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 8,101–8,200 of 14,752
Indoor localization using SLAM in parallel with a natural marker detector
Teixeira, L., Raposo, A. B., & Gattass, M. (2013) · ACM Symposium on Applied Computing · doi:10.1145/2480362.2480370 · Cited by 4
A framework of timestamp replantation for panorama video surveillance
Yu, X., Cheng, J. T., Wu, S., & Wu, S. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-3051-1 · Cited by 4
A real-time object tracking via L2-RLS and compressed Haar-like features matching
Wu, Z., Yang, J., Liu, H., & Zhang, Q. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3356-8 · Cited by 4
Domain adaptation of image classification based on collective target nearest-neighbor representation
Tang, S. Y., Ye, M., Liu, Q., et al. (2016) · Journal of Electronic Imaging · doi:10.1117/1.jei.25.3.033006 · Cited by 4
Multiple Scaled Person Re-Identification Framework for HD Video Surveillance Application
Yang, H., Wang, X., Ma, W., et al. (2015) · Communications in computer and information science · doi:10.1007/978-3-662-48570-5_21 · Cited by 4
“To handle viewpoint and illumination changes, SURF descriptor[17]is used as a complementary feature to color histograms, which are also L2 normalized.”
MethodGPCA-SIFT: A New Local Feature Descriptor for Scene Image Classification
Ju, L., Xie, K., Zheng, H., et al. (2016) · Communications in computer and information science · doi:10.1007/978-981-10-3005-5_24 · Cited by 4
Guzman, L., Commandeur, F., Acosta, O., et al. (2016) · doi:10.1109/embc.2016.7590911 · Cited by 4
“2) Multiresolution Salient Point Detection: A multiresolution analysis is done using SURF [1], yielding the salient points (SPs) invariant to illumination, scale”
MethodVisual odometry using motion vectors from visual feature points
Marouane, C., Maier, M., Leupold, A., & Linnhoff–Popien, C. (2016) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2016.7743646 · Cited by 4
“It has already been shown in previous studies that the SURF method (Speeded Up Robust Features) [1] is well-suited for the usage in the field of visual odometry and positioning [10][11].”
MethodA Review of Detector Descriptors' on Object Tracking
S.Khachikian, M. E. (2016) · International Journal of Advanced Research in Electrical Electronics and Instrumentation Engineering · doi:10.15662/ijareeie.2016.0507002 · Cited by 7
“800*640) [8] FH-9 is faster than DoG and Hessian Laplace by 5 and 10 times respectively.”
BackgroundMethodResultInfluentialAn improved approach for model-based detection and pose estimation of texture-less objects
Zhang, H., Cao, Y., Zhu, X., Fujie, M. G., & Cao, Q. (2016) · IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO) · doi:10.1109/arso.2016.7736292 · Cited by 4
3D Reconstruction of Indoor Scenes Using RGB-D Monocular Vision
Liu, S., Zhu, W., Zhang, C., et al. (2016) · International Conference on Robots & Intelligent System · doi:10.1109/icris.2016.116 · Cited by 4
“SIFT algorithm, proposed SURF [9] (speeded up robust features ) algorithm, SURF algorithm inherits the advantages of the scale of the SIFT algorithm, and greatly improve the efficiency of the implementation.”
MethodInfluentialLocal Binary Pattern and Its Variants for Target Recognition in Infrared Imagery
Akula, A., Ghosh, R., Kumar, S., et al. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-981-10-2104-6_27 · Cited by 4
Artificial Bee Colony Optimization for Feature Selection of Traffic Sign Recognition
da Silva, D. L., Seijas, L. M., & Bastos-Filho, C. J. A. (2017) · International Journal of Swarm Intelligence Research · doi:10.4018/ijsir.2017040104 · Cited by 4
An approach to vision-based localisation with binary features for partially sighted people
Oszust, M., Padjasek, J., & Kasprzyk, P. (2017) · Signal Image and Video Processing · doi:10.1007/s11760-017-1083-x · Cited by 4
Technologies for Visual Localization and Augmented Reality in Smart Cities
Amato, G. M., Cardillo, F. A., & Falchi, F. (2017) · Geotechnologies and the environment · doi:10.1007/978-3-319-50518-3_20 · Cited by 4
Automated Fiducial Points Detection Using Human Body Segmentation
Rajbdad, F., Aslam, M., Azmat, S., et al. (2017) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-017-2646-4 · Cited by 4
“In [20–22], Scale Invarent Feature Transform (SIFT), Harris-Laplacian, and Speeded-Up Robust Features (SURF) have been used to detect significant points within images.”
MethodAli, M. M., Liu, H., Stoll, N., & Thurow, K. (2017) · Advances in Science Technology and Engineering Systems Journal · doi:10.25046/aj0203155 · Cited by 4
Real-time moving object detection and segmentation in H.264 video streams
Konda, K. R., Tefera, Y. T., Conci, N., & Natale, F. G. B. D. (2017) · IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) · doi:10.1109/bmsb.2017.7986161 · Cited by 5
“Most of the proposed techniques rely on the analysis of visual features extracted in the spatial and/or temporal domain, and are usually based on the color, edge, or texture information [1][2][3][4].”
MethodSTARE: Realtime, Wearable, Simultaneous Gaze Tracking and Object Recognition from Eye Images
Hafi, L. E., Ding, M., Takamatsu, J., et al. (2017) · SMPTE Motion Imaging Journal · doi:10.5594/jmi.2017.2711899 · Cited by 4
An SAR image registration method based on pyramid model
Zhang, Y., & Wu, T. (2016) · CIE International Conference on Radar (RADAR) · doi:10.1109/radar.2016.8059494 · Cited by 4
“In 2006, Bay put forward the method comparable to SURF algorithm, called SIFT, which improves in speed largely[6].”
MethodMechanical CAD Parts Recognition for Industrial Automation
Jain, T., Meenu, & Sardana, H. K. (2017) · Smart innovation, systems and technologies · doi:10.1007/978-981-10-5547-8_35 · Cited by 4
Event-based real-time optical flow estimation
Lee, A. J., & Kim, A. (2017) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas.2017.8204333 · Cited by 4
“SURF has high performance as SIFT and is much faster in computation.”
MethodAn application of vision technology on intelligent sorting system by delta robot
Wang, S., Hu, L., Gai, R., et al. (2017) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom.2017.8210773 · Cited by 4
Third Case Study for the Dynamic Multilevel Component Selection
Deak, R., Sterca, A., & Bădărînză, I. (2017) · Studia Universitatis Babeș-Bolyai Informatica · doi:10.24193/subbi.2017.2.02 · Cited by 4
Real-Time Prototype of Driver Assistance System for Indian Road Signs
Saranya, K. C., & Singhal, V. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-981-10-5272-9_14 · Cited by 4
Super-resolution image reconstruction using surface fitting with hierarchical structure
Wang, X., Zhou, D., Zeng, N., et al. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.03.011 · Cited by 4
Multiple-target tracking on mixed images with reflections and occlusions
Zhang, T.-H., & Tang, C. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.02.001 · Cited by 4
An In Depth Review Paper on Numerous Image Mosaicing Approaches and Techniques
Rahim, M. A. –., & Zheng-sheng, Y. (2018) · International Journal of Engineering and Management Research · doi:10.31033/ijemr.v8i02.11607 · Cited by 4
Body Height Estimation System Based on Binocular Vision
Yang, G., Li, D., Ru, G., et al. (2018) · International Journal of Online and Biomedical Engineering (iJOE) · doi:10.3991/ijoe.v14i04.8400 · Cited by 4
Research on SIFT Image Matching Based on MLESAC Algorithm
Deng, L., Piao, Y., & Liu, S. (2018) · doi:10.1145/3193025.3193059 · Cited by 4
“BAY proposed the speeded up robust features (SURF) algorithm in feature point detection [9].”
MethodEfficient Large-scale Image Search With a Vocabulary Tree
Uriza, E., Fernández, F. G., & Rais, M. (2018) · Image Processing On Line · doi:10.5201/ipol.2018.199 · Cited by 4
A Dense-Depth Representation for VLAD Descriptors in Content-Based Image Retrieval
Magliani, F., Fontanini, T., & Prati, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03801-4_58 · Cited by 7
“They allow to densely extract features from images, that are better than the ones extracted with hand-crafted methods like SIFT [16] or SURF [4], because they can catch more details on the images through the high number of convolution layers.”
MethodMORB: A Multi-Scale Binary Descriptor
Xompero, A., Lanz, O., & Cavallaro, A. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451024 · Cited by 4
Estimating the Number of Correct Matches Using Only Spatial Order
Talker, L., Moses, Y., & Shimshoni, I. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2869560 · Cited by 4
SVO-PL: Stereo Visual Odometry with Fusion of Points and Line Segments
Zhou, Y., Han, K., Luo, C., & Wang, J. (2018) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2018.8484479 · Cited by 4
“Compared with popular SIFT [16] and SURF [17] methods, ORB features are not only fast to compute and match but also have good invariance to viewpoint.”
MethodAn Improved Learning Framework for Covariant Local Feature Detection
Doiphode, N., Mitra, R., Ahmed, S., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20876-9_17 · Cited by 4
Local Geometric Deformations in the DHT Domain With Applications
Silván-Cárdenas, J. L., & Salazar-Garibay, A. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2881836 · Cited by 4
“pared with the well-known Scale Invariant Feature Transform (SIFT) [35] and the Speeded-up Robust Features (SURF) [36] image matching methods.”
MethodDistributed Video Decoding on Hadoop
Yoon, I., Yi, S., Oh, C., et al. (2018) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2018pap0014 · Cited by 4
Image Feature Matching Based on Semantic Fusion Description and Spatial Consistency
Zhang, W., & Zhang, G. (2018) · Symmetry · doi:10.3390/sym10120725 · Cited by 4
“Up to now, researchers have carried out a lot of research on image feature extraction and description, and have produced many classic feature description and extraction methods, such as SIFT (scale-invariant feature transform) [1], SURF (speeded up robust features) [2], ORB (oriented FAST and rotated BRIEF) [3], and F…”
MethodA Face Recognition Based Biometric Solution in Education
Dahmouni, A., Aharrane, N., Moutaouakil, K. E., et al. (2018) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661818040065 · Cited by 4
A Distributed Sensing Approach for Single Platform Image-Based Localization
Akal, O., Mukherjee, T., Barbu, A., Paquet, J., George, K., & Pasiliao, E. L. (2018) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2018.00103 · Cited by 5
“Several different algorithms can be used for the purpose of computing the match (e.g. matching using Scale Invariant Feature Transform (SIFT) [3] or Speed up Robust Features (SURF) [4]).”
MethodArabic Manuscript Content Based Image Retrieval: A Comparison between SURF and BRISK Local Features
Bagasi, E. A. B. (2018) · International Journal of Computing and Digital Systems · doi:10.12785/ijcds/070604 · Cited by 4
“SURF is proposed by Herbert Bay [6] as a novel scaleand rotation-invariant Interest point detector and descriptor.”
MethodRelevance prediction in similarity-search systems using extreme value theory
Oliveira, A., Oakley, E., Torres, R. D. S., et al. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.02.019 · Cited by 4
Nikolov, I. A., & Madsen, C. B. (2019) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0007444208840891 · Cited by 4
2D art recognition in uncontrolled conditions using one-shot learning
Skoryukina, N. S., Nikolaev, D., & Arlazarov, V. V. (2019) · International Conference on Machine Vision · doi:10.1117/12.2523017 · Cited by 4
The problems of image superimposition with one-pixel accuracy
Aleksanin, A. I., MOROZOV, M. A., & Fomin, E. V. (2019) · Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa · doi:10.21046/2070-7401-2019-16-1-9-16 · Cited by 4
Object Recognition for Robotics Based on Planar Reconstructed B-Rep Models
Rohner, D., & Henrich, D. (2019) · IEEE International Conference on Robotic Computing (IRC) · doi:10.1109/irc.2019.00027 · Cited by 5
Altuntaş, C. (2019) · Reports on Geodesy and Geoinformatics · doi:10.2478/rgg-2019-0001 · Cited by 4
“The rst variety of SIFT is the SURF algorithm, which de nes keypoints with lower-dimensional feature vectors for fast evaluation (Bay et al., 2006).”
MethodInertia Sensor Aided Alignment for Burst Pipeline in Low Light Conditions
Zhang, S., & Stevenson, R. L. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451134 · Cited by 4
Accessing Urban History using Spatial Historical Photographs
Niebling, F., Maiwald, F., Münster, S., Bruschke, J., & Henze, F. (2018) · Digital Heritage International Congress · doi:10.1109/digitalheritage.2018.8809998 · Cited by 5
Saddle: Fast and repeatable features with good coverage
Aldana-Iuit, J., Mishkin, D., Chum, O., & Matas, J. (2019) · Image and Vision Computing · doi:10.1016/j.imavis.2019.08.011 · Cited by 4
Object detection in the police surveillance scenario
Wilkowski, A., Kasprzak, W., & Stefańczyk, M. (2019) · Annals of Computer Science and Information Systems · doi:10.15439/2019f291 · Cited by 4
Digital Watermark System with an Ability of its Extraction from Hard Copies of Data
Korzhik, V. I., & Flaksman, D. (2019) · Proceedings of Telecommunication Universities · doi:10.31854/1813-324x-2019-5-3-75-85 · Cited by 4
Zheng, Y., & Zheng, P. (2019) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/siprocess.2019.8868783 · Cited by 4
“Corner detectors commonly used in image matching are the Harris-Laplace detector [8], the SIFT detector [9-10], the SURF detector [11-12] and so on.”
MethodTowards a SLAM-based augmented reality application for the 3D annotation of rock art
Abergel, V., Jacquot, K., Luca, L. D., et al. (2019) · International Journal of Virtual Reality · doi:10.20870/ijvr.2019.19.2.2910 · Cited by 4
Joint Image Deblurring and Matching with Blurred Invariant‐Based Sparse Representation Prior
Shao, Y., Sang, N., Peng, J., & Gao, C. (2019) · Complexity · doi:10.1155/2019/3829263 · Cited by 4
Image Retrieval From Video Streams Databases Using Similarity Of Clustering Histogram
كريم, ع., & ناصر, أ. ف. (2018) · doi:10.36541/0231-000-029-001 · Cited by 4
Vision-based vehicle behavior monitoring method using a novel clustering algorithm
Wang, X., & Dai, Z. (2019) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-019-01581-y · Cited by 4
“In our approach, we use correspondences from feature points (Rublee et al. 2011; Rosten and Drummond 2006; Calonder et al. 2010; Rosin 1999; Lowe 2004; Bay et al. 2006; El-Alfy and Binsaadoon 2019; Leutenegger et al. 2011; Alcantarilla et al. 2012) as entries for motion segmentation.”
Development of Speed Up Robust Feature Algorithm for aerial image feature extraction
Banerjee, S., Chaturvedi, S. K., & Tiwari, S. P. (2019) · INCAS BULLETIN · doi:10.13111/2066-8201.2019.11.4.5 · Cited by 4
An Attention-Based User Profiling Model by Leveraging Multi-modal Social Media Contents
Li, Z., Guo, B., Sun, Y., Wang, Z., Wang, L., & Yu, Z. (2019) · Communications in computer and information science · doi:10.1007/978-981-15-1925-3_20 · Cited by 6
Image Enhancement and Quality Assessment Methods in Turbid Water: A Review Article
Hmue, P. M., & Pumrin, S. (2019) · IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) · doi:10.1109/icce-asia46551.2019.8942216 · Cited by 5
“[14], in which the detector is based on Hessian matrix.”
MethodA Color Image Representation Approach for Content-Based Image Retrieval
Liu, C.-H., Lee, C.-H., Shih, J.-L., & Han, C. (2019) · International Symposium on Computing and Networking · doi:10.1109/candar.2019.00014 · Cited by 5
“Some widely-used local features, including scale-invariant feature transform (SIFT) descriptor [5-8], speeded up robust features (SURF) [9], local binary patterns (LBP) [10], local color statistics (LCS), etc, were proposed for image classification or retrieval.”
MethodInfluentialTaylor, H. M., Dondrup, C., & Lohan, K. S. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967521 · Cited by 5
“SIFT [8], SURF [9] and ORB [10] continue to be popular algorithms for feature detection and are actively used for SLAM.”
MethodKinect based Frontal Gait Recognition using skeleton and depth derived features
Sheshadri, M. G. H., & Okade, M. (2020) · National Conference on Communications · doi:10.1109/ncc48643.2020.9056001 · Cited by 4
“Superpixel segmentation using the Simple Linear Iterative Clustering (SLIC) algorithm [10] is then applied and the superpixel image thus obtained is used to extract Speeded Up Robust Features (SURF) [11].”
MethodHW/SW Co-design and FPGA Acceleration of a Feature-Based Visual Odometry
Chien, C.-H., Chien, C., & Hsu, C.-C. J. (2019) · International Conference on Robotics and Automation Engineering (ICRAE) · doi:10.1109/icrae48301.2019.9043811 · Cited by 4
“Many feature-based VO use FAST [1] or SURF [2] algorithms for feature extraction, while KLT tracking [3] and FLANN [4] are often employed for feature matching.”
MethodRenal Cell Cancer Nuclei Segmentation from Histopathology Image Using Synthetic Data
Hossain, M. S., & Sakib, N. (2020) · IEEE International Colloquium on Signal Processing & Its Applications (CSPA) · doi:10.1109/cspa48992.2020.9068701 · Cited by 5
GUIDED FEATURE MATCHING FOR MULTI-EPOCH HISTORICAL IMAGE BLOCKS POSE ESTIMATION
Li, Z., Rupnik, E., & Pierrot-Deseilligny, M. (2020) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-2-2020-127-2020 · Cited by 5
CS-FREAK: An Improved Binary Descriptor
Wang, J., Wang, X., Yang, X., & Aigang, Z. (2014) · Communications in computer and information science · doi:10.1007/978-3-662-45498-5_15 · Cited by 5
Real-time mosaicking for infrared videos from an oblique sweeping camera
Lu, J., Sun, F., Dong, J., Han, S., & Su, A. (2020) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2020.03.033 · Cited by 4
Feature Selection in Big Image Datasets
Figueira-Domínguez, J. G., Bolón‐Canedo, V., & Remeseiro, B. (2020) · doi:10.3390/proceedings2020054040 · Cited by 4
A Novel Harris Feature Detection-Based Registration for Remote Sensing Image
Wang, Y., Lai, H., Ma, H., et al. (2020) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-020-01151-2 · Cited by 4
“…methods: To verify the matching performance improvement, the proposed algorithm is compared with the SIFT algorithm (Lowe 2004), the SURF algorithm (Bay et al. 2006), the SAR-SIFT algorithm (Michel et al. 2014), the PSO-SIFT (Ma et al. 2017), and the algorithm proposed in Fan et al. (2014), and…”
MethodToward Classification of Arabic Manuscripts Words Based on the Deep Convolutional Neural Networks
Elmansouri, M., Makhfi, N. E., & Aghoutane, B. (2020) · International Conference on Intelligent Systems and Computer Vision (ISCV) · doi:10.1109/iscv49265.2020.9204305 · Cited by 4
“Most traditional methods are based on feature extractors such as Scale Invariant Feature Transform algorithm (SIFT) [9] [10], Speeded Up Robust Features algorithm (SURF) [11], geometric features and HOG-based descriptors.”
MethodVehicle detection for intelligent traffic surveillance system
Abid, N., Ouni, T., & Abid, M. (2020) · International Conference on Advanced Technologies for Signal and Image Processing · doi:10.1109/atsip49331.2020.9231936 · Cited by 3
“The most popular are Haar-like features [4], Local Binary Pattern (LBP) [5], Histograms of Oriented Gradients (HOG) [6] and Speeded up Robust Features (SURF) [17].”
BackgroundLe, H., Nguyen, M., Nguyen, Q., Nguyen, H. N., & Yan, W. Q. (2020) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr49794.2020.9237760 · Cited by 7
Multi-support Vector Machine Based Dempster-Shafer Theory for Gesture Intention Understanding
Chen, L., Wu, M., Witold Pedrycz, C., & Hirota, K. (2020) · Studies in computational intelligence · doi:10.1007/978-3-030-61577-2_8 · Cited by 3
ECHO: Extended Convolution Histogram of Orientations for Local Surface Description
Mitchel, T. W., Rusinkiewicz, S. M., Chirikjian, G. S., & Kazhdan, M. M. (2020) · Computer Graphics Forum · doi:10.1111/cgf.14181 · Cited by 8
“Successful image descriptors, such as SIFT [Low99, Low04] and SURF [BTVG06, BETVG08], are both highly descriptive, in that characterizations of different neighbourhoods are sufficiently unique so as to differentiate between the two without ambiguity, repeatable, in that descriptions of regions that…”
BackgroundRobot Navigation in a Dynamically Changing Environment
Zhidkov, V. N., Kim, N. V., & Владимировна, У. Н. (2020) · International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon) · doi:10.1109/fareastcon50210.2020.9271534 · Cited by 3
“Most of the approaches use neural networks based on CVS [14, 15], which function under the conditions of direct visibility of reference points.”
BackgroundMethodTowards Large Scale Image Retrieval System Using Parallel Frameworks
Mezzoudj, S. (2021) · Multimedia Information Retrieval · doi:10.5772/intechopen.94910 · Cited by 4
Secure Multimodal Access with 2D and 3D Ears
Ganapathi, I. I., Prakash, S., & Ali, S. S. (2021) · Studies in big data · doi:10.1007/978-981-15-9492-2_1 · Cited by 4
PhosopNet: An improved grain localization and classification by image augmentation
Mookdarsanit, P., & Mookdarsanit, L. (2021) · TELKOMNIKA (Telecommunication Computing Electronics and Control) · doi:10.12928/telkomnika.v19i2.18321 · Cited by 5
Chen, B., Ouyang, Y., Ou‐Yang, M., et al. (2020) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss39084.2020.9324496 · Cited by 4
Kumar, P., H, P. B., Nagendraswamy, H. S., et al. (2021) · International Journal of Distributed Artificial Intelligence · doi:10.4018/ijdai.2021010101 · Cited by 4
Research on Volleyball Image Classification Based on Artificial Intelligence and SIFT Algorithm
Lin, W. (2021) · Mathematical Problems in Engineering · doi:10.1155/2021/5547689 · Cited by 4
LARGER RECEPTIVE FIELD BASED RGB VISUAL RELOCALIZATION METHOD USING CONVOLUTIONAL NETWORK
Qin, J., Li, M., Li, D., Liao, X., Zhong, J., & Zhang, H. (2021) · 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-xliii-b2-2021-47-2021 · Cited by 3
Multi-surface hydraulic valve block technique hole plug inspection from monocular image
Wang, Y., Wang, X., & Chen, Y. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/ac1460 · Cited by 5
“But traditional key point extractors [7, 8] are struggle with texture-less objects like metal parts.”
Categorization and Selection of Crowdsourced Images Towards 3D Reconstruction of Heritage Sites
Tabib, R. A., Santoshkumar, T., Pradhu, V., et al. (2021) · Springer eBooks · doi:10.1007/978-3-030-57907-4_7 · Cited by 4
An efficient and low power deep learning framework for image recognition on mobile devices
Liu, G., Dai, X., Liu, X., Chen, M., Huang, Z., & Xing, T. (2021) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-021-00076-0 · Cited by 5
“The accuracy of these machine learning clustering methods on the public data sets CIFAR-100 (Krizhevsky and Hinton 2009) and ILSVRC2012 1K (Deng et al. 2009) is very low, because they rely on the feature extraction algorithms SIFT (Lowe 2004) and SURF (Bay et al. 2006).”
MethodA Survey on Feature Point Extraction Techniques
Huang, K., Li, J., Liu, Y., Chang, L., & Zhou, J. (2021) · International SoC Design Conference · doi:10.1109/isocc53507.2021.9613858 · Cited by 5
Deshmukh, S., & Fernandes, F. (2021) · IEEE Mysore Sub Section International Conference (MysuruCon) · doi:10.1109/mysurucon52639.2021.9641535 · Cited by 4
An Automatic Image Stitching Method for Infrared Image Series
Zhi-jian, H., Hui, B., & Shujin, S. (2021) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais52680.2021.9624642 · Cited by 4
Novel semi-supervised learning approach for descriptor generation using artificial neural networks
Alwindawi, A. F., Osman Nuri, U. C. A. N., İbrahim, A. A., & Yusuf, A. (2022) · Soft Computing · doi:10.1007/s00500-022-06742-4 · Cited by 4
“…features in techniques such as the Haar (Viola and Jones 2001), scale-invariant feature transform (Lowe 1999) and speeded-up robust features (Bay et al. 2006) methods for generating descriptors for the input samples limits the efficiency of the generated descriptors, as the significance of…”
MethodMünster, S., Lehmann, C. U., Lazariv, T., Maiwald, F., & Karsten, S. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-93186-5_5 · Cited by 7
Car Pose Estimation Through Wheel Detection
Roch, P., Nejad, B. S., Handte, M., & Marrón, P. J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-90439-5_21 · Cited by 4
Convolutional Neural Network for Traffic Sign Recognition based on Color Space
Yıldız, G., & Dızdaroğlu, B. (2021) · International Informatics and Software Engineering Conference (IISEC) · doi:10.1109/iisec54230.2021.9672400 · Cited by 4
Learning Two-View Correspondences and Geometry Using Neighbor-Aware Network
Zheng, W., Shi, Z., Xiao, G., et al. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3159571 · Cited by 4
Emotion Recognition Using Facial Expression
Kumar, S., Jaiswal, S., Kumar, R., & Singh, S. K. (2018) · IGI Global eBooks · doi:10.4018/978-1-5225-5204-8.ch074 · Cited by 5
A Moving Object Tracking Technique Using Few Frames with Feature Map Extraction and Feature Fusion
AlArfaj, A. A., & Mahmoud, H. A. H. (2022) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi11070379 · Cited by 4
The Robust Semantic SLAM System for Texture-Less Underground Parking Lot
Liu, C., & Yao, J. (2022) · Journal of Advanced Transportation · doi:10.1155/2022/9681455 · Cited by 5
“Moreover, SIFT [8], SURF [9], BRIEF [10], and ORB [11] descriptors are widely used by researchers in describing the features to make these features unique.”
NCTR: Neighborhood Consensus Transformer for Feature Matching
Lu, X., & Ду, С. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897245 · Cited by 4
“Before the rise of deep learning methods, there are many well-known works on handcrafted detection and description methods [4, 5, 6, 7], which have good performance and are widely used in 3D computer vision tasks.”
MethodTag Association Based Graphical Password Using Image Feature Matching
Kawagoe, K., Sakaguchi, S., Sakon, Y., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-29035-0_22 · Cited by 4
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.