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 2,501–2,600 of 14,752
Vision-Based Human Detection Techniques: A Descriptive Review
Sumit, S. S., Rambli, D. R. A., & Mirjalili, S. (2021) · IEEE Access · doi:10.1109/access.2021.3063028 · Cited by 35
“A large number of standard features have been offered by computer vision community for object detection, for example ‘‘scale-Invariant Feature Transform (SIFT)’’ [50], ‘‘Speeded Up Robust Features (SURF)’’ [51] and ‘‘Histogram of oriented Gradients (HoG)’’ [52].”
BackgroundMethodInfluentialTracking‐DOSeqSLAM: A dynamic sequence‐based visual place recognition paradigm
Tsintotas, K. A., Bampis, L., Gasteratos, A. C., & FIET (2021) · IET Computer Vision · doi:10.1049/cvi2.12041 · Cited by 29
Monocular Visual-Inertial Navigation for Dynamic Environment
Fu, D., Xia, H., & Qiao, Y. (2021) · Remote Sensing · doi:10.3390/rs13091610 · Cited by 29
Debnath, R., & Bhowmik, M. K. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103165 · Cited by 34
Confidence-Based 6D Object Pose Estimation
Huang, W.-L., Hung, C.-Y., & Lin, I. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3092149 · Cited by 33
A Survey on Perspective-n-Point Problem
Pan, S., & Wang, X. (2021) · Chinese Control Conference (CCC) · doi:10.23919/ccc52363.2021.9549863 · Cited by 34
“Because perfect results can not always be obtained due to scaling, illumination, shadow and occlusion in image feature detection and matching approaches, such as SURF [20], BRISK [21] and ORB [22].”
BackgroundA Visual Navigation System for UAV under Diverse Illumination Conditions
Jiang, H., Hao, Y., Zou, F., Lin, F., & Han, S. (2021) · Applied Artificial Intelligence · doi:10.1080/08839514.2021.1985799 · Cited by 29
“Using SIFT (Lowe 2004) (Lowe 2004), SURF (Bay 2006) (Bay, Tuytelaars, and Gool 2006), and GMS (Bian 2017) (Bian et al. 2017) algorithm to match the pre-processed images with the reference images and calculating the average number of successful matching points.”
MethodAudenhaege, L. V., Matabos, M., Brind’Amour, A., et al. (2022) · Progress In Oceanography · doi:10.1016/j.pocean.2022.102791 · Cited by 28
Machine learning-based approaches for tomato pest classification
Pattnaik, G., & Parvathy, K. (2022) · TELKOMNIKA (Telecommunication Computing Electronics and Control) · doi:10.12928/telkomnika.v20i2.19740 · Cited by 28
“The SURF is a novel scale and rotation invariant point detector and descriptor [21].”
Semantic scan context: a novel semantic-based loop-closure method for LiDAR SLAM
Li, L., Kong, X., Zhao, X., Huang, T., & Liu, Y. (2022) · Autonomous Robots · doi:10.1007/s10514-022-10037-w · Cited by 29
“In the field of visual SLAM, the loop-closure detection based on local features (Bay et al. 2006; Rublee et al. 2011) and Bag-of-Words (BoW) (Galvez-López and Tar-dos 2012)have been very mature and have been widely used (Mur-Artal and Tardós 2017; Qin et al. 2018).”
MethodAn interactive time series image analysis software for dendritic spines
Argunşah, A. Ö., Erdil, E., Ghani, M. U., Ramiro‐Cortés, Y., Hobbiss, A. F., Karayannis, T., Çetin, M., Israely, I., & Ünay, D. (2022) · Scientific Reports · doi:10.1038/s41598-022-16137-y · Cited by 23
MobileSP: An FPGA-Based Real-Time Keypoint Extraction Hardware Accelerator for Mobile VSLAM
Liu, Y., Li, J., Huang, K., Li, X., Qi, X., Chang, L., Long, Y., & Zhou, J. (2022) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2022.3190300 · Cited by 32
“For example, the SURF [10] leverages square-shaped filter instead of Difference of Gaussian as an approximate replacement of scale-normalized Laplacian of Gaussian, which significantly speeds up the keypoint detection.”
MethodETR: An Efficient Transformer for Re-ranking in Visual Place Recognition
Zhang, H., Chen, X., Jing, H., Zheng, Y., Wu, Y., & Jin, C. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00562 · Cited by 43
“The local descriptors can also be treated as key-point descriptors or regional descriptors, including the traditional hand-crafted local features ( e.g ., SIFT [23], SURF [4]) and more recent learning-based features ( e.g ., DELF [24], R2D2 [30]).”
BackgroundRelation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems
Ghosh, A., Shanmugalingam, K., & Lin, W.-Y. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00482 · Cited by 35
Text Localization and Recognition in Complex Scenes Using Local Features
Zheng, Q., Chen, K., Zhou, Y., Gu, C., & Guan, H. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19318-7_10 · Cited by 31
A study on fast SIFT image mosaic algorithm based on compressed sensing and wavelet transform
Xie, X., Xu, Y., Liu, Q., et al. (2015) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-015-0319-2 · Cited by 28
Appearance-based mapping and localization for mobile robots using a feature stability histogram
Bacca, E., Salví, J., & Cufí, X. (2011) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2011.06.008 · Cited by 29
“features using the nearest neighbor method described in [28].”
MethodResultInfluentialEvolutionary granular approach for recognizing faces altered due to plastic surgery
Bhatt, H. S., Bharadwaj, S., Singh, R., Mayank Vatsa, A., & Afzel Noore, B. (2011) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2011.5771337 · Cited by 30
“Further, two feature extractors, namely Uniform Circular Local Binary Pattern (UCLBP) [13] and Speeded Up Robust Features (SURF) [6], are used for extracting discriminating information from face granules.”
BackgroundMethodObject recognition for blind people based on features extraction
Jabnoun, H., Benzarti, F., & Amiri, H. (2014) · IEEE International Conference on Image Processing, Applications and Systems (IPAS) · doi:10.1109/ipas.2014.7043293 · Cited by 28
A Novel Image Representation via Local Frequency Analysis for Illumination Invariant Stereo Matching
Mouats, T., Aouf, N., & Richardson, M. A. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2426014 · Cited by 30
Rabatel, G., & Labbé, S. (2016) · Precision Agriculture · doi:10.1007/s11119-016-9437-x · Cited by 31
Robust handwriting extraction and lecture video summarization
Lee, G. C., Yeh, F.-H., Chen, Y., et al. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3353-y · Cited by 28
Traffic video surveillance: Vehicle detection and classification
Saran, K. B., & Sreelekha, G. (2015) · doi:10.1109/iccc.2015.7432948 · Cited by 28
“Speeded up Robust Feature (SURF) [11] is another image descriptor which use some interest points to identify objects.”
BackgroundB-HMAX: A fast binary biologically inspired model for object recognition
Zhang, H., Lu, Y., Kang, T., et al. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.08.051 · Cited by 28
Hybrid Teams: Flexible Collaboration Between Humans, Robots and Virtual Agents
Schwartz, T., Zinnikus, I., Krieger, H., Bürckert, C., Folz, J., Kiefer, B., Hevesi, P., Lüth, C., Pirkl, G., Spieldenner, T., et al. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-45889-2_10 · Cited by 30
Extraction of accurate tie points for automated pose estimation of close-range blocks
Barazzetti, L., Fabio Remondino, A., & Scaioni, M. (2010) · Virtual Community of Pathological Anatomy (University of Castilla La Mancha) · Cited by 28
Loop Detection and Correction of 3D Laser-Based SLAM with Visual Information
Zhu, Z., Yang, S., Dai, H., & Li, F. (2018) · Computer Animation (CA) · doi:10.1145/3205326.3205357 · Cited by 28
“[23] create a loop closure detection mechanism using bags of words [14] with SURF [1] features.”
MethodWang, D., Liu, H., & Cheng, X. (2018) · Sensors · doi:10.3390/s18072243 · Cited by 27
Underwater Image Dehazing via Unpaired Image-to-image Translation
Cho, Y., Jang, H., Malav, R., Pandey, G., & Kim, A. (2020) · International Journal of Control Automation and Systems · doi:10.1007/s12555-019-0689-x · Cited by 29
“We chose Speeded Up Robust Features (SURF) [31] detector and descriptor.”
MethodWang, L., Sun, M., Liu, J., Cao, L., & Ma, G. (2020) · Remote Sensing · doi:10.3390/rs12203339 · Cited by 30
Time-Variant Registration of Point Clouds Acquired by a Mobile Mapping System
Han, J.-Y., Chen, C., & Lo, C.-T. (2013) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2013.2252417 · Cited by 28
Intelligent Multimedia Group of Tsinghua University at TRECVID 2006
Cao, J., Lan, Y., Li, J., et al. (2006) · TRECVID · Cited by 28
DeepDOF-SE: affordable deep-learning microscopy platform for slide-free histology
Jin, L., Tang, Y., Coole, J. B., Tan, M. T., Zhao, X., Badaoui, H., Robinson, J. T., Williams, M. D., Vigneswaran, N., Gillenwater, A. M., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-47065-2 · Cited by 36
GeoFormer: An Effective Transformer-Based Siamese Network for UAV Geolocalization
Li, Q., Yang, X., Fan, J., Lu, R., Tang, B., Wang, S., & Su, S. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3392812 · Cited by 29
Local All-Pair Correspondence for Point Tracking
Cho, S., Huang, J., Nam, J., An, H., Kim, S., & Lee, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72684-2_18 · Cited by 94
Robust SAR Image Registration Based on Edge Matching and Refined Coherent Point Drift
Zhang, H., Ni, W., Yan, W., et al. (2015) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2015.2451396 · Cited by 27
“Methods such as scale-invariant feature transform (SIFT) [5] and the speeded-up robust feature (SURF) [6] can automatically detect reliable image feature points whose feature descriptors are invariant to scale and rotation transform.”
MethodSpatiotemporal Descriptor for Wide-Baseline Stereo Reconstruction of Non-rigid and Ambiguous Scenes
Trulls, E., Sanfeliu, A., & Moreno-Noguer, F. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33712-3_32 · Cited by 28
A fast affine-invariant features for image stitching under large viewpoint changes
Ma, X., Liu, D., Zhang, J., & Xin, J. L. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.10.045 · Cited by 28
Vehicle Detection from UAVs by Using SIFT with Implicit Shape Model
Chen, X., & Meng, Q. (2013) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2013.535 · Cited by 28
“In SURF, it creates a “stack” is created without the sampling for higher levels in the pyramid [11].”
BackgroundMethodFeature point detection under extreme lighting conditions
Přibyl, B., Chalmers, A. G., & Zemčík, P. (2012) · Spring Conference on Computer Graphics · doi:10.1145/2448531.2448550 · Cited by 28
Arbitrary Category Classification of Websites Based on Image Content
Akusok, A., Miché, Y., Karhunen, J., Björk, K.-M., Nian, R., & Lendasse, A. (2015) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2015.2405317 · Cited by 31
SUPER: towards real-time event recognition in internet videos
Jiang, Y. (2012) · International Conference on Multimedia Retrieval · doi:10.1145/2324796.2324805 · Cited by 28
Point-pattern matching method using SURF and Shape Context
Gui, Y., Su, A., & Du, J. (2012) · Optik · doi:10.1016/j.ijleo.2012.05.037 · Cited by 26
A system for large-scale analysis of distributed cameras
Kaseb, A. S., Berry, E., Koh, Y., et al. (2014) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2014.7032135 · Cited by 27
FRIF: Fast Robust Invariant Feature
Wang, Z., Fan, B., & Wu, F. (2013) · British Machine Vision Conference (BMVC) · doi:10.5244/c.27.16 · Cited by 25
Visual orientation inhomogeneity based scale-invariant feature transform
Zhong, S.-H., Liu, Y., & Chen, Q. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.01.012 · Cited by 27
“So our goal is to develop both a detector and descriptor that, in comparison to the state-of-the-art, is fast to compute without sacrificing much performance (Bay et al., 2008).”
BackgroundMethodObtaining Liftoff Indoors: Autonomous Navigation in Confined Indoor Environments
Shen, S., Michael, N., & Kumar, V. (2013) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2013.2253172 · Cited by 27
Progressively weighted affine adaptive correlation matching for quasi-dense 3D reconstruction
Shin, D., & Müller, J. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.03.023 · Cited by 25
“The third experiment is more focussed on the comparison with SURF matching result [33].”
BackgroundSavchenko, A., & Khokhlova, Y. I. (2014) · Optical Memory and Neural Networks · doi:10.3103/s1060992x14010068 · Cited by 28
“SVM, kNN, MLP classified image eigenvectors (the result of the PCA), which are common tools for audiovisual speech recognition [10, 22], popular SURF descrip tors [21] and our weighted HOG (3)–(7) together with the kNN and the SVM were used as features.”
BackgroundMethodMaddern, W., Stewart, A. D., & Newman, P. M. (2014) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2014.6856471 · Cited by 28
“Recent successful approaches to robust image patch features [3], [12], [13] compute descriptors based on combinations of gradients and histograms of local greyscale patches around the point of interest.”
BackgroundAn Energy Efficient Full-Frame Feature Extraction Accelerator With Shift-Latch FIFO in 28 nm CMOS
Jeon, D., Henry, M. B., Kim, Y., et al. (2014) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2014.2309692 · Cited by 27
“The authors of [8] claim it achieves identical or even superior extraction quality while”
InfluentialArora, A., Gupta, A., Bagmar, N., Mishra, S., & Bhattacharya, A. (2012) · CLEF (Online Working Notes/Labs/Workshop) · Cited by 39
Template Matching via Densities on the Roto-Translation Group
Bekkers, E. J., Loog, M., Romeny, B. M. T. H., & Duits, R. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2652452 · Cited by 31
Wang, C., Yuan, J., & Xie, L. (2017) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2017.8023500 · Cited by 32
Dress Like a Star: Retrieving Fashion Products from Videos
García, N., & Vogiatzis, G. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.270 · Cited by 27
SnapLink: Fast and Accurate Vision-Based Appliance Control in Large Commercial Buildings
Chen, K., Fürst, J., Kolb, J., Kim, H., Jin, X., Culler, D., & Katz, R. H. (2018) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3161173 · Cited by 28
“This is because of the robust nature of salient features [5] as well as the auto exposure adjustment in modern smartphone cameras.”
BackgroundMethodInfluentialA Leaf Recognition Approach to Plant Classification Using Machine Learning
Ali, R. A., Hardie, R. C., & Essa, A. E. (2018) · IEEE National Aerospace and Electronics Conference (NAECON) · doi:10.1109/naecon.2018.8556785 · Cited by 31
“SURF is more stable and reputable than their Harrisbased counterparts [14].”
BackgroundMethodVision-based UAVs Aerial Image Localization: A Survey
Xu, Y., Pan, L., Du, C., Li, J., Jing, N., & Wu, J. (2018) · ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery (GeoAI) · doi:10.1145/3281548.3281556 · Cited by 38
“However, SIFT runs slowly due to its large amount of information and has been improved by different researchers to speed up, such as PCA-SIFT[34], BRISK[38], SURF[4], ORB[58].”
MethodLarge-scale and rotation-invariant template matching using adaptive radial ring code histograms
Yang, H. S., Huang, C., Wang, F., Song, K., Zheng, S., & Yin, Z. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.03.003 · Cited by 29
Lou, Y., Duan, L., Wang, S., Chen, Z., Bai, Y., Chen, C. W., & Gao, W. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2916488 · Cited by 25
A Novel Key-Point Detector Based on Sparse Coding
Hong-Phuoc, T., & Guan, L. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2934891 · Cited by 25
“We first compare the average repeatability of the proposed detector with popular hand-crafted detectors such as SIFT [3], SURF [4], MSER [5], SFOP [6], Hessian Laplace [33], Harris Laplace [33], Hessian Affine [33] and Harris Affine [33].”
BackgroundMethodInfluentialResearch on Binocular Visual System of Robotic Arm Based on Improved SURF Algorithm
Sheng, H., Wei, S., Yu, X., & Tang, L. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2951601 · Cited by 27
“SURF algorithm is an effective feature point extraction and matching algorithm, and its high efficiency and high stability performance beyond the same kind of algorithm [11], so this paper adopted SURF algorithm to extract and match the feature points of the captured image.”
MethodEfficient subaperture stitching method for measurement of large area microstructured topography
Chen, S., Lu, W., Chen, W., et al. (2019) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2019.105974 · Cited by 27
Automatic Discovery of Political Meme Genres with Diverse Appearances
Theisen, W., Brogan, J., Thomas, P. B., Moreira, D., Phoa, P., Weninger, T., & Scheirer, W. J. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v15i1.18097 · Cited by 34
“The specific feature representation used is a 64-dimensional SURF feature [1], which is a compact representation designed for very fast matching.”
MethodLi, X., Yang, J., & Ma, J. (2020) · IEEE Access · doi:10.1109/access.2020.2982560 · Cited by 29
Li, D., Yang, W., Shi, X., Guo, D., Long, Q., Qiao, F., & Wei, Q. (2020) · IEEE Access · doi:10.1109/access.2020.2989480 · Cited by 27
A review on visual content-based and users’ tags-based image annotation: methods and techniques
Bouchakwa, M., Ayadi, Y., & Amous, I. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08862-1 · Cited by 33
A Pipeline for 3-D Object Recognition Based on Local Shape Description in Cluttered Scenes
Tao, W., Hua, X., Yu, K., Chen, X., & Zhao, B. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2998683 · Cited by 29
Zaatari, S. E., Wang, Y., Li, W., & Peng, Y. (2020) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2020.102109 · Cited by 28
The role of homing in visual topological navigation
Liu, M., Pradalier, C., Pomerleau, F., & Siegwart, R. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385640 · Cited by 27
Pixel-Perfect Structure-From-Motion With Featuremetric Refinement
Sarlin, P.-E., Lindenberger, P., Larsson, V., & Pollefeys, M. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3237269 · Cited by 40
Learning Deep Local Features with Multiple Dynamic Attentions for Large-Scale Image Retrieval
Wu, H., Wang, M., Zhou, W., & Li, H. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01122 · Cited by 35
HarrisZ+: Harris corner selection for next-gen image matching pipelines
Bellavia, F., & Mishkin, D. (2022) · Pattern Recognition Letters · doi:10.1016/j.patrec.2022.04.022 · Cited by 33
“This solution was originally employed by the Speeded-Up Robust Feature (SURF) detector (Bay et al., 2008) as alternative to SIFT.”
A CNN-Based Advertisement Recommendation through Real-Time User Face Recognition
Kim, G., Choi, I., Li, Q., & Kim, J. (2021) · Applied Sciences · doi:10.3390/app11209705 · Cited by 37
Das, S. K., Roy, P., & Mishra, A. K. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6690 · Cited by 27
“(28) At the final step, histogram is generated using total gradient and orientation.”
BackgroundDetecting Fake News on Social Media
Shu, K., & Liu, H. (2019) · Synthesis Lectures on Data Mining and Knowledge Discovery · doi:10.2200/s00926ed1v01y201906dmk018 · Cited by 83
Li, Z., Wu, F., Hong, F., Gai, X., Cao, W., Zhang, Z., Yang, T.-M., Wang, J., Gao, S., & Peng, C. (2022) · Frontiers in Microbiology · doi:10.3389/fmicb.2022.823324 · Cited by 35
“…on the above qualitative diagnostic characteristics from orthopedists, three handcrafted features were extracted from spinal TB CT images, including three types of feature descriptors of the vertebral column in CT slices: SIFT (Lowe, 2004), SURF (Bay et al., 2006), and ORB (Rublee et al., 2011).”
MethodObject Detection in Indian Food Platters using Transfer Learning with YOLOv4
Pandey, D., Parmar, P., Toshniwal, G., Goel, M., Agrawal, V., Dhiman, S., Gupta, L., & Bagler, G. (2022) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew55742.2022.00021 · Cited by 29
Moghimi, A., Çelik, T., & Mohammadzadeh, A. (2022) · International Journal of Remote Sensing · doi:10.1080/01431161.2022.2102951 · Cited by 27
“To gain a thorough understanding of the original SURF and its scale representation, the reader is referred to read research works presented by Bay, Tuytelaars, and Van Gool (2006); Oyallon and Rabin (2015) and Evans (2009).”
MethodInfluentialHardware implementation of SLAM algorithms: a survey on implementation approaches and platforms
Eyvazpour, R., Shoaran, M., & Karimian, G. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10310-5 · Cited by 37
The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs
Rockwell, C., Johnson, J., & Fouhey, D. F. (2022) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv57658.2022.00028 · Cited by 52
Descriptor Learning for Omnidirectional Image Matching
Masci, J., Migliore, D., Bronstein, M. M., & Schmidhuber, J. (2013) · Studies in computational intelligence · doi:10.1007/978-3-642-44907-9_3 · Cited by 31
Becker, B. C., Yang, S., MacLachlan, R. A., & Riviere, C. N. (2012) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob.2012.6290813 · Cited by 31
“Speeded Up Robust Features (SURF) [27] keypoints are detected in one of the stereo images and matched from an initial frame to the most recent frame.”
BackgroundInfluentialResearch of image matching algorithm based on SURF features
Hui, D., & Yuan, H. D. (2012) · International Conference on Computer Science and Information Processing · doi:10.1109/csip.2012.6309059 · Cited by 27
Constant Time Joint Bilateral Filtering Using Joint Integral Histograms
Zhang, K., Lafruit, G., Lauwereins, R., & Gool, L. V. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2198220 · Cited by 27
Self-citationVisual Odometry through Appearance- and Feature-Based Method with Omnidirectional Images
García, D. V., Rojo, L. F., Gil, A., Castelló, L. P., & Reinoso, Ó. (2012) · Journal of Robotics · doi:10.1155/2012/797063 · Cited by 29
Learning reliable and efficient navigation with a humanoid
Oßwald, S., Hornung, A., & Bennewitz, M. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509420 · Cited by 27
“To integrate observations zt in the UKF, we extract the state of the art Speeded-Up Robust Features (SURF, [21]) from camera images as visual landmarks (see Fig.”
MethodRGB-D camera-based parallel tracking and meshing
Lieberknecht, S., Huber, A., Ilić, S., & Benhimane, S. (2011) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2011.6092380 · Cited by 36
Dynamic visual understanding of the local environment for an indoor navigating robot
Tsai, G., & Kuipers, B. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6385735 · Cited by 28
Robust online map merging system using laser scan matching and omnidirectional vision
Tungadi, F., Lui, W. L. D., Kleeman, L., & Jarvis, R. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5654446 · Cited by 27
“To resolve this issue, we intend to extend this system by calibrating the omnidirectional vision system using the proposed calibration method in [21] in order to compute the 3D location of distinctive SURF features [3] in the unwarped panoramic images.”
Method3-D object modeling from 2-D occluding contour correspondences by opti-acoustic stereo imaging
Babaee, M., & Negahdaripour, S. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2014.10.007 · Cited by 27
GPU-ASIFT: A fast fully affine-invariant feature extraction algorithm
Codreanu, V., Dong, F., Liu, B., Roerdink, J. B. T. M., Williams, D., Yang, P., & Yasar, B. (2013) · International Conference on High Performance Computing & Simulation (HPCS) · doi:10.1109/hpcsim.2013.6641456 · Cited by 29
Place recognition based on matching of planar surfaces and line segments
Cupec, R., Nyarko, E. K., Filko, D., Kitanov, A., & Petrovic, I. K. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364914548708 · Cited by 30
Analyzing and exploring feature detectors in images
Drews, P., de, R., & de Melo, A. (2011) · 2022 IEEE 20th International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin.2011.6034893 · Cited by 27
Visualization of Real-World Events with Geotagged Tweet Photos
Nakaji, Y., & Yanai, . (2012) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2012.53 · Cited by 27
“As visual features to represent tweet photos, we use color histogram and Bag-of-Features representation of SURF features [4] with the codebook the size of which is 2000.”
MethodTerrestrial photogrammetry without ground control points
Forlani, G., Pinto, L., Roncella, R., et al. (2013) · Earth Science Informatics · doi:10.1007/s12145-013-0127-1 · Cited by 27
Place recognition based on deep feature and adaptive weighting of similarity matrix
Li, Q., Li, K., You, X., Bu, S., & Liu, Z. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.03.029 · Cited by 27
“The other is to represent the image based on the local descriptors, like Scale Invariant Feature Transform (SIFT) [8], Speed-Up Robust Feature (SURF) [9, 10], which describe the salient patches around key points within the image.”
MethodJames, D. W., Belblidia, F., Eckermann, J., et al. (2016) · Computer-Aided Design and Applications · doi:10.1080/16864360.2016.1199751 · Cited by 27
“In addition, triangulation algorithms such as Lowe’s Scale-invariant feature transform SIFT [14] and its variations [5] have proved to be computationally efficient in correctly identifying and matching corresponding key points in a collection of photographs with different scales and transformations.”
MethodTwo-stage pooling of deep convolutional features for image retrieval
Zhi, T., Duan, L., Wang, Y., & Huang, T. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532802 · Cited by 32
“Traditionally, hand-crafted local features such as SIFT [1] and SURF [2] are aggregated to a global representation by methods such as Bag-of-Words (BoW) [3], Vector of Locally Aggregated Descriptors (VLAD) [4] and Fisher Vector (FV) [5].”
Method3D Reconstruction of Plant/Tree Canopy Using Monocular and Binocular Vision
Ni, Z., Burks, T., & Lee, W. S. (2016) · Journal of Imaging · doi:10.3390/jimaging2040028 · Cited by 27
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.