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








Verification
Claims the paper makes
0 Valid · 2 Not valid · 12 Not checked · 30 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The number of interest points found is on average very similar for all detectors.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 4 × 4 sub-region division solution provided the best results.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SURF outperformed the other descriptors for almost all the comparisons.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The SURF descriptor outperforms the other descriptors in a systematic and significant way, with sometimes more than 10% improvement in recall for the same level of precision.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in the results section, the performance is comparable to the one using the discretised and cropped Gaussians.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
8 more claims
Create a free account to see all 44 claims and every source verdict.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This transition marked a new era, where we moved beyond the classic approaches and task-specific feature engineering of earlier days [Lowe 2004; Bay et al. 2006; Rosten and Drummond 2006] towards models that could be trained once over large amounts of data, and then adapted for a broad variety of tasks, such as image recognition, object detection, and image segmentation [Krizhevsky et al. 2012; Sz”
From On the Opportunities and Risks of Foundation Models (2021) · cites this paper as Bay et al. 2006
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · cited 14×
“This PCA-SIFT yields a 36-dimensional descriptor which is fast for matching, but proved to be less distinctive than SIFT in a second comparative study by Mikolajczyk et al. [8] and slower feature computation reduces the effect of fast matching.”
BackgroundMethodResultInfluentialMarr, D., & Hildreth, E. (1980) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1980.0020 · Cited by 6,510
PCA-SIFT: a more distinctive representation for local image descriptors
Ke, Y., & Sukthankar, R. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.183 · Cited by 3,932
Robust wide-baseline stereo from maximally stable extremal regions
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.02.006 · Cited by 3,686
Scalable Recognition with a Vocabulary Tree
Nister, D., & Stewenius, H. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.264 · Cited by 3,579
Scale & Affine Invariant Interest Point Detectors
Mikolajczyk, K., & Schmid, C. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000027790.02288.f2 · Cited by 3,436
Cited by
Items 11,901–12,000 of 14,752
Using 3D contours and their relations for cognitive vision and robotics
Başeski, E., Bodenhagen, L., Pugeault, N., et al. (2009) · International Symposium on Computer and Information Sciences · doi:10.1109/iscis.2009.5291815 · Cited by 1
Tartalo: the door knocker robot
Jauregi, E., Martínez‐Otzeta, J. M., Sierra, B., & Lazkano, E. (2007) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2007.4522320 · Cited by 2
“For on-line applications, each one of the three steps (detection of local extrema, keypoint description computation and keypoint matching) should be computed faster [3].”
MethodSTEREO VISION ALGORITHMS IN RECONFIGURABLE HARDWARE FOR ROBOTICS APPLICATIONS
Lidholm, J. (2011) · DiVA (Mälardalen University College) · Cited by 1
Mobile robot localization using appearance based place recognition
Mitsuhashi, M., Sakai, A., & KURODA, Y. (2010) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2010.5723383 · Cited by 1
“From this data set we computed the clustering of SURF descriptors that form our vocabulary, then compute the Chow Liu tree for the vocabulary.”
BackgroundMethodInfluentialSensing Highly Non-Rigid Objects with RGBD Sensors for Robotic Systems
Willimon, R. B. (2013) · TigerPrints (Clemson University) · Cited by 1
Song, R., & Szymanski, J. E. (2007) · IEEE International Conference on Automation and Logistics (ICAL) · doi:10.1109/ical.2007.4338954 · Cited by 1
Scale-Euclidean invariant object retrieval
Balmashnova, E. E. (2007) · TU/e Research Portal · doi:10.6100/ir629338 · Cited by 1
A New Method of Depth Measurement with Binocular Vision Based on SURF
Wang, C., & Ying-he, S. (2009) · doi:10.1109/wcse.2009.733 · Cited by 1
Indexing heterogeneous features with superimages
Luo, Q., Zhang, S. S., Huang, T., Gao, W., & Tian, Q. (2014) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-014-0064-x · Cited by 1
“Some other SIFTlike descriptors include SURF [2], PCA-SIFT [18], and GLOH [24], etc.”
MethodA-ne-invariant spatial vocabularies
Bronstein, A. M., & Bronstein, M. M. (2009) · Cited by 1
The Link Between Image Segmentation and Image Recognition
Sharma, K. (2000) · doi:10.15760/etd.199 · Cited by 1
Interactive service recommendation based on ad concept hierarchy
Wang, B., Wang, J., Duan, L., et al. (2010) · International Conference on Internet Multimedia Computing and Service · doi:10.1145/1937728.1937749 · Cited by 1
“Some global features (Color histogram and Grid Gabor texture) and local features (SURF [9], Shape-Context [10] and Geometric-Blur [11]) are used.”
MethodAn Online Image Registration Method Based on Hough Transform
Xu, H., & Sun, Q. (2009) · Chinese Conference on Pattern Recognition · doi:10.1109/ccpr.2009.5344091 · Cited by 1
“∑ ∈ = R c r q p q p c r a n ) , ( , 1 (3) 上式中归一化的矩是由图像中的位置决定的。在多 数情况下,使特征不随图像中区域的位置变化而变化是 很有用的。这可以通过计算相对于区域重心的矩来实 现。这些中心矩是在 ) 2 ( ≥ + q p 时由下式计算得到:”
Jain, M., Vempati, S., Pulla, C., & Jawahar, C. V. (2009) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1646396.1646428 · Cited by 1
Monocular object pose computation with the foveal-peripheral camera of the humanoid robot Armar-III
Alenyà, G., & Torras, C. (2008) · Frontiers in artificial intelligence and applications · doi:10.3233/978-1-58603-925-7-355 · Cited by 1
3D ordinal constraint in spatial configuration for robust scene recognition
Teo, C. L., Li, S., Cheong, L., et al. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4761022 · Cited by 1
Detection and filtering of landmark occlusions using Terrain Spatiograms
Lyons, D. M. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509231 · Cited by 1
“Cummins & Newman [3] describe an appearance based-approach to localization and mapping using the bag-of-words approach popular in image retrieval [12] and employing SURF [1] features.”
A Comparative Study of Robust Feature Detectors for 2D Electrophoresis Gel Image Registration.
Möller, B., Greß, O., & Posch, S. (2008) · German Conference on Bioinformatics · Cited by 1
Calibration and Component Placement in Structured Light Systems for 3D Reconstruction Tasks
Thesis, A. (2009) · Cited by 1
THREE NEW METHODS FOR COLOR AND TEXTURE BASED IMAGE MATCHING IN CONTENT-BASED IMAGE RETRIEVAL
Scotia, N. (2010) · Cited by 1
KSU Willie in the AAAI 2007 Semantic Vision Challenge
Gustafson, D. A., Marlen, M., Chavez, A., et al. (2007) · Cited by 1
COMPUTER VISION AND IMAGE PROCESSING LARGE TECHNIQUES FOR MOBILE APPLICATIONS
Liu, X., & Doermann, D. (2008) · Cited by 1
Utility-based map reduction for ground and flight vehicle navigation
Steiner, T. J. (2015) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 1
Extending Surf to the Color Domain
Gossow, D., Decker, P., & Paulus, D. W. R. (2010) · Conference on Colour in Graphics Imaging and Vision · doi:10.2352/cgiv.2010.5.1.art00035 · Cited by 1
“Both are defined on the scale space representation Lk,k ∈ [1,2,3] of the image Ik:”
BackgroundMethodInfluentialText extraction from natural scene: Methodology and application
Yi, C. (2014) · CUNY Academic Works (City University of New York) · Cited by 2
Selecting feature detectors for accurate visual odometry
Cumani, A., & Guiducci, A. (2009) · Cited by 1
Sparse Grouping and Invariant Representations for Estimation and Recognition
Yu, G. (2009) · OpenGrey (Institut de l'Information Scientifique et Technique) · Cited by 1
Human and Animal Behavior Understanding
Chen, W. (2014) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.192 · Cited by 1
Design and application of an automated system for camera photogrammetric calibration
de Villiers, J. (2015) · Open University of Cape Town (University of Cape Town) · Cited by 1
Natural hand interaction for augmented reality.
Piumsomboon, T. (2015) · UC Research Repository (University of Canterbury) · doi:10.26021/1571 · Cited by 3
THREE-DIMENSIONAL RECONSTRUCTION OF PLANETARY SURFACES FROM STEREO SATELLITE IMAGES
Re, C. (2014) · Padua Research Archive (University of Padova) · Cited by 1
RISAS: A Novel Rotation, Illumination, Scale Invariant Appearance and Shape FeaturePreprint
Wu, K., Li, X., Ranasinghe, R., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.04134 · Cited by 1
Human Action Recognition in Still Images
Lai, B. (2013) · doi:10.33915/etd.670 · Cited by 1
An Enhancement and Stitching System for X-Ray Images
Wang, W., & Gwun, O. (2011) · doi:10.2316/p.2011.723-052 · Cited by 1
Farag, M. (2013) · doi:10.18297/etd/2278 · Cited by 1
Pothitos, M. (2015) · Defense Technical Information Center (DTIC) · doi:10.21236/ad1009200 · Cited by 1
Mosaickingalgorithmus zur schnellen Panoramabilderstellung in der Fluoreszenzendoskopie
Behrens, A., Bommes, M., Stehlé, T., et al. (2010) · RWTH Publications (RWTH Aachen) · Cited by 1
Stereo Visual Odometry With Windowed Bundle Adjustment
Angeles, L. (2015) · Cited by 1
A new approach to object recognition
Sergeev, N. (2012) · OPen Access Repositorium der Universität Ulm (OPARU) (Ulm University) · doi:10.18725/oparu-2424 · Cited by 1
Davies, E. R. (2005) · Elsevier eBooks · doi:10.1016/b978-0-12-206093-9.50043-5 · Cited by 1
Multimodal data collection in the AMASS++project
Martens, S., Becker, J. H., Tuytelaars, T., et al. (2008) · Cited by 1
Self-citationArchitectural and runtime enhancements for dynamically controlled multi-level concurrency on GPUs
Ukidave, Y. (2015) · doi:10.17760/d20204341 · Cited by 1
Data Processing in Current 3D Robotic Perception Systems
Ye, C. (2015) · doi:10.1002/9781119036821.ch23 · Cited by 1
“This may be achieved through the following efforts: (1) investigate other feature descriptors and adopt one with less computational cost such as the SURF (Speeded Up Robust Features) [25] for the VR-odometry; and (2) use spatial invariants between the detected features’ 3D points (e.”
MethodAppearance modeling for persistent object tracking in wide-area and full motion video
Pelapur, R. (2016) · MOspace Institutional Repository (University of Missouri) · doi:10.32469/10355/57252 · Cited by 1
Tozadore, D. C. (2016) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.55.2016.tde-04102016-110603 · Cited by 2
Video‐Based Parking Management
Sidla, O., & Lipetski, Y. (2017) · Wiley eBooks · doi:10.1002/9781118971666.ch8 · Cited by 1
Multi-modality fusion : registering photographs, videos, and LIDAR range scans
Morago, B. (2016) · doi:10.32469/10355/56548 · Cited by 1
“Several groups have expanded on the SIFT descriptor to develop feature matching methods that are faster and more robust to various transformations [47] [48] [49].”
Enhanced Visual Navigation for Mobile Robots
West, B. P. (2014) · Cited by 1
Adaptive Cost Function for Pointcloud RegistrationPreprint
Ekekrantz, J., Folkesson, J., & Jensfelt, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.07910 · Cited by 1
“A large body of work has been put into finding distinctive descriptors for visual information, such as SIFT [17], SURF[18], BRIEF [19], ORB [20] and GRIEF [21].”
Performance Improvements for Lidar-based Visual Odometry
Dong, H. (2013) · TSpace (University of Toronto) · Cited by 2
Detecção e classificação de objetos em imagens para rastreamento de veículos
Montanari, R. (2016) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.55.2016.tde-08012016-113715 · Cited by 6
Algoritmos de casamento de imagens com filtragem adaptativa de outliers
Ramos, J. D. S. (2017) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.55.2017.tde-02022017-110428 · Cited by 1
3D pose estimation in complex environments
Peñate-Sánchez, A. (2017) · UPCommons institutional repository (Universitat Politècnica de Catalunya) · doi:10.5821/dissertation-2117-108233 · Cited by 1
Robotic 3D Visual Mapping for Augmented Situational Awareness in Unstructured Environments
Miró, J. V., & Dissanayake, G. (2008) · Cited by 1
Prastiwi, P. A. D., Harto, A. B., Wikantika, K., & Irawan, D. E. (2017) · INA-Rxiv (OSF Preprints) · doi:10.31227/osf.io/bsejq · Cited by 1
Affine Differential Invariants for Invariant Feature Point DetectionPreprint
Tuznik, S. L., Olver, P. J., & Tannenbaum, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.01669 · Cited by 1
REST: Real-to-Synthetic Transform for Illumination Invariant Camera LocalizationPreprint
Shoman, S., Mashita, T., Plopski, A., Ratsamee, P., Uranishi, Y., & Takemura, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.09448 · Cited by 1
Extração de features 3D para o reconhecimento de objetos em nuvem de pontos
Sales, D. O. (2018) · doi:10.11606/t.55.2018.tde-07022018-091205 · Cited by 1
Excavate Condition-invariant Space by Intrinsic EncoderPreprint
Xu, J. B., Wang, C., Shi, C., & Xiao, B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.11306 · Cited by 1
“Traditionally hand-crafted features such as SIFT [26] and SURF [3] are used extensively in many computer vision tasks.”
MethodA Comparative Study of Feature Detection Methods for AUV Localization
Kim, A. Y. (2018) · doi:10.15368/theses.2018.49 · Cited by 1
Multimodal Indexable Encryption for Mobile Cloud-based Applications (Extended Version).Preprint
Ferreira, B., Leitao, J. C. A., & Domingos, H. (2017) · IACR Cryptology ePrint Archive · Cited by 1
Explicit Pose Deformation Learning for Tracking Human Poses.Preprint
Sun, X. N., Li, C., & Lin, S. C.-F. (2018) · arXiv (Cornell University) · Cited by 1
Data driven methods for characterizing individual differences in brain MRI
Kumar, K. (2018) · Espace ÉTS (ETS) · doi:10.13140/rg.2.2.12193.71525 · Cited by 1
SIVO: Semantically Informed Visual Odometry and Mapping
Ganti, P. (2018) · UWSpace (University of Waterloo) · Cited by 2
Teaching robots to imitate a human with no on-teacher sensors. What are the key challenges?Preprint
Škoviera, R., Štěpánová, K., Tesař, M., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.08335 · Cited by 1
“When objects are richly textured, methods based on matching local invariant features such as SIFT [17] or SURF [18] produce reasonable results.”
BackgroundMethodInfluentialA Hybrid SLAM and Object Recognition System for Pepper RobotPreprint
Ardón, P., Kushibar, K., & Peng, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.00675 · Cited by 3
Scalable Facial Image Compression with Deep Feature ReconstructionPreprint
Wang, S., Wang, S., Zhang, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.05921 · Cited by 1
Ling, S., Li, J., Che, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.12107 · Cited by 1
Using Range Information to Reduce Local Descriptor Computations
Stefánsson, S. F. (2011) · Cited by 1
Low-latency Visual SLAM with Appearance-Enhanced Local Map BuildingPreprint
Zhao, Y., Ye, W., & Vela, P. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.07797 · Cited by 1
VICSOM: VIsual Clues from SOcial Media for psychological assessmentPreprint
Dehshibi, M. M., Pons, G., Baiani, B., & Masip, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.06203 · Cited by 3
An Automated CNN Recommendation System for Image Classification TasksPreprint
Wang, S., Sun, L., Fan, W., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.08484 · Cited by 1
From Bits to Images: Inversion of Local Binary DescriptorsPreprint
d'Angelo, E., Jacques, L., Alahi, A., et al. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1211.1265 · Cited by 1
The CUDA LATCH Binary Descriptor: Because Sometimes Faster Means BetterPreprint
Parker, C., Daiter, M., Omar, K., Levi, G., & Hassner, T. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.03986 · Cited by 2
Temporally Robust Global Motion Compensation by Keypoint-based CongealingPreprint
Safdarnejad, S. M., Atoum, Y., & Liu, X. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.03968 · Cited by 1
DSR: Direct Self-rectification for Uncalibrated Dual-lens CamerasPreprint
Xiao, R., Sun, W., Pang, J., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.09763 · Cited by 1
Fine-Grained Product Class Recognition for Assisted ShoppingPreprint
George, M., Mircic, D., Sörös, G., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1510.04074 · Cited by 1
Dynamic Concept Composition for Zero-Example Event DetectionPreprint
Chang, X., Yang, Y. P., Long, G., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1601.03679 · Cited by 1
A novel shape matching descriptor for real-time hand gesture recognitionPreprint
Lazarou, M., Li, B., & Stathaki, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.03923 · Cited by 1
Mukhopadhyay, A., Qian, Z. Y., Bhandarkar, S. M., et al. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1302.3155 · Cited by 1
Weakly Supervised Labeling of Dominant Image Regions in Indoor Sequences
Murillo, A. C., Košecká, J., Mičušík, B., et al. (2008) · Cited by 1
Resonansi: Suatu Perspektif Dalam Kajian Gerakan Politik-Keagamaan Ikhwanul Muslimin Di IndonesiaPreprint
Khoirnafiya, S. (2017) · INA-Rxiv (OSF Preprints) · doi:10.31227/osf.io/bh6r8 · Cited by 2
Método automático para detecção de nematóides em lavoura cafeeira usando imagens aéreas.
de Oliveira, A. (2019) · doi:10.14393/ufu.di.2019.2314 · Cited by 2
Obstacle and Change Detection Using Monocular Vision
Bluteau, R. (2019) · Scholarship at UWindsor (University of Windsor) · Cited by 1
Dittimi, T. V. (2019) · Spectrum Research Repository (Concordia University) · Cited by 2
Attributed Relational SIFT-based Regions Graph (ARSRG): concepts and applicationsPreprint
Manzo, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.09972 · Cited by 1
“Table 1: Quantitative comparison using MRR measure among SIFT(Lowe, 2004), SURF(Bay et al., 2006), ORB(Rublee et al., 2011), FREAK(Alahi et al., 2012), BRIEF(Calonder et al., 2010) and ARSRG matching on dataset in(Haladov´a & ˇSikudov´a, 2010).”
MethodInfluentialCalzadillas, E. A. (2019) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2019-13841 · Cited by 1
Plane Pair Matching for Efficient 3D View RegistrationPreprint
Kaiser, A., Zepeda, J. A. Y., & Boubekeur, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.07058 · Cited by 1
Deep-Geometric 6 DoF Localization from a Single Image in Topo-metric MapsPreprint
Roussel, T., Chakravarty, P., Pandey, G., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.01210 · Cited by 1
Self-citationIntelligent AutofocusPreprint
Wang, C., Huang, Q., Cheng, M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.12389 · Cited by 1
DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape ReconstructionPreprint
Jin, J., Patil, A. G., Xiong, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.09204 · Cited by 1
Development of schlieren-image based flow diagnostics and analysis for supersonic jet flows
Lim, D. (2020) · doi:10.32657/10356/136858 · Cited by 1
Learning Local Features with Context Aggregation for Visual LocalizationPreprint
Hong, S., Li, K., Zhang, Y., Fu, Z., Liu, M., & Guo, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.12880 · Cited by 2
Map3D: Registration Based Multi-Object Tracking on 3D Serial Whole Slide ImagesPreprint
Deng, R., Yang, H., Jha, A., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.06038 · Cited by 1
“SURF [6] was employed in this study to improve initial alignment.”
MethodInfluentialDecorrelated Clustering with Data Selection BiasPreprint
Wang, X., Fan, S., Kuang, K., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.15874 · Cited by 1
Accelerated Object Tracking with Local Binary Features
Minnehan, B. (2014) · RIT Scholar Works (Rochester Institute of Technology) · Cited by 1
Vats, V., Goel, P., Agarwal, A., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.01179 · Cited by 1
“The Speeded Up Robust Features (SURF) algorithm determines the points where the direction of the boundary changes abruptly [9].”
Real-time Collaboration Between Mixed Reality Users in Geo-referenced Virtual EnvironmentPreprint
Singh, S. K., Ma, Z., Giunchi, D., & Steed, A. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.01023 · Cited by 1
“Depth information is calculated by using different images of the same scene with distinct feature points [2,21].”
MethodA Scale and Rotational Invariant Key-point Detector based on Sparse CodingPreprint
Hong-Phuoc, T., & Guan, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.06264 · Cited by 1
Metadata
- Authors
- Bay, H., Tuytelaars, T., & Van Gool, L.
- Affiliations
- ETH Zurich (CH)
- KU Leuven (BE)
- ORCID
- Tuytelaars, Tinne
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2006
- Pages
- 404-417
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1677409904
- Semantic Scholar
- 9ad3179098eb9ac7f0c81bf89b6bdcde91752880
- Cited by
- 14,955
- References
- 39
- Citations by year
- 2026: 210 · 2025: 519 · 2024: 727 · 2023: 757 · 2022: 878 · 2021: 975 · 2020: 978 · 2019: 1036 · 2018: 968 · 2017: 976 · 2016: 930 · 2015: 1079 · 2014: 1006 · 2013: 982 · 2012: 884
- FWCI
- 196.80
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Lecture notes in computer science (publishedVersion)
- Lirias (KU Leuven) (submittedVersion, other-oa)
- Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Object Detection Techniques
- Keywords
- SURF, keypoint detection, feature descriptors, scale invariance, rotation invariance, integral image, Hessian matrix, feature matching, object recognition, repeatability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.