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 12,101–12,200 of 14,752
Extracting corresponding-point on textureless object surface based on texture synthesis
Mao, M., Hao, K., & Ding, Y. (2014) · International Conference on Mechatronics and Control · doi:10.1109/icmc.2014.7231574
“On the other hand, if ( )T • is a affine transform, then descriptors such as SIFT, SURF et.al. are both satisfy the condition (2) with this transformation.”
BackgroundDeng, W. (2014) · Nottingham ePrints (University of Nottingham)
Adquisición y procesamiento de imágenes aéreas para sensado remoto
Manera, J. F., Domı́nguez, L., Delrieux, C. A., et al. (2009) · El Servicio de Difusión de la Creación Intelectual (National University of La Plata)
Wang, P.-C., Tseng, W.-T., Cheng, C.-M., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39191-0_67
박원창, 류대현, & 최태완 (2014)
Detection of flat ground area by single camera on mobile vehicles
Tanaka, M., & Onishi (2011) · International Conference on Advanced Mechatronic Systems
Leon, L. M. C. (2012) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.45.2012.tde-31102013-094950
Procesamiento de video digital: reconocimiento de patrones aplicado a la detección de key-frames
Iparraguirre, J., & Delrieux, C. A. (2010) · El Servicio de Difusión de la Creación Intelectual (National University of La Plata)
Interactive on-device Mobile Landmark Recognition with compact binary codes
Guan, T., Cao, L., Cai, L., et al. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178148
A New Approach for Instance-Based Skew Estimation
Shiraishi, S., Feng, Y., & Uchida, S. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23866-6_21
“The proposed method exploits SURF[3], focusing on the partial features of characters in the document.”
MethodMulti-camera real-time breathing guidance system for radiotherapy
Lai, C.-L., Chen, H., Cheng, Y., et al. (2015) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-tw.2015.7216951
“[6] H.”
MethodPerception de la géométrie de l'environment pour la navigation autonome
Berger, C., & LACROIX, S. (2009) · Thèses en ligne de l'Université Toulouse III (Université Toulouse III)
Visual Vocabulary Learning and Its Application to 3D and Mobile Visual SearchPreprint
Cao, L. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1207.7244
Couto, L. N. (2012) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.55.2012.tde-04092012-110014 · Cited by 6
Method of Interest Points Characterization Based C-HOG Local Descriptor
Grand-Brochier, M., Tilmant, C., & Dhome, M. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-17277-9_23
“The various tests [2,5] show that the Fast-Hessian has the best repeability rate.”
BackgroundMethodInfluentialXu, Q., Lan, C., Geng, X., et al. (2014)
Recognition of Hits in a Target
Semerak, V., & Drahanský, M. (2010) · Communications in computer and information science · doi:10.1007/978-3-642-17641-8_5
Berger, C., & Lacroix, S. (2007) · HAL (Le Centre pour la Communication Scientifique Directe)
Registration method for multispectral skin images
Kadiķis, R. (2015) · International Conference Radioelektronika · doi:10.1109/radioelek.2015.7129018
“Thus, if one would choose a similar feature-based approach to [7], faster descriptors, such as SURF [10] or ORB [11], might be considered.”
BackgroundRaytchev, B., Kikutsugi, Y., Tamaki, T., et al. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19318-7_20
GPU accelerated feature algorithms for mobile devices
Hall, S. (2014) · Tuwhera (Auckland University of Technology) · Cited by 2
Automatic Object Recognition and Registration of Dynamic Heavy Equipment Using a Hybrid LADAR System
Gai, M. (2012) · Lincoln (University of Nebraska)
Kusumoto, A. Y., de Vasconcelos, L. E. G., Leite, N. P. O., et al. (2014) · doi:10.5162/etc2014/4.4
Borgne, H. L., & Shabou, A. (2012) · Wiley eBooks · doi:10.1002/9781118577851.ch16
Robust Vision-based Thermal Control Systems with Industrial Applications
Yang, T. B. (2010) · Scholarship at UWindsor (University of Windsor)
Albán, W. R. G. (2014) · Americanae (AECID Library)
Improving multi-view image classification using higher order information and triangulation embedding
Doerr, K., Samarabandu, J. K., & Wang, X. (2014) · International Conference on Information and Automation for Sustainability (ICIAfS) · doi:10.1109/iciafs.2014.7069598
A General Preprocessing Method for Improved Performance of Epipolar Geometry Estimation AlgorithmsPreprint
Kushnir, M., & Shimshoni, I. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1501.06716
Background subtraction and object tracking with applications in visual surveillance
Ng, K. K. (2011) · Purdue e-Pubs (Purdue University System)
Análise de formas usando wavelets em grafos
Leandro, J. D. J. G. (2014) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.45.2014.tde-02072014-150049
Tracking with split and merge processes
Cai, Y., Zhao, Q., & Wang, Y. (2012) · International Conference on Computing and Convergence Technology
A robust structure and motion replacement for bundle adjustment
Mitchell, S. K., Warren, M., McKinnon, D. H., & Upcroft, B. (2010) · QUT ePrints (Queensland University of Technology)
Background subtraction with PTZ cameras
Serra, R. R. (2012)
User tracking using a wearable camera
Redzic, M., Brennan, C., & O'Connor, N. E. (2012) · Arrow@dit (Dublin Institute of Technology)
Jeong, H. (2014) · Wiley eBooks · doi:10.1002/9781118659199.ch7
Prakash, S., & Gupta, P. (2015) · Augmented vision and reality · doi:10.1007/978-981-287-375-0_2
Creating large and accurate mosaics of the mid-atlantic ridge
Vila, J. F., Gracias, N., Delaunoy, O., et al. (2007) · Instrumentation viewpoint
Dense real-time 3D reconstruction from multiple images
Ling, L. (2014) · RMIT Research Repository (RMIT University Library) · doi:10.25439/rmt.27332865
García, I. O. (2012) · UPM Digital Archive (Technical University of Madrid) · doi:10.20868/upm.thesis.14724
Hernández-García, R., García-Reyes, E. B., Cózar, J. R., & Guil, N. (2014) · Revista Cubana de Ciencias Informáticas · Cited by 3
Efficient vision-based loop closing techniques for delayed state robot mapping
Ila, V., Andrade‐Cetto, J., & Sanfeliu, A. (2008) · RECERCAT (Consorci de Serveis Universitaris de Catalunya)
Warsop, T., & Singh, S. K. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21227-7_37
“Typical features used in such scenarios include Harris corners ([13, 15, 6]), SIFT features ([27]) and more recently, SURF features ([1]).”
BackgroundView extension for teleoperated MAV
Lim, R. F., Torii, A., & Okutomi, M. (2015) · doi:10.1109/mva.2015.7153247
“This way, the system will only compute SURF descriptors on new features (Process C) and the position of existing features are updated without recomputing their descriptors.”
MethodInfluentialImage synthesis using searching and tracking techniques in combined vision systems
Alpatov, B. A., Babayan, P. V., & Khosenko, M. (2015) · Mediterranean Conference on Embedded Computing (MECO) · doi:10.1109/meco.2015.7181888
Digital Signature: A Novel Adaptative Image Segmentation Approach
Freire-Obregón, D., Castrillón-Santana, M., & Déniz, Ó. (2011) · InTech eBooks · doi:10.5772/18097
Texture-Independent Feature-Point Matching (TIFM) from Motion Coherence
Li, P., Farin, D., Gunnewiek, R. K., et al. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-76386-4_75
“proposed a new rotation- and scale-invariant interest point detector and descriptor, called SURF (Speeded Up Robust Features) [8].”
BackgroundDIOTRI, F., Roncella, R., Lucianaz, C., et al. (2011) · PORTO Publications Open Repository TOrino (Politecnico di Torino)
Molina, P. J. (2011) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)
Redzic, M., Brennan, C., & O'Connor, N. E. (2010) · Dublin City University Open Access Institutional Repository (Dublin City University)
Increasing the precision of junction shaped features
Cordes, K., & Östermann, J. (2015) · doi:10.1109/mva.2015.7153189
Affinity Propagation for Class Exemplar Mining
Xia, S., Song, R., & Hancock, E. R. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-14980-1_18
“A variety of feature detectors have been developed [8][14][9][15], and these include SIFT [9] and SURF ( Speeded Up Robust Features ) [8].”
MethodAn approach for pre-filtering images from big data sets
Kanungo, S., & Tiwari, S. (2015) · International Conference on Computing, Communication and Automation · doi:10.1109/ccaa.2015.7148541
“Now we are applying measurement on collected small particles of images, if the collected particles are lower than 30% as per skin color model then we are assuming that there is no human face, if it more than 50% then we are assuming that this is human face and update our database and if it is in between 30% to 50% the…”
Descritor de bordas e quantização espacial flexível aplicados a categorização de objetos
Lara, A. C. (2013) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.45.2013.tde-29042013-111855
Human tracking method based on multi-template color-texture mean-shift algorithm
Wen, L., Jia, S., & Wang, L. (2015) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2015.7237904
“Common descriptors have algorithms such as SIFT [6] [7], GLOH [8], SURF [9].”
MethodEfficient Subwindow Search for Object Localization
Blaschko, M. B., Hofmann, T., & Lampert, C. H. (2007) · MPG.PuRe (Max Planck Society)
Computer-aided data processing for GPR profiling applications
Kapustin, V. V., & Shirobokov, M. P. (2015) · International Workshop on Advanced Ground Penetrating Radar · doi:10.1109/iwagpr.2015.7292646
“Our research showed that the best data for the available test radargrams set was obtained while using SURF (Speeded Up Robust Features) method [5].”
MethodA Keygraph Classification Framework for Real-Time Object DetectionPreprint
Hashimoto, M., & Junior, R. M. C. (2009) · arXiv (Cornell University) · doi:10.48550/arxiv.0901.4953
Automated Surveillance Systems with Multi-Camera and Robotic Platforms
Chen, C. H. (2009)
Action recognition based on hybrid features
Han, H. W., Zhang, H., Gu, J., & Xie, F. (2012) · Cited by 1
Visual Search: A Large-Scale Perspective
Piramuthu, R., Bhardwaj, A., Di, W., & Sundaresan, N. (2013) · Handbook of statistics · doi:10.1016/b978-0-444-53859-8.00011-4 · Cited by 2
Geometric modeling of non-rigid 3D shapes : theory and application to object recognition.
Abdelrahman, M. (2013) · ThinkIR: The University of Louisville's Institutional Repository (University of Louisville) · doi:10.18297/etd/4 · Cited by 1
Prados, R., García, R., & Neumann, L. (2014) · SpringerBriefs in computer science · doi:10.1007/978-3-319-05558-9_2
Activation models for biologically grounded visual perception in robotics
Varadarajan, K. M., & Vincze, M. (2015) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2015.7283928
Object Class Recognition Using Surf Descriptors and Shape Skeletons
Sahzabi, V. A., & Omar, K. (2013) · Communications in computer and information science · doi:10.1007/978-3-642-40409-2_22
Object modeling for environment perception through human-robot interaction
Kim, S., Kim, D. H., & Park, S.-K. (2010) · doi:10.1109/iccas.2010.5669918
Topic Uncovering and Image Annotation via Scalable Probit Normal Correlated Topic Models
Yu, X. (2015) · RIT Scholar Works (Rochester Institute of Technology)
KAZE Algorithm Applied in Augmented Reality
Zhu, Q., & Lei, Z. (2015) · Advances in engineering research/Advances in Engineering Research · doi:10.2991/asei-15.2015.278
“KLT algorithm is a fast feature point tracking method, its accuracy can meet the real-time requirements of augmented reality even when in the scene that owns less iterations [4].”
MethodEvent video retrieval using global and local descriptors in visual domain
Carlos, J. R., Lux, M., Giró-i-Nieto, X., et al. (2015) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2015.7153622
“We used SIMPLE with the CEDD feature, the SURF key point detector [16], and k-means to create a visual vocabulary of 512 visual words.”
MethodÄrleryd, S. (2014) · Uppsala University Publications (Uppsala University)
A Novel Way of Tracking People in an Indoor Area
Narang, A., Joglekar, S. P., Dhanapal, K. B., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-29280-4_10
Visual Room-Awareness for Humanoid Robot Self-LocalizationPreprint
Bader, M., Prankl, J., & Vincze, M. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1304.5878
Testing Image Segmentation for Topological SLAM with Omnidirectional Images
Romero, A., & Cazorla, M. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-16761-4_24
Constructing Binary Descriptors with a Stochastic Hill Climbing SearchPreprint
Markuš, N., Pandzic, I. S., & Ahlberg, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1501.04782
Alansary, A. (2014) · ThinkIR: The University of Louisville's Institutional Repository (University of Louisville) · doi:10.18297/etd/24
“To match the target images with atlas images, they used the Affine-Scale Invariant Feature Transform (ASIFT) [112] and Speeded Up Robust Features (SURF) [113] registration techniques.”
Multi-Cue Based Place Learning for Mobile Robot Navigation
Siddiqui, J. R., & Lindley, C. A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-31368-4_7
Building Face Reconstruction from Sparse View of Monocular Camera
Le, M.-H., & Jo, K.-H. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-25944-9_73
Local Descriptors in Temporal Video Segmentation: A Performance Evaluation
Sio, K. I., & Martins, P. (2015) · Advances in computer science research · doi:10.2991/csic-15.2015.75
Computer vision component to environment scanning
Soares, P. E. P. (2012) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)
Using a RGB-D camera for 6DoF SLAM
Jose, M., Pastor, D., Gil, P., Méndez, S. T. P., & Cazorla, M. (2012) · Frontiers in artificial intelligence and applications · doi:10.3233/978-1-61499-139-7-143
VIAssist: Assistance for the Visually Impaired
Marathe, A. S., George, D., & Malve, R. (2015) · International Journal of Computer Applications · doi:10.5120/21720-4864
AFORAPRO: reconhecimento de objetos invariante sob transformações afins.
Lopez, G. A. P. (2011) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.3.2011.tde-31052011-155411 · Cited by 1
A Game-Theoretic Approach to the Enforcement of Global Consistency in Multi-view Feature Matching
Rodolà, E., Albarelli, A., & Torsello, A. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-14980-1_34
Visual Registration Method for a Low Cost Robot
Aldavert, D., Arnau Ramisa, A., Toledo, R., & de Mántaras, R. L. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04667-4_21
An Efficient Video Copy Detection Method Combining Vocabulary Tree and Inverted File
Li, X., Li, B., Hu, W., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-36669-7_75
Endoscopic laser treatment system for intrauterine fetal surgery
Yamanaka, N., Yamashita, H., Masamune, K., et al. (2011)
Ilbay, M. F. Ñ., & Córdova, L. G. T. (2013)
Low Complexity Image Recognition Algorithms for Handheld devices
Ayyalasomayajula, P. (2013) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.5075/epfl-thesis-5912
A Survey of Hardware Accelerated Methods for Intelligent Object Recognition on Camera
Karimaa, A. (2013) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-01857-7_51
PANORAMA IMAGING FOR MOBILE PHONES
Bordallo, M. (2016)
Nested Graph Words for Object RecognitionPreprint
Karaman, S., Benois‐Pineau, J., & Mégret, R. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1106.2729
Hassan, D., Madani, K., & Sabourin, C. (2015) · IEEE International Conference on Awareness Science and Technology (iCAST) · doi:10.1109/icawst.2015.7314047
“An as well scale-invariant as rotation-invariant efficient interest point detector and descriptor, based on a precomputed integral image, called SURF (Speed Up Robust Algorithm), has been proposed by [3].”
MethodA Kinect-Based Front-End for Graph-SLAM Using Plane Matching in Planar Indoor Environments
Yuan, Z., Rosa, S., Russo, L. O., & Bona, B. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-08338-4_29
Sistema de navegación monocular para robots móviles en ambientes interiores/exteriores
Cristóforis, P. D. (2013) · Repositorio Digital Institucional de la Universidad de Buenos Aires (Universidad de Buenos Aires) · Cited by 1
BMAX: A Bag of Features Based Method for Image Classification
Senna, P., Drummond, I. N., & Bastos, G. S. (2015) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2015.24
“In future works, we intend to test fastest feature extractors, like SURF [24] or ORB [25].”
MethodVision based indoor positioning in a retail environment
Uitto, J. (2011) · Työväentutkimus Vuosikirja
Towards Learning Free Naive Bayes Nearest Neighbor-Based Domain Adaptation
Saeedan, F., & Barbara Caputo, B. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23234-8_30
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.