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 2,101–2,200 of 14,752
FusionEye: Perception Sharing for Connected Vehicles and its Bandwidth-Accuracy Trade-offs
Liu, H., Ren, P., Jain, S., et al. (2019) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/sahcn.2019.8824839 · Cited by 34
“Then we adopt other features with varying sizes and overhead, including SIFT [10], SURF [11], and color histograms of bounding box patches of the detected vehicles in a captured image to further associate vehicles from two separate views and analyze how these different features affect our merging accuracy as well as n…”
MethodImproved RANSAC features image‐matching method based on SURF
Liu, J., & Bu, F. (2019) · The Journal of Engineering · doi:10.1049/joe.2018.9198 · Cited by 34
A scene-adaptive descriptor for visual SLAM-based locating applications in built environments
Xu, L., Feng, C., Kamat, V. R., & Menassa, C. C. (2020) · Automation in Construction · doi:10.1016/j.autcon.2019.103067 · Cited by 40
Image Retrieval Based on a Multi-Integration Features Model
Chu, K., & Liu, G. (2020) · Mathematical Problems in Engineering · doi:10.1155/2020/1461459 · Cited by 38
“To avoid the requirement of accurate segmentation, some feature descriptors exhibit strength in object recognition, such as shape context [21], scale-invariant feature transform (SIFT) descriptors [22], histogram of oriented gradients [23], and SURF descriptors [24].”
MethodUniversal Face Photo-Sketch Style Transfer via Multiview Domain Translation
Peng, C., Wang, N., Li, J., & Gao, X. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3016502 · Cited by 37
“Instead of the HOG feature, there are many other hand-crafted features such as SURF [70] and SIFT [71], which can be used instead in our method.”
MethodTarget detection using features for sonar images
Tueller, P., Kastner, R., & Diamant, R. (2020) · IET Radar Sonar & Navigation · doi:10.1049/iet-rsn.2020.0224 · Cited by 34
Feature matching for multi-epoch historical aerial images
Zhang, L., Rupnik, E., & Marc Pierrot-deseilligny, A. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.10.008 · Cited by 46
“Other popular traditional features include ASIFT [10], SURF [11], Hessian Affine keypoint detector [12] and KAZE [13].”
MethodShi-Tomasi corner detector for cattle identification from muzzle print image pattern
Kaur, A., Kumar, M., & Jindal, M. K. (2022) · Ecological Informatics · doi:10.1016/j.ecoinf.2021.101549 · Cited by 45
Farmland Aerial Images Fast-Stitching Method and Application Based on Improved SIFT Algorithm
Liu, Y. Y., He, M. X., Wang, Y., et al. (2022) · IEEE Access · doi:10.1109/access.2022.3204657 · Cited by 34
Naeem, A., Anees, T., Ahmed, K. T., Naqvi, R. A., Ahmad, S., & Whangbo, T. K. (2022) · Complex & Intelligent Systems · doi:10.1007/s40747-022-00866-8 · Cited by 48
“In traditional CBIR techniques, color, shape and texturebased features are used to search relevant images [1, 2].”
MethodInfluentialDomain Adaptation for Time-Series Classification to Mitigate Covariate Shift
Ott, F., Rügamer, D., Heublein, L., Bischl, B., & Mutschler, C. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548167 · Cited by 55
“Classical DA methods range from feature selection [3, 70] (both domains share similarities in the features), distribution adaptation (distributions of both domains are different but share similarities), and subspace learning (a lower-dimensional shared representation).”
BackgroundLearning Pixel-wise Alignment for Unsupervised Image Stitching
Jia, Q., Feng, X., Liu, Y., Fan, X., & Latecki, L. J. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612298 · Cited by 50
Real-time hand status recognition from RGB-D imagery
Bagdanov, A. D., Bimbo, A. D., Seidenari, L., et al. (2012) · Cited by 34
Reducing redundancy in wireless capsule endoscopy videos
Lee, H.-G., Choi, M.-K., Shin, B., & Lee, S. (2013) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2013.02.009 · Cited by 33
EasySnap: real-time audio feedback for blind photography
White, S., Ji, H., & Bigham, J. P. (2010) · Adjunct proceedings of the 23nd annual ACM symposium on User interface software and technology · doi:10.1145/1866218.1866244 · Cited by 34
“We determined this distance to be ideal for both capturing an initial SURF feature set [2] and allowing blind users to physically orient themselves with respect to their subject.”
BackgroundAutomated surface deformations detection and marking on automotive body panels
Borsu, V., Yogeswaran, A., & Payeur, P. (2010) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2010.5584643 · Cited by 36
Comparison of different approaches to visual terrain classification for outdoor mobile robots
Zou, Y., Chen, W., Xie, L., & Wu, X. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2013.11.004 · Cited by 36
“Filitchkin and Byl (2012) applied BOVW to terrain classification based on SURF features (Bay et al., 2006) and SVM classifier.”
MethodAUTOMATIC REGISTRATION OF MULTIPLE LASER SCANS USING PANORAMIC RGB AND INTENSITY IMAGES
Alba, M. I., Barazzetti, L., Scaioni, M., et al. (2012) · 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-xxxviii-5-w12-49-2011 · Cited by 34
Training for Task Specific Keypoint Detection
Strecha, C., Lindner, A. J., Ali, K., & Fua, P. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03798-6_16 · Cited by 35
Kernel integral images: A framework for fast non-uniform filtering
Hussein, M. E., Porikli, F., & Davis, L. S. (2008) · 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/cvpr.2008.4587641 · Cited by 40
Utilizing Model Structure for Efficient Simultaneous Localization and Mapping for a UAV Application
Karlsson, R., Schön, T. B., Törnqvist, D., Conte, G., & Gustafsson, F. (2008) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero.2008.4526442 · Cited by 33
Visual odometry and mapping for Underwater Autonomous Vehicles
Botelho, S. S. D. C., Drews, P., Oliveira, G. L., & Figueiredo, M. D. S. (2009) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars.2009.5418320 · Cited by 39
Fine-Grained Product Class Recognition for Assisted Shopping
George, M., Mircic, D., Sörös, G., Flörkemeier, C., & Mattern, F. (2015) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2015.77 · Cited by 36
Robust Direct Visual Localisation using Normalised Information Distance
Pascoe, G., Maddern, W., & Newman, P. M. (2015) · British Machine Vision Conference (BMVC) · doi:10.5244/c.29.70 · Cited by 38
Action recognition with multi-scale trajectory-pooled 3D convolutional descriptors
Lu, X., Yao, H., Zhao, S., Sun, X., & Zhang, S. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5251-3 · Cited by 34
The performance evaluation of multi-image 3D reconstruction software with different sensors
Mousavi, V., Khosravi, M., Ahmadi, M., et al. (2018) · Measurement · doi:10.1016/j.measurement.2018.01.058 · Cited by 34
Stream Processing Dual-Track CGRA for Object Inference
Fan, X., Wu, D., Cao, W., Luk, W. W., & Wang, L. (2018) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2018.2797600 · Cited by 38
Classification of Breast Cancer Histopathological Images Using KAZE Features
Morillo, D., González, J., García‐Rojo, M., & Ortega, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-78759-6_26 · Cited by 38
Scalable Facial Image Compression with Deep Feature Reconstruction
Wang, S., Wang, S., Zhang, X., Wang, S., Ma, S., & Gao, W. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803255 · Cited by 34
Baguley, D., & Norman, M. (2001) · PubMed · Cited by 34
Combining visual features and Growing Neural Gas networks for robotic 3D SLAM
Viejo, D., García‐Rodríguez, J., & Cazorla, M. (2014) · Information Sciences · doi:10.1016/j.ins.2014.02.053 · Cited by 33
A Systematic Literature Review of Waste Identification in Automatic Separation Systems
Arbeláez-Estrada, J. C., Vallejo, P., Aguilar, J., Tabares, M. S., Ríos-Zapata, D., Ruiz-Arenas, S., & Vélez, E. R. (2023) · Recycling · doi:10.3390/recycling8060086 · Cited by 50
Semantic segmentation of satellite images with different building types using deep learning methods
Amirgan, B., & Erener, A. (2024) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2024.101176 · Cited by 33
Design and Verification of a Low-Cost Multispectral Camera for Precision Agriculture Application
Barjaktarović, M. Č., Santoni, M., & Bruzzone, L. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3377104 · Cited by 43
“As keypoint detectors, SIFT [54], SURF [55], or ORB [56] are the most common choices.”
MethodUAV‐based simultaneous localization and mapping in outdoor environments: A systematic scoping review
Wang, K., Kooistra, L., Pan, R., Wang, W., & Valente, J. R. P. (2024) · Journal of Field Robotics · doi:10.1002/rob.22325 · Cited by 45
“Currently, there are many different feature points (such as oriented fast and rotated brief [ORB] points, Rublee et al., 2011; scale ‐ invariant feature transform points, Lowe, 2004; speeded up robust features points, Bay et al., 2006) which can be used in visual odometry.”
BackgroundRobust traffic sign recognition with feature extraction and k-NN classification methods
Yan, H., Virupakshappa, K., & Oruklu, E. (2015) · IEEE International Conference on Electro Information Technology · doi:10.1109/eit.2015.7293386 · Cited by 33
“SURF is claimed as scale, rotation invariance and partial skew invariance [14].”
BackgroundArdizzone, E., Bruno, A., & Mazzola, G. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41181-6_78 · Cited by 41
Tag refinement in an image folksonomy using visual similarity and tag co-occurrence statistics
Lee, S., Neve, W. D., & Ro, Y. M. (2010) · Signal Processing Image Communication · doi:10.1016/j.image.2010.10.002 · Cited by 33
Spatio-temporal features for robust content-based video copy detection
Willems, G., Tuytelaars, T., & Gool, L. V. (2008) · Multimedia Information Retrieval · doi:10.1145/1460096.1460143 · Cited by 38
Self-citationFusion of Global and Local Motion Estimation for Distributed Video Coding
Abou-Elailah, A., Dufaux, F., Farah, J., et al. (2012) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2012.2203211 · Cited by 33
Matching Features Correctly through Semantic Understanding
Kobyshev, N., Riemenschneider, H., & Gool, L. V. (2014) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2014.15 · Cited by 32
Self-citationContent-Based Image Retrieval using SIFT for binary and greyscale images
Bakar, S. A., Hitam, M. S., & Yussof, W. N. J. H. W. (2013) · IEEE International Conference on Signal and Image Processing Applications (ICSIPA) · doi:10.1109/icsipa.2013.6707982 · Cited by 33
A biologically inspired spiking model of visual processing for image feature detection
Kerr, D., McGinnity, T. M., Coleman, S., & Clogenson, M. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.01.011 · Cited by 37
Design and capabilities of the Munich Cognitive Automobile
Goebl, M., Althoff, M., BUSS, M. J., Färber, G., Hecker, F., Heißing, B., Kraus, S., Nagel, R., León, F. P., Rattei, F., et al. (2008) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2008.4621255 · Cited by 33
Pedestrian Detection in Far-Infrared Daytime Images Using a Hierarchical Codebook of SURF
Besbes, B., Rogozan, A., Rus, A.-M., Bensrhair, A., & Broggi, A. (2015) · Sensors · doi:10.3390/s150408570 · Cited by 34
Visual Object Tracking Based on Combination of Local Description and Global Representation
Sun, L., & Liu, G. (2010) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2010.2087815 · Cited by 33
Pilet, J., & Saitô, H. (2010) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr.2010.5444811 · Cited by 35
“Stability and repeatability are the main goals of well known feature detectors such as SIFT, SURF, or FAST [10, 2, 19].”
MethodLeaving Flatland: Toward real-time 3D navigation
Morisset, B., Rusu, R. B., Sundaresan, A., Hauser, K. K., Agrawal, M., Latombe, J., & Beetz, M. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152715 · Cited by 33
“While SIFT [17] and SURF [18] are the features of choice, they are not suitable for real-time implementations (15 Hz or greater).”
BackgroundAnalyzing program flow within a many-kernel OpenCL application
Mistry, P., Gregg, C., Rubin, N., et al. (2011) · doi:10.1145/1964179.1964193 · Cited by 33
Defocus Blur-Invariant Scale-Space Feature Extractions
Saad, E., & Hirakawa, K. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2555702 · Cited by 37
3DSEM++: Adaptive and intelligent 3D SEM surface reconstruction
Tafti, A. P., Holz, J. D., Baghaie, A., Owen, H. A., He, M. M., & Yu, Z. (2016) · Micron · doi:10.1016/j.micron.2016.05.004 · Cited by 39
Robust Feature Matching for Remote Sensing Image Registration Based on $L_{q}$ -Estimator
Li, J., Hu, Q., & Ai, M. (2016) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2016.2620147 · Cited by 33
“Feature-based matching methods (to name a few, scale-invariant feature transform (SIFT) [1] and speeded up robust features (SURF) [2]) are very popular techniques to provide control points between an image pair.”
MethodCopy-move forgery detection in digital images using affine-SIFT
Shahroudnejad, A., & Rahmati, M. (2016) · International Conference on Signal Processing and Intelligent Systems (ICSPIS) · doi:10.1109/icspis.2016.7869896 · Cited by 33
On writer identification for Arabic historical manuscripts
Asi, A., Abdalhaleem, A., Fecker, D., et al. (2017) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-017-0289-3 · Cited by 33
Comparison of CNN models for application in crop health assessment with participatory sensing
Bhatt, P. V., Sarangi, S., & Pappula, S. (2017) · IEEE Global Humanitarian Technology Conference (GHTC) · doi:10.1109/ghtc.2017.8239295 · Cited by 38
Fu, Z., Qin, Q., Luo, B., et al. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2018.2867635 · Cited by 33
“SIFT, SURF, and NG-SIFT perform better than PIIFD and EOH in Fig.”
MethodInfluentialJunjun, P., Yong, Z., Dong, S., & Qin, H. (2018) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv.2018.00016 · Cited by 34
“In [18], its proposed BoVW scheme is based on Speeded-Up Robust Features (SURF) [4] local descriptor.”
MethodDetection and Classification of Moving Vehicle From Video Using Multiple Spatio-Temporal Features
Wang, Y., Ban, X.-J., Wang, H., Wu, D., Wang, H., Yang, S.-W., Liu, S.-N., & Lai, J. (2019) · IEEE Access · doi:10.1109/access.2019.2923199 · Cited by 22
“[33] H. Bay, T. Tuytelaars, and L. Van Gool, ‘‘SURF: Speeded up robust features,’’ in Proc.”
MethodGeometric Algebra in Signal and Image Processing: A Survey
Wang, R., Wang, K., Cao, W., & Wang, X. (2019) · IEEE Access · doi:10.1109/access.2019.2948615 · Cited by 32
“Therefore, the improved method GA-SURF has higher calculation efficiency.”
MethodInfluentialImage retrieval based on gradient-structures histogram
Yuan, B., & Liu, G. (2020) · Neural Computing and Applications · doi:10.1007/s00521-019-04657-0 · Cited by 36
Baumgartl, H., & Buettner, R. (2020) · Hawaii International Conference on System Sciences (HICSS) · doi:10.24251/hicss.2020.069 · Cited by 33
A Segmentation Based Robust Deep Learning Framework for Multimodal Retinal Image Registration
Wang, Y., Zhang, J., An, C., Cavichini, M., Jhingan, M., Amador-Patarroyo, M. J., Long, C. P., Bartsch, D., Freeman, W. R., & Nguyen, T. Q. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054077 · Cited by 35
“…(Source) Vessel Segmentation Network [13] (Target) [19] SuperPoint Network [19] Outlier Rejection Network [24] Two-way nearest neighbor matching Traditional feature detection and description method includes scale invariant feature transformation (SIFT) [7] and speeded up robust features (SURF) [8].”
MethodMoving Object Detection Based on Background Compensation and Deep Learning
Zhu, J., Wang, Z., Wang, S., & Chen, S. (2020) · Symmetry · doi:10.3390/sym12121965 · Cited by 41
“Figure 2 shows the detection results obtained by the SIFT, Harris, features from the accelerated segment test (FAST) [34], and speeded up robust features (SURF) [35] feature point detection algorithms.”
InfluentialRoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching
Parihar, U. S., Gujarathi, A., Mehta, K., Tourani, S., Garg, S., Milford, M. J., & Krishna, K. M. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636619 · Cited by 38
Yu, Q., Wang, B., & Su, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3072897 · Cited by 41
Kieu, H. T., & Law, A. W. (2021) · Journal of Hydro-environment Research · doi:10.1016/j.jher.2021.04.003 · Cited by 37
Improving Computer Vision-Based Perception for Collaborative Indoor Navigation
Ruotsalainen, L., Morrison, A. J., Mäkelä, M., Rantanen, J., & Sokolova, N. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3106257 · Cited by 33
Keeping an Eye on Things: Deep Learned Features for Long-Term Visual Localization
Gridseth, M., & Barfoot, T. D. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3136867 · Cited by 40
Fast and Efficient Method for Large-Scale Aerial Image Stitching
Pham, N. T., Park, S., & Park, C. (2021) · IEEE Access · doi:10.1109/access.2021.3111203 · Cited by 36
“Various features have been widely investigated, including SIFT [28], SURF [29], and ORB [30].”
MethodAvola, D., Cinque, L., Mambro, A. D., Diko, A., Fagioli, A., Foresti, G. L., Marini, M. R., Mecca, A., & Pannone, D. (2021) · Information · doi:10.3390/info13010002 · Cited by 42
Fan, Y., Wang, F., & Wang, H. (2022) · Remote Sensing · doi:10.3390/rs14051175 · Cited by 34
3D Scene Geometry Estimation from 360° Imagery: A Survey
da Silveira, T. L. T., Pinto, P. G. L., Murrugarra-Llerena, J., & Jung, C. R. (2022) · ACM Computing Surveys · doi:10.1145/3519021 · Cited by 68
Gu, Y., Wang, C., & Li, X. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3211202 · Cited by 36
Evaluation of Local Descriptors for Action Recognition in Videos
Biliński, P., & Brémond, F. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23968-7_7 · Cited by 33
“For example [15] proposed Scale-Invariant Feature Transform (SIFT) descriptor, [1] proposed Speeded Up Robust Features (SURF), [3] proposed Histogram of Oriented Gradients (HOG) descriptor.”
MethodLeveraging RGB-D Data: Adaptive fusion and domain adaptation for object detection
Spinello, L., & Arras, K. O. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6225137 · Cited by 42
“Examples include SIFT [17], SURF [1], HOG [4], or Centrist [32].”
Method2-D direction histogram based entropic thresholding
Yimit, A., Hagihara, Y., MIYOSHI, T., et al. (2013) · Neurocomputing · doi:10.1016/j.neucom.2012.10.031 · Cited by 33
“In pattern recognition, invariant feature vectors such as SIFT [17] and SURF [18,19] features were also extracted from the local edge information of scaled images.”
MethodFeature Tracking Evaluation for Pose Estimation in Underwater Environments
Shkurti, F., Rekleitis, I. M., & Dudek, G. (2011) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2011.28 · Cited by 39
MIFT: A Mirror Reflection Invariant Feature Descriptor
Guo, X., Cao, X., Zhang, J., & Li, X. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-12304-7_50 · Cited by 33
“SURF adopts Fast-Hessian detector to quickly detect features within images which owes much to the integral images and uses the Harr wavelet response to capture the texture properties around interest points.”
MethodNavigation and Mapping for Aerial Vehicles Based on Inertial and Imaging Sensors
Sjanic, Z. (2013) · Linköping University Electronic Press eBooks · doi:10.3384/diss.diva-97317 · Cited by 33
Abdullah, A., Veltkamp, R. C., & Wiering, M. (2009) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2009.5178743 · Cited by 32
Visual odometry learning for unmanned aerial vehicles
Guizilini, V., & Ramos, F. T. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979706 · Cited by 39
Visual recognition of aircraft mechanical parts for smart maintenance
Cusano, C., & Napoletano, P. (2017) · Computers in Industry · doi:10.1016/j.compind.2017.01.001 · Cited by 38
Removal of specular reflections from image sequences using feature correspondences
Shah, S. M. Z. A., Marshall, S., & Murray, P. (2017) · Machine Vision and Applications · doi:10.1007/s00138-017-0826-6 · Cited by 33
“Several algorithms exist which allow us to detect points of interest in images [30-34].”
Saitou, T., Kiyomatsu, H., & Imamura, T. (2018) · Scientific Reports · doi:10.1038/s41598-018-21005-9 · Cited by 33
Recognition and Tracking of 3D Objects
Wiedemann, C., Ulrich, M., & Steger, C. T. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-69321-5_14 · Cited by 33
PLPF‐VSLAM: An indoor visual SLAM with adaptive fusion of point‐line‐plane features
Yan, J., Zheng, Y., Yang, J., Mihaylova, L. S., Yuan, W., & Gu, F. (2023) · Journal of Field Robotics · doi:10.1002/rob.22242 · Cited by 36
LCPR: A Multi-Scale Attention-Based LiDAR-Camera Fusion Network for Place Recognition
Zhou, Z., Xu, J., Xiong, G., & Ma, J. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3346753 · Cited by 36
Visual Features—From Early Concepts to Modern Computer Vision
Weinmann, M. (2013) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-5520-1_1 · Cited by 40
Automated image mosaics by non‐automated light microscopes: theMicroMossoftware tool
Piccinini, F., Bevilacqua, A., & Lucarelli, E. (2013) · Journal of Microscopy · doi:10.1111/jmi.12084 · Cited by 34
Learning place-dependant features for long-term vision-based localisation
McManus, C., Upcroft, B., & Newman, P. M. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9463-y · Cited by 32
“, scale invariant feature transform (Lowe 2004) or speededup robust features (Bay et al. 2008)] over the entire image at various scales.”
BackgroundDERF: Distinctive Efficient Robust Features From the Biological Modeling of the P Ganglion Cells
Weng, D., Wang, Y., Gong, M., Tao, D., Wei, H., & Huang, D. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2409739 · Cited by 34
Interactive Multimodal Visual Search on Mobile Device
Li, H., Wang, Y., Mei, T., Wang, J., & Li, S. (2013) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2012.2234730 · Cited by 30
“Traditional features such as MPEG-7 image signature, SIFT, Speeded Up Robust Feature (SURF) [2], and Oriented FAST and Rotated BRIEF (ORB) [33] are widely used in such visual search systems because of their invariance to illumination, scale and rotation.”
MethodAppearance Based Indexing for Relocalisation in Real-Time Visual SLAM
Chekhlov, D., Mayol-Cuevas, W. W., & Calway, A. D. (2008) · British Machine Vision Conference (BMVC) · doi:10.5244/c.22.37 · Cited by 33
“An effective way of gaining improved robustness is to base matching on more distinctive descriptors, such as those developed in recent years for object recognition [6, 10].”
BackgroundA visual odometry method based on the SwissRanger SR4000
Ye, C., & Bruch, M. (2010) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.850349 · Cited by 32
Joint Feature Correspondences and Appearance Similarity for Robust Visual Object Tracking
Khan, Z. H., & Gu, I. Y. (2010) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2010.2050312 · Cited by 33
“Bay [13] proposes speeded up robust features (SURF) having a similar performance as SIFT [14], however, much faster.”
MethodA rotation invariant feature descriptor O-DAISY and its FPGA implementation
Fischer, J., Ruppel, A., Weißhardt, F., & Verl, A. W. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094813 · Cited by 36
Automatic Co-registration of Satellite Time Series via Least Squares Adjustment
Barazzetti, L., Scaioni, M., & Gianinetto, M. (2014) · European Journal of Remote Sensing · doi:10.5721/eujrs20144705 · Cited by 31
“SURF relies on a Hessian matrix-based measure for the detector and the distribution of the first-order Haar wavelet responses for the descriptor [Bay et al., 2008].”
MethodEfficient image signatures and similarities using tensor products of local descriptors
Picard, D., & Gosselin, P.-H. (2013) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2013.02.004 · Cited by 36
Vision-based sense-and-avoid framework for unmanned aerial vehicles
Huh, S., Cho, S., Jung, Y., & Shim, D. H. (2015) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2015.140252 · Cited by 37
Pepperell, E., Corke, P., & Milford, M. J. (2016) · The International Journal of Robotics Research · doi:10.1177/0278364915618766 · Cited by 32
“…vision algorithms used keypoint feature descriptors, such as Scale Invariant Feature Transforms (SIFT) (Lowe, 1999) or Speeded Up Robust Features (SURF) (Bay et al., 2006), often contained within a geometry-free, “Bag-of-Words” (BoW) (Sivic and Zisserman, 2003) representation of each image.”
Method
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.