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 2,701–2,800 of 14,752
Woźniak, M., & Połap, D. (2014) · International Conference on Signal Processing and Multimedia Applications · doi:10.5220/0005015801570164 · Cited by 25
MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network
Duffhauss, F., Demmler, T., & Neumann, G. M. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9982268 · Cited by 27
Cross-Level Multi-Modal Features Learning With Transformer for RGB-D Object Recognition
Zhang, Y., Yin, M., Wang, H., & Hua, C. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3275814 · Cited by 31
Hydra-Multi: Collaborative Online Construction of 3D Scene Graphs with Multi-Robot Teams
Chang, Y., Hughes, N., Ray, A., & Carlone, L. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341838 · Cited by 61
The Devil Is in the Boundary: Boundary-Enhanced Polyp Segmentation
Liu, Z., Zheng, S., Sun, X., Zhu, Z., Zhao, Y., Yang, X., & Zhao, Y. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3348598 · Cited by 35
“General speaking, K ( · ) can be achieved in many pathways, e.g. hand-craft designing-based [23], [24], [25], [26] and learning-based [27], [28], [29].”
Deep Learning-Based Stereopsis and Monocular Depth Estimation Techniques: A Review
Lahiri, S., Ren, J., & Lin, X. (2024) · Vehicles · doi:10.3390/vehicles6010013 · Cited by 36
“Later, with the rise of computer vision, several probabilistic graph models and hand-made features came up such as speeded-up robust features (SURF) [4], pyramid histogram of oriented gradient (PHOG) [5], scale-invariant feature transform (SIFT) [6], Conditional Random Field (CRF) [7], and Markov…”
BackgroundMethodZeng, D., Liu, X., Huang, K., & Liu, J. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3398491 · Cited by 27
“Feature matching is a crucial component of SLAM, with extensive studies focusing on point matching compared to line matching [14], [17], [18], [19], for line matching is a more challenging task.”
BackgroundJamMa: Ultra-lightweight Local Feature Matching with Joint Mamba
Lu, X., & Ду, С. (2025) · 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/cvpr52734.2025.01391 · Cited by 58
Bag-of-Words Image Representation: Key Ideas and Further Insight
Law, M. T., Thome, N., & Cord, M. (2014) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-05696-8_2 · Cited by 32
“The structural features are nested multi-layered local graphs built upon sets of SURF [3] feature points with Delaunay triangulation.”
MethodSpatial Statistics of Image Features for Performance Comparison
Bostancı, E., Kanwal, N., & Clark, A. F. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2286907 · Cited by 25
3D MODELS COMPARISON OF COMPLEX SHELL IN UNDERWATER AND DRY ENVIRONMENTS
Troisi, S., Pizzo, S. D., Gaglione, S., et al. (2015) · 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-xl-5-w5-215-2015 · Cited by 25
“Each survey was oriented using an automatic tie point extraction operator (Lowe, 1999), (Bay et al., 2006), that provides highly distinctive features invariant to image scaling and rotations and partial invariant to brightness.”
MethodFPGA based implementation of FAST and BRIEF algorithm for object recognition
Heo, H., Lee, J.-Y., Lee, K.-Y., & Lee, C. (2013) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2013.6718842 · Cited by 24
Word length reduction for the integral image
Belt, H. J. W. (2008) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2008.4711877 · Cited by 25
“Indeed, even though the intermediate results ii[7, 3] and ii[7, 1] have overflown, with wmax hmax = 8 we get the correct result from ii7.”
BackgroundInfluentialGeneration and weighting of 3D point correspondences for improved registration of RGB-D data
Khoshelham, K., dos Santos, D. R., & George Vosselman, A. (2013) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-ii-5-w2-127-2013 · Cited by 24
LiDAR Point Cloud Registration by Image Detection Technique
Han, J.-Y., Perng, N.-H., & Chen, H.-J. (2012) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2012.2221075 · Cited by 25
“It makes use of 2-D Haar wavelet responses, integral images, and scale-space technique and results in better detection performance than SIFT [12], [13].”
MethodInfluentialFPGA-Based Real-Time Moving Target Detection System for Unmanned Aerial Vehicle Application
Tang, J. W., Shaikh-Husin, N., Sheikh, U. U., & Marsono, M. N. (2016) · International Journal of Reconfigurable Computing · doi:10.1155/2016/8457908 · Cited by 28
LIRE: open source visual information retrieval
Lux, M., Riegler, M. A., Halvorsen, P., Pogorelov, K., & Anagnostopoulos, N. (2016) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/2910017.2910630 · Cited by 34
“Local features are based on the OpenCV implementations of SIFT [15] and SURF [2].”
MethodObject Detection by Simple Fuzzy Classifiers Generated by Boosting
Gabryel, M., Korytkowski, M., Scherer, R., & Rutkowski, L. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-38658-9_49 · Cited by 25
Fine scale image registration in large-scale urban LIDAR point sets
Guislain, M., Digne, J., Chaine, R., & Monnier, G. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.12.004 · Cited by 24
“Feature based registration me-thods rely on establishing correspondences between feature points obtained using methods such as SIFT [1], or SURF [2] on real and synthetic 2D images.”
InfluentialFree viewpoint video (FVV) survey and future research direction
Lee, C.-C., Tabatabai, A. J., & Tashiro, K. (2015) · APSIPA Transactions on Signal and Information Processing · doi:10.1017/atsip.2015.18 · Cited by 25
Color Texture Image Retrieval Based on Local Extrema Features and Riemannian Distance
Pham, M., Mercier, G., & Bombrun, L. (2017) · Journal of Imaging · doi:10.3390/jimaging3040043 · Cited by 25
Afifi, M., & Hussain, K. F. (2019) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-019-00322-3 · Cited by 30
“These features are described using a feature descriptor – in our case we have used the SURF descriptor.”
MethodInfluentialDiscriminative Deep Feature Learning for Semantic-Based Image Retrieval
Song, K., Li, F., Long, F., Wang, J., & Ling, Q. (2018) · IEEE Access · doi:10.1109/access.2018.2862464 · Cited by 26
“SIFT [16] and SURF [26] are the common local features which are widely used in image representation.”
BackgroundIOT-Based Smart Museum Using Wearable Device
Kumar, V. D. A., Saranya, G., Elangovan, D., Chiranjeevi, V. R., & Kumar, V. D. A. (2018) · Lecture notes in networks and systems · doi:10.1007/978-981-13-2324-9_5 · Cited by 25
Automatic Stitching for Hyperspectral Images Using Robust Feature Matching and Elastic Warp
Zhang, Y., Wan, Z., Jiang, X., et al. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3001022 · Cited by 25
“First, we compare different feature point extraction algorithms, including SIFT [5], SURF [6], and SS-SIFT [7], on hyperspectral image (HSIs) datasets.”
MethodInfluentialMetric Learning in Optimal Transport for Domain Adaptation
Kerdoncuff, T., Emonet, R., & Sebban, M. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/299 · Cited by 33
Annapurna: An automated smartwatch-based eating detection and food journaling system
Sen, S., Subbaraju, V., Misra, A., Balan, R. K., & Lee, Y. (2020) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2020.101259 · Cited by 28
A sub-pixel image registration algorithm based on SURF and M-estimator sample consensus
Wu, S., Zeng, W., & Chen, H. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.09.031 · Cited by 25
Yakovleva, O., & Nikolaieva, K. (2020) · Advanced Information Systems · doi:10.20998/2522-9052.2020.4.13 · Cited by 25
Gao, K., Aliakbarpour, H., Fraser, J., Nouduri, K., Bunyak, F., Massaro, R. D., Seetharaman, G. S., & Palaniappan, K. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3042810 · Cited by 28
Robust Stereo Visual SLAM for Dynamic Environments With Moving Object
Li, G., Liao, X., Huang, H., Song, S., Liu, B., & Zeng, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3059866 · Cited by 26
“Popular feature extraction methods include scale-invariant feature transform (SIFT) [25], speeded-up robust features (SURF) [26], and features from accelerated segment test (FAST) [27].”
MethodEstimating 6D Aircraft Pose from Keypoints and Structures
Fan, R., Xu, T.-B., & Wei, Z. (2021) · Remote Sensing · doi:10.3390/rs13040663 · Cited by 27
Misra, I., Rohil, M. K., Moorthi, S. M., & Dhar, D. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3081768 · Cited by 27
“In recent times, more powerful feature detectors like SIFT [23], SURF [24], ORB [25], and KAZE [26] have been applied to multitemporal remote-sensing images to go to subpixel level coregistration accuracies [27], [28].”
MethodAutonomous Exploration of Small Bodies Toward Greater Autonomy for Deep Space Missions
Nesnas, I., Hockman, B. J., Bandopadhyay, S., Morrell, B. J., Lubey, D. P., Villa, J., Bayard, D. S., Osmundson, A., Jarvis, B., Bersani, M., et al. (2021) · Frontiers in Robotics and AI · doi:10.3389/frobt.2021.650885 · Cited by 29
Chen, J., Cheng, B., Zhang, X., Long, T., Chen, B., Wang, G., & Zhang, D. (2022) · Remote Sensing · doi:10.3390/rs14061393 · Cited by 25
Guide Local Feature Matching by Overlap Estimation
Chen, Y., Huang, D., Xu, S., Liu, J., & Liu, Y. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19913 · Cited by 39
3D Structure from 2D Dimensional Images Using Structure from Motion Algorithms
Elkhrachy, I. (2022) · Sustainability · doi:10.3390/su14095399 · Cited by 30
MobiDepth: real-time depth estimation using on-device dual cameras
Zhang, J., Yang, H., Ren, J., Zhang, D., He, B., Cao, T., Li, Y., Zhang, Y., & Liu, Y. (2022) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3495243.3560517 · Cited by 33
“In addition, the existing approaches typically use image matching algorithms to crop the FoVs, such as SIFT [30], SURF [5], ORB [36].”
MethodUnsupervised Global and Local Homography Estimation With Motion Basis Learning
Liu, S., Lu, Y., Jiang, H., Ye, N., Wang, C., & Zeng, B. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3223789 · Cited by 25
“Traditional methods often estimate homographies by first detecting and matching image keypoints, where SIFT [23], SURF [3], ORB [31], LPM [26], GMS [4], SOSNet [36], LIFT [43], SuperPoint [7], BEBLID [34], OAN [45], and SuperGlue [32] are commonly used to build correspondences between two sets of…”
MethodFan, Y., Du, X., Luo, L., & Shen, J. (2022) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv57592.2022.10004331 · Cited by 33
Cattle identification system: a comparative analysis of SIFT, SURF and ORB feature descriptors
Kaur, A., Kumar, M., & Jindal, M. K. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14478-y · Cited by 28
“[3] introduced SURF feature extraction method.”
A Review: How Deep Learning Technology Impacts the Evaluation of Traditional Village Landscapes
Wang, T., Chen, J., Liu, L., & Guo, L. (2023) · Buildings · doi:10.3390/buildings13020525 · Cited by 29
Template matching based on convolution neural network for UAV visual localization
Cao, Y., Ren, K., & Chen, Q. (2023) · Optik · doi:10.1016/j.ijleo.2023.170920 · Cited by 27
Video-Based Vehicle Speed Estimation Using Speed Measurement Metrics
Sangsuwan, K., & Ekpanyapong, M. (2024) · IEEE Access · doi:10.1109/access.2024.3350381 · Cited by 39
Negahdaripour, S., Aykin, M. D., & Sinnarajah, S. (2011) · doi:10.23919/oceans.2011.6107093 · Cited by 25
Learning Real-Time Perspective Patch Rectification
Hinterstoißer, S., Lepetit, V., Benhimane, S., Fua, P., & Navab, N. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-010-0379-x · Cited by 25
Robust image retrieval using multiview scalable vocabulary trees
Chen, D. M., Tsai, S. S., Chandrasekhar, V., Gabriel Takacs, A., Singh, J., & Girod, B. (2008) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.805606 · Cited by 25
“After classification, it is known how many times ni(j) the j node in the SVT is visited by the i database feature set, resulting in a vector of node visit counts di = [ni(1), ni(2), .”
BackgroundInfluentialEKF-SLAM based Approach for Spacecraft Rendezvous Navigation with Unknown Target Spacecraft
Sonnenburg, A., Tkocz, M., & Janschek, K. (2010) · IFAC Proceedings Volumes · doi:10.3182/20100906-5-jp-2022.00058 · Cited by 26
Tracking Vehicles Through Shadows and Occlusions in Wide-Area Aerial Video
Aeschliman, C., Park, J., & Kak, A. C. (2014) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2013.120404 · Cited by 25
Off-line signature verification using G-SURF
Pal, S., Chanda, S., Pal, U., et al. (2012) · International Conference on Intelligent Systems Design and Applications (ISDA) · doi:10.1109/isda.2012.6416603 · Cited by 25
SHIMURA, K., Yoshinobu, A. N. D. O., Yoshimi, T., et al. (2014) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2014.7028055 · Cited by 25
Wohlfeil, J., Hirschmüller, H., Piltz, B., 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-xxxix-b3-75-2012 · Cited by 25
Fernández, C., Llorca, D. F., Sotelo, M. Á., et al. (2013) · International Journal of Automotive Technology · doi:10.1007/s12239-013-0013-3 · Cited by 25
Hardware‐in‐the‐loop simulation for visual target tracking of octorotor UAV
Trilaksono, B. R., Triadhitama, R., Adiprawita, W., Wibowo, A., & Sreenatha, A. G. (2011) · Aircraft Engineering and Aerospace Technology · doi:10.1108/00022661111173289 · Cited by 26
The use of digital image processing for IC reverse engineering
Quijada, R., Raventós, A., Tarrés, F., et al. (2014) · IEEE International Multi-Conference on Systems, Signals & Devices (SSD) · doi:10.1109/ssd.2014.6808796 · Cited by 25
Amato, G. M., Falchi, F., & Bolettieri, P. (2010) · doi:10.1109/mmedia.2010.20 · Cited by 25
“SURF The basic idea of Speeded Up Robust Features (SURF) [14] is quite similar to SIFT.”
BackgroundMethodEl-Saban, M., Izz, M., Kaheel, A., et al. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6115723 · Cited by 25
Image warping for face recognition: From local optimality towards global optimization
Pishchulin, L., Gass, T., Dreuw, P., & Ney, H. (2011) · Pattern Recognition · doi:10.1016/j.patcog.2011.10.017 · Cited by 25
Canonical dependency analysis based on squared-loss mutual information
Karasuyama, M., & Sugiyama, M. (2012) · Neural Networks · doi:10.1016/j.neunet.2012.06.009 · Cited by 25
“In this experiment, we first extracted visual features from each image using the speed up robust features (SURF) algo-rithm (Bay et al., 2008), and obtained 500 visual words as the cluster centers in the SURF space.”
MethodActivity Detection in Scientific Visualization
Özer, S., Silver, D. E., Bemis, K. G., & Martin, P. (2013) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2013.117 · Cited by 26
Making Residual Vector Distribution Uniform for Distinctive Image Representation
Liu, Z., Li, H., Zhou, W., Rui, T., & Tian, Q. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2409693 · Cited by 28
“bag-of-visual-words (BoVW) model and adopt the invariant local features for image representation [24], [25].”
BackgroundAn integrated artificial vision framework for assisting visually impaired users
Chessa, M., Noceti, N., Odone, F., Solari, F., Sosa-García, J., & Zini, L. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.11.007 · Cited by 27
Tree of Words for Visual Loop Closure Detection in Urban SLAM
Callmer, J., Granström, K., Nieto, J. I., & Ramos, F. T. (2008) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · Cited by 30
On the use of binary feature descriptors for loop closure detection
Garcia‐Fidalgo, E., & Ortiz, A. (2014) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2014.7005121 · Cited by 26
Surveying apple orchards with a monocular vision system
Roy, P., & Isler, V. (2016) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2016.7743500 · Cited by 32
FPGA accelerator for real-time SIFT matching with RANSAC support
Vourvoulakis, J. V., Kalomiros, J. A., & Lygouras, J. N. (2016) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2016.11.011 · Cited by 27
Chinese calligraphic style representation for recognition
Gao, P., Gang, G., Wu, J., & Baogang, W. (2017) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-016-0277-z · Cited by 25
“Herbert [22] presented a faster method called SURF, which used Fast-Hessian detector.”
MethodOn the way to airborne gravelometry based on 3D spatial data derived from images
Detert, M., Kadinski, L., & Weitbrecht, V. (2018) · International Journal of Sediment Research · doi:10.1016/j.ijsrc.2018.02.001 · Cited by 27
Video authentication using spatio temporal relationship for tampering detection
Sowmya, K. N., Chennamma, H. R., & Rangarajan, L. (2018) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2018.07.002 · Cited by 30
Image Processing Based Indoor Localization System for Assisting Visually Impaired People
Heya, T. A., Arefin, S. E., Chakrabarty, A., et al. (2018) · doi:10.1109/upinlbs.2018.8559936 · Cited by 25
Classification of texture based on Bag-of-Visual-Words through complex networks
de Lima, G. V. L., Saito, P. T. M., Lopes, F. M., & Bugatti, P. H. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.05.021 · Cited by 29
Markiewicz, J. S., Abratkiewicz, K., Gromek, A., Ostrowski, W., Samczyński, P., & Gromek, D. (2019) · Sensors · doi:10.3390/s19245500 · Cited by 25
DFVS: Deep Flow Guided Scene Agnostic Image Based Visual Servoing
Harish, Y. V. S., Pandya, H., Gaud, A., Terupally, S., Shankar, S., & Krishna, K. M. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196753 · Cited by 27
Learning Deep Network for Detecting 3D Object Keypoints and 6D Poses
Zhao, W., Zhang, S., Guan, Z., Zhao, W., Peng, J., & Fan, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01414 · Cited by 32
Elibol, A., Gracias, N., & García, R. (2010) · Journal of Field Robotics · doi:10.1002/rob.20357 · Cited by 30
GIS and Augmented Reality: State of the Art and Issues
Hugues, O., Cieutat, J.-M., & Guitton, P. (2011) · Springer eBooks · doi:10.1007/978-1-4614-0064-6_33 · Cited by 30
3-D Reconstruction from Sparse Views using Monocular Vision
Saxena, A., Sun, M., & Ng, A. Y. (2007) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2007.4409219 · Cited by 28
“In detail, we start by computing 128 SURF features [27], and then calculate matches based on the Euclidean distances between the features found.”
MethodReal-time vision-based tracking and reconstruction
Bleser, G., Becker, M., & Stricker, D. (2007) · Journal of Real-Time Image Processing · doi:10.1007/s11554-007-0034-0 · Cited by 29
Automatic extrinsic camera self-calibration based on homography and epipolar geometry
Miksch, M., Yang, B., & Zimmermann, K. D. (2010) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2010.5548048 · Cited by 25
“Standard methods like the ScaleInvariant Feature Transform (SIFT [10]) or the Speeded Up Robust Features (SURF [11]) can be applied to extract the feature pairs.”
MethodRate-efficient, real-time cd cover recognition on a camera-phone
Tsai, S. S., Chen, D., Singh, J. P., et al. (2008) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1459359.1459561 · Cited by 25
Lee, S. Y., Sim, J.-Y., Kim, C., et al. (2013) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2013.2271747 · Cited by 25
“Another approach to the correspondence matching problem is to employ feature detection techniques, such as the scale invariant feature transform (SIFT) [8] or the speeded up robust features (SURF) [9].”
BackgroundMethodChen, Y., Schmid, C., & Sminchisescu, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.05820 · Cited by 25
Interpretability Beyond Classification Output: Semantic Bottleneck NetworksPreprint
Losch, M., Fritz, M., & Schiele, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.10882 · Cited by 72
Recent Advances in Deep Learning for Object DetectionPreprint
Wu, X., Sahoo, D., & Hoi, S. (2019) · Neurocomputing · doi:10.48550/arxiv.1908.03673 · Cited by 975
Multi-View Monocular Pose Estimation for Spacecraft Relative Navigation
Rondao, D., & Aouf, N. (2018) · 2018 AIAA Guidance, Navigation, and Control Conference · doi:10.2514/6.2018-2100 · Cited by 25
Wen, Y., & Wang, L. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02175-7 · Cited by 25
“Early researchers utilized traditional image processing methods to extract defect features, such as Histogram of Oriented Gradients (HOG) [23], Scale-Invariant Feature Transform (SIFT) [24], and Speeded Up Robust Features (SURF) [25].”
Shirahama, K., & Grzegorzek, M. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2292-8 · Cited by 24
ChiNet: Deep recurrent convolutional learning for multimodal spacecraft pose estimation
Rondao, D., Aouf, N., & Richardson, M. A. (2022) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2022.3193085 · Cited by 24
“An alternative approach constructs a database by discretising the 3D object into 2D keyframes representing multiple viewpoints [18], and then using local keypoint detectors and descriptors (e.g. SIFT [19], SURF [20], or the more modern ORB [21]) to obtain the matches.”
MethodFeature-Based Occupancy Map-Merging for Collaborative SLAM
Sunil, S., Mozaffari, S., Singh, R., Shahrrava, B., & Alirezaee, S. (2023) · Sensors · doi:10.3390/s23063114 · Cited by 28
Zhong, J., Yan, J., Li, M., & Barriot, J. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.10.021 · Cited by 29
Khan, M. A., & Ghamdi, M. A. A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17446-8 · Cited by 28
A review of image features extraction techniques and their applications in image forensic
Kumar, D., Pandey, R. C., & Mishra, A. K. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17950-x · Cited by 37
Hash-Based Remote Sensing Image Retrieval
Han, L., Paoletti, M. E., Tao, X., Wu, Z., Haut, J. M., Li, P., Vargas, R., & Plaza, A. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3429350 · Cited by 35
“Prior to the advent of deep learning, feature extraction relied on hand-crafted feature extractors, such as the scale-invariant feature transform (SIFT) [21], the histogram of oriented gradient (HOG) [22], speeded-up robust features (SURF) [23], and principal component analysis (PCA) [24].”
MethodTayyab, M., Alateyah, S. A., Alnusayri, M., Alatiyyah, M. H., AlHammadi, D. A., Jalal, A., & Liu, H. (2025) · Sensors · doi:10.3390/s25020441 · Cited by 27
“Several feature descriptors can be used to identify body parts in images to help detect events such as SURF (Speeded-Up Robust Features) [20], BRIEF (Binary Robust Independent Elementary Features) [21], MSER (Maximally Stable External Regions) [22], HOG (Histogram of Orientated Gradients) [23], DOF…”
3D reconstruction from photographs by CMP SfM web service
Heller, J., Havlena, M., Jančošek, M., Torii, A., & Pajdla, T. (2015) · Machine Vision Applications · doi:10.1109/mva.2015.7153126 · Cited by 24
“The method avoids performing costly exhaustive pairwise matching of all images by selecting similar ones using SURFbased visual words and tf-idf scores.”
MethodInfluentialCoding binary local features extracted from video sequences
Baroffio, L., Ascenso, J., Cesana, M., et al. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025565 · Cited by 24
“Traditional keypoint description algorithms such as SIFT [1] and SURF [2] assign a signature to each interest point by means of a set of real-valued elements represented by means of floating point numbers.”
MethodArashloo, S. R., & Kittler, J. (2014) · Pattern Recognition Letters · doi:10.1016/j.patrec.2014.05.017 · Cited by 26
A 470mV 2.7mW feature extraction-accelerator for micro-autonomous vehicle navigation in 28nm CMOS
Jeon, D., Kim, Y., Lee, I., et al. (2013) · Digest of technical papers/Digest of technical papers - IEEE International Solid-State Circuits Conference · doi:10.1109/isscc.2013.6487684 · Cited by 24
“This paper proposes a power-efficient speeded-up robust features (SURF) extraction accelerator targeted primarily for micro air vehicles (MAVs) with autonomous navigation (Fig.”
MethodLearning invariant region descriptor operators with genetic programming and the F-measure
Pérez, C. B., & Gustavo Olague, A. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4761178 · Cited by 24
Contextual object category recognition for RGB-D scene labeling
Ali, H., Shafait, F., Giannakidou, E., Vakali, A. I., Figueroa, N., Varvadoukas, T., & Mavridis, N. (2013) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2013.10.001 · Cited by 26
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.