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 12,901–13,000 of 14,752
Muscle strain field estimation using object tracking in high definition video sequences
Zamora, M. A., Franco, H., Fang, Q., et al. (2017) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-981-10-4086-3_97
The Role of Registration and Representation in Facial Affect Analysis
Sarıyanidi, E., Güneş, H., & Cavallaro, A. (2017) · Elsevier eBooks · doi:10.1016/b978-0-12-801851-4.00012-4
Automatic Aerial Image Alignment for GeoMemories
Amato, G. M., Falchi, F., Rabitti, F., et al. (2013) · Advances in Multimedia
3D localization for unmanned vehicles using visual inputs
Mou, W. (2017) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/70516 · Cited by 1
Multisensory Omni-directional Long-term Place Recognition: Benchmark Dataset and AnalysisPreprint
Mathur, A., Han, F., & Zhang, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.05215
Ballet, R., dos Santos, D. A., & Sjanic, Z. (2016) · Anais do ... Congresso Nacional de Engenharia Mecânica · doi:10.20906/cps/con-2016-0515
“In practice, the algorithms developed in the subsequent sections depends on a reliable landmark position estimation through image processing, which can be found in great detail in Bay et al. (2006) and Lowe (1999).”
MethodInvariance against local affine deformation for feature based object detection systems
Bulla, C., & Ohm, J.-R. (2016) · Picture Coding Symposium · doi:10.1109/pcs.2016.7906351
“Approved solutions to this problems are invariant local features like SIFT: Scale Invariant Feature Transform [1] or SURF: Speeded Up Robust Features [2].”
MethodMulti-scale integral orientationsPreprint
Wagan, A. I. (2010) · HAL
Graph transformation for keypoint trajectory coding
Tian, D., Sun, H., & Vetro, A. (2016) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2016.7905881
Spline warp model for registering pushbroom multispectral imagery
Saquib, S. S., Egan, M. D., & Gittins, C. M. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2266796
Active Stitching: Beyond Batch Processing of PanoramasPreprint
Summa, B., Tierny, J., Bremer, P., et al. (2013) · HAL (Le Centre pour la Communication Scientifique Directe)
sWSI: A Low-cost and Commercial-quality Whole Slide Imaging System on Android and iOS SmartphonesPreprint
Ma, S., & Wang, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.01088
Computer Vision-Based Sensor of Autonomous Mobile Robot for Detection of Stairs
A.Papsys, G. D. (2015) · International Journal of Advanced Research in Electrical Electronics and Instrumentation Engineering · doi:10.15662/ijareeie.2015.0406002
SeaVipers - Computer Vision and Inertial Position Reference Sensor System (CVIPRSS)
Erdman, J. (2015) · Louisiana State University · doi:10.31390/gradschool_dissertations.1208
A feature matching algorithm applied to welding trajectory revising
Zhecheng, L., Xin, H., & Xu, L. (2016) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/compcomm.2016.7924750
“To solve these problems, many scholars have been devoted to the improvement [17]-[19], such as Ke Y proposed PCA-SIFT algorithm [17] to reduce the dimension of characteristic by using principal component analysis method; Bay H proposed accelerated SIFT algorithm [18] by using square filter to replace SIFT Gaussian fil…”
MethodStudy on Optimal Image Set for Inputs for Super Resolution of On-Vehicle Fisheye Camera
Takano, T., Ono, S., Matsushita, Y., et al. (2017) · doi:10.11188/seisankenkyu.69.73
3D Reconstruction: Novel Method for Finding of Corresponding Points using Pseudo Colors
Bolecek, L., Říčný, V., & Slanina, M. (2013) · Brno University of Technology Digital Library (Brno University of Technology)
METHODS OF RELEVANT IMAGES SEARCH BASED ON THE MEDIAN PROCESSING OF STRUCTURAL DESCRIPTIONS
Gorokhovatsky, V. A. (2017) · Radio Electronics Computer Science Control · doi:10.15588/1607-3274-2017-1-12
Direct Perception and Action Decision for Unknown Object Grasping
Masuta, H., Motoyoshi, T., Sawai, K., et al. (2017) · International Journal of Artificial Life Research · doi:10.4018/ijalr.2017010103
An Adaptive FAST Corner Detector based on High Contrast Grid Image
Wu, T., Zhang, Z., Zhao, J., et al. (2017) · International Conference on Mechatronics Engineering and Information Technology (ICMEIT) · doi:10.2991/icmeit-17.2017.128
Research on the influence of non-scene factors on visual-based loop closure detection
Zhang, Z., & Dong, R. (2017) · CRC Press eBooks · doi:10.1201/9781315158570-26
Object tracking with SURF: ARM-Based platform Implementation
Hassnaoui, H., BADRI, A. B., Sahel, A., & Akil, M. (2017) · International Journal of Computer Applications Technology and Research · doi:10.7753/ijcatr0606.1002
“SURF detector is based on the Hessian matrix because of its good performance in computation time and accuracy [11].”
BackgroundMethodInfluentialOn-line, Incremental Visual Scene Understanding for an Indoor Navigating Robot.
Tsai, G. (2014) · Deep Blue (University of Michigan)
Improving visual SLAM by filtering outliers with the aid of optical flow
Özaslan, T. (2011) · Bilkent University Institutional Repository (Bilkent University)
Towards Automatic Linkage of Knowledge Worker’s Claims with Associated Evidence from Screenshots
Jones, P., Medd, D., Ramakrishnan, S., Shah, R., Keyton, J., & Samatova, N. F. (2017) · IEEE International Conference on Big Data Computing Service and Applications (BigDataService) · doi:10.1109/bigdataservice.2017.21
“Our approach accomplishes this using a template matching algorithm [7] implemented in OpenCV to locate key template features of editor window corner edges, without the need to perform traditional boundary detection (such as Canny edge detection [8][9]), which is notoriously messy.”
MethodFerraz, C. T. (2016) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.18.2016.tde-28092016-141219 · Cited by 1
Fundamental Theories and Techniques
Hontani, H., Hirano, Y., Dong, X. M., Shimizu, A., & Hanaoka, S. (2017) · Springer eBooks · doi:10.1007/978-4-431-55976-4_2
Development of Image Reconstruction Engine for Hand Scanner
Kim, W.-S. (2017) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3055635.3056636
Mapeamento e Reconstrução 3D com a utilização da Estereoscópia e SURF
Cordeiro, J., & Fernandes, B. T. (2016) · Revista de Engenharia e Pesquisa Aplicada · doi:10.25286/repa.v2i1.378
A Document Image Retrieval Method Based on Multi-feature Fusion
Zhu, Z., Ren, D., Zhou, G., et al. (2016) · International Conference on Network and Information Systems for Computers (ICNISC) · doi:10.1109/icnisc.2016.073
“Then multiple features (SURF feature, color feature, position feature and connected-component feature) of the feature points are extracted in the third step.”
BackgroundMethodInfluentialKim, W.-S. (2017) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3055635.3056630
Reconstrução 3D baseada em estereoscopia com a utilização de detectores de características
Cordeiro, J., & Fernandes, B. J. T. (2016) · Revista de Engenharia e Pesquisa Aplicada · doi:10.25286/repa.v2i1.518
Comparing Feature Matching Algorithms for Measuring In-Plane Strains on Civil Infrastructures
Feng, Y., Dai, F., & Zhao, J. (2017) · Joint Conference on Computing in Construction (JC3) · doi:10.24928/jc3-2017/0165
“As to the description-based algorithms, we selected the SIFT algorithm (Lowe 2004) and the SURF algorithm (Bay et al. 2006) for their superiority over other detectors and descriptors (Zhu and Davari 2015).”
MethodJia, Q., Wang, X., & Laien, Z. (2017) · doi:10.1145/3080845.3080870
“As it can be observed form the result, our approach outperform SIFT, HARRIS and FAST detectors in some conditions especially Gaussian noise, viewpoints change and blur image, and outperforms the SURF detectors in zooming and rotation.”
InfluentialHybrid Document Matching Method for Page Identification of Digilog Books
Park, J.-H., & Woo, W. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-31439-1_3
“Figure 1(b) shows a matching result of FAST+SURF (FAST features using SURF descriptor) on a text image [1].”
MethodStochastic Modeling for Video Object Tracking and Online Learning: manifolds and particle filters
Khan, Z. H. (2012) · Chalmers Publication Library (Chalmers University of Technology)
Saito, T., & KURODA, Y. (2013) · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · doi:10.1299/jsmermd.2013._1a2-h02_1
1P1-T01 Local Image Feature Based on Census Transform for Mobile Robot(Robot Vision)
Touma, Y., Hagiwara, H., & Asami, K. (2014) · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · doi:10.1299/jsmermd.2014._1p1-t01_1
The Application of Monocular Vision Camera Calibration and Feature Matching in SLAM
Wangpeng, Zhaohanqing, Wangjiangfeng, Liuhongbin, & Chenwei (2017) · AIACT '17 · doi:10.1145/3080845.3080876
Automatic image selection from images with similar contents
Bardak, B., & Demirci, M. F. (2017) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2017.7960673
“Bu yöntemler kısaca görüntülerdeki SIFT (Scale Invariant Feature Transform) [8] ve SURF (Speeded Up Robust Features) [9] gibi yerel öznitelikler çıkararak bu öznitekilerle bir dizin oluşturur ve neredeyse özdeş görüntüler bu dizin üzerinde arama yapılarak bulur.”
Understanding human-centric images : from geometry to fashion
Serra, E. S. (2015) · UPCommons institutional repository (Universitat Politècnica de Catalunya) · doi:10.5821/dissertation-2117-95985 · Cited by 2
Construction of visual codebook to speed up visual-based simultaneous localization and mapping
Sasaki, H., Hamatsu, F., & Hamagami, T. (2017) · Journal of International Council on Electrical Engineering · doi:10.1080/22348972.2017.1345371
2A2-R04 Image and Shape features combined Landmarks based Graph SLAM(Localization and Mapping)
Okada, N., Abe, D., Suzuki, S., et al. (2014) · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · doi:10.1299/jsmermd.2014._2a2-r04_1
Auto-calibration for Image Mosaicing and Stereo Vision
Spizhevoy, A., & Eruhimov, V. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39759-2_5
System Design for Intelligent Web Services
Hauswald, J. (2017) · Deep Blue (University of Michigan)
Antiblurry Dejitter Image Stabilization Method of Fuzzy Video for Driving Recorders
Xiong, J.-Y., Dai, M., Zhao, C., & Wang, R. (2017) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2017.06.016
“That means more low quality or marginal feature were detected in SIFT [6], SURF [9], ORB [11] and BRISK [12], which were prone to disappearing, be distorted or difficult to match.”
BackgroundInteractive digital photography at scale
Pascucci, V., & Summa, B. (2013)
ROS2D: Image feature detector using rank order statistics
Yousif, K., Taguchi, Y., Ramalingam, S., & Bab‐Hadiashar, A. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989524
Object Independent AR Space Generation
Jeon, J., & Woo, W. (2017) · International Symposium on Ubiquitous Virtual Reality · doi:10.1109/isuvr.2017.21
“Local features(SIFT, SURF, ORB)[5,6,7] are usually affected by the motion of the object because it is detected around the discriminative object and not on the wall where no pattern exists.”
BackgroundSecure SURF with Fully Homomorphic EncryptionPreprint
Shortell, T., & Shokoufandeh, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.05905
“Our focus on secure signal processing leads us to Speeded Up Robust Features (SURF) [2] [3].”
MethodKaris, M. S., Ali, N. M., Saad, W. H. M., et al. (2017) · Jurnal Teknologi · doi:10.11113/jt.v79.11285
“This technique spot a SURF feature and matching the feature point in the images [11, 12].”
MethodAn accelerated matching algorithm for SIFT-like features
Zhang, H., Luo, J., Wang, Z., et al. (2017) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc.2017.7984527
NS-SOF: A non-feature matching approach for sparse optical flow
Hu, G., Wang, Y., & Guo, L. (2017) · Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) · doi:10.1109/acirs.2017.7986056
“Harris [5], SIFT [6], SURF [7]) and so on.”
BackgroundMethodA blur-invariant local feature for motion blurred image matching
Tong, Q. K., & Aoki, T. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2281710
“Unlike traditional interest point detectors [5-7] which detect corners (very sensitive to blur) or blobs from images by calculating gradients or intensities (both are sensitive to blur), our detector is based on a new concept - “Moment Symmetry” which is similar to line symmetry but robust to strong blur.”
BackgroundMethodInfluentialA visual perceptual descriptor with depth feature for image retrieval
Wang, T., & Qin, Z. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2282077
Evaluation of computational efficiency on image-block cutting area in stitching orthophoto
Tsai, C.-F., Tsou, C.-Y., Hung, Y.-C., et al. (2017) · International Conference on Applied System Innovation · doi:10.1109/icasi.2017.7988598
SIFT,SURF&Seasons:Appearance-basedLong-termLocalization inOutdoorEnvironments
Lilienthal, A. J. (2009)
SPEEDING UP SIFT, PCA-SIFT AND SURF USING IMAGE PYRAMID
Amami, M. M. (2017) · The Journal of The University of Duhok · doi:10.26682/sjuod.2017.20.1.32
Rotation and affine invariant accurate feature selection and matching method for RGBD images
Dharmasiri, V. T., Nurse, K., & Yuguchi, Y. (2017) · IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA) · doi:10.1109/civemsa.2017.7995334
“Harris corner [4], SIFT [5], SURF [6], ORB [7], MSER [8] or BRISK [9] are well used feature detection algorithms.”
MethodInfluentialZhou, Q., Tong, X., Liu, S., Lu, X., Liu, S., Chen, P., Jin, Y., & Xie, H. (2017) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlii-3-w1-219-2017
“Bay et al. (2006) presents the Speeded Up Robust Feature (SURF), which is an improved version of SIFT.”
A Copy-Move Forgery Detection Method for VDR Image
Mei-dong, H. U., Wang, X., & Xu, G. (2017) · DEStech Transactions on Computer Science and Engineering · doi:10.12783/dtcse/cst2017/12560
“Algorithm Implementation The specific steps of the improved SURF algorithm are as follows: Step 1: Read the input image I; Step 2: Use BEMD to decompose the image into five IMF components and one residue; Step 3: Use the SURF algorithm to extract the feature points of the IMF layers and residue layer and generate the…”
MethodInfluentialA novel and blur-invariant local feature image matching
Tong, Q. K., & Aoki, T. (2017) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-china.2017.7990994
“Both detectors and descriptors of the existing schemes are very sensitive to strong blur, even though a number of local feature schemes have been proposed such as SIFT [1], SURF [2], BRSIK [3], etc.”
Depth dependent invariant features applied to person detection using 3D camera
Asl, A. S., & Oskoei, M. A. (2017) · Iranian Joint Congress on Fuzzy and Intelligent Systems · doi:10.1109/cfis.2017.8003592
Fine-Grained Infer $$PM_{2.5}$$ Using Images from Crowdsourcing
Li, S., Xi, T., Que, X., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-65482-9_53
“We extract speeded up robust features (surf) [10] of the new images and template image as their descriptor.”
MethodSevere-occluded 3D object identification via region-based descriptions
Escudero-Viñolo, M., & Bescós, J. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.07.007
Fast Registration of Remote Sensing Image Based on Corner Feature
钱, 社. (2016) · Journal of Image and Signal Processing · doi:10.12677/jisp.2016.51006
Karimov, K., & Volkov, M. V. (2015) · Scientific and technical journal of information technologies mechanics and optics · doi:10.17586/2226-1494-2015-15-3-365-372
ĐÁNH GIÁ HIỆU NĂNG GIẢI THUẬT FAB-MAP* ĐỊNH VỊ ROBOT TRONG NHÀ SỬ DỤNG THÔNG TIN HÌNH ẢNH
Hùng, N. Q., Vu, H., Hải, T. T. T., & Hoan, N. Q. (2017) · Nghiên cứu cơ bản và ứng dụng Công nghệ thông tin (FAIR) · doi:10.15625/vap.2016.00012
SIFT with the F-transform Pre-processing
Hurtík, P., Števuliáková, P., & Perfilieva, I. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-66824-6_22
Learning data-efficient hierarchical features for robotic graspable object recognition
Wang, Z., Wang, B., Guo, C., Li, Z., Liu, Y., & Liu, H. (2017) · IEEE International Conference on Advanced Intelligent Mechatronics (AIM) · doi:10.1109/aim.2017.8014081
Planetary landing point tracking based on multiple reference points
Wang, P., Qin, Z., & Zou, W. (2017) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2017.8015958
“SURF [17] descriptor, developed by Bay et al, besides the robustness to illumination variance and noise, it has relatively high efficiency and high discrimination.”
MethodInfluentialCross spectral, active and passive approach to face recognition for improved performance
Kowalski, M., Grudzień, A., & Szustakowski, M. (2017) · doi:10.1117/12.2279141
Theoharatos, C., Kastaniotis, D., Besiris, D., et al. (2017) · Smart innovation, systems and technologies · doi:10.1007/978-3-319-56904-8_23
A Low Rank Regularization Method for Motion Adaptive Video Stabilization
Wu, H., Shim, H. J., & Xiao, L. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67777-4_48
AN INDOOR SLAM METHOD BASED ON KINECT AND MULTI-FEATURE EXTENDED INFORMATION FILTER
Chang, M., & Kang, Z. (2017) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlii-2-w7-327-2017
Foreground Detection Using Region of Interest Analysis Based on Feature Points Processing
Ustyuzhanin, N., & Gilmutdinov, M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67380-6_62
Learning and Searching Methods for Robust, Real-Time Visual Odometry.
Richardson, A. (2015) · Deep Blue (University of Michigan)
Research on extended target tracking with partial region feature
Wang, C. (2017) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac.2017.8054353
Implement of a 6-DOF manipulator with machine vision and machine learning algorithms
Chen, P.-Y., Chen, W., Pai, N., et al. (2017) · International Conference on Applied Electronics · doi:10.23919/ae.2017.8053583
“The most commonly used Keypoint detection algorithms used now are SURF[3] and SIFT[4].”
MethodDevelopment of a Secure Biometric Recognition System
Rajesh Kumar, M. (2016) · Northumbria Research Link (Northumbria University)
Person Re-identification Based on Minimum Feature Using Calibrated Camera
Zhang, T., Shen, X., Xiu, Q., et al. (2017) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-6499-9_51
Visual Tracking via the Fusion of Compressive Sensing and Speed Up Robust Feature Information
Wang, Y., & Li, D. (2017) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc.2017.176
“In this paper, we introduce SURF[10] (Speed Up Robust Feature) algorithm to solve the problems that target’s feature is simple and scale variation effectively in the compressive sensing target tracking.”
MethodRobust Image Dehazing and Matching Based on Koschmieder s Law And SIFT Descriptor
nbspAfthab Baik, K. A., & nbspBeena, M. V. (2015) · International Journal of Engineering Development and Research
360° Panoramic Video from a 3-Camera Rig
Safdarnejad, S. M., Liu, X., & Liu, J. (2017) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-3187-8_47
Augmented Robust PCA For Foreground-Background Separation on Noisy, Moving Camera VideoPreprint
Gao, C., Moore, B. E., & Nadakuditi, R. R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.09328
Image Retrieval Framework Based on Dual Representation Descriptor
YOSHIDA, Y., & TOYOFUKU, T. (2017) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2017edp7050
Introducing Image Saliency Information into Content Based Indexing and Emotional Impact Analysis
Gbèhounou, S., Urruty, T., Lecellier, F., & Fernández-Maloigne, C. (2017) · Springer eBooks · doi:10.1007/978-3-319-57687-9_4
SPATIO-TEMPORAL VIDEO COPY REGISTRATION USING MULTIMODAL FEATURES
Kumar.K, N. (2014) · International Journal of Engineering Development and Research
A Projectivity Diagnosis of Local Feature Using Template Matching
Ohki, H., Taniguchi, R.-I., Inoue, S., et al. (2017) · Electronics and Communications in Japan · doi:10.1002/ecj.11995
Application of Local Features for Calibration of a Pair of CCTV Cameras
Lach, A., & Grega, M. (2017) · Communications in computer and information science · doi:10.1007/978-3-319-69911-0_6
Saxena, P. (2017) · e-Publications@Marquette (Marquette University) · Cited by 1
Visual navigation using natural landmark based on local features
Xiao, L., Hu, R., Zhang, W., et al. (2017) · doi:10.1117/12.2281944
“SURF([8]) features of natural landmarks are also extracted and saved.”
BackgroundA Method of Object Re-identiciation Applicable to Multicamera Surveillance Systems
Lisowski, K., & Czyżewski, A. (2017) · Communications in computer and information science · doi:10.1007/978-3-319-69911-0_8
Structure-aware sample consensus for robust stereo visual odometry
Liu, C., Li, Z., Chen, Z. Q., et al. (2017) · International Journal of Distributed Sensor Networks · doi:10.1177/1550147717736655
A Multi-scale Image Registration Algorithm Based on Wavelet Transform
Sun, Q., & Zhang, J. (2017) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-3229-5_93
Design of multi-sensors integrated navigation system
Wu, P., Zhai, W., Song, Y.-B., et al. (2016) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip.2016.8079894
“(a) Feature point extraction SURF was proposed by Bay Herber and others [4][5], is Multi-scale and based on gray gradient, can deal with the movement of target, partial occlusion and noise.”
MethodVisual Self-localization via Inferring View-to-Map Correspondences
Xu, Q., & Liu, X. (2017) · doi:10.1145/3132734.3132740
A Point and Line Features Based Method for Disturbed Surface Motion Estimation
Li, X., & Zhou, Y. F. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70090-8_14
Object detection with BRIEF descriptors and locality sensitive matching for augmented reality
Özuysal, M. (2017) · Pamukkale University Journal of Engineering Sciences · doi:10.5505/pajes.2017.92604 · Cited by 1
“[11] Bay H, Ess A, Tuytelaars T, Gool L V.”
Background
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.