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 4,201–4,300 of 14,752
Deep learning model with low-dimensional random projection for large-scale image search
Alzu’bi, A., & Abuarqoub, A. (2020) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2019.12.004 · Cited by 20
Kizel, F., & Benediktsson, J. A. (2020) · Remote Sensing · doi:10.3390/rs12081255 · Cited by 15
Detection of Copy-Move Forgery Using Hybrid approach of DCT and BRISK
Jaiswal, A. K., Gupta, D., & Srivastava, R. (2020) · International Conference on Signal Processing and Integrated Networks (SPIN) · doi:10.1109/spin48934.2020.9071015 · Cited by 16
Aggressive Action Recognition Using 3D CNN Architectures
Saveliev, A. I., Uzdiaev, M., & Malov, D. (2019) · International Conference on Developments in eSystems Engineering (DeSE) · doi:10.1109/dese.2019.00165 · Cited by 17
“This procedure can be typically performed with various spatial image descriptors: histogram descriptors, spectral descriptors, SIFT [4], SURF [5], HOG [6], CNN [7], etc. Extracted spatial features are processed in the block of temporal analysis of spatial features.”
PaintNet: A shape-constrained generative framework for generating clothing from fashion model
Lin, J., Song, X., Gan, T., Yao, Y., Liu, W., & Nie, L. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09009-y · Cited by 14
“– SURF [3]: We adopted the traditional retrieval method based on Speeded Up Robust Features (SURF), which obtain the feature descriptors based on the sum of the Haar wavelet response around interest points.”
MethodDeployment of Unmanned Aerial Vehicles for Anisotropic Monitoring Tasks
Wang, W., Dai, H., Dong, C., et al. (2020) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.3012791 · Cited by 14
Robust mosaicking of maize fields from aerial imagery
Aktar, R., Kharismawati, D. E., Palaniappan, K., Aliakbarpour, H., Bunyak, F., Stapleton, A. E., & Kazic, T. (2020) · Applications in Plant Sciences · doi:10.1002/aps3.11387 · Cited by 15
“Scale-invariant feature transform (SIFT), SURF, and affine SIFT (ASIFT) are local descriptors that employ different strategies and statistics for feature matching and are widely used (Lowe, 2004; Bay et al., 2006; Morel and Yu, 2009).”
Li, S. (2020) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.4117 · Cited by 16
Pyramid Point: A Multilevel Focusing Network for Revisiting Feature Layers
Varney, N. M., & Asari, V. K. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3191743 · Cited by 25
“Classical computer vision methods such as Scale Invariant Feature Transforms (SIFT) [21] and Speeded Up Robust Features (SURF) [5] rely heavily on these methods.”
MethodAn Infrared-Visible Image Registration Method Based on the Constrained Point Feature
Li, Q., Han, G., Liu, P., Yang, H., Luo, H., & Wu, J. (2021) · Sensors · doi:10.3390/s21041188 · Cited by 16
A high-quality stitching algorithm based on fisheye images
Xue, L., Zhu, J., Zhang, H., et al. (2021) · Optik · doi:10.1016/j.ijleo.2021.166520 · Cited by 14
Unsupervised Trademark Retrieval Method Based on Attention Mechanism
Cao, J., Huang, Y., Dai, Q., & Ling, B. W. (2021) · Sensors · doi:10.3390/s21051894 · Cited by 18
Zheng, P., Qin, D., Han, B., et al. (2021) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi10060402 · Cited by 14
Hossein‐Nejad, Z., & Nasri, M. (2021) · The Visual Computer · doi:10.1007/s00371-021-02261-9 · Cited by 15
“The Speed Up Robust Features (SURF) algorithm is a resilient local feature detector that has been proposed to enhance the speed of SIFT, which is also constant against rotation and scale [54].”
MethodA Novel Mosaic Method for Spaceborne ScanSAR Images Based on Homography Matrix Compensation
Tian, J., Wu, Y., Cai, Y., et al. (2021) · Remote Sensing · doi:10.3390/rs13152866 · Cited by 14
Keypoint Selection Algorithm for Palmprint Recognition with SURF
Ignat, A., & Păvăloi, I. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.08.028 · Cited by 14
3D Recognition Based on Sensor Modalities for Robotic Systems: A Survey
Manzoor, S., Joo, S.-H., Kim, E., Bae, S.-H., In, G.-G., Pyo, J.-W., & Kuc, T. (2021) · Sensors · doi:10.3390/s21217120 · Cited by 15
Indoor Atlas Service as a Tool for Building an Interior Navigation System
Štancel, M., Hurtuk, J., Hulič, M., & Červeňák, J. (2021) · Acta Polytechnica Hungarica · doi:10.12700/aph.18.9.2021.9.6 · Cited by 16
“The server component uses the Speeded Up Robust Features comparison algorithm [9], which provides fast, memory-efficient extraction and description of recognition points from a local photograph.”
MethodA study on recognizing multi-real world object and estimating 3D position in augmented reality
Lee, T., Jung, C., Lee, K.-T., & Seo, S. (2021) · The Journal of Supercomputing · doi:10.1007/s11227-021-04161-0 · Cited by 19
“Scale invariant feature transform(SIFT) [9], speeded up robust features(SURF) [10], and oriented FAST and rotated BRIEF(ORB) [11] are the commonly used algorithms.”
MethodYang, C., Chen, Q., Yang, Y., Zhang, J., Wu, M., & Mei, K. (2022) · IEEE Access · doi:10.1109/access.2022.3144845 · Cited by 17
Hierarchical forest based fast online loop closure for low-latency consistent visual-inertial SLAM
Xie, H., Chen, W., & Wang, J. (2022) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2022.104035 · Cited by 14
Visual Loop-Closure Detection via Prominent Feature Tracking
Papapetros, I. T., Balaska, V. E., & Gasteratos, A. C. (2022) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-022-01581-9 · Cited by 16
“integrated the tracking approach, creating a guided feature selection procedure to trace SURF (speeded up robust features) [9] through multiple sequential frames using the Kanade-Lucas-Tomasi (KLT) point tracker [41] and used the average of their descriptors to produce the visual words.”
BackgroundMethodIvanov, I. E., Yeh, L.-H., Pérez-Bermejo, J. A., Byrum, J. R., Kim, J. Y. S., Leonetti, M. D., & Mehta, S. B. (2022) · Biomedical Optics Express · doi:10.1364/boe.455770 · Cited by 12
Recent Object Detection Techniques: A Survey
Diwakar, & Raj, D. (2022) · International Journal of Image Graphics and Signal Processing · doi:10.5815/ijigsp.2022.02.05 · Cited by 21
“Directly after in 2006, SURF was proposed by H. Bay et al.[4]. inspired by the scale-invariant feature transform (SIFT) descriptor.”
Consistent Data Association in Multi-robot Systems with Limited Communications
Aragüés, R., Montijano, E., & Sagüés, C. (2011) · The MIT Press eBooks · doi:10.7551/mitpress/9123.003.0017 · Cited by 14
Hussain, M., Ali, N., & Hong, J. (2022) · Sensors · doi:10.3390/s22176610 · Cited by 18
“It has good robustness to angle change and noise affine transformation, which is crucial in the ADSs domain.”
BackgroundA Fine-Grained Attention Model for High Accuracy Operational Robot Guidance
Chu, Y., Feng, D., Liu, Z., Zhang, L., Zhao, Z., Wang, Z., Feng, Z., & Xia, X. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3206388 · Cited by 15
A Coupled Visual and Inertial Measurement Units Method for Locating and Mapping in Coal Mine Tunnel
Zhu, D., Ji, K., Wu, D. M., & Liu, S. (2022) · Sensors · doi:10.3390/s22197437 · Cited by 16
Hierarchical Clustering-Based Image Retrieval for Indoor Visual Localization
Feng, G., Jiang, Z., Tan, X., & Cheng, F. (2022) · Electronics · doi:10.3390/electronics11213609 · Cited by 15
“Rublee, E.; Rabaud, V.; Konolige, K.; Bradski, G. ORB: An efficient alternative to SIFT or SURF.”
MethodInfluentialConvolutional Hough Matching Networks for Robust and Efficient Visual Correspondence
Min, J., Kim, S., & Cho, M. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3233884 · Cited by 24
A Novel 3D Topography Stitching Algorithm Based on Reflectance and Multimap
Lemesle, J., Guibert, R., & Bigerelle, M. (2023) · Applied Sciences · doi:10.3390/app13020857 · Cited by 14
Infrared and Visible Image Homography Estimation Using Multiscale Generative Adversarial Network
Luo, Y., Wang, X., Wu, Y., et al. (2023) · Electronics · doi:10.3390/electronics12040788 · Cited by 14
Spatial Visualization Based on Geodata Fusion Using an Autonomous Unmanned Vessel
Włodarczyk-Sielicka, M., Połap, D., Prokop, K., et al. (2023) · Remote Sensing · doi:10.3390/rs15071763 · Cited by 14
Scene Reconstruction Algorithm for Unstructured Weak-Texture Regions Based on Stereo Vision
Chen, M., Duan, Z., Lan, Z., et al. (2023) · Applied Sciences · doi:10.3390/app13116407 · Cited by 14
Ren, K., Sun, W., Meng, X., Yang, G., Peng, J., Huang, J., & Li, J. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3286858 · Cited by 19
Matching between Different Image Domains
Toth, C. K., Ju, H., & Grejner‐Brzezinska, D. A. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24393-6_4 · Cited by 14
Contrast Invariant Interest Point Detection by Zero-Norm LoG Filter
Miao, Z., Jiang, X., & Yap, K. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2470598 · Cited by 14
“The SURF detector uses the box filters and the integral images to further accelerate the Hessian-Laplace detector.”
BackgroundMethodInfluentialVisual Topological Map Building in Self-similar Environments
Goedemé, T., Tuytelaars, T., & Gool, L. V. (2008) · Springer eBooks · doi:10.1007/978-3-540-79142-3_16 · Cited by 14
Self-citationSee ColOr: Seeing Colours with an Orchestra
Deville, B., Bologna, G., Vinckenbosch, M., & Pun, T. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-00437-7_10 · Cited by 17
A Robust Technique for Feature-based Image Mosaicing using Image Fusion
Bind, V. S., Muduli, P. R., & Pati, U. C. (2013) · Cited by 14
Robot Head Pose Detection and Gaze Direction Determination Using Local Invariant Features
Ruíz-del-Solar, J., & Loncomilla, P. (2009) · Advanced Robotics · doi:10.1163/156855308x397497 · Cited by 14
“Taking into account the impressive development of object recognition algorithms based on local invariant features in recent years [13–17], and the fact that, for a given robot model, head and face variability is much smaller than in humans, we believe that matching against reference images using…”
BackgroundGradient preserving quantization
Makar, M. A., Lakshman, H., Chandrasekhar, V., et al. (2012) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2012.6467407 · Cited by 14
Dynamic selection of a feature-rich query frame for mobile video retrieval
Chen, D., Cheung, N., Tsai, S. S., et al. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5650653 · Cited by 14
“The second row in that figure plots the number of SURF features per frame versus the time offset from t0.”
BackgroundMethodInfluentialPeriodic motion detection with ROI-based similarity measure and extrema-based reference selection
Li, G., Han, X., Lin, W., et al. (2012) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2012.6311341 · Cited by 14
“In this paper, for an input frame, we first calculate the SURF feature vectors for the interest points [11] in each ROI and then sum them up for representing this ROI [11].”
MethodBadura, S., & Foltán, S. (2010) · Proceedings of the International Multiconference on Computer Science and Information Technology · doi:10.1109/imcsit.2010.5679924 · Cited by 14
Detection of potential mosquito breeding sites based on community sourced geotagged images
Agarwal, A., Chaudhuri, U., Chaudhuri, S., & Seetharaman, G. S. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2058121 · Cited by 19
Kandel, B. M., Wang, D. J. J., Detre, J. A., Gee, J. C., & Avants, B. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2014.10.052 · Cited by 13
“…(Ranzato et al., 2007; Aharon et al., 2006; Mairal et al., 2008), rotation-invariant feature transforms (Lowe, 1999; Ke and Sukthankar, 2004; Bay et al., 2006; Toews and Wells, 2013), dictionary learning methods (Chen et al., 2012; Barthelemy et al., 2012), and modality synthesis algorithms…”
BackgroundCORRELATION-EXTREME VISUAL NAVIGATION OF UNMANNED AIRCRAFT SYSTEMS BASED ON SPEED-UP ROBUST FEATURES
Kharchenko, V. P., & Mukhina, M. P. (2014) · Aviation · doi:10.3846/16487788.2014.926645 · Cited by 14
“Here the modified speed-up robust feature (SURF) method (Bay et al. 2006) will be considered for the practical implementation aboard the UAS.”
MethodNear-duplicate keyframe retrieval by semi-supervised learning and nonrigid image matching
Zhu, J., Hoi, S. C. H., Lyu, M. R.-T., & Yan, S. (2011) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/1870121.1870125 · Cited by 14
Clustering and retrieval of video shots based on natural stimulus fMRI
Han, J., Ji, X., Hu, X., Han, J., & Liu, T. (2014) · Neurocomputing · doi:10.1016/j.neucom.2013.11.052 · Cited by 13
ONSUM: A system for generating online navigation summaries
Girdhar, Y., & Dudek, G. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5650315 · Cited by 18
Sharma, K., Kim, S. G., & Singh, M. P. (2012) · International Journal of Precision Engineering and Manufacturing · doi:10.1007/s12541-012-0179-z · Cited by 14
Vision-based adaptive grasping of a humanoid robot arm
Song, K., & Tsai, S.-C. (2012) · IEEE International Conference on Automation and Logistics (ICAL) · doi:10.1109/ical.2012.6308189 · Cited by 14
GPU-based fast scale invariant interest point detector
Xie, H., Gao, K., Zhang, Y., et al. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5494898 · Cited by 14
Visual odometry based on Random Finite Set Statistics in urban environment
Zhang, F., Chen, G., Stähle, H., Buckl, C., & Knoll, A. (2012) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2012.6232201 · Cited by 15
“Additionally, we use SURF [6](Speeded Up Robust Features) instead of SIFT to satisfy real-time constraints.”
MethodReal-time adaptive obstacle detection based on an image database
Morales, N., Toledo, J. T., Acosta, L., & Arnay, R. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.05.004 · Cited by 14
B-SIFT: A Binary SIFT Based Local Image Feature Descriptor
Ni, Z.-S. (2012) · International Conference on Digital Home (ICDH) · doi:10.1109/icdh.2012.69 · Cited by 19
Herumurti, D., Uchimura, K., Koutaki, G., et al. (2013) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis.2013.24 · Cited by 14
“The SURF is a robust method for object recognition that introduced by Bay et al [6].”
MethodTechniques for efficient and effective transformed image identification
Awrangjeb, M., & Lu, G. (2009) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2009.07.004 · Cited by 14
Robust Registration of Remote Sensing Image Based on SURF and KCCA
Yan, W., She, H., & Yuan, Z. (2013) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-013-0324-x · Cited by 14
“Best known examples of feature based methods are Scale Invariant Feature Transform (SIFT) (Lowe 2004) and Speeded Up Robust Features (SURF) (Bay et al. 2008).”
MethodInfluentialSchaub, A., & Burschka, D. (2013) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2013.6629605 · Cited by 15
Wang, D., Wang, Z., Li, X., et al. (2007) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc.2007.105 · Cited by 14
Robust digital image watermarking using interest points and DFT domain
Cedillo-Hernández, M., Garcia-Ugalde, F. J., Nakano-Miyatake, M., et al. (2012) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2012.6256390 · Cited by 14
PIRF-Nav 2: Speeded-up online and incremental appearance-based SLAM in an indoor environment
Tongprasit, N., Kawewong, A., & Hasegawa, O. (2011) · Proceedings · doi:10.1109/wacv.2011.5711496 · Cited by 14
A robust SVM classification framework using PSM for multi-class recognition
Chen, J., Takiguchi, T., & Ariki, Y. (2015) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-015-0061-x · Cited by 16
Object tracking and visual servoing using features computed from local feature descriptor
Anh, L. T., & Song, J.-B. (2010) · doi:10.1109/iccas.2010.5669666 · Cited by 14
Feature vector field and feature matching
Wu, F. C., Wang, Z., & Wang, X. G. (2010) · Pattern Recognition · doi:10.1016/j.patcog.2010.05.001 · Cited by 14
Automatic generation of privacy-protected videos using background estimation
Nakashima, Y., Babaguchi, N., & Fan, J. (2011) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2011.6011955 · Cited by 14
Outdoor Environment Monitoring with Unmanned Aerial Vehicles
Piciarelli, C., Micheloni, C., Martinel, N., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41184-7_29 · Cited by 14
“For this scope, we adopted the widely used SURF features [1].”
MethodDiscrepancy Norm as Fitness Function for Defect Detection on Regularly Textured Surfaces
Stübl, G., Bouchot, J.-L., Haslinger, P., & Moser, B. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-32717-9_43 · Cited by 14
Regularized Bayesian Metric Learning for Person Re-identification
Liong, V. E., Lu, J., & Ge, Y. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16199-0_15 · Cited by 14
Ege, Y., Nazlıbilek, S., Kakilli, A., Çıtak, H., Kalender, O., Ertürk, K. L., Şengül, G., & Karacor, D. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2015.2488838 · Cited by 14
“In order to solve this problem, image matching methods such as Lowe’s scale-invariant feature transform (SIFT) method [12], principal component analysis (PCA)SIFT method [13], and speeded-up feature transform (SURF) [14] are proposed in the literature, and those algorithms are applied in many fields.”
MethodMulti-resolution map building and loop closure with omnidirectional images
Korrapati, H., & Mezouar, Y. (2016) · Autonomous Robots · doi:10.1007/s10514-016-9560-6 · Cited by 14
“We make use of Vector of Locally Aggregated Descriptors (VLAD) for node level loop closure and image sequence partitioning, and local image descriptors (like SIFT, SURF, etc)forimagelevelloopclosure(ILLC).”
MethodInfluentialREAL-TIME OBJECT DETECTION AND TRACKING FOR INDUSTRIAL APPLICATIONS
(2008) · Proceedings of the Third International Conference on Computer Vision Theory and Applications · doi:10.5220/0001074903370345 · Cited by 14
Fast Hierarchical Template Matching Strategy for Real-Time Pose Estimation of Texture-Less Objects
Ye, C., Li, K., Jia, L., Zhuang, C., & Xiong, Z. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-43506-0_19 · Cited by 16
“For 2D image, SIFT [2], SURF [3], ORB [4], FREAK, [5] and HOG [6] are the most popular features which is invariant to changes in scale, rotation and illumina‐ tion.”
MethodMaking Sense of Mobile Eye-Tracking Data in the Real-World
Fong, A., Hoffman, D., & Ratwani, R. M. (2016) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/1541931213601362 · Cited by 14
“The vision algorithms, such as SIFT and SURF, rely on object dictionaries that can be used to match images in the eye-tracking data (Bay, 2006; Lowe, 2004).”
MethodA review on vision-based pedestrian detection
Zheng, G., & Chen, Y. (2012) · IEEE Global High Tech Congress on Electronics (GHTCE) · doi:10.1109/ghtce.2012.6490122 · Cited by 20
Image forgery detection using segmentation and swarm intelligent algorithm
Zhao, F., Shi, W., Qin, B., & Liang, B. (2017) · Wuhan University Journal of Natural Sciences · doi:10.1007/s11859-017-1227-4 · Cited by 14
A novel multi-cue integration system for efficient human fall detection
Wang, X., Liu, H., & Liu, M. (2016) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2016.7866509 · Cited by 14
3D gesture-based interaction for immersive experience in mobile VR
Yousefi, S., Kidane, M., Delgado, Y. R., et al. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899949 · Cited by 14
CaPSuLe: A camera-based positioning system using learning
Moon, Y., Noh, S., Park, D., Luo, C., Shrivastava, A., Hong, S., & Palem, K. V. (2016) · IEEE International System-on-Chip Conference (SOCC) · doi:10.1109/socc.2016.7905476 · Cited by 14
Akkas, O., Lee, C. H., Hu, Y. H., et al. (2017) · Ergonomics · doi:10.1080/00140139.2017.1346208 · Cited by 14
Prediction of pain intensity using multimedia data
Singh, S., Tiwari, S., Abidi, A., & Singh, A. (2017) · Multimedia tools and applications · doi:10.1007/s11042-017-4718-6 · Cited by 11
Energy Efficient Object Detection in Camera Sensor Networks
Đào, T. A., Khalil, K., Roy–Chowdhury, A. K., Krishnamurthy, S. V., & Kaplan, L. (2017) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2017.152 · Cited by 17
“For each frame, we extract the HOG features [3] and SURF (speeded-up robust features) key-points7 [28] of the image using OpenCV.”
MethodAn, F., Zhang, X., Luo, A., Chen, L., & Mattausch, H. J. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2726564 · Cited by 14
“The templates of the Haar-like descriptor for SURF as proposed in [6] are used for local cell feature extraction of input images during recognition.”
BackgroundMethodShredded banknotes reconstruction using AKAZE points
Nabiyev, V. V., Yılmaz, S., Günay, A., et al. (2017) · Forensic Science International · doi:10.1016/j.forsciint.2017.07.014 · Cited by 14
“Step 1: The main orientation of the current keypoint is determined similar to SURF algorithm [30].”
MethodInfluentialIdentifying uncollected garbage in urban areas using crowdsourcing and machine learning
Singh, S., Mehta, K. S., Bhattacharya, N., et al. (2017) · IEEE Region 10 Symposium (TENSYMP) · doi:10.1109/tenconspring.2017.8070078 · Cited by 14
Bangla sign language interpretation using bag of features and Support Vector Machine
Uddin, J., Arko, F. N., Tabassum, N., et al. (2017) · International Conference on Electrical Information and Communication Technology (EICT) · doi:10.1109/eict.2017.8275173 · Cited by 14
“The bag of feature uses SURF (Speeded up Robust Feature) to compute the local features from the training set [11].”
MethodWide-angle image stitching using multi-homography warping
Xu, B., & Jia, Y. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296525 · Cited by 14
“The feature points were detected using SURF [22].”
MethodDesign and implementation of prototype service robot for shopping in a supermarket
Cheng, C.-H., Chen, C., Liang, J.-J., et al. (2017) · International Conference on Advanced Robotics and Intelligent Systems (ARIS) · doi:10.1109/aris.2017.8297181 · Cited by 14
“SURF uses the Hessian matrix as its base detector.”
BackgroundInfluentialNCC-Net: Normalized Cross Correlation Based Deep Matcher with Robustness to Illumination Variations
Subramaniam, A., Balasubramanian, P., & Mittal, A. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00215 · Cited by 21
An Efficient ORB based Face Recognition framework for Human-Robot Interaction
Vinay, A., Cholin, A. S., Bhat, A. D., Murthy, K. N. B., & Natarajan, S. (2018) · Procedia Computer Science · doi:10.1016/j.procs.2018.07.095 · Cited by 18
Bandwidth and Energy Efficient Image Sharing for Situation Awareness in Disasters
Zuo, P., Hua, Y., Sun, Y., Liu, X., Wu, J., Guo, Y., Xia, W., Cao, S., & Feng, D. (2018) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2018.2859930 · Cited by 14
“8, SIFT obtains the highest precision and the precision of SURF is close to that of SIFT.”
BackgroundInfluentialAssessing Image Retrieval Quality at the First Glance
Sun, S., Zhou, W., Tian, Q. C., Yang, M., & Li, H. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2864919 · Cited by 17
“For feature extraction, some early works aimed to enhance the image representation by designing hand-crafted features such as color correlogram [13], SIFT [18], and SURF [25].”
Real-Time Detection of Pedestrian Traffic Lights for Visually-Impaired People
Ghilardi, M. C., Simoes, G., Wehrmann, J., Manssour, I. H., & Barros, R. C. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489516 · Cited by 17
“One of those services is the pedestrian traffic light detection that was developed based on SURF (Speeded-Up Robust Features) [24].”
MethodConvolutional Neural Network Based Sensors for Mobile Robot Relocalization
Sinha, H., Patrikar, J., Dhekane, E. G., Pandey, G., & Kothari, M. (2018) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2018.8485921 · Cited by 17
“Some of the iconic examples of the feature representations used in these techniques are SIFT by [1], SURF by [2] and ORB by [3].”
MethodTraining CNNs from Synthetic Data for Part Handling in Industrial Environments
Andulkar, M. V., Hodapp, J., Reichling, T., et al. (2018) · 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2018.8560470 · Cited by 14
“Over the last decade, several methods like SIFT [1], SURF [2] and HOG [3] have been developed for object detection which use feature extraction and linear classifiers for making predictions.”
MethodA Deep Learning Approach to Sensory Navigation Device for Blind Guidance
Ying, J. J.-C., Li, C., Wu, G.-W., Li, J., Chen, W.-J., & Yang, D. (2018) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc/smartcity/dss.2018.00201 · Cited by 17
An Accelerated Sequential PCP-Based Method for Ground-Moving Objects Detection From Aerial Videos
ElTantawy, A., & Shehata, M. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2923376 · Cited by 18
“Moreover, using feature-based matching, such as SURF [76],”
MethodSonar image registration for swarm AUVs navigation: Results from SWARMs project
Leblond, I., Tauvry, S., & Pinto, M. A. (2019) · Journal of Computational Science · doi:10.1016/j.jocs.2019.07.008 · Cited by 15
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.