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 12,501–12,600 of 14,752
Calculate distance to object in the area where car, using video analysisPreprint
Legchekova, E., & Titov, O. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.07963
Unsupervised Grouping of Local Components for Object Segmentation
Islam, M. K., Jahan, F., Baek, J.-H., et al. (2015) · American Scientific Research Journal for Engineering, Technology, and Sciences
Li, J., Kaneko, A. M., & Fukushima, E. F. (2013) · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · doi:10.1299/jsmermd.2013._1a1-r11_1
Localization based on vision using stereo System and SIFT features
Mohamed, S., Mail, A. N., El-Sayed, M. H. F., et al. (2015) · Artificial Intelligence Research · doi:10.5430/air.v5n1p95
“(2) Orientation assignment that is determined by constructing a circular region with radius 6σ around the detected interest point, with σ the scale at which the interest point is detected and the dominant orientation describes the orientation of interest point.[18, 19] (3) Interest point descriptor is represented by a…”
BackgroundA speed up efficient match kernel for visual estimation and detection
Hong, H., & Tong, M. (2015) · SiPS ... design and implementation - IEEE Workshop on Signal Processing Systems · doi:10.1109/sips.2015.7345020
Linking the virtual and physical worlds )
Girod, B., Chandrasekhar, V., Chen, D. M., Cheung, N. M., Grzeszczuk, R., Reznik, Y. A., Gabriel Takacs, A., Tsai, S. S., & Vedantham, R. (2011)
Multi-Camera Person Tracking using Particle Filters
Andersen, M. S., & Andersen, R. S. (2010)
Photo Tagging in Urban Environments
Simon, C., & Maliosz, M. (2011)
Dhar, A. (2010)
ASSESSMENTS OF NONLINEAR LEAST SQUARES METHODS FOR UAV VISION BASED NAVIGATION
Sheta, B. I., Elhabiby, M., & El‐Sheimy, N. (2012)
A Network Robot System for Object Identification and Localization
Borissov, A., & Janecek, J. (2008)
Classification of wild animals situated in Slovak Country
Matúška, S., & Hudec, R. (2013)
NHK STRL at TRECVID 2011: Surveillance Event Detection and Semantic Indexing
Takahashi, M., Kawai, Y., Naemura, M., Fujii, M., & Satoh, S. (2011)
A New Mobile Manipulation Platform for Automatic Coffee Retrieval
Anderson, C. D., Axelrod, B., Case, J. P., et al. (2006)
An Iterative Approach to Reconstruct Depth Map for Image Relighting and Matching
Saleem, M., & Altaf, Q. (2014)
Automated City Modeling from Omnidirectional Image Sequences
Havlena, M. (2007)
Location -based augmented reality on cellphones
Turk, M. (2009)
Jang, B. (2011) · Digital Repository Service (Northeastern University) · doi:10.17760/d20002062
Parallelizing Scale Invariant Feature Transform On A Distributed Memory Cluster
Bobovych, S. (2011) · Journal of the Arkansas Academy of Science
Penz, H., Daubner, F., Bodenstorfer, E., et al. (2015) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-6741-9_4
Efficient Video Copy Detection: Sequence Matching in the H.264 Compressed Domain
Kaes, C., & Nicolas, H. (2011) · HAL (Le Centre pour la Communication Scientifique Directe)
NHK STRL at TRECVID 2012: Semantic Indexing
Kawai, Y., Mochizuki, T., Sumiyoshi, H., & Sano, M. (2012) · TRECVID
Chavéz-García, R. O., Montes, M., & Sucar, L. E. (2011)
Improved object recognition algorithm based on template matching
Ding, X., Li, Y., & Ma, X. (2015)
Universiteit Leiden Opleiding Informatica
Zaaijer, S., & Bohrweg, N. (2013)
SUSurE:SpeededUpSurroundExtremaFeatureDetectorandDescriptor forRealtimeApplications
Ebrahimi, M., & Mayol-Cuevas, W. W. (2009)
Displayed Object Recognition for Smartphone Interaction
Kadar, K., de Sorbier, F., & Saitô, H. (2013)
Envisor: Online Environment MapConstruction forMixedReality
DiVerdi, S. (2008)
A Unified framework for local visual descriptors
Kihl, O., Picard, D., Gosselin, P.-H., Atlantique, R. B., & Beaulieu, C. U. D. (2014)
Autonomous Intelligent Systems Lab
Burgard, W. (2007)
Structured graphical models for unsupervised image segmentation
Príncipe, J. C., & Kampa, K. (2011)
A REVIEW ON OBJECT RECOGNITION TECHNIQUES FOR PRACTICAL APPLICATION
Nayak, S. D., & Rautaray, S. S. (2015)
túìõêóìåGZkGñâëå äõGõôàäíêïéGúöêï éGyvpGàïãG kñúâìåGmêìõåôêïé GçñôGhúéîåïõåãGy åàìêõ
Park, J.-H., Seo, D., Ku, M.-S., et al. (2011)
Target Handoff with Appearance Model Inheriting and Learning
Dong, W., & Qu, P. (2014) · International Journal of Signal Processing Image Processing and Pattern Recognition · doi:10.14257/ijsip.2014.7.5.11
COIN RECOGNIZATION USING GENETIC ALGORITHM: A REVIEW
Dakhode, A., & Deshmukh, P. R. (2013)
Deng, Z., Lei, L., & Zhou, S. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2194427
“, feature identification and extraction) is divided into two main types: corner based detector (Moravec[6], Harris[7], SUSAN[8], FAST[9]) and area based detector(SIFT(Scale Invariant Feature Transform)[10], SURF(Speeded Up Robust Features)[11], BFSIFT(Bilateral Filter SIFT)[12], KAZE[13]).”
BackgroundInfluentialcal Kernel Color Histo Based Descriptor
Jalilvand, A., & Boroujeni, H. S. (2011)
Motion Recovery of a Single Camera Installed on a Wheeled Vehicle
Mirabdollah, M. H., & Mertsching, B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39094-4_47
“To find the correspondent points between two frames, we utilized the SURF method [1] which gave a good ratio of inliers at a reasonable computation cost.”
MethodMODEL-BASED DEFORMABLE REGISTRATION OF MRI BREAST IMAGES WITH ENHANCED FEATURE SELECTION
Abarghouei, S. E. (2015)
Kalman-Filter 予測を用いた特徴点マッチングとMean-Shiftを組合せた粗密探索に基づく特徴点追跡
史陽, 冨., 高嗣, 平., & 健二, 間. (2014) · 画像電子学会誌 · doi:10.11371/iieej.43.318
2nd URV Doctoral Workshop in Computer Science and Mathematics
Autores, V. (2015) · Publicacions URV eBooks · doi:10.17345/9788484243991
Robot Pose and Velocity Estimation Using a Binocular Vision
Wang, Y.-T., Wang, S., Feng, Y.-C., et al. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-23147-6_17
An Improved Laparoscopic Image Registration Algorithm Based on Sift
Zhou, J., Mao, J., & He, X. (2014) · Communications in computer and information science · doi:10.1007/978-3-662-45643-9_19
“Reference [4] introduces an Speeded Up Robust Features(SURF) which is based on integral image haar derivation and reduces the operation time.”
BackgroundVues Multiples non-calibrées : Applications et Méthodologies
Carrasco, M. (2010) · HAL
Detection of 3-dimensional textured object without depth information
Lee, S.-I., & Kim, H. J. (2015) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.1109/iccas.2015.7364938
Panoramic Background Generation and Abnormal Behavior Detection in PTZ Camera Networks
Cho, S. H., & Kang, H.-B. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24028-7_69
Uso de fluxo óptico na odometria visual aplicada a robótica
Araújo, D. C. D. S. (2015) · doi:10.47749/t/unicamp.2015.945968
Sliding window based landmark extraction for indoor 2D SLAM using forward-looking monocular camera
Chae, H.-W., Park, C.-S., & Song, J.-B. (2015) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.1109/iccas.2015.7364934
Surface Oriented Traverse for robust instance detection in RGB-D
Wang, R., Medioni, G. G., & Zhao, W. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353983
“Knopp et al. [15] develop the SURF [2] feature to handle the 3D case and perform object recognition by a Hough transform procedure.”
MethodThe Principal Component Analysis Method Based Descriptor for Visual Object Classification
Kurt, Z., Özkan, K., & Işık, Ş. (2015) · International Journal of Intelligent Systems and Applications in Engineering · doi:10.18201/ijisae.08060
A new robotic context-based object recognition algorithm for humanoid robots
Yoo, J. H., & Kim, D. H. (2015) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2015.7363521
“In a lot of matching problems, feature descriptors such as SIFT, SURF, ORB [11], BRIEF [12] and BRISK [13], as well as interest points by corner detectors [14][15][8] or local extrema detectors [6][7], are widely used to improve matching performance.”
BackgroundMethodStructured representation learning from complex data
Nguygen, T. D. (2015)
Robust Method for Deforestation Analysis of Satellite Images
Ispas, I. (2015) · International Journal of Environmental Monitoring and Analysis · doi:10.11648/j.ijema.20150306.16
Euclidean reconstruction of natural underwater scenes using optic imagery sequence
Hu, H. (2015) · University of New Hampshire Scholars Repository (University of New Hampshire at Manchester)
Color correction for stereoscopic images
Yu, J.-J., & Park, C.-J. (2015) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc.2015.7354781
“3, H means a 3*3 homography matrix estimated by RANSAC using the SURF features. xrefer and xtgt are three dimensional homogeneous vectors which are coordinates of SURF features in the reference image and the target image.”
MethodInfluentialLatent subspace sparse representation-based unsupervised domain adaptation
Liu, S., Sun, H., Zhao, F., et al. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2205702
Object Recognition Based on Local Features Using Camera – Equipped Mobile Phone
Koceski, S., Koceska, N., & Krstev, A. B. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-19325-5_30
Object and Scene Category Recognition using a Combination of Dense Color SIFT Descriptors
Rassem, T. H., Khoo, B. E., Bayuaji, L., Makbol, N. M., & Suryanti, A. (2015) · UMP Institutional Repository (Universiti Malaysia Pahang)
Jayawardena, S., Gould, S. J., Li, H., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16628-5_47
Object tracking: Appearance modeling and feature learning
Almomani, R. (2015) · Human Biology
Feature Coverage Indexes for Dual Homography Estimation in Constructing Panorama Image
Jun, K., & Kim, S.-J. (2015) · Journal of Sensors · doi:10.1155/2016/1350750
“The results of SURF and ORB are not satisfactory.”
MethodInfluentialWhat Vision Can, Can’t and Should Do
Zillich, M. (2014) · Cognitive systems monographs · doi:10.1007/978-3-319-06614-1_9
Efficient dense reconstruction using geometry and image consistency constraints
Shashkov, M. M., Mak, J., Recker, S., Nguyen, C., Owens, J. D., & Joy, K. I. (2015) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2015.7444539
3D Scene Exploration with External Controllers
Wojciechowski, A. (2012) · Studies in computational intelligence · doi:10.1007/978-3-642-27446-6_6
A Study of Ancient Ceramics Verification Based on Vision Methods
Tang, Y., Ding, J., & Guo, W. (2014) · Communications in computer and information science · doi:10.1007/978-3-662-45643-9_7
Relating PLI Data Across Scales
Strohmer, S., Axer, M., Reckfort, J., et al. (2013)
Object Localization Using Kinect
Mocanu, I. G., & Curt, I. (2014) · RePEc: Research Papers in Economics
Autonomous Mapping in Polluted Environments
Szőke, I., Majdik, A., Lupea, D., et al. (2010) · Hungarian Journal of Industry and Chemistry · doi:10.1515/299
3D sparse feature model using short baseline stereo and multiple view registration
Watson, M., Bhatti, A., & Nahavandi, S. (2011) · International Conference on Mechatronics
Fast locality-constrained low-rank coding for image classification
Min, F., Wang, F., Kai, W., Xin, S., & Liu, Z. (2015) · Chinese Automation Congress · doi:10.1109/cac.2015.7382578
“Namely, given an image, the low-level features such as SIFT[7], HOG[8], SURF[9] can be extracted from densely sampled patches; those raw features then can be encoded with a codebook constructed simply using K-means clustering; in order to make the coding robust to different transformation of the image, maxpooling is p…”
MethodFine-tuning SIMPLE based Content Based Image Retrieval system
Vu, V.-H., Le, H.-S., Kanishcheva, O., et al. (2015) · International Symposium on Information and Communication Technology · doi:10.1145/2833258.2833273
“First, the region points are detected by for example SIFT [14] or SURF [2] detector.”
MethodArchitectural support for irregular programs and performance monitoring for heterogeneous systems
Mistry, P. (2014) · Digital Repository Service (Northeastern University) · doi:10.17760/d20005005
Chitaliya, N. G. (2012) · INFLIBNET
Robustness of Biometrics by Image Processing Technology
Fay, R., & Ruland, C. (2015) · Springer eBooks · doi:10.1007/978-3-319-13156-6_6
Accelerated Wide Baseline Matching using OpenCL
Cao, J., Liang, J., Xie, X., et al. (2013)
Gai, M., & Cho, Y. K. (2013) · Proceedings of the ... ISARC · doi:10.22260/isarc2013/0061
Selective submap joining SLAM for autonomous vehicles
Masó, A., & Josep, M. (2011) · TDX (Tesis Doctorals en Xarxa)
High Performance Low Power Embedded Vision Systems
Nikitakis, A. (2014)
Video event recognition and prediction based on temporal structure analysis
Li, K. (2015) · Digital Repository Service (Northeastern University) · doi:10.17760/d20128341
Scale-Adaptive Object Tracking with Diverse Ensembles
Elkerdawy, S., Eldesokey, A., Salaheldin, A. M., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14249-4_61
Identificação Visual de Caixas de Medicamentos Usando Features Correspondentes
Benjamim, X. C. (2012) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)
Contour Detection-Based Discovery of Mid-Level Discriminative Patches for Scene Classification
Yang, J., Zhang, J., Wang, G., & Li, M. (2016) · International Journal of Advanced Robotic Systems · doi:10.5772/62266
“In low-level representation, great progress has been achieved with the invention of local invariant descriptors, such as SIFT [1], SURF [2] and ORB [3].”
Analyzing the impact of mobile technology on mobile-centric youth in South Africa
Allen, S. L. (2012) · Open University of Cape Town (University of Cape Town)
Multi-object Template Matching Using Radial Ring Code Histograms
Zheng, S., Zhang, B., & Yang, H. S. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-21963-9_51
“The latest matching algorithms based on scale and rotation invariant key-points with histograms of gradient information, like SIFT[12],[13], PCA-SIFT[14], SURF[15] and GLOH[16],[17], present very spectacular recognition performance.”
MethodYang, Z. (2012) · Institutional Repositories DataBase (IRDB)
An Improvement of Energy-Transfer Features Using DCT for Face Detection
Fusek, R., Sojka, E., Mozdřeň, K., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-07998-1_59
“The Speeded up Robust Feature (SURF) descriptor by Bay et al.[2] is also one of the widely used keypoint descriptors.”
MethodRobust Object Recognition Under Partial Occlusions Using an RGB-D Camera
Yoo, Y.-H., & Kim, J.-H. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-16841-8_58
“The advantage of DBN is that features are extracted by not hand-crafted method like SIFT [9], SURF [10], but learning.”
MethodUnsupervised visual object categorization
Kinnunen, T. (2008) · Doria (University of Helsinki)
Research on Method for Constructing High-Dimensional SURF
Weilu, Z., Xu, H., Weibin, Z., et al. (2012) · Lecture notes in electrical engineering · doi:10.1007/978-3-642-25792-6_59
RETRACTED: A Novel Approach for Ranking Images Using User and Content Tags
ur, A., Muzammal, M., Ahmad, H. Z., Majeed, A., & Jan, Z. (2015) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2015.061216
RetractedGeneració de mapes a partir d'imatges preses amb un UAV
Perarnau, G., & Lumbreras, F. (2015) · Dipòsit Digital de Documents de la UAB (Universitat Autònoma de Barcelona)
Sharing Computation Resources in Image and Speech Recognition for Embedded Systems
Lee, S. E. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-23324-1_25
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.