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 10,101–10,200 of 14,752
Autonomous Image Georeferencing Based on Database Image Matching
Hakim, P. R., Jayani, A. P. S., Sarah, A., et al. (2018) · IEEE International Conference on Aerospace Electronics and Remote Sensing Technology (ICARES) · doi:10.1109/icares.2018.8547086 · Cited by 2
“SURF algorithm will detect blob features in the images, while both FAST and BRISK algorithms will detect corner features [14][15]16].”
MethodAnzid, H., Goïc, G. L., Bekkari, A., et al. (2019) · INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY · doi:10.24297/ijct.v18i0.7956 · Cited by 2
MREAK: Morphological Retina Keypoint Descriptor
Vaghela, H., Oza, M., & Bagul, S. (2019) · doi:10.1109/icaiit.2019.8834665 · Cited by 2
“SURF uses BLOB detector based on Hessian matrix to detect keypoints.”
MethodInfluentialA Hardware–Software Co-Design Framework for Real-Time Video Stabilization
Javed, H., Bilal, M., & Masud, S. (2019) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126620500279 · Cited by 2
Bandyopadhyay, T., Kubíček, J., Penhaker, M., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-14802-7_27 · Cited by 2
Performance Analysis of Image Mosaicing Methods for Unmanned Aerial Vehicles
Tahtirvanci, A., & Durdu, A. (2018) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai.2018.8679007 · Cited by 2
Benchmarking GPU-Based Phase Correlation for Homography-Based Registration of Aerial Imagery
Schubert, F., & Mikolajczyk, K. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40246-3_11 · Cited by 2
Towards a Semantic Video Analysis using Deep Learning and Ontology
Bornia, J., Mahmoudi, S. A., Frihida, A., et al. (2018) · doi:10.1109/cloudtech.2018.8713340 · Cited by 2
“Speeded Up Robust Features (SURF) [27] is a descriptor based on the SIFT descriptor whose computation is three times faster but provides lower performance.”
MethodMotion tracking of iris features for eye tracking
Chaudhary, A. K. (2019) · ACM Symposium on Eye Tracking Research and Applications (ETRA) · doi:10.1145/3314111.3322872 · Cited by 2
“Until now, we have focused on the use of Speeded Up Robust Features [Bay et al. 2006] to extract features from iris images.”
MethodHardware Designs for Histogram of Oriented Gradients in Pedestrian Detection: A Survey
Bagavathi, C., & Saraniya, O. (2019) · International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs.2019.8728486 · Cited by 4
“SURF [15] detects interest points by an efficient algorithm which was developed by Bay for representation invariant to neighborhood points and correlation.”
MethodInfluentialA High-Efficient Infrared Mosaic Algorithm Based on GMS
Pei, X., Guo, B., Wang, G., et al. (2019) · Smart innovation, systems and technologies · doi:10.1007/978-981-13-9710-3_11 · Cited by 2
Identifying Image Related Sentences in News Articles
İlter, M. E., Akarun, L., & Özgür, A. (2019) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2019.8806258 · Cited by 2
“Bu çalışmada kilit noktaları bulmak için Hızlandırılmış Güçlü Özellikler (Speeded-Up Robust Features / SURF) [8] yöntemi kullanılmıştır.”
InfluentialShi, L., Copot, C., Derammelaere, S., & Vanlanduit, S. (2019) · International Conference on Control, Automation and Robotics (ICCAR) · doi:10.1109/iccar.2019.8813478 · Cited by 2
Parametric Registration for Mobile Phone Images
Zhang, X., Gilliam, C., & Blu, T. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803769 · Cited by 2
Joint Image Restoration and Matching Based on Hierarchical Sparse Representation
Li, W., Sang, N., Gao, C., et al. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803466 · Cited by 2
“The first of which measure the similarity of feature vectors extracted from the query image and the reference image, and the typical approaches are as Canny operator [2], Harris operator [3], SUSAN operator [4], SIFT feature descriptor [5], SURF operator[6] and Ridge let transform [7].”
MethodWell-Distributed Feature Extraction for Image Registration Using Histogram Matching
Mahmood, M. T., & Lee, I. H. (2019) · Applied Sciences · doi:10.3390/app9173487 · Cited by 2
Deep Learning and Binocular Stereovision to Achieve Fast Detection and Location of Target
Wang, Q., Liang, Y., Wang, Z., Li, W., Jiang, Z., & Zhao, Y. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-981-32-9686-2_36 · Cited by 2
Visual Servo Tracking of a Wheeled Mobile Robot Utilizing Both Feature and Depth Information
Liu, C.-Y., Chang, Z.-W., & Chen, C. (2019) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2019.8834363 · Cited by 2
Faster RCNN-CNN-Based Joint Model for Bird Part Localization in Images
Pankajakshan, A., & Bhavsar, A. V. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-981-32-9291-8_17 · Cited by 2
An improved algorithmofmedian flow for visual object tracking and its implementation on TI OMAP
Varfolomieiev, A. Y., & Lysenko, O. M. (2012) · doi:10.1109/ederc.2012.6532268 · Cited by 2
Nicolas, F., Arnold-Bos, A., Quidu, I., et al. (2019) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceanse.2019.8867211 · Cited by 2
Set-up error validation with EPID images: Measurements vs Egs_cbct simulation
van Eeden, D., O’Reilly, F., & du Plessis, F. C. P. (2019) · Reports of Practical Oncology & Radiotherapy · doi:10.1016/j.rpor.2019.09.013 · Cited by 2
Descriptor-Length Reduction Using Low-Variance Filter for Visual Odometry
Kalambe, S. S., Rufus, E., Karar, V., & Poddar, S. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-981-32-9291-8_1 · Cited by 2
Domoguen, J. K. L., Suarez, J. J. P., & Naval, P. C. (2019) · International Conference on Imaging, Signal Processing and Communications (ICISPC) · doi:10.1109/icispc.2019.8935657 · Cited by 2
Saliency and Burstiness for Feature Selection in CBIR
Guissous, K., & Gouet-Brunet, V. (2019) · European Workshop on Visual Information Processing · doi:10.1109/euvip47703.2019.8946126 · Cited by 2
Automatic plant recognition system for challenging natural plant species
Kazerouni, M. F., Schlemper, J., & Kuhnert, K.-D. (2017) · Digital Library (University of West Bohemia) · Cited by 4
Altyntsev, M. A., & Shlyahova, M. M. (2019) · Vestnik SSUGT (Siberian State University of Geosystems and Technologies) · doi:10.33764/2411-1759-2019-24-4-58-69 · Cited by 2
Loose Fruit Recognition System With Implementation Of SURF Feature Extraction Method
Hassan, M. S., Hasan, W. Z. W., Mustafa, M. F., et al. (2019) · doi:10.1109/icsys47076.2019.8982441 · Cited by 2
An Innovative Smartphone-based Solution for Traffic Rule Violation Detection
Alasmary, W. (2020) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2020.0110177 · Cited by 3
Improved Object-Tracking Algorithm for an Underground Mining Environment
Wang, J., Ye, G., Li, J., & Kou, Q. (2019) · International Conference on Soft Computing & Machine Intelligence (ISCMI) · doi:10.1109/iscmi47871.2019.9004354 · Cited by 2
Optimization and Implementation of Synthetic Basis Feature Descriptor on FPGA
Lee, D.-J., Fuller, S. G., & McCown, A. S. (2020) · Electronics · doi:10.3390/electronics9030391 · Cited by 2
Spatial Pyramid Pooling based Convolutional Autoencoder Network for Loop Closure Detection
Xiang, R., Liu, Y., Zhang, Q., & Cheng, J. T. (2019) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar47638.2019.9044155 · Cited by 2
“Local feature descriptors such as scale-invariant feature transforms (SIFT) [8], speeded-up robust features (SURF) [9], as well as Oriented FAST and Rotated BRIEF (ORB) [10] can effectively extract local features such as corners or contours of an image, but do not consider the spatial or structural information of the…”
BackgroundAdaptive evolution strategy sample consensus for 3D reconstruction from two cameras
Toda, Y., Hsu, H.-Y., Matsuno, T., Minami, M., & Zhou, D. (2020) · Artificial Life and Robotics · doi:10.1007/s10015-020-00603-9 · Cited by 2
“In local features, Scale-Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF) are the most commonly used in order to extract the corresponding points from the multiple images [9, 10].”
BackgroundFaster R-CNN with Attention Feature Map for Robust Object Detection
Lee, Y., & Jo, K.-H. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-4818-5_14 · Cited by 2
Automated Complex for Aerial Reconnaissance Tasks in Modern Armed Conflicts
Prystavka, P., Sorokopud, V., Chyrkov, A., et al. (2020) · doi:10.55056/ceur-ws.org/vol-2588/paper6.pdf · Cited by 2
“The Template Matching methods also require a reference base; in addition, some methods [18]–[19] are not robust to noise, and some [20] do not provide sufficient performance.”
2D Visual Servoing meets Rapidly-exploring Random Trees for collision avoidance
Nascimento, M. F., Vicente, P., & Bernardino, A. J. M. (2020) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc49921.2020.9096133 · Cited by 2
“In [3] SURF features ( [4]) are used within an IBVS framework.”
MethodVideo Flame Detection Method Based on Improved Fast Robust Feature
Lingkai, Z., & Li, L. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1518/1/012065 · Cited by 2
Extraction of ORB Features with an Improved Method
Yang, B., Wang, Z., & Yu, X. (2019) · International Conference on Vision, Image and Signal Processing (ICVISP) · doi:10.1145/3387168.3387169 · Cited by 2
Xu, H., Xie, S., & Chen, F. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00344 · Cited by 2
3D model retrieval using MeshSIFT descriptor and fuzzy C-means clustering
Hamza, N. A., Jafer, S. H., & Hadi, R. M. (2020) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v19.i3.pp1452-1460 · Cited by 2
Creating Video Summary Using Speeded Up Robust Features
Banwaskar, M. R., & Rajurkar, A. M. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-4029-5_31 · Cited by 2
Vehicle Counting Framework for Intelligent Traffic Monitoring System
Shaweddy, V., & Wahyono, W. (2019) · doi:10.1109/icst47872.2019.9166440 · Cited by 2
“In order to detect the object candidate, a blob analyser [8] will be applied.”
MethodEfficient Target Detection Technique Using Image Matching Via Hybrid Feature Descriptors
Kamel, M. M., Hussein, S., Salama, G. I., et al. (2020) · doi:10.1109/iceeng45378.2020.9171756 · Cited by 2
“SIFT (Scale-Invariant Feature Transform) [3] and SURF (Speeded Up Robust Features) [5] are examples for the real-valued (floating-point) descriptors whereas ORB (Oriented FAST and Rotated BRIEF) [6], BRISK (Binary Robust Invariant Scalable Keypoints) [7] and AKAZE (Accelerated KAZE) [8] are…”
BackgroundMethodWeißkirchen, N., Reddy, M. V., Wendemuth, A., & Siegert, I. (2020) · IEEE International Conference on Human-Machine Systems (ICHMS) · doi:10.1109/ichms49158.2020.9209538 · Cited by 2
Towards Robust Localization Deep Feature Extraction by CNN
Carlbaum, E., Mansouri, S. S., Kanellakis, C., et al. (2020) · Proceedings of the Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon43393.2020.9254941 · Cited by 2
“Additionally, KAZE [9] is a feature detection method which operates in a nonlinear scale space in contrary to most of the methods which perform in Gaussian scale space (SIFT [6] or SURF [10]).”
MethodHybrid Feature Enhance Filter (HFEF) for Underwater Vision Navigation
Amarasinghe, C. K., Ratnaweera, A., & Maitripala, S. (2020) · IEEE International Conference on Computing, Communication and Automation (ICCCA) · doi:10.1109/iccca49541.2020.9250713 · Cited by 2
An Appearance and Viewpoint Invariant Visual Place Recognition for Seasonal Changes
Arshad, S., & Kim, G.-W. (2020) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas50221.2020.9268397 · Cited by 2
“Instead of using CNN based features which consumes large amount of memory and computational resources; or non-binary high-dimensional features i.e. SIFT [5] and SURF [6] and then applying the quantization methods for reducing the resource consumption as done in previous works [7], this research makes use of the binary…”
MethodSeparating real-world photos from computer graphics: comparative study of classification algorithms
Boytsov, A., & Gladilin, P. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.11.046 · Cited by 2
Landmark Segmentation and Selective Feature Extraction in Street-View Image
Vilera, R., Rachmadi, R. F., & Yuniarno, E. M. (2020) · International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM) · doi:10.1109/cenim51130.2020.9298008 · Cited by 2
“The most notable among the earlier local feature descriptors are scale-invariant feature transform (SIFT) [7] and speeded-up robust feature (SURF) [8].”
BackgroundTracking Additive Manufacturing Using Machine Vision
Davis, L. A., Donnal, J. S., & Kutzer, M. D. M. (2020) · IEEE International Conference Nanomaterials: Applications & Properties (NAP) · doi:10.1109/nap51477.2020.9309721 · Cited by 2
“5) Correlate shared features from the stereo image pair to features from an adjacent instance in time using the SURF algorithm [10].”
MethodInfluentialLocalization of Intelligent Vehicles Based on LiDAR: A Review
You, X., Mao, P., Zhang, H., et al. (2020) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2020-01-5233 · Cited by 2
da Silva, A. M. R., Angonese, A. T., & Rosa, P. F. F. (2020) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars/sbr/wre51543.2020.9306931 · Cited by 2
“Additionally, three Local Features Descriptors renowned in the literature and SLAM applications were evaluated too: Scale Invariant Feature Transform (SIFT) [23], [24], Speeded-up Robust Features (SURF) [25], and KAZE [26].”
MethodImproving Visual- Inertial Odometry with Robust Outlier Rejection and Loop Closure
Jia, C., Cao, Y., Yang, J., et al. (2020) · International Conference on Awareness Science and Technology (iCAST) · doi:10.1109/icast51195.2020.9319474 · Cited by 2
A Systematic Hybrid Smart Region based Detection (SRBD) Method for Object Detection
Anitha, R., & Jayalakshmi, S. L. (2020) · International Conference on Intelligent Sustainable Systems (ICISS) · doi:10.1109/iciss49785.2020.9315973 · Cited by 2
RnR: Retrieval and Reprojection Learning Model for Camera Localization
Yang, S., & Shi, D. (2021) · IEEE Access · doi:10.1109/access.2021.3061634 · Cited by 3
“They use conventional feature detection algorithm and is described, for example, are all hand-crafted local features, such as sift [2], surf [3] orb [4] and so on.”
MethodLuo, Y., Zhou, X., Li, K., et al. (2020) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1109/icaice51518.2020.00110 · Cited by 2
“In these processes, specialists design precise methods to obtain hand-crafted features, including Histogram of Oriented Gradient (HOG) [3], scale in variant feature transform (SIFT) [4] and speeded up robust features (SURF) [5].”
MethodBayrak, M., Kilinç, O., & Arıca, N. (2020) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu49456.2020.9302446 · Cited by 2
“Çalı¸smada öznitelik bulmak için SURF [5] algoritması kullanılmı¸stır.”
Learning to Detect Local Features Using Information Change
Cho, Y., Faisal, M., Sadiq, U., Arif, T., Hafiz, R., Seo, J., & Ali, M. (2021) · IEEE Access · doi:10.1109/access.2021.3065014 · Cited by 2
Optimization of Face Retrieval and Real Time Face Recognition Systems Using Heuristic Indexing
Sawat, D. D., Santosh, K., & Hegadi, R. S. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-0507-9_7 · Cited by 2
Stereo visual odometry with velocity constraint for ground vehicle applications
Liu, F., Sarvrood, Y. B., Liu, Y., & Gao, Y. (2021) · Journal of Navigation · doi:10.1017/s037346332100028x · Cited by 2
“are used to find common features in consecutive images (Tomasi and Kanade, 1992; Shi and Tomasi, 1993; Bay et al., 2006; Rosten and Drummond, 2006).”
MethodA Pilot Aid for Real-Time Vision-Based Coverage Estimation for Seabed Surveying Applications
Mahajan, A., & Rock, S. M. (2020) · Global Oceans 2020: Singapore – U.S. Gulf Coast · doi:10.1109/ieeeconf38699.2020.9389190 · Cited by 2
Ice Topography Reconstruction and Panoramic Stitching using Forward Looking Sonar Images
Spears, A., Meister, M. R., Ramey, C., et al. (2020) · Global Oceans 2020: Singapore – U.S. Gulf Coast · doi:10.1109/ieeeconf38699.2020.9389296 · Cited by 2
The Application of Computer Vision in the Detection of Ancient Ceramic Art
He, Y. (2021) · doi:10.24205/03276716.2020.4031 · Cited by 2
“This kind of transformation may take the form of attached step, roof and flange [10].”
BackgroundMikolka-Flöry, S., & Pfeifer, N. (2021) · Remote Sensing · doi:10.3390/rs13091705 · Cited by 2
Chen, L., & Wei, M. (2021) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-210065 · Cited by 2
“In image processing, sift and its variant [26] show outstanding performance, so researchers try to apply it to point cloud feature representation.”
Automatic decision making system with environmental and traffic data
Ersoy, S., Waqar, T., & Toptaş, E. (2021) · Mathematical Models in Engineering · doi:10.21595/mme.2021.22020 · Cited by 2
Local Surf-Based Keypoint Transfer Segmentation
Bralet, A., Kéchichian, R., & Valette, S. (2021) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi48211.2021.9434106 · Cited by 3
Quadric-based Traffic Sign Landmarks Initialization for Object-oriented EKF-SLAM
Hrustic, E., & Vivet, D. (2020) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf51394.2020.9443297 · Cited by 2
“Traditional SLAM approaches use geometrical handcrafted features such as ORB [1], SURF [2] or SIFT [3].”
MethodResearch and Application of Visual SLAM Based on Embedded GPU
Ma, T., Bai, N., Shi, W., Wang, L., & Wu, T. T. (2021) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-77569-8_1 · Cited by 2
House Price Prediction using Machine learning and Image Processing
chougale, J., Shinde, A., Deshmukh, N., Sawant, D., & Latke, V. (2021) · Journal of University of Shanghai for Science and Technology · doi:10.51201/jusst/21/05280 · Cited by 3
A Framework and Techniques for Image-based Search Application with an E-commerce Domain
Bansal, I., Dhar, S., Yuvraj, et al. (2021) · International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei51242.2021.9453093 · Cited by 2
“then, it directly returns to the most suitable results in terms of our matching work(Ruchi Jayaswal, 2018)[22].”
BackgroundParameterized Splitting of Summed Volume Tables
Reinbold, C., & Westermann, R. (2021) · Computer Graphics Forum · doi:10.1111/cgf.14294 · Cited by 2
“Since then, SATs have found use in many computer vision and signal processing tasks such as object detection [BTVG06, VJ04, GGB06, Por05], block matching [FLML14], optical character recognition [SKB08] and region fil-tering [HPD08,Hec86,BSB10].”
Robust Pose Estimation Based on Maximum Correntropy Criterion
Zhang, Q., & Chen, B. (2021) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-79150-6_44 · Cited by 2
Mardani, M., & Tahmoresnezhad, J. (2021) · Knowledge and Information Systems · doi:10.1007/s10115-021-01586-0 · Cited by 2
Fingerprint Identification by Training a LSTM Network with Fingerprint Segments as Sequence Inputs
Nithya, B., & Sripriya, P. (2021) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces51350.2021.9489036 · Cited by 3
“(7) Here I(x,y) represents the input image, S(x,y) is the addition of pixel intensities of filter area [15].”
BackgroundGraph matching based point correspondence with alternating direction method of multipliers
Yang, J., Yang, X., Zhou, Z., Liu, Z., & Fan, M. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.08.002 · Cited by 2
Incorporating learnt local and global embeddings into monocular visual SLAM
Huang, H., Ye, H., Sun, Y., Wang, L., & Liu, M. (2021) · Autonomous Robots · doi:10.1007/s10514-021-10007-8 · Cited by 3
“Compared with traditional methods in lo-cal feature detection [31–33] and description [15, 34, 35], learning-based approaches [12–14,36,37] exhibit a competitive performance in both matching accuracy and efficiency.”
Interpretation of Spatial Relationships by Objects Tracking in a Complex Streaming Video
Alabid, N. N. (2021) · ECTI Transactions on Computer and Information Technology (ECTI-CIT) · doi:10.37936/ecti-cit.2021152.240953 · Cited by 3
You, Y., Li, C., & Zhou, W. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3104844 · Cited by 2
Huang, L., Zhu, M., & Zhang, M. (2021) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess52187.2021.9522158 · Cited by 2
“For example, local features such as SIFT [1], SURF [2] and ORB [3] are used to artificially describe features to construct BoW [4].”
MethodPhishing Detection Using Computer Vision
Khandelwal, S., & Das, R. K. K. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-16-3728-5_9 · Cited by 5
Image Fusion in Multi-view Videos Using SURF Algorithm
Yashika, B. L., & Durdi, V. B. (2021) · Lecture notes in networks and systems · doi:10.1007/978-981-16-0882-7_96 · Cited by 2
Multi-temporal remote sensing image registration based on siamese network
Liu, J., Li, Y., & Chen, Y. (2021) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea53728.2021.00072 · Cited by 4
A Line Descriptor for SLAM (LDFS)
Wang, C., Shen, X. R., & Ji, L. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-8155-7_379 · Cited by 2
Design and Implementation of the UAV Reconnaissance System
Zhou, H., Ma, Z., Niu, Y., et al. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-8155-7_179 · Cited by 2
Integrating Geometric, Motion and Appearance Constraints for Robust Tracking in Aerial Videos
Hasan, M. (2013) · eScholarship (California Digital Library) · Cited by 2
Kul, S., & Sayar, A. (2021) · European Journal of Science and Technology · doi:10.31590/ejosat.1023889 · Cited by 2
Hyperspectral VNIR and NIR Sensors for the Analysis of Human Normal Brain and Tumor Tissue
León, R., Fabelo, H. A., Ortega, S., et al. (2021) · doi:10.1109/dcis53048.2021.9666168 · Cited by 2
Image-Based Localization for Augmented Reality application: A Review
Fatouh, W. S., Ali, H. F., Mashali, S. A., & Seliem, A. S. (2021) · International Conference Virtual and Augmented Reality Simulations · doi:10.1145/3463914.3463916 · Cited by 2
Integrating Traditional Machine Learning and Neural Networks for Image Processing
Витальевич, Л. Н., Витальевич, Л. В., Gerget, O. M., & Kolpashchikov, D. Y. (2021) · International Conference on Computer Graphics and Vision (GraphiCon) · doi:10.20948/graphicon-2021-3027-896-904 · Cited by 2
“…extraction carried out by feature detection algorithms, such as Scale Invariant Feature Transform (SIFT) [24], Speeded Up Robust Features (SURF) [25], Histogram of Oriented Gradients (HOG) [26] and etc. Feature extraction algorithm used to find key points and form a feature vector necessary for…”
MethodSeal Imprint Verification Using SVM Classifier and Unmatched Key Point Features
Tan, W., Guo, H., & Yao, Q. (2021) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip52628.2021.9688941 · Cited by 2
“It should be easy to apply the idea to other similar features like SURF [25] and ORB [26].”
MethodReal Object Registration Algorithm Based on SURF and RANSAC
Dai, C., Liu, D., & Hu, W. (2021) · IEEE International Conference on Networking, Sensing and Control (ICNSC) · doi:10.1109/icnsc52481.2021.9702198 · Cited by 3
Real-time Scale and Rotation Invariant Multiple Template Matching
Kim, J. R., & Jeon, J. W. (2022) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1109/imcom53663.2022.9721742 · Cited by 2
Image Registration Based on Redundant Keypoint Elimination SARSIFT Algorithm and MROGH Descriptor
Hossein‐Nejad, Z., & Nasri, M. (2022) · doi:10.1109/mvip53647.2022.9738737 · Cited by 2
Feature matching for 3D AR: Review from handcrafted methods to deep learning
Halmaoui, H., & Haqiq, A. (2022) · International Journal of Hybrid Intelligent Systems · doi:10.3233/his-220001 · Cited by 2
“The SURF algorithm [4] allows to accelerate SIFT by approximations with filters.”
InfluentialApplication of an Improved Fast Corner Detection Algorithm in ORB-SLAM2
Huo, X., Zhang, L., Liu, G., et al. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-9492-9_180 · Cited by 2
Iris Recognition Using Supervised Learning Based on Matching Features
Hernandez-Garcia, E., Martín-González, A., & Legarda-Sáenz, R. (2022) · Communications in computer and information science · doi:10.1007/978-3-030-98457-1_4 · Cited by 3
The New Approach to Camera Calibration – GCPs or TLS Data?
Markiewicz, J. S., Podlasiak, P., Kowalczyk, M., et al. (2016) · 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/isprsarchives-xli-b3-75-2016 · Cited by 2
Vongbunyong, S., & Chen, W. (2015) · Sustainable production, life cycle engineering and management · doi:10.1007/978-3-319-15183-0_4 · Cited by 2
Guo-Rong, C., Shaozi, L., Wu, Y., et al. (2011) · International Journal of Computational Intelligence Systems · doi:10.1080/18756891.2011.9727838 · Cited by 2
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.