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 13,101–13,200 of 14,752
Context-Aware Model Applied to Hog Descriptor for People Detection
Ramirez-Martinez, M., Brunet, P., Senouci, S., et al. (2018) · HAL (Le Centre pour la Communication Scientifique Directe)
Substantial improvement of stereo visual odometry by multi-path feature tracking
Chien, H.-J., & Klette, R. (2017) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2017.8402460
Salient point region Local Binary Patterns descriptor for target tracking
Oguz, O., Toker, K. G., Dobrucalı, O., et al. (2018) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2018.8404281
“[5] Bay, Herbert, Tinne Tuytelaars, and Luc Van Gool.”
BackgroundVehicles Recognition Based on Point Cloud Representation
Kamencay, P., Hudec, R., Orjesek, R., et al. (2018) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-319-93710-6_9
Markerless Planar Tracking in Augmented Reality Using Geometric Structure
Fan, C., Zhao, Y., & Feng, L. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14364-4_33
Chihaoui, T., Kachouri, R., Jlassi, H., et al. (2018) · Communication and Signal Processing · doi:10.1515/9783110470383-008
Multi-criteria-based fusion for clustering texts and images case study on Flickr
Khatir, N., & Bahloul, S. N. (2018) · Kybernetes · doi:10.1108/k-01-2018-0030
Content-based 3D shape retrieval using deep learning approach
Benjelloun, M., Dadi, E. W., Daoudi, E. M., et al. (2018) · doi:10.1145/3230905.3230957
“Currently, scientific communities distinguish between two types of feature extraction methods: classical methods [9, 10] such as SIFT[8], SURF[2], etc... and methods based on deep learning[12].”
MethodLearning-based Natural Geometric Matching with Homography PriorPreprint
Xu, Y., Liao, T., & Chen, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.05119
“For feature characterization, many hand-crafted image descriptors 6,7 were proposed in the last decades, which aimed to reliably localize a set of stable local regions under various imaging conditions.”
BackgroundWeak-structure-aware visual object tracking with bottom-up and top-down context exploration
Liu, N., Liu, C., Wu, H., Zhu, H., & Zhan, J. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.08.005
Candela, E. M. (2018) · RUA, Repositorio Institucional de la Universidad de Alicante (Universidad de Alicante)
Performance Analysis and Robustification of Single-query 6-DoF Camera Pose EstimationPreprint
Fu, J., Pertuz, S. D., Matas, J., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.05848
Large-scale learning of discriminative image representations
Simonyan, K. (2013) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.5287/ora-aeakqmpba · Cited by 2
Jeon, S.-Y. (2018) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2018.16.8.65
Aguirre, D. I. G. (2018) · Cognitive systems monographs · doi:10.1007/978-3-319-97841-3_3
An End-to-End Image Retrieval System Based on Gravitational Field Deep Learning
Zheng, Q., Yang, M., Zhang, Q., et al. (2017) · International Conference on Computer Systems, Electronics and Control (ICCSEC) · doi:10.1109/iccsec.2017.8447006
“The traditional content-based image retrieval system mainly uses low-level visual features, such as color, shape, texture, etc., or through the matching of feature points (SIFT [1], SURF [2] and so on) to complete the image retrieval.”
BackgroundParallel Processing of Computed Tomography Images
Połap, D., & Woźniak, M. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-99996-8_9
Viewing Experience Model of First-Person Videos
Ma, B., & Reibman, A. R. (2018) · Journal of Imaging · doi:10.3390/jimaging4090106 · Cited by 1
Compactification of Affine Transformation Filter Using Tensor Decomposition
Kawai, K., Hasegawa, T., Yamauchi, Y., et al. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451195
Intelligent Land Cover Detection in Multi-sensor Satellite Images
Aroma, R. J., & Raimond, K. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-00612-9_11
Benchmarking Convolutional Neural Networks for Object Segmentation and Pose Estimation
Le, T., Hamilton, L., & Torralba, A. B. (2017) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2017.8457942 · Cited by 1
IMPLEMENTING SIFT AND BI-TRIANGULAR PLANE TRANSFORMATION FOR INTEGRATING DIGITAL TERRAIN MODELS
Massad, I., Doytsher, Y., & Dalyot, S. (2018) · 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-4-411-2018
Blur-Countering Keypoint Detection via Eigenvalue AsymmetryPreprint
Zhang, C., Lu, X., & Akashi, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.01456
Implementation of Video Stabilization Algorithm for Surveillance System
Kawade, H., & Deshpande, A. M. (2017) · International Conference on Computing Communication Control and automation · doi:10.1109/iccubea.2017.8463700
Coding Trajectory: Enable Video Coding for Video Denoising
Ren, Z., Dai, P., Liu, S., et al. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451492
“However, the alignment requires detecting image features [7] and manipulate”
BackgroundJoseph, S., Hipiny, I., & Ujir, H. (2018) · Unimas Institutional Repository (Universiti Malaysia Sarawak) · doi:10.48550/arxiv.1810.01562
Video Magnification for Structural Analysis Testing
Whitmore, J. C. (2018) · doi:10.15368/theses.2018.70
Fusing Omnidirectional Visual Data for Probability Matching Prediction
Valiente, D., Payá, L., Jiménez, L. M., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01449-0_48
NETWORK ADJUSTMENT OF AUTOMATIC RELATIVE ORIENTATION FROM IMAGE SEQUENCES
Lin, C. C., Tseng, Y. H., Lin, K.-Y., & Chiang, K. (2018) · 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-1-269-2018
“SURF (Speeded up robust features) (Bay et al., 2006) and SIFT (Scale-invariant feature translation) (Lowe, 2004) are two most popular feature-based methods.”
MethodSORB: improve ORB feature matching by semantic segmentation
Hu, W., Fei, L., Chen, H., & Wang, K. (2018) · Emerging Imaging and Sensing Technologies for Security and Defence · doi:10.1117/12.2325423 · Cited by 1
Rotation Invariant on Harris Interest Points for Exposing Image Region Duplication Forgery
Badi, H. H., Sabbri, B., & Ajeel, F. (2018) · InTech eBooks · doi:10.5772/intechopen.76332
Augmented Reality Travel App Based on Image Retrieval Algorithm
Yafang, Z., Tie, Y., & Qi, L. (2018) · International Conference on Computing and Pattern Recognition (ICCPR) · doi:10.1145/3232829.3232834
“The main feature extraction algorithm are Scale-invariant feature transform (SIFT), Speeded-Up Robust Features (SURF), Features From Accelerated Segment Test (FAST) [4].”
MethodInfluentialBag of Visual Words Based on Co-HOG Features for Word Spotting in Handwritten Documents
Thontadari, C., & Prabhakar, C. J. (2018) · Advances in computer and electrical engineering book series · doi:10.4018/978-1-5225-5628-2.ch007
Real Time Monocular Visual Odometry Using Hybrid Features and Distance Ratio for Scale Estimation
Nugroho, D. S., Ardiyanto, I., & Cahyadi, A. I. (2018) · International Journal on Advanced Science Engineering and Information Technology · doi:10.18517/ijaseit.8.5.3247
“These algorithms are employed due to their fast computation and stability to detect the same feature across viewpoint change [14] [15].”
MethodImage Registration Based on Patch Matching Using a Novel Convolutional Descriptor
Xie, W., Gao, H., & Chen, Z. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03335-4_25
Efficient Expression Recognition Based on Shape-indexed Features
Wang, Y., & Guoying, Z. (2018) · IEEE International Conference on Smart Cloud (SmartCloud) · doi:10.1109/smartcloud.2018.00018
Three-dimensional Imaging, Visualization and Recognition in Low Light Environments
Markman, A. S. (2018) · OpenCommons - UConn (University of Connecticut)
Fast Robust Image Feature Matching Algorithm Improvement and Optimization
Chen, P., Li, Y., & Gong, G. (2018) · International Conference on Vision, Image and Signal Processing (ICVISP) · doi:10.1145/3271553.3271585
“David G. Lowe proposed SIFT algorithm[7], Herbert Bay et al. proposed SURF algorithm[2], Stefan Leutenegger et al. proposed BRISK algorithm [9], and Ethan Rublee et al. proposed ORB algorithm [3], and Alexandre Alahi et al. proposed FREAK algorithm [8].”
MethodJahangard, S. (2018) · International Journal of Engineering & Technology · doi:10.14419/ijet.v7i4.10575
“…study, a number of image descriptors including Scale Invariant Feature Transform )SIFT( [13], RootSIFT [14], Speed Up Robust Features (SURF) [15], Geometric Blur [16], Scene Gist [17] , Color Moments [18], Color Correlogram [19], Gabor filter [20, 21] , Biologically inspired hierarchical…”
BackgroundMethodEvaluation of Neural Network-Based Sensing and Perception in Experimental Vehicles
Horváth, E., Pozna, C. R., & Ballagi, Á. (2018) · IEEE International Conference on Intelligent Engineering Systems (INES) · doi:10.1109/ines.2018.8523952
Infrared and visible light image registration algorithm based on clustering and mutual information
Chen, Z., Du, Z., Cheng, F., et al. (2018) · doi:10.1117/12.2500763
Eremeev, V. V., Kochergin, A., Kuznetcov, A., et al. (2018) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2018.8517368
“It has been shown that using the SURF algorithm, false juxtapositions are random while veritable displacements are systematic.”
MethodInfluentialEingesetzte wissenschaftliche Methoden
Kümmert, F., Albers, A., Bremer, C., Büttner, S., Dellnitz, M., Dumitrescu, R., Gräler, M., Just, V., Mucha, H., Peitz, S., et al. (2018) · Intelligente Technische Systeme, Lösungen aus dem Spitzencluster it’s OWL · doi:10.1007/978-3-662-56390-8_3
Guide-Wire Detecting Based on Speeded up Robust Features for Percutaneous Coronary Intervention
Prasong, P., Xie, X., & Hou, Z. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04212-7_35
Pan-Sharpening with Hessian Nuclear Norm Induced Spatial Consistency
Liu, P., Xiao, L., & Tang, S. (2018) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2018.8517670
“Moreover, the famous Hessian detector [19] and fast Hessian detector [20] for interest point detection can mainly response locating on corners, blobs, and in strongly textured image areas.”
BackgroundEffect of Illumination and Blur Change on Markerless Image Registration Methods
Gupta, N., & Rohil, M. K. (2018) · International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct.2018.8529385
“[2], PCA-SIFT, proposed by Ke and Sukthankar [3], Affine-SIFT (ASIFT), proposed by Yu and Morel [4] etc.”
BackgroundMethodAgarwal, N., Suthar, S., Jain, H., Godara, P., & Vaidya, B. (2018) · IEEE International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct.2018.8529577
“The linear classifier can be given as Where W is the normal to the hyperplane, b is the bias and W is the weight vector The SVM models are first trained using different features like HOG, SURF, SIFT.”
BackgroundInfluentialEstudio de métodos de construcción de ensembles de clasificadores y aplicaciones
Díez-Pastor, J.-F. (2015) · Repositorio Institucional de la Universidad de Burgos (University of Burgos) · doi:10.36443/10259/5016 · Cited by 1
Taffar, M., & Miguet, S. (2017) · Advances in multimedia and interactive technologies book series · doi:10.4018/978-1-5225-2848-7.ch009
Celik, T., Hughes, B., & Burghardt, T. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-13469-3_113
Real-Time Texture-less Object Recognition on Mobile Devices
Chan, J., Lee, J. A., & Kemao, Q. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545158
“In recent years however, as mobile processing power improves, mainstream recognition algorithms such as ORB [6] and SURF [7] started to make its way to these devices, enhancing the overall recognition performance in mobile applications.”
BackgroundLocal Feature Reliability Measure Consistent with Match Conditions for Mobile Visual Search
Matsuzaki, K., Tasaka, K., & Yanagihara, H. (2018) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2018edp7107
Kawanishi, Y., Murase, H., Xu, J., et al. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545208
“Generally, the specific object retrieval is achieved by following steps; keypoints are detected from an query image, features are calculated around the keypoints [1], [2], [3], [4], [5], image similarities are calculated between the query and each image in the dataset by using the keypoints and features, and finally,…”
MethodBednarek, M., & Walas, K. (2018) · Signal Processing: Algorithms, Architectures, Arrangements, and Applications · doi:10.23919/spa.2018.8563402
“Except this one, there are plenty of alternatives such as SURF [2] which is supposed to be a speeded-up version of SIFT.”
BackgroundInfluentialLogo Matching and Recognition Based on Context
Das, T. K. (2018) · Advances in multimedia and interactive technologies book series · doi:10.4018/978-1-5225-5775-3.ch009
Timescape Image Panorama Registration Techniques
Ali, H. K. (2017) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2017-11799
“The SURF local feature detector and descriptor are partly inspired by a SIFT descriptor which is several times faster than SIFT and more robust against different image transformations than SIFT [9].”
BackgroundMethodInfluentialObject Localization and Activities Identification Using Attribute Details in SMART Meeting Rooms
Andriana, D., Prihatmanto, A. S., Hidayat, E., et al. (2018) · doi:10.5121/csit.2018.81606
“In visual object detection, object features has also been investigated through SIFT, SURF, BRISK, BRIEF, FREAK, AKAZE, and ORB [20][21][22][23][24] which are based on corner detector as the best features.”
MethodEye on the Sky: An Upward-Looking Monocular Teach-and-Repeat System for Indoor Environments
Zhang, N., Warren, M., & Barfoot, T. D. (2018) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2018.00056
“1) Monocular Initialization: To initialize the VO, Speeded-Up Robust Features (SURF) keypoints and descriptors [3] are extracted from the first image and then matched against those from subsequent frames.”
MethodPeer-to-Peer Network-Based Image Retrieval
Su, C.-R., & Chen, J. (2012) · IGI Global eBooks · doi:10.4018/978-1-4666-2660-7.ch013
A Novel Image Coding Scheme based on License Plate Recognition
Wang, J., & Liu, D. (2018) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac.2018.8577748
“Another recent work develops SIFT [4] and SURF [5] features, which has also been found useful in many visual tasks.”
MethodGraphical models for inference and learning in computer vision
McAuley, J. (2011) · ANU Open Research (Australian National University) · doi:10.25911/5d611c34235c0
TROVE Feature Detection for Online Pose Recovery by Binocular CamerasPreprint
Liu, Y., & Chen, M. Z. Q. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.10967
Interest Point Detection based on Adaptive Ternary CodingPreprint
Miao, Z., Yap, K., & Jiang, X. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.00031
Simulation of greyscale image colouring using blob detection
Azimi, A. I. F. (2017)
Mori, Y., & Takagi, N. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00071
“SIFT[7], SURF[8], ORB[9], and AKAZE[10] are representative of the local features.”
Non-Rigid Point Set Registration via Gaussians Mixture Model with Local Constraints
Yang, K., Liu, X., Chen, Y., et al. (2018) · doi:10.1145/3285996.3286011
“[12] H. Bay and T. Tuytelaars, "SURF: Speeded up robust features," in Anonymous Berlin, Heidelberg: Springer Berlin Heidelberg, 2006, pp. 404-417”
MethodInfluentialAn in-depth evaluation framework for spatio-temporal features
Stöttinger, J., Bhatti, N., & Hanbury, A. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-018-7032-z
“In case rotational invariance is required in the spatial domain, the dominant orientation is estimated similar to [1].”
BackgroundEnhancing the Effectiveness of Local Descriptor Based Image Matching
Hossain, M. T., Teng, S. W., Zhang, D., et al. (2018) · Digital Image Computing: Techniques and Applications · doi:10.1109/dicta.2018.8615800
A Visual Servoing with Collision Avoidance Mechanism for Redundant Manipulators
Hwang, K., Cho, Y.-Y., & Jiang, W. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00315
“[2] E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, “ORB: an efficient alternative to SIFT or SURF,” in IEEE International Conference on Computer Vision (ICCV), vol. 13, 2011.”
MethodInfluentialYuliwulandari, R., & Prayuni, K. (2017) · INA-Rxiv (OSF Preprints) · doi:10.31227/osf.io/b32gx
Localization: A Missing Link in the Pipeline of Object Matching and RegistrationPreprint
Mishra, D., Ranjan, R., Chaudhury, S., Sarkar, M., & Soin, A. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.00223
“Traditional methods in this domain have focused on development of sophisticated descriptors and establish correspondence between key-points [10, 11, 12, 13].”
MethodAdvances in Automated Volume Analysis Based on Large Scale Pointclouds
Stojcsics, D., Domozi, Z., & Molnár, A. (2018) · International Journal of Simulation Systems Science & Technology · doi:10.5013/ijssst.a.19.02.09
An incremental loop closure detection method based on depth information for indoor dynamic scenes
Deng, Z., Wu, Q., Jiao, J., Sun, Y., Mo, Y., & Zhang, C. (2018) · Joint International Information Technology, Mechanical and Electronic Engineering Conference (JIMEC) · doi:10.2991/jimec-18.2018.59
“There are two different approaches to depicting the scene[8], [9], [10], [11]: The first is to use the global descriptors to present the whole images such as the Gist[8], [9].”
MethodA PSEUDO-SPLICING ALGORITHM FOR PARTIAL FINGERPRINT RECOGNITION BASED ON SIFT
Zhu, Z. D., Li, A., Jiang, R., et al. (2018) · doi:10.5121/csit.2018.81702
“Matching algorithms based on local features include SIFT (Scale Invariant Feature Transform)[25] and SURF (Speeded Up Robust Features)[26].”
MethodDouble Peak CAMS Algorithm Based Object Searching for a Human Partner System
Kao, M.-C., Li, T. S., & Kuo, P. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00316
Guidance Algorithm for Unmanned Aerial Vehicles on a Basis System of Technical Viewing
Пікенін, О. О., & Marynoshenko, O. (2019) · Advances in computer and electrical engineering book series · doi:10.4018/978-1-5225-7588-7.ch008
Techniques for assisting users in making security decisions
Duman, S. (2017) · Digital Repository Service (Northeastern University) · doi:10.17760/d20253675
The Multi-scale Dominant Binary Pattern Learning for Image Recognition
Yi, L., Zhang, D., Xu, H., et al. (2018) · World Congress on Intelligent Control and Automation · doi:10.1109/wcica.2018.8630450
“Traditional local feature extraction techniques are usually based on local region description,such as SIFT[2] and SURF[3] describe 4×4 lattice neighborhood of the key points, GLOH[4] divides the neighborhood into 16 sectors, DAISY[5] uses a circular neighborhood, HOG[6] adopts the cell regions, etc.”
MethodAnti-rotation Binary Descriptor for Circular Image Recognition
Chen, H., Zhang, D., Yi, L., et al. (2018) · Chinese Automation Congress · doi:10.1109/cac.2018.8623066
New 2D-Feature Descriptor Free from Orientation Compensation
Benaissa, M., & Bennia, A. (2018) · International Conference on Electrical Sciences and Technologies in Maghreb · doi:10.1109/cistem.2018.8613393
Anzid, H., Goïc, G. L., Bekkari, A., et al. (2018) · International Conference on Intelligent Systems: Theories and Applications · doi:10.1145/3289402.3289502
“Originally, Speeded up robust feature (SURF) proposed by Herbert Bay [3], is a local rotation and scale invariant fast feature point detector and distinctive features point descriptor.”
BackgroundMethodConcept‐Based and Event‐Based Video Search in Large Video Collections
Markatopoulou, F., Galanopoulos, D., Tzelepis, C., et al. (2019) · doi:10.1002/9781119376996.ch2
Advanced Content based Medical Image Retrieval
Sanjay, D. S., Shivakumara, S. M., Santhosh Babu Yadav, S., et al. (2018)
A Robust Visual SLAM System Based on RGB-D Camera Used in Various Indoor Scenes
Li, L., Li, A., Tian, Y., et al. (2018) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2018.8665252
Irregular Motion Detection in Automotive Navigation Systems with Soft Map Rotation
Pollot, M., Springer, D., Schleifer, R., et al. (2019) · International Conference on Consumer Electronics · doi:10.1109/icce.2019.8661963
“Reasons for choosing BRISK is its high speed that is required to process long sequences that can take up to several hours, compared to approaches like SIFT [5] or SURF [6], which are significantly slower.”
MethodLimitations of Metric Loss for the Estimation of Joint Translation and Rotation
Roman, P., Desbarats, P., Domenger, J., & Buendia, A. (2019) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0007525005900597 · Cited by 1
“Structure-FromMotion algorithms (Häming and Peters, 2010) can retrieve the position and orientation of a camera given a set of images using descriptors such as SIFT (Lowe, 1999) or SURF (Bay et al., 2006) and RANSAC regression.”
MethodNatural Stereo Camera Array using Waterdrops for Single Shot 3D Reconstruction
Furukawa, A., Sakaue, F., & Sato, J. (2019) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0007582609010907
Elibol, A., Chong, N. Y., Shim, H., et al. (2019) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-019-00089-0
Learning dense 3D models from monocular video
Yu, R. (2017) · UCL Discovery (University College London)
Spontaneous Reorientation for Self-localization
Bader, M., & Vincze, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-44468-9_40
Explicit Spatiotemporal Joint Relation Learning for Tracking Human PosePreprint
Sun, X. N., Li, C., & Lin, S. C.-F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.07123
A novel method for SIFT features matching based on feature dimension matching degree
Yang, Y., Wei, J., Zhan, X., et al. (2019) · MATEC Web of Conferences · doi:10.1051/matecconf/201927702027
“SIFT[7] is known as the most representative feature extraction and matching method currently, and it had been improved by many researchers[8-10].”
Method3D Object Detection Using a New Descriptor with RGB-D
Arıcan, E., & Aydın, T. (2019) · Bilge International Journal of Science and Technology Research · doi:10.30516/bilgesci.491557
“In literature, it can be found many studies using descriptor which are very preferred in computer vision (Lowe 2004; Bay et al. 2006; Shechtman and Irani 2007; Calonder et al. 2010; Rublee et al. 2011) Nowadays, technology is going better and cheaper therefore it can be found and access 3D image…”
BackgroundMethodPerformance Evaluation of Linear and Nonlinear Scale Descriptor Based Algorithms
Manur, V. B., & Ali, L. (2018) · International Conference on Computing, Power and Communication Technologies (GUCON) · doi:10.1109/gucon.2018.8674950
Challenges in Embedded Vision for Augmented Reality
Narasimha, R., Stöffler, N. O., Stanimirović, D., et al. (2014) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-09387-1_7
COMPARISON OF BRIEF AND ORB BINARY DESCRIPTORS
Mukhina, M. P., Trach, Y., & Prymak, A. P. (2018) · Electronics and Control Systems · doi:10.18372/1990-5548.58.13507
Retinal Image Registration Based on Bifurcation Point and SURF
Xia, H., & Chen, D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-17642-6_12
KAWASAKI, A., Saitô, H., & Kosuke, H. A. R. A. (2015) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.81.1146
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.