audio, Language and Image Processing · doi:10.1109/icalip.2010.5685056 · Cited by 2
Oriented Edge-Based Feature Descriptor for Multi-Sensor Image Alignment and Enhancement
Ju, M.-H., Kwak, D.-M., & Kang, H.-B. (2013) · International Journal of Advanced Robotic Systems · doi:10.5772/56788 · Cited by 2
3D structure estimation from monocular video clips
Donate, A., & Liu, X. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543795 · Cited by 2
Registration of multi-spectral satellite images with scale-restricted SURF
Teke, M., & Temizel, A. (2010) · IEEE Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2010.5650776 · Cited by 2
Learning Representative Features for Robot Topological Localization
Zhao, Z., Feng, X., Fang, W., et al. (2013) · International Journal of Advanced Robotic Systems · doi:10.5772/56324 · Cited by 2
A Distributed Computing Workflow for Modelling Environmental Flows in Complex Terrain
Mead, S. R., Prakash, M., Magill, C. R., et al. (2015) · IFIP advances in information and communication technology · doi:10.1007/978-3-319-15994-2_32 · Cited by 2
“Currently implemented matching methods are SIFT [11], SURF [12] and BRISK [13].”
MethodkPose: A New Representation For Action Recognition
Zhou, Z., Song, M., Zhang, L., Tao, D., Bu, J., & Chen, C. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19318-7_34 · Cited by 2
Visual Loop Closure Detection with Scene Mutual Information for Mobile Robot
Liu, N., & Wu, J.-J. (2014) · Journal of Computers · doi:10.4304/jcp.9.11.2642-2647 · Cited by 2
Android Application to Assist Visually Impaired with Outfit Coordination
Kareem, N., Hamdy, A., & Nagaty, K. (2014) · International Journal of Computer Applications · doi:10.5120/19018-0086 · Cited by 2
Foreground Detection Optimization for SoCs embedded on Smart Cameras
Carletti, V., Pizzo, L. D., Percannella, G., et al. (2014) · International Conference on Distributed Smart Cameras · doi:10.1145/2659021.2659060 · Cited by 2
Computer vision issues in the design of a scrub nurse robot
Agovic, A., Levine, J. I., Agovic, A., et al. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980494 · Cited by 2
“Due to the nature of the SIFT and SURF features we had to rely more heavily on projective reconstruction than anticipated.”
MethodInfluentialSoftferns for homography estimation
Liu, S., Wang, H., Zhang, J., Davoine, F., & Pan, C. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6116288 · Cited by 2
Mobile robot localization using place recognition in outdoor environments with similar scenes
Mitsuhashi, M., & KURODA, Y. (2011) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2011.6027041 · Cited by 2
“Feature descriptors are expressed as high-dimensional vector such as Scale Invariant Feature Transform (SIFT) [5] and Speeded Up Robust Features (SURF) [3].”
BackgroundMethodInfluentialPaper stitching using maximum tolerant seam under local distortions
Fan, W., Sun, J., & Naoi, S. (2014) · ACM Symposium on Document Engineering (DocEng) · doi:10.1145/2644866.2644873 · Cited by 2
“In this paper, FAST detector and SURF descriptor are utilized.”
MethodMahiddine, A., Seinturier, J., Peloso, D., et al. (2013) · 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/isprsarchives-xl-5-w2-409-2013 · Cited by 2
Occluded Fingerprint Recognition Algorithm Based on Multi Association Features Match
Liu, W.-C., & Guo, H.-T. (2014) · Journal of Multimedia · doi:10.4304/jmm.9.7.910-917 · Cited by 2
Aerial Video Images Registration Based on Optimal Derivative Filters with Scene-Adaptive Corners
Yi, M., Guo, B., & Yan, C. (2011) · International Conference on Image and Graphics · doi:10.1109/icig.2011.171 · Cited by 2
Joint utilization of appearance and geometry for determining correspondences
Soysal, M., Alatan, A. A., & Karadeniz, T. (2009) · International Symposium on Computer and Information Sciences · doi:10.1109/iscis.2009.5291918 · Cited by 2
“Automatic interest point detection is performed by SURF [14] and local regions are represented by the SIFT descriptor [18].”
BackgroundMethodLevel-of-interest estimation for personalized TV program recommendation
Clippingdale, S., Okuda, M., Takahashi, M., et al. (2013) · International Conference on Consumer Electronics · doi:10.1109/icce.2013.6487066 · Cited by 2
“The Expression Module is a “bag-of-visual-words” system that extracts SURF features [4] from face images and uses a support vector machine (SVM) [5] to assess how far the expression deviates from neutral.”
MethodUsing symmetrical regions of interest to improve visual SLAM
Kootstra, G., & Schomaker, L. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354402 · Cited by 2
Learning end-effector orientations for novel object grasping tasks
Balaguer, B., & Carpin, S. (2010) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/ichr.2010.5686826 · Cited by 2
A real-time and robust approach for short-term multiple objects tracking
Zhu, D., Sun, H., & Yang, N. (2012) · doi:10.1109/csip.2012.6308890 · Cited by 2
Camera tracking using partially modeled 3-D objects with scene textures
Seo, B.-K., Park, J.-I., & Park, H. (2011) · doi:10.1109/isvri.2011.5759654 · Cited by 2
“The feature points are detected by using the SURF and are matched to their correspondences by comparing each descriptor with the help of k-nearest neighbor (KNN) algorithm.”
MethodInfluentialPapachristou, C., & Delopoulos, A. N. (2013) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2013.12.004 · Cited by 2
Influence of blur on feature matching and a geometric approach for photogrammetric deblurring
Sieberth, T., Wackrow, R., & Chandler, J. H. (2014) · 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/isprsarchives-xl-3-321-2014 · Cited by 2
“These algorithms detect suitable candidate features in the images, which are invariant to scaling, translation and rotation (Lowe, 2004, Bay et al., 2006).”
BackgroundMultiscale TILT Feature Detection with Application to Geometric Image Segmentation
Lam, C.-P., Yang, A. Y., Elhamifar, E., & Sastry, S. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.79 · Cited by 2
“Arguably the most influential ones are the affine-invariant SIFT features and many of its variants [16, 19, 20, 1].”
BackgroundStereo Camera Tracking for Mobile Devices
Gasparini, S., & Bertolino, P. (2013) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2013.7 · Cited by 2
Optimized algorithm for Gaussian second order derivative filters in fast Hessian detector
Han, B., Jia, X., & Wang, Y. (2010) · doi:10.1109/iccsit.2010.5564462 · Cited by 2
DIGITAL RECONSTRUCTION OF THE CHURCH OF SAN ILDEFONSO AT ZAMORA (SPAIN) USING ORTHOWARE
Pérez, A., Cachero, R., Navarro, S., et al. (2012) · 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/isprsarchives-xxxviii-5-w16-61-2011 · Cited by 2
“For the location of these features the descriptor search process called Speeded Up Robust Features (SURF) is used [Bay et al 2006].”
MethodMobile Camera as a Human Vision in Augmented Reality
Weng, E. N. G., Khan, R. U., Adruce, S. A. Z., & Bee, O. Y. (2012) · TELKOMNIKA Indonesian Journal of Electrical Engineering · doi:10.11591/telkomnika.v11i7.2798 · Cited by 2
Steps towards the object semantic hierarchy
Xu, C. (2011) · Texas ScholarWorks (Texas Digital Library) · Cited by 2
Keypoint Recognition with Two-Stage Randomized Trees
Shimizu, S., & Fujiyoshi, H. (2012) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e95.d.1766 · Cited by 2
Camera Alignment Using Trajectory Intersections in Unsynchronized Videos
Kuo, T., Sunderrajan, S., & Manjunath, B. S. (2013) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.143 · Cited by 2
Generation of 3D Sparse Feature Models Using Multiple Stereo Views
Watson, M., Bhatti, A., Abdi, H., & Nahavandi, S. (2012) · InTech eBooks · doi:10.5772/45905 · Cited by 2
Multiple faces tracking based on joint kernel density estimation and robust feature descriptors
Ji, H., Su, F., & Du, G. (2009) · IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC) · doi:10.1109/icnidc.2009.5360967 · Cited by 2
AnySURF: Flexible Local Features Computation
Sadeh-Or, E., & Kaminka, G. A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-32060-6_15 · 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.