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 11,801–11,900 of 14,752
Lins, E. T., Freire, E. O., Molina, L., Carvalho, E. Á. N., & Silva, W. F. (2021) · Anais do ... Simpósio Brasileiro de Automação Inteligente/Simpósio Brasileiro de Automação Inteligente · doi:10.20906/sbai.v1i1.2677 · Cited by 1
Visual Odometryin Principle and Practice
Persson, M. (2022) · Linköping studies in science and technology. Dissertations · doi:10.3384/9789179291693 · Cited by 1
Accurate Matching of Invariant Features Derived from Irregular Curves
Liu, H., Yin, S., Sui, H., et al. (2022) · Remote Sensing · doi:10.3390/rs14051198 · Cited by 1
Optical Flow-Based Place Recognition: Bridging the Gap Between Simulation and Real-World Experiments
Diamantas, S. C., & Dasgupta, P. (2022) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc54503.2022.9720910 · Cited by 1
Ghaffari, S., Capson, D. W., & Li, K. F. (2022) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2022.3151896 · Cited by 1
Multisource Mobile Transfer Learning Algorithm Based on Dynamic Model Compression
Gao, P., Li, J., & Ding, C. (2022) · Security and Communication Networks · doi:10.1155/2022/3234078 · Cited by 1
Image Retrieval through sketches based on Descriptor with Data Retrieval using Reversibility Method
Birari, D., Hiran, D., & Narawade, V. E. (2022) · International Conference for Advancement in Technology (ICONAT) · doi:10.1109/iconat53423.2022.9726045 · Cited by 1
Sonugür, G., & Gökçe, B. (2022) · Proceedings of the Bulgarian Academy of Sciences · doi:10.7546/crabs.2022.03.11 · Cited by 1
“The most common of these are Speeded-Up Robust Feature (Surf) [ 6 ], Fast and Harris Corner Detector [ When these methods are examined, it is observed that they have computational complexity that can lead to temporal problems when used in real-time movements.”
BackgroundWu, J., & Liao, S. (2022) · Tehnicki vjesnik - Technical Gazette · doi:10.17559/tv-20220222034206 · Cited by 1
“In 2013, Turcsany et al. [7] proposed using SURF [8] feature detector and feature descriptor based on BoVW method to train SVM [9], and obtained 99.07% accuracy and 4.31% error rate.”
Influential3D Reconstruction of the Colon from Monocular Sequences Evaluation by 3D-printed Phantom Data
Hackner, R., Eixelberger, T., Schmidle, M., et al. (2022) · Informatik aktuell · doi:10.1007/978-3-658-36932-3_31 · Cited by 1
Combining Wearable Tracking Data and Deep Learning for Moving Camera Calibration
Carey, D. L., Bedin, T., Jackson, K. B., & Morgan, S. (2022) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-99333-7_18 · Cited by 1
Ausprägungen von Uploadfiltern
Steinebach, M. (2022) · DuD-Fachbeiträge · doi:10.1007/978-3-658-33306-5_20 · Cited by 1
Extended Object Detection: Flexible Object Description System for Detection in Robotic Tasks
Moscowsky, A. (2022) · Studies in systems, decision and control · doi:10.1007/978-3-030-97004-8_3 · Cited by 1
Wang, Y., Fu, Y., Zheng, R., Wang, L., & Qi, J. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-9423-3_38 · Cited by 2
Face Match for Family Reunification: Real-World Face Image Retrieval
Borovikov, E., Vajda, S., & Gill, M. (2018) · IGI Global eBooks · doi:10.4018/978-1-5225-5204-8.ch028 · Cited by 1
Constructing 3D Feature Maps from Video Sequences by Optic Flow Estimation
Khurshudov, A. A. (2015) · St Petersburg State Polytechnical University Journal Computer Science Telecommunications and Control Systems · doi:10.5862/jcstcs.217-222.10 · Cited by 1
Toennies, K. D. (2017) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-7320-5_5 · Cited by 1
Monocular Visual Odometry Based on Homogeneous SURF Feature Points
Si, Z., Wu, X., & Liu, G. (2017) · doi:10.23977/acsat.2017.1002 · Cited by 1
Improved Center-symmetric Local Binary Pattern Descriptor For Local Feature Region Description
Zeng, H., Dong, X., & Wang, X. (2011) · Energy Procedia · doi:10.1016/j.egypro.2011.10.353 · Cited by 1
Scherer, R. (2019) · Studies in computational intelligence · doi:10.1007/978-3-030-12195-2_2 · Cited by 1
Higher accuracy self-supervised visual odometry with reliable projection
Zhou, S. S., Yang, Z., Zhu, M., Li, H., Serikawa, S., Mizumachi, M., & Zhang, L. (2022) · Artificial Life and Robotics · doi:10.1007/s10015-022-00766-7 · Cited by 1
“So, the famous SIFT [17], SURF features [18] are designed to break these limitations, but their computational cost becomes higher at the same time.”
BackgroundGIFdroid: An Automated Light-weight Tool for Replaying Visual Bug Reports
Feng, S., & Chen, C. (2022) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse-companion55297.2022.9793742 · Cited by 1
Improvement of Visual Odometry Using Classic Features by Semantic Information
Adachi, M., Ishida, H., & Miyamoto, R. (2022) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit55151.2022.9804085 · Cited by 1
Extending generalized unsupervised manifold alignment
Yin, X., Cui, Z., Chang, H., Ma, B., & Shan, S. (2022) · Science China Information Sciences · doi:10.1007/s11432-019-3019-3 · Cited by 2
DKNAS: A Practical Deep Keypoint Extraction Framework Based on Neural Architecture Search
Liu, L., Cai, X., Li, G., & Li, T. H. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812101 · Cited by 2
End-to-End Car Make and Model Classification using Compound Scaling and Transfer Learning
Bourja, O., Maach, A., Zannouti, Z., Derrouz, H., Abdelali, H. A., Thami, R. O. H., & Bourzeix, F. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.01305111 · Cited by 2
Video-Based Pedestrian Re-identification with Non-local Attention Module
Zhang, J., Cheng, L., Xin, Z., et al. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-06767-9_36 · Cited by 1
BPrice: An Optimal Price Recommendation Framework Based on Product Identification
Wang, Y. (2022) · International Conference on Electronics Technology (ICET) · doi:10.1109/icet55676.2022.9824412 · Cited by 1
Content-Based Image Retrieval for Painting Style with Convolutional Neural Network
Tan, W. S., Chin, W. Y., & Lim, K. Y. (2021) · doi:10.56453/icdxa.2021.1007 · Cited by 1
“…was motivated by the advancement and the efficiency of the features extraction in CNN. Handcrafted features methods such as SIFT (Lowe,1999), SURF (bay et al., 2006) and GIST (Oliva and Torralba, 2016) were popular in CBIR, however, we wish to understand if we can profit more fully and flawlessly…”
MethodRe-thinking Pitfalls of Premodel Building for Adaptive CNNs Model Selection on ImageNet
Yarovenko, V., Park, J.-G., & Lee, M.-H. (2022) · International Conference on Advances in Computer Technology, Information Science and Communications (CTISC) · doi:10.1109/ctisc54888.2022.9849779 · Cited by 1
An Outdoor Pedestrian Localization Scheme Fusing PDR and VPR
Liu, Y., Gong, Q., Wang, S., Zhang, L., & Xu, F. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/2898343 · Cited by 1
Automated Vehicle Number Plate (VNP) Detection based on Optimized Segmentation and Machine Learning
Radha, R., & Viju, V. (2022) · International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) · doi:10.1109/icscds53736.2022.9760741 · Cited by 1
Pal, D., Singh, A., & Alladi, A. (2022) · IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct55679.2022.9865711 · Cited by 2
Dynamic Places’ Definition for Sequence-Based Visual Place Recognition
Tsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2022) · Springer tracts in advanced robotics · doi:10.1007/978-3-031-09396-8_4 · Cited by 2
Chen, Z., Zhang, X., Ou, Y., & Wang, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-15937-4_60 · Cited by 1
Guo, Z., Hong-Phuoc, T., Khan, N., et al. (2022) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr54900.2022.00070 · Cited by 1
A Robust Parallel Initialization Method for Monocular Visual-Inertial SLAM
Zhong, M., Yao, Y., Xu, X., & Wei, H. (2022) · Sensors · doi:10.3390/s22218307 · Cited by 1
“For visual measurement processing, it can be divided into the optical flow methods [13] and the feature-based methods [14–16] according to the matching strategy.”
MethodAutonomous Control of the Large-Angle Spacecraft Maneuvers in a Non-Cooperative Mission
Huang, C., Cao, T., & Huang, J. (2022) · Sensors · doi:10.3390/s22228586 · Cited by 1
“At present, for pose estimation of non-cooperative targets, traditional methods rely on artificially designed features [5,6] and pose priors.”
MethodRDDP: Reliable Detection and Description of Interest Points
Gao, Y., Qi, L., & Tie, Y. (2022) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53654.2022.9945200 · Cited by 1
“Nowadays, the main ways to extract and describe features are detect-then-describe [13], detect-and-describe [7], [9] and describe-then-detect [14].”
BackgroundQuantitative Analysis of Object Detectors for Autonomous Driving and Autonomous Parking
Gohil, P., Plöger, P. G., & Hinkenjann, A. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956080 · Cited by 1
“Scale Invariant Feature Transform (SIFT) [19], Speeded Up Robust Features (SURF) [47] (an extended version of SIFT), HOG [20] and Deformable Part Model (DPM) [21] (an extended version of YOLOv1,v2,v3 ( the HOG detector) are some of the most popular classical object detectors.”
BackgroundLiu, X. (2022) · Academic Journal of Computing & Information Science · doi:10.25236/ajcis.2022.051204 · Cited by 1
“The problem of spatial domain difference of viewpoints between ground and aerial views makes it difficult for traditional manual feature methods such as SIFT (ScaleInvariant Feature Transform) [3] and SURF (Speed Up Robust Feature) [4] methods to extract complex and discriminative viewpoint invariant features, and cro…”
MethodGenerating Adaptive Targeted Adversarial Examples for Content-Based Image Retrieval
Pan, J., Zhu, X., & Liu, P. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892178 · Cited by 1
“In this paper, we focus on the system which generates impact CNN-based embeddings of retrieved images, where back-end algorithms like spatial verification [4], [21], [22] and re-ranking [23], [24] is not taken into consideration.”
BackgroundA Feature Point Extraction Method for Capsule Endoscope Localization
Ma, J., Wang, Y., Qian, P., et al. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-23473-6_34 · Cited by 1
Content-Aware Deep Feature Matching
Wang, W., Li, Z., Zheng, X., Lai, T., & Keikhosrokiani, P. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-20099-1_29 · Cited by 1
Single Image Printed Circuit Board Functional Similarity Clustering Using Vision Transformers
Fafard, A., Mohieldin, S., & Spielberg, J. (2022) · IEEE Physical Assurance and Inspection of Electronics (PAINE) · doi:10.1109/paine56030.2022.10014831 · Cited by 1
“These features ranged from keypoints such as those detected with scale-invariant feature transform (SIFT) or speeded up robust features (SURF) [3], [15] to those output from the feature space of a CNN. Unsurprisingly, these CNN features have consistently outperformed human crafted features as a…”
BackgroundMonocular Depth Estimation of Old Photos via Collaboration of Monocular and Stereo Networks
Kim, J. H., Ko, K.-L., Ha, T. L., & Jung, S. (2023) · IEEE Access · doi:10.1109/access.2023.3241348 · Cited by 2
“Classical stereo matching algorithms are extensively studied to find correspondence between stereo images by calculating matching costs [14], [15], [16], [17].”
BackgroundFast Relocalization and Loop Closing in Keyframe-Based 3D LiDAR SLAM
Cui, Y., Wu, Q., Hao, Y., et al. (2022) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio55434.2022.10011670 · Cited by 1
Applying the Robust Back-End in a Complete SLAM System on A Real-World Dataset
Sünderhauf, N. (2023) · Springer tracts in advanced robotics · doi:10.1007/978-3-031-24017-1_7 · Cited by 1
Liu, Z., Liu, W., & Zhong, J. (2023) · Advances in high-speed rail technology · doi:10.1007/978-981-99-0953-7_2 · Cited by 1
AR Long-Term Tracking Combining Multi-Attention and Template Updating
Mengru, G., & Chen, Q. (2023) · Applied Sciences · doi:10.3390/app13085015 · Cited by 1
Low-level feature image retrieval using representative images from minimum spanning tree clustering
Khunsongkiet, P., Bootkrajang, J., & Techawut, C. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15605-5 · Cited by 1
“Some research [41] applied the SIFT CBIR system while speeded up robust features (SURF) is applied approximates the DOG with box filters instead of gaussian averaging the image [2].”
Picture-Driven User Interface Development for Applications on Multi-platforms
Nguyen, V.-T., Tran, M., & Duong, A.-D. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-07233-3_33 · Cited by 1
Lunar Terrain and Albedo Reconstruction of the Apollo 15 Zone
Nefian, A., Kim, T., Moratto, Z. M., et al. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-17289-2_66 · Cited by 1
Hardware/Software Co-design of Embedded Real-Time KD-Tree Based Feature Matching Systems
Shoaib, S., Hafiz, R., & Shafique, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14364-4_90 · Cited by 1
A Hypergraph Matching Framework for Refining Multi-source Feature Correspondences
Zhang, H., Du, B., Wang, Y., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-18224-7_11 · Cited by 1
Power line feature extraction based on optimized SURF algorithm
Wang, Q., Zhao, Z., Gao, Q., et al. (2012) · International Conference on Applied Robotics for the Power Industry (CARPI) · doi:10.1109/carpi.2012.6356430 · Cited by 1
3D Non-Rigid Reconstruction with Prior Shape Constraints
Tao, L. (2014) · CLOK (University of Central Lancashire) · Cited by 2
Metric Learning across Heterogeneous Domains by Respectively Aligning Both Priors and PosteriorsPreprint
Qian, Q., & Chen, S. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1208.1829 · Cited by 1
Matching Forensic Sketches to Mug Shot Photos using Speeded Up Robust Features
Kotha, D. K. (2012) · Cited by 1
Target following camera system based on real-time recognition and tracking
Kumar, R. V. (2014) · Cited by 1
Detecting hands in video images using scale invariant local descriptors
Richarz, J., Plötz, T., & Fink, G. A. (2007) · Cited by 1
Estimation for Sensor Fusion and Sparse Signal Processing
Zachariah, D. (2013) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 1
IMAGE UNDERSTANDING USING SELF-SIMILAR SIFT FEATURES
Hering, N., Schmitt, F., & Priese, L. (2009) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0001753501140119 · Cited by 1
Planar Robot Position and Orientation Measurement Using a Monocular Vision
Wang, Y.-T., Chen, K.-W., Li, P.-H., et al. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-23147-6_16 · Cited by 1
Content-based video summarization in Object Maps
Asensio, M. M. (2013) · Cited by 1
Mining and querying multimedia data
Faloutsos, C., & Guo, F. (2011) · Cited by 1
A fast interest point detection algorithm
Chavez, A. (2008) · K-State Research Exchange (Kansas State University) · Cited by 1
Sufficient Component Analysis for Supervised Dimension ReductionPreprint
Yamada, M., Niu, G., Takagi, J. S., et al. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1103.4998 · Cited by 1
LUNAR TERRAIN AND ALBEDO RECONSTRUCTION FROM APOLLO IMAGERY
Nefian, A., Kim, T., Broxton, M. J., et al. (2010) · NASA Technical Reports Server (NASA) · Cited by 1
Reducing Keypoint Database Size
Jamshy, S., Krupka, E., & Yeshurun, Y. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04146-4_14 · Cited by 1
“This representation is called keypoint descriptor (see [15,16,17] and [18] for comparison).”
BackgroundDynamically reconfigurable architecture for embedded computer vision systems
Lareo, N., & Manuel, A. (2013) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 1
System-theoretic approach to image interest point detectionPreprint
Pimenov, V. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1003.4021 · Cited by 1
Visual Codebooks Survey for Video On-Line Processing
Beran, V., & Zemčík, P. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15910-7_1 · Cited by 1
Compressive image feature extraction by means of folding
Gardiner, B. (2012) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 1
Open-Ended Learning of Visual and Multi-Modal Patterns
Luo, J. (2011) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.5075/epfl-thesis-5233 · Cited by 3
Gangloff, J. A., Nageotte, F. P., & Poignet, P. (2013) · Wiley eBooks · doi:10.1002/9781118562147.ch6 · Cited by 1
Adaboost with "Keypoint Presence Features" for Real-Time Vehicle Visual DetectionPreprint
Bdiri, T., Moutarde, F., Bourdis, N., et al. (2009) · arXiv (Cornell University) · doi:10.48550/arxiv.0910.1273 · Cited by 1
Face recognition based on multi-scale local features
Geng, C. (2012) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/50725 · Cited by 1
Recognition using SIFT and its Variants on Improved Segmented Iris
Pathak, A. (2013) · Cited by 1
Computer Vision Aiding Smartphone Sensors for Indoor Location Applications
Kazemipur, B. (2015) · Libraries and Cultural Resources (University of Calgary) · doi:10.11575/prism/25403 · Cited by 1
Plane-based 3D Mapping for Structured Indoor Environment
Yuan, Z. (2013) · PORTO@Iris · doi:10.6092/polito/porto/2506288 · Cited by 2
Wallenberg, M. (2013) · DiVA (Digitala Vetenskapliga Arkivet) · Cited by 1
Automatic Shoeprint Image Retrieval Using Local Features
Bouridane, A. (2009) · Signals and communication technology · doi:10.1007/978-0-387-09532-5_9 · Cited by 1
Contributions to the content-based image retrieval using pictorial queries
Angosto, A. B. (2009) · TDX (Tesis Doctorals en Xarxa) · Cited by 1
Classifying a New Descriptor Based on Marr’s Visual Theory
Pérez-Lorenzo, J. M., Galán, S. G., Bandera, A. J., Vázquez-Martín, R., & Marfil, R. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02264-7_22 · Cited by 1
Novel colour constancy algorithms for digital colour imagery
Shi, L. (2009) · Summit (Simon Fraser University) · Cited by 1
Constrained Motion Estimation for a Multi-Camera System
Tehrani, M. M. (2015) · Libraries and Cultural Resources (University of Calgary) · doi:10.11575/prism/25425 · Cited by 1
A Behavior Based Control System for Surveillance UAVs
Oyekan, J. O., Lu, B., Li, B., et al. (2010) · Advanced information and knowledge processing · doi:10.1007/978-1-84996-329-9_10 · Cited by 1
Extracting geometric information from images with the novel Self Affine Feature Transform
Prohászka, Z., & Lantos, B. (2009) · Periodica Polytechnica Electrical Engineering · doi:10.3311/pp.ee.2009-3-4.08 · Cited by 1
Exploiting contextual data for event retrieval in surveillance video
Kelly, P., Conaire, C. Ó., & O'Connor, N. E. (2009) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1646396.1646437 · Cited by 4
Physical Computing With No Clock to Implement the Gaussian Pyramid of SIFT AlgorithmPreprint
Li, Y., Wei, Q., Qiao, F., & Yang, H. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1408.2289 · Cited by 1
A NOVEL ALGORITHM FOR SPEEDING UP KEYPOINT DETECTION AND MATCHING
Li, J., Yang, T., Pan, Q., et al. (2008) · International Journal of Image and Graphics · doi:10.1142/s0219467808003283 · Cited by 1
A multimodal labeling interface for wearable computing
Li, S., & Jia, Y. (2010) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/1719970.1720027 · Cited by 1
Depth-from-trajectories for uncalibrated multiview video
Ardis, P. A., Singhal, A., & Brown, C. M. (2008) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.806816 · Cited by 1
Spectrally queued feature selection for robotic visual odometery
Pirozzo, D. M., Frederick, P. A., Hunt, S. D., et al. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.876679 · Cited by 1
An improved visual inspection system using visual servo
Zang, C., & Hashimoto, K. (2010) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2010.5708294 · Cited by 1
“To improve its performance and accelerate processing speed, various algorithms have been proposed, including PCA-SIFT [11] and SURF (Speed up Robust Features) [12].”
MethodStanciu, S. G., Hristu, R., Boriga, R. E., et al. (2009) · International Conference on Transparent Optical Networks · doi:10.1109/icton.2009.5185282 · Cited by 1
“Later on, another invariant feature detector/descriptor has been published, being entitled SURF (Speed Up Robust Features) [3].”
BackgroundVideo Tracking Algorithm for UnmannedAerial Vehicle Surveillance
Samuelsson, O. (2012) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 1
A robust image retrieval system for mobile guide applications
Lee, J. A., Yow, K., & Kumazawa, I. (2012) · International Journal of Intelligent Systems · doi:10.1002/int.21522 · Cited by 1
Keypoint induced distance profiles for visual recognition
Chin, T.-J., & Suter, D. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2009.5206734 · Cited by 1
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.