SURF: Speeded Up Robust Features
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index; none of the 18 sources its claims cite is checked for support yet.
Overview
CoChat Summary
TL;DR
SURF is a scale- and rotation-invariant interest point detector and descriptor that uses integral images, Hessian-based detection, and Haar-wavelet responses to be faster than prior methods while matching or exceeding their repeatability and distinctiveness. It reports strong results on standard benchmarks and a museum object recognition task.
Key findings
- The Fast-Hessian detector is more than 3× faster than DoG and 5× faster than Hessian-Laplace, with comparable or better repeatability on Graffiti, Leuven, Boat, and Wall; on the first Graffiti image (800×640), computation times were 120 ms for Fast-Hessian, 400 ms for DoG, 650 ms for Hessian-Laplace, and 1800 ms for Harris-Laplace.
- SURF’s 64-dimensional descriptor outperformed GLOH, SIFT, and PCA-SIFT in most comparisons, sometimes by more than 10% improvement in recall for the same precision; SURF-128 was slightly better but slower to match.
- Joint detector-descriptor computation times on the first Graffiti image were 255 ms for U-SURF, 354 ms for SURF, 391 ms for SURF-128, and 1036 ms for SIFT.
- In museum object recognition, recognition rates were 85.7% for SURF-128, 83.8% for U-SURF, 82.6% for SURF, 78.3% for GLOH, 78.1% for SIFT, and 72.3% for PCA-SIFT.
Methods
- Design: a scale- and rotation-invariant detector/descriptor. The detector uses the determinant of the Hessian with box-filter approximations evaluated via integral images; the descriptor uses Haar-wavelet responses in a 4×4 subregion grid, producing a 64-dimensional vector, with an upright U-SURF variant and an extended SURF-128 variant.
- Data: standard evaluation sequences from Mikolajczyk (including Graffiti, Wall, Boat, Leuven, Bikes, Trees, and Ubc; Bark excluded from descriptor evaluations) and a real-life museum object recognition database of 216 images of 22 objects, with 116 test images at 320×240.
- Analysis: detector repeatability scores, descriptor recall-(1-precision) graphs under similarity-threshold and nearest-neighbour-ratio matching, recognition rates, and computation timings on a standard Linux PC (Pentium IV, 3 GHz).
Limitations
- The paper has no explicit limitations section. It states that space limitations prevent showing results on all sequences, and it assumes skew, anisotropic scaling, and perspective effects are second-order effects covered only by overall descriptor robustness.
- Evident from the text: the method is scale- and rotation-invariant but not affine-invariant; Fig. 4 notes the interest points are not affine invariant, and the descriptor does not use colour.
- Evident from the text: the object recognition experiment uses small 320×240 test images and matching without additional geometric constraints, which the authors say would reduce false positives but were omitted for comparison purposes.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
0 Valid · 2 Not valid · 12 Not checked · 30 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The number of interest points found is on average very similar for all detectors.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 4 × 4 sub-region division solution provided the best results.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SURF outperformed the other descriptors for almost all the comparisons.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The SURF descriptor outperforms the other descriptors in a systematic and significant way, with sometimes more than 10% improvement in recall for the same level of precision.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in the results section, the performance is comparable to the one using the discretised and cropped Gaussians.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
8 more claims
Create a free account to see all 44 claims and every source verdict.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This transition marked a new era, where we moved beyond the classic approaches and task-specific feature engineering of earlier days [Lowe 2004; Bay et al. 2006; Rosten and Drummond 2006] towards models that could be trained once over large amounts of data, and then adapted for a broad variety of tasks, such as image recognition, object detection, and image segmentation [Krizhevsky et al. 2012; Sz”
From On the Opportunities and Risks of Foundation Models (2021) · cites this paper as Bay et al. 2006
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · cited 14×
“This PCA-SIFT yields a 36-dimensional descriptor which is fast for matching, but proved to be less distinctive than SIFT in a second comparative study by Mikolajczyk et al. [8] and slower feature computation reduces the effect of fast matching.”
BackgroundMethodResultInfluentialMarr, D., & Hildreth, E. (1980) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1980.0020 · Cited by 6,510
PCA-SIFT: a more distinctive representation for local image descriptors
Ke, Y., & Sukthankar, R. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.183 · Cited by 3,932
Robust wide-baseline stereo from maximally stable extremal regions
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.02.006 · Cited by 3,686
Scalable Recognition with a Vocabulary Tree
Nister, D., & Stewenius, H. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.264 · Cited by 3,579
Scale & Affine Invariant Interest Point Detectors
Mikolajczyk, K., & Schmid, C. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000027790.02288.f2 · Cited by 3,436
Cited by
Items 11,001–11,100 of 14,752
3D Depth Measurement for Holoscopic 3D Imaging System
Alazawi, E., Swash, M. R., & Abbod, M. (2016) · Journal of Computer and Communications · doi:10.4236/jcc.2016.46005 · Cited by 1
“in 2006 [34] and Scale Invariant Feature Transform (SIFT) descriptor proposed by Lowe in 2004 [35] were used.”
MethodINDOOR POSITIONING AND NAVIGATION BASED ON CONTROL SPHERECAL PANORAMIC IMAGES
Huang, T.-C., & Tseng, Y. (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-b6-251-2016 · Cited by 1
Eliminating False Matches Using Geometric Context
Zhang, M., Zhang, Y., & Wang, J. (2012) · Communications in computer and information science · doi:10.1007/978-3-642-34447-3_30 · Cited by 1
A dynamic online background modeling framework for moving object detection from airborne videos
Lan, X., Li, S., Zhu, C., et al. (2015) · IEEE International Conference on Progress in Informatics and Computing · doi:10.1109/pic.2015.7489831 · Cited by 1
Automatic 3D Coordinate Extraction from High Resolution Digital Aerial Images
Acar, H., Karslı, F., & Dihkan, M. (2016) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-016-0600-7 · Cited by 1
“…1985), Heitger detector (Heitger et al. 1992), Susan detector (Smith and Brady 1997), scale invariant feature transform (SIFT) detector (Lowe 2004; Shen and Bao 2014), SURF detector (Bay et al. 2006), and the features from accelerated segment test (FAST) detector (Trajkovic and Hedley 1998).”
MethodSifting for better features to track: exploiting time and space
Boult, T. E., & Eckmann, M. (2007) · Cited by 1
Hwang, S. S., & Hong, S. H. (2016) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-1409-3_25 · Cited by 1
Madani, K., Hassan, D., & Sabourin, C. (2016) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-016-0559-2 · Cited by 2
“An as well scale-invariant as rotation-invariant efficient interest point detector and descriptor, based on a pre-computed integral image, called SURF (speed up robust algo-rithm), has been proposed by [23].”
MethodContour Detection at Range Images Using Sparse Normal Detector
Cruz-Bernal, A., Alamanza-Ojeda, D.-L., & Ibarra-Manzano, M.-A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-39393-3_12 · Cited by 1
Design and Implementation of a Smartphone-Based Positioning System
Yeh, C., Lo, Y.-C., & Chang, C.-C. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-42007-3_84 · Cited by 1
A super depth of field height measurement based on local disparity
Li, C., Yi, L., Yu, M., et al. (2015) · Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu · doi:10.5277/oa150207 · Cited by 1
Objects Classification for Mobile Robots Using Hierarchic Selective Search Method
Xu, C. L., Cao, T., Li, Z., & Xiao, X. (2016) · MATEC Web of Conferences · doi:10.1051/matecconf/20166803001 · Cited by 2
Image and Video Copy Detection Using Content-Based Fingerprinting
Fatourechi, M., Lv, X., Esmaeili, M. M., Wang, Z. J., & Ward, R. K. (2012) · CRC Press eBooks · doi:10.1201/b11716-22 · Cited by 4
Rushmeier, H. (2015) · Cited by 1
Robust Video Copy Detection Based on Constrained Feature Points Matching
Chen, D.-Y., & Chiu, Y.-M. (2012) · Smart innovation, systems and technologies · doi:10.1007/978-3-642-35473-1_36 · Cited by 1
Multimodal Biometrics Recognition for Newborns
Tiwari, S., & Singh, S. K. (2013) · Advances in information security, privacy, and ethics book series · doi:10.4018/978-1-4666-4868-5.ch002 · Cited by 1
Entity Association Using Context for Wide Area Motion Imagery Target Tracking
Blasch, E., Liang, P., Shi, X., Li, P., & Ling, H. (2016) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-28971-7_21 · Cited by 1
Linking Traditional TV Advertising to Internet Advertising
Duan, L., Wang, J., Gao, W., et al. (2011) · Advances in multimedia and interactive technologies book series · doi:10.4018/978-1-60960-189-8.ch010 · Cited by 1
Design of LED marker for camera calibration of rapid deployment
Lin, M., Zhao, Q., Лю, Б., et al. (2016) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2016.7531153 · Cited by 1
Sinčák, P., Smolar, P., & Ondo, J. (2015) · International Conference on Emerging eLearning Technologies and Applications (ICETA) · doi:10.1109/iceta.2015.7558510 · Cited by 1
Indoor place recognition based on set operation of keypoints databases
Long, X., Wang, K., Li, R., et al. (2016) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2016.7558706 · Cited by 1
Two-step matching strategy combining global-local descriptor
Tang, Q., Liu, B., Xu, Z., et al. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2244153 · Cited by 1
“improved SIFT and proposed a more accurate and more robust algorithm, called SURF[2].”
MethodLocal Dual-Cross Ternary Pattern for Feature Representation
Zhou, P., Peng, Y., Shen, J., Zhang, B., & Yang, W. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46654-5_66 · Cited by 1
Object orientation estimation for high speed 3D object retrieval system
Sintunata, V., & Aoki, T. (2016) · doi:10.1109/icoict.2016.7571933 · Cited by 1
B-SIFT: A Simple and Effective SIFT for Real-Time Application
Feng, Y., Liu, Y., & Liu, H. (2016) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-2338-5_35 · Cited by 1
Detection of Catenary Support System
Liu, Z. (2016) · Advances in high-speed rail technology · doi:10.1007/978-981-10-2753-6_6 · Cited by 1
New improved image registration based tracking system
Agrawal, D. N., & Bodkhe, S. (2016) · doi:10.1109/startup.2016.7583908 · Cited by 1
“The detection are often explicit as follows [13]: Given a point x = (x, y) in an image I , its Hessian matrix at scales is defined as H(X,σ) = Lxx(X,σ) Lxy(X,σ) Lyx(X,σ) Lyy(X,σ)”
BackgroundMethodApplication of clustering analysis and dynamic programming in the image mosaic
Gong, Y., Xie, H., & Yu, L. (2013) · doi:10.1109/mic.2013.6758025 · Cited by 1
3D object retrieval system using skewness database
Sintunata, V., & Aoki, T. (2016) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit.2016.7593547 · Cited by 1
Hu, J., Tseng, C.-Y., & Chen, M. (2013) · International Automatic Control Conference · doi:10.1109/cacs.2013.6734149 · Cited by 1
Hierarchical image browsing based on visual information
Szücs, G. (2013) · IEEE International Conference on Cognitive Infocommunications · doi:10.1109/coginfocom.2013.6719221 · Cited by 1
Suzuki, T., & Ikenaga, T. (2016) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.e99.a.1937 · Cited by 1
Sakagami, N., & Choi, S. K. (2016) · Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications · doi:10.5687/sss.2016.259 · Cited by 1
Robust feature descriptor and vehicle motion model with tracking-by-detection for active safety
Kataoka, H., Tamura, K., Aoki, Y., et al. (2013) · Proceedings of the Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon.2013.6699519 · Cited by 1
“We need to fix the template using a point-of-interest tracker; for example, the SIFT (Scale Invariant Feature Transform) [17] or SURF (Speeded Up Robust Features) [18].”
MethodImage Forgery Detection using FREAK Binary Descriptor and Level Set Segmentation
Youssef, B. A. B., & Atta, E. H. (2016) · Cited by 1
Scale and Topology Preserving SIFT Feature Hashing
Chen, K., Zhu, L., & Qian, X. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48896-7_19 · Cited by 1
Hosomi, Y., Oyama, K., Honda, T., et al. (2016) · doi:10.1109/ijcnn.2016.7727576 · Cited by 1
Enhanced obfuscation for multi-part biometric templates
Gottemukkula, V., Derakhshani, R. R., & Saripalle, S. K. (2016) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2016.7743952 · Cited by 1
Using Dense 3D Reconstruction for Visual Odometry Based on Structure from Motion Techniques
NASCIMENTO, M. D. M., Loaiza, M., & Raposo, A. B. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-50832-0_47 · Cited by 1
Effective place scene clustering using straight lines
Moon, H., Lee, J. H., Lee, S., et al. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759098 · Cited by 1
A bag of relevant regions model for visual place recognition in coral reefs
Maldonado-Ramírez, A., & Torres-Méndez, L. A. (2016) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans.2016.7761188 · Cited by 1
Registration of Modern and Historic Imagery for Timescape Creation
Ali, H. K., & Whitehead, A. D. (2016) · Conference on Computer and Robot Vision (CRV) · doi:10.1109/crv.2016.17 · Cited by 1
Real time Object Distance Measurement System with tracking based on Stereo Vision
Govindiya, B. N., & Shaikh, N. (2015) · Cited by 1
Panoramic Image Mosaics Using Local Wavelet-Features
Guo, F., & Wang, Y. (2016) · International Conference on Network-Based Information Systems · doi:10.1109/nbis.2016.47 · Cited by 1
“Although there are some algorithms like SIFT [5], and SURF [6], each concentrating on a particular feature of the image, and has it's strong points and weak points.”
MethodVision-Based Marker-Less Motion Measurement for Berthing
Mizuchi, Y., Kawabata, Y., Kim, Y. B., et al. (2016) · Lecture notes in electrical engineering · doi:10.1007/978-3-319-50904-4_26 · Cited by 1
Aids for Visually Impaired Persons for Obstacle Acknowledgment: A Study and Proposed New Framework
Kaur, P., & Kaur, S. (2016) · IJCA Proceedings on International Conference on Advancements in Engineering and Technology · Cited by 1
Towards Fixation Prediction: A Nonparametric Estimation-Based Approach through Key-Points
Oliveira, S. A. F., Neto, A. R. R., & Gomes, J. P. P. (2016) · Brazilian Conference on Intelligent Systems · doi:10.1109/bracis.2016.077 · Cited by 1
Image stitching system with scanning microscopy for histopathological applications
Qidwai, U. A., & Akbar, M. A. (2016) · IEEE-EMBS Conference on Biomedical Engineering and Sciences · doi:10.1109/iecbes.2016.7843505 · Cited by 1
“in 2006 [10], while a revision of which 2016 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES)”
BackgroundVisually servoed trajectory tracking of quadrotors with the kinematic model
Lin, P., & Wang, K. (2016) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2016.7838743 · Cited by 1
An improved feature fusion algorithm for image retrieval
Che, S., Chen, D., & Wang, X. (2016) · International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) · doi:10.1109/cisp-bmei.2016.7852741 · Cited by 1
“On this dataset, we use N-S score method to evaluate our method.”
MethodIdentification of irregular motion in automotive navigation systems using novelty detection
Pollot, M., Springer, D., Schleifer, R., et al. (2016) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2016.7850000 · Cited by 1
Traffic Sign Recognition System for Imbalanced Dataset
Aydın, Y. (2017) · Journal of Computers · doi:10.17706/jcp.12.6.543-549 · Cited by 1
“Also SITF+SURF feature robust than sift so proposed method’s accuracy rate increased.”
MethodInfluentialLow-power coprocessor for Haar-like feature extraction with pixel-based pipelined architecture
Luo, A., An, F., Fujita, Y., et al. (2017) · Japanese Journal of Applied Physics · doi:10.7567/jjap.56.04cf06 · Cited by 1
Zhang, Y., Wu, Y., Zhang, Y., et al. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2251537 · Cited by 1
Enhanced SURF-Based Image Matching Using Pre- and Post-processing
Zhang, C., Wu, Y., Liu, N., et al. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-4211-9_9 · Cited by 1
“One of the most effective algorithms for identifying several images with similar feature is SURF (Speeded Up Robust Features) [1].”
MethodSOFF: Scalable and oriented FAST-based local features
Bouhlel, N., Ammar, A. B., Ksibi, A., et al. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2268405 · Cited by 1
“In reviewing a large number of existing local feature detectors, the SIFT[3] and SURF[4] detectors have already been broadly accepted as the most effective detectors, with high robustness against various image transformations[5], [6].”
BackgroundStrip wrinkling detection based on feature extraction and sparse representation
Chen, X., Wang, W., & Pan, Y. (2017) · International Journal of Wireless and Mobile Computing · doi:10.1504/ijwmc.2017.10003980 · Cited by 1
On-site AR Interface based on Web-based 3D Database for Cultural Heritage in Egypt
Yasumuro, Y., Matsushita, R., Higo, T., et al. (2016) · Eurographics · doi:10.2312/gch.20161403 · Cited by 1
“We use SURF (Speeded up robust features) [BTG06] as the keypoint for feature extraction, considering the robustness and computational costs.”
MethodNew Compact 3-Dimensional Shape Descriptor for a Depth Camera in Indoor Environments
Choi, H., & Kim, E. (2017) · Sensors · doi:10.3390/s17040876 · Cited by 1
Feature descriptor based on local intensity order relations of pixel group
Liao, W., Wu, C., & Lin, M.-C. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899926 · Cited by 1
“[6] RUBLEE, Ethan, et al. ORB: an efficient alternative to SIFT or SURF.”
MethodFace Sketch Matching Using Speed up Robust Feature Descriptor
Bansode, N. K., & Sinha, P. K. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-4859-3_38 · Cited by 1
Development of Height Indicators using Omnidirectional Images and Global Appearance Descriptors
Amorós, F., Payá, L., Ballesta, M., & Reinoso, Ó. (2017) · Applied Sciences · doi:10.3390/app7050482 · Cited by 1
“SURF features are used with this aim [45].”
Vehicle X-ray Scans Registration: A One-Dimensional Optimization Problem
Marciano, A., Cohen, L. D., & Gadi, N. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-58771-4_46 · Cited by 1
Rapid Triangle Matching Based on Binary Descriptors
Tian, M., & Lin, Q. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59081-3_40 · Cited by 1
Local Keypoint-Based Image Detector with Object Detection
Grycuk, R., Scherer, M. M., & Voloshynovskiy, S. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59063-9_45 · Cited by 1
Uchida, K. (2016) · doi:10.1109/aiccsa.2016.7945646 · Cited by 1
“Due to the high computational cost of SIFT, SIFT-like descriptors have been proposed that compute local features faster, such as SURF (Speeded Up Robust Features) [18], BRIEF (Binary Robust Independent Elementary Features) [19], BRISK (Binary Robust Invariant Scalable Keypoints) [20], ORB (Oriented-BRIEF) [21], KAZE […”
MethodContext-aware vocabulary tree for mobile landmark recognition
Chen, T., Lu, S., & Fan, J. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.05.002 · Cited by 1
Rate-coverage analysis and optimization for joint audio-video multimedia retrieval
Ning, G., Zhang, Z., Ren, X., et al. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952689 · Cited by 1
“In content-based multimedia retrieval [5], video and audio data are often represented by feature vectors, such as SIFT [6], SURF [7] and GLOH [8].”
MethodResilient Image Feature Description through Evolution
Bostancı, E. (2017) · International Journal of Intelligent Systems and Applications in Engineering · doi:10.18201/ijisae.2017528728 · Cited by 1
“The binary descriptors include BRIEF [18], ORB [19], BRISK [20], FREAK [21] and LATCH [22], whereas the integer and floating-point descriptors are SIFT [23], SURF [24], KAZE [25] and AKAZE [26].”
MethodEffective Palm Tracking with Integrated Tracker and Offline Detector
Yang, Z., Zhu, Y., & Yuan, B. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-09339-0_33 · Cited by 1
“Different from the standard KLT tracker [19], we used SURF feature points [20] and, for each SURF point within the bounding box Bf in the frame F, its location in F was tracked.”
MethodPicking from Clutter: An Object Segmentation Method for Robot Grasping
Chen, Y., Wang, Y., Hu, J., & Xiong, R. (2016) · International Conference on Cognitive Systems and Signal Processing · doi:10.1007/978-981-10-5230-9_35 · Cited by 1
Time series classification using point-wise features
Ergezer, H., & Leblebicioğlu, K. (2017) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2017.7960437 · Cited by 1
Visual Odometry with loop closing detection using Iterative Closest SURF Point
Chaib, K., Hamerlain, M., Achour, N., et al. (2017) · International Conference on Systems and Control (ICSC) · doi:10.1109/icosc.2017.7958677 · Cited by 1
“Index Terms— Depth camera, Features, guide robot, ICP, ICP-VSLAM, ICP-VSLAM-Key, Key image, Kinect sensor, SURF detector, Visual Odometry.”
BackgroundMethodInfluentialImproving the Performance of the CamShift Algorithm Using Dynamic Parallelism on GPU
Tian, Y., Taylor, C., & Ji, Y. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-54978-1_84 · Cited by 1
Local Intensity Ordering based Binary Patterns for Image Region Description
Kannan, R., & Kannaiyan, S. (2017) · Advances In Image and Video Processing · doi:10.14738/aivp.53.3279
Change Detection from Media Sharing Community
Kito, N., Zhou, X., Qin, D. L., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-63579-8_30 · Cited by 1
“Examples on descriptors include SIFT[4], PCA-SIFT[5], SURF[6], GLOH[7], and Eff(2)[8] etc.”
MethodVisual Moving Objects Tracking Using Shape Detectors and Object Models
Wang, Y.-T., & Shen, C.-A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-65515-4_16 · Cited by 1
Zhu, Y., Tsukamoto, T., & Tanaka, S. (2017) · International Conference on Solid-State Sensors, Actuators and Microsystems · doi:10.1109/transducers.2017.7994189 · Cited by 1
“Some computer vision technologies such as SURF (speeded up robust features) feature detection [11], Harr-wavelet response, FLANN (fast approximate nearest neighbor search library) matching [12], and homography transformation [13] was used to realize the ability of translation, scale, and rotation invariance of the obj…”
MethodReal-Time Visual Odometry by Patch Tracking Using GPU-Based Perspective Calibration
Saracchini, R. F. V., Ortega, C. A. C., Minetto, R., et al. (2017) · Communications in computer and information science · doi:10.1007/978-3-319-64870-5_23 · Cited by 1
Boosted ringlet features for robust object tracking
Krieger, E. W., Essa, A. E., Paheding, S., et al. (2016) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2016.8010574 · Cited by 1
“The Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF) methods are scale invariant feature descriptors [1-2].”
MethodA Distributed CBIR System Based on Improved SURF on Apache Spark
Huang, T., Yu, Z., Lin, X., et al. (2017) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-6451-7_18 · Cited by 1
Visual query compression with embedded transforms on Grassmann manifold
Zhang, Z., Li, L., & Li, Z. (2017) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew.2017.8026255 · Cited by 1
“To improve retrieval speed, Speed-Up Robust Feature (SURF) was published in [6].”
MethodPutranto, E. H. E., Suzuki, T., Usuki, S., et al. (2017) · doi:10.1117/12.2273559 · Cited by 1
ROBUST 2D AUGMENTED REALITY BASED ON HOMOGRAPHY REFINEMENT AND TEMPORAL COHERENCE
Kim, K., & Song, H. P. J. (2013) · International Conference on Digital Information Processing and Communications · Cited by 1
Two-dimensional peak filter in almost linear time
Belov, A. M., Verichev, A., & Myasnikov, V. (2017) · Procedia Engineering · doi:10.1016/j.proeng.2017.09.662 · Cited by 1
Comparison of Visual Descriptors for 3D Reconstruction of Non-rigid Planar Surfaces
Bednarek, M. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-68720-9_22 · Cited by 1
Stereo System for Remote Monitoring of River Flows
Bacharidis, K., Moirogiorgou, K., Κούκιου, Γ., et al. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5148-1 · Cited by 1
“The reference patterns are compared with each isolated particle in the subsequent frames by assessing their similarity rates on their SURF features [2].”
MethodElection Based Pose Estimation of Moving Objects
Gao, L., & Wang, C. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-6442-5_4 · Cited by 1
Menon, H. P., & Nitheesh, A. S. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-68385-0_30 · Cited by 1
Corner-point criterion for assessing nonlinear image processing imagers
Landeau, S., Foing, J. ‐., Swiathy, G., et al. (2017) · doi:10.1117/12.2278592 · Cited by 2
High Resolution Image Registration for Micro-Colonies Monitoring on Petri Dishes
Betzner, M., Pierquin, J., Kohler, S., & Dieterlen, A. (2017) · IRBM · doi:10.1016/j.irbm.2017.10.004 · Cited by 1
Core Algorithm for Structural Verification of Keypoint Matches
Malashin, R. O. (2017) · Intelligent systems reference library · doi:10.1007/978-3-319-67516-9_9 · Cited by 1
Movement Direction Estimation Using Omnidirectional Images in a SLAM Algorithm
Berenguer, Y., Payá, L., Reinoso, Ó., et al. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-70833-1_52 · Cited by 1
Iterative Template Matching with Rotation Invariant Best-Buddies Pairs
Chen, Z., Yang, Y., Chen, W., et al. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-7299-4_38 · Cited by 1
Indoor location estimation based on robust floor fingerprint identification
Uchida, K., & Fujita, S. (2017) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2017.8115962 · Cited by 1
“Due to the high computational cost of SIFT, SIFT-like descriptors have been proposed that compute local features faster, such as SURF (Speeded Up Robust Features) [13], KAZE[14], and AKAZE (Accelerated KAZE) [15].”
MethodJorge, C. A. F., Seixas, J. M., da Silva, E. A. B., Mól, A. C. A., Monteiro, J. G. T., de Lira, G. R., & Silva, P. H. S. (2017) · Progress in Nuclear Energy · doi:10.1016/j.pnucene.2017.10.013 · Cited by 1
Computer Vision for Natural Interfaces
Bimbo, A. D., Ferracani, A., Pezzatini, D., et al. (2017) · Human-computer interaction series · doi:10.1007/978-3-319-61036-8_3 · Cited by 1
Parallel program system for HIL experiments on visual navigation of unmanned aerial vehicles
Stepanov, D. (2016) · Program systems theory and applications · doi:10.25209/2079-3316-2016-7-4-287-303 · Cited by 1
The face detection algorithm based on local elastic potential energy feature
Jiang, C., & Zhang, Y. (2017) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2017.8170918 · Cited by 1
“If we only learn features [1] in one scale, we will lose some features which can be acquired only in other scales.”
BackgroundLocal descriptors robust to out-of-plane rotations
Bednarek, M., & Walas, K. (2017) · Signal Processing: Algorithms, Architectures, Arrangements, and Applications · doi:10.23919/spa.2017.8166856 · Cited by 1
“Besides SIFT, there are other options available such as SURF [3] which was supposed to be a speeded-up version of SIFT.”
Method
Metadata
- Authors
- Bay, H., Tuytelaars, T., & Van Gool, L.
- Affiliations
- ETH Zurich (CH)
- KU Leuven (BE)
- ORCID
- Tuytelaars, Tinne
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2006
- Pages
- 404-417
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1677409904
- Semantic Scholar
- 9ad3179098eb9ac7f0c81bf89b6bdcde91752880
- Cited by
- 14,955
- References
- 39
- Citations by year
- 2026: 210 · 2025: 519 · 2024: 727 · 2023: 757 · 2022: 878 · 2021: 975 · 2020: 978 · 2019: 1036 · 2018: 968 · 2017: 976 · 2016: 930 · 2015: 1079 · 2014: 1006 · 2013: 982 · 2012: 884
- FWCI
- 196.80
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Lecture notes in computer science (publishedVersion)
- Lirias (KU Leuven) (submittedVersion, other-oa)
- Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Object Detection Techniques
- Keywords
- SURF, keypoint detection, feature descriptors, scale invariance, rotation invariance, integral image, Hessian matrix, feature matching, object recognition, repeatability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.