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 5,901–6,000 of 14,752
Facial Recognition in Degraded Conditions Using Local Interest Points
Ouannes, L., Khalifa, A. B., & Amara, N. E. B. (2020) · International Multi-Conference on Systems, Signals & Devices (SSD) · doi:10.1109/ssd49366.2020.9364124 · Cited by 9
Image stitching by feature positioning and seam elimination
Qin, Y., Li, J., Jiang, P., et al. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10694-6 · Cited by 8
“In 2006, Herbert Bay proposed an improved algorithm for the SIFT algorithm, Speeded Up Robust Features (SURF) [2], which uses the integral image to increase the computational speed of SIFT.”
MethodOffline signature recognition system using oriented FAST and rotated BRIEF
Al-Tamimi, A.-K., Qasaimeh, A., & Qaddoum, K. S. (2021) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v11i5.pp4095-4103 · Cited by 8
ID documents matching and localization with multi-hypothesis constraints
Chiron, G., Ghanmi, N., & Awal, A. M. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412437 · Cited by 8
MIST: Multiple Instance Spatial Transformer
Angles, B., Jin, Y., Kornblith, S., Tagliasacchi, A., & Yi, K. M. (2021) · 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/cvpr46437.2021.00244 · Cited by 12
StruMonoNet: Structure-Aware Monocular 3D Prediction
Yang, Z., Li, L. E., & Huang, Q. (2021) · 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/cvpr46437.2021.00733 · Cited by 7
“…include learning a machine translator between two minor languages by composing machine translators via a mother language [19], solving 6D object pose prediction via intermediate keypoint detections [1, 31, 28, 36, 27, 29, 34], and predicting 3D human poses through 2D keypoint predictions [44].”
BackgroundInstance search via instance level segmentation and feature representation
Yu, Z., & Zhao, W. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103253 · Cited by 13
“All these approaches are built upon image local features such as SIFT [21], Root-SIFT [22], SURF [23].”
MethodConnecting Images through Sources: Exploring Low-Data, Heterogeneous Instance Retrieval
Gominski, D., Gouet-Brunet, V., & Chen, L. (2021) · Remote Sensing · doi:10.3390/rs13163080 · Cited by 10
Attribute-Aware Feature Encoding for Object Recognition and Segmentation
Yang, S., Wang, Y., Chen, K., Zeng, W., & Fei, Z. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3103605 · Cited by 9
CE-Dedup: Cost-Effective Convolutional Neural Nets Training based on Image Deduplication
Li, X., Chang, L., & Liu, X. (2021) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom52081.2021.00017 · Cited by 14
RFDoc: Memory Efficient Local Descriptors for ID Documents Localization and Classification
Matalov, D. P., Limonova, E. E., Skoryukina, N. S., & Arlazarov, V. V. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86331-9_14 · Cited by 9
Empirical Analysis of Feature Points Extraction Techniques for Space Applications
Borse, J. H., & Patil, D. D. (2021) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2021.0120910 · Cited by 8
Joint Learning for Relationship and Interaction Analysis in Video with Multimodal Feature Fusion
Zhang, B., Yu, F., Gao, Y., Ren, T., & Wu, G. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3479214 · Cited by 15
“Feature matching methods use scale invariant features like speed up robust features (SURF) [1] to detect local feature of an image.”
MethodA Concise Review of Deep Learning Deployment in 3D Computer Vision Systems
Shaqwi, F. S., Audah, L., Hassan, M. H., Jubair, M. A., Wahab, M. H. A., & Mostafa, S. A. (2021) · International Symposium on Agents, Multi-Agent Systems and Robotics (ISAMSR) · doi:10.1109/isamsr53229.2021.9567757 · Cited by 9
Automatic Foreground Detection at 784 FPS for Ultra-High-Speed Human–Machine Interactions
Ду, С., Cai, P., Hu, T., & Ikenaga, T. (2021) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2021.3126476 · Cited by 9
Ullah, F., Kwon, O., & Choi, S. (2021) · Applied Sciences · doi:10.3390/app112211019 · Cited by 8
A particle‐filtering framework for integrity risk of GNSS‐camera sensor fusion
Mohanty, A., Gupta, S., & Gao, G. (2021) · NAVIGATION Journal of the Institute of Navigation · doi:10.1002/navi.455 · Cited by 8
EMDQ: Removal of Image Feature Mismatches in Real-Time
Zhou, H., & Jayender, J. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3134456 · Cited by 10
End-to-end learning of self-rectification and self-supervised disparity prediction for stereo vision
Zhang, X., Zhao, Y., Wang, H., Zhai, H., Sun, H., & Zheng, N. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.04.095 · Cited by 8
Ren, K., Ye, Y., Gu, G., et al. (2022) · Optik · doi:10.1016/j.ijleo.2022.169033 · Cited by 8
Matching-range-constrained real-time loop closure detection with CNNs features
Bai, D., Wang, C., Zhangt, B., Yi, X., & Tang, Y. (2016) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar.2016.7784003 · Cited by 9
Georeferencing Urban Nighttime Lights Imagery Using Street Network Maps
Schwind, P., & Storch, T. (2022) · Remote Sensing · doi:10.3390/rs14112671 · Cited by 10
Hu, E., & Sun, L. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2022.05.021 · Cited by 8
“Nonetheless, the detecting and matching of 3D keypoints are much less reliable than 2D ones (e.g. SIFT Lowe, 2004, SURF Bay et al., 2006), so it may easily generate mismatched or spurious results, usually named outliers , among the putative correspondences established.”
Rinaldi, A. M., Russo, C., & Tommasino, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-10450-3_8 · Cited by 8
Sergi, I., Leo, M., Carcagnì, P., et al. (2022) · Journal of Communications Software and Systems · doi:10.24138/jcomss-2022-0001 · Cited by 8
Coarse-to-fine spatial-channel-boundary attention network for image copy-move forgery detection
Zhong, J., Yang, J., Gan, Y., Huang, L. F., & Hua, Z. (2022) · Soft Computing · doi:10.1007/s00500-022-07432-x · Cited by 9
“With keypoint-based methods, as the name implies, local descriptors are extracted, such as Scale-Invariant Feature Transform (SIFT) (Lowe 2004; Li and Zhou 2019; Pun et al. 2015; Yang et al. 2021; Li et al. 2014), Speeded Up Robust Features (SURF) (Bay et al. 2006; Silva et al. 2015; Shivakumar and Baboo 2011), Orient…”
BackgroundMethodInfluentialEnabling Product Recognition and Tracking Based on Text Detection for Mobile Augmented Reality
Hwang, S., Lee, J., & Kang, S. (2022) · IEEE Access · doi:10.1109/access.2022.3205344 · Cited by 8
Ling, H., Sun, Q., Ren, Z., Liu, Y., Wang, H., & Wang, Z. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547979 · Cited by 8
RANET: A Grasp Generative Residual Attention Network for Robotic Grasping Detection
Hong, Q.-Q., Yang, L., & Zeng, B. (2022) · International Journal of Control Automation and Systems · doi:10.1007/s12555-021-0929-8 · Cited by 10
The current state on usage of image mosaic algorithms
Lungisani, B. A., Lebekwe, C. K., Zungeru, A. M., et al. (2022) · Scientific African · doi:10.1016/j.sciaf.2022.e01419 · Cited by 8
Attention-Guided Disentangled Feature Aggregation for Video Object Detection
Muralidhara, S., Hashmi, K. A., Pagani, A., Liwicki, M., Stricker, D., & Afzal, M. Z. (2022) · Sensors · doi:10.3390/s22218583 · Cited by 8
Evaluation of RGB-D SLAM in Large Indoor Environments
Muravyev, K., & Yakovlev, K. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-23609-9_9 · Cited by 11
Improving generalizability of ML-enabled software through domain specification
Barzamini, H., Rahimi, M., Shahzad, M., & Alhoori, H. (2022) · IEEE/ACM International Conference on AI Engineering – Software Engineering for AI (CAIN) · doi:10.1145/3522664.3528589 · Cited by 15
“Before the success of deep CNNs in computer vision tasks, a variety of handcrafted feature descriptors, including SIFT [36], LBP [40], SURF [4], HOG [10], and Haar [66], have been investigated in the context of pedestrian detection.”
BackgroundKim, J. J. Y., Urschler, M., Riddle, P., & Wicker, J. S. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981542 · Cited by 8
Multi-Source Feature Fusion for Object Detection Association in Connected Vehicle Environments
Thornton, S., Flowers, B., & Dey, S. (2022) · IEEE Access · doi:10.1109/access.2022.3228735 · Cited by 10
Mollica, G., Legittimo, M., Dionigi, A., Costante, G., & Valigi, P. (2023) · Sensors · doi:10.3390/s23042286 · Cited by 8
Utilization of Merge-Sorting Method to Improve Stitching Efficiency in Multi-Scene Image Stitching
Liu, W., Zhang, K., Zhang, Y., et al. (2023) · Applied Sciences · doi:10.3390/app13052791 · Cited by 8
Ruitao, F., Du, Q., Heng, L., et al. (2021) · National Remote Sensing Bulletin · doi:10.11834/jrs.20209280 · Cited by 8
Automatic fast feature-level image registration for high-resolution remote sensing images
Mengmeng, H. E., Guo, Q., Li, A., et al. (2018) · National Remote Sensing Bulletin · doi:10.11834/jrs.20186420 · Cited by 8
Wang, X., Luo, Y., Fu, Q., et al. (2023) · Remote Sensing · doi:10.3390/rs15143535 · Cited by 8
Improving sparse graph attention for feature matching by informative keypoints exploration
Jiang, X., Zhang, S., Zhang, X.-P. S., & Ma, J. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103803 · Cited by 12
Foryś, P., Sitnik, R., Markiewicz, J. S., & Bunsch, E. (2023) · Heritage Science · doi:10.1186/s40494-023-01018-y · Cited by 10
3D Modelling of Static Environments Using Multiple Spherical Stereo
Kim, H., & Hilton, A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35740-4_14 · Cited by 8
“A 3D rigid transform is calculated between views using SURF feature matching [16] and RANSAC algorithm to register the reconstructed models from multiple viewpoints.”
MethodA visual attention model for stereoscopic 3D images using monocular cues
Iatsun, I., Larabi, M., & Fernández-Maloigne, C. (2015) · Signal Processing Image Communication · doi:10.1016/j.image.2015.05.009 · Cited by 8
Mobile Visual Search from Dynamic Image Databases
Chen, X., & Koskela, M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21227-7_19 · Cited by 8
“In this work, we extract and use SURF descriptors for the matching.”
BackgroundInfluentialZhang, W., Liu, L., Yin, S., et al. (2013) · Science China Information Sciences · doi:10.1007/s11432-013-4786-9 · Cited by 8
Ensemble Learning with LDA Topic Models for Visual Concept Detection
Tang, S., Zheng, Y.-T., Cao, G., Zhang, Y., & Li, J. (2012) · InTech eBooks · doi:10.5772/37716 · Cited by 9
“After extraction of visual features, such as local features SIFT (Lowe, 2004) or SURF (Bay et al., 2006), BoVW consists of two main steps: visual vocabulary construction and feature quantization.”
MethodMachine Learning Methods for Automatic Image Colorization
Charpiat, G., Bezrukov, I., Hofmann, M., Altun, Y., Schölkopf, B., & Lukáč, R. (2010) · Cited by 9
The mobile museum guide: Artwork recognition with eigenpaintings and SURF
Temmermans, F., Jansen, B. M. P., Deklerck, R., et al. (2011) · Research Repository (Delft University of Technology) · Cited by 8
Yazdkhasti, S., Ulrich, S., & Sąsiadek, J. Z. (2015) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2015.7283868 · Cited by 8
“The SURF [19] descriptor was chosen as it has proved to be highly efficient in terms of scale-invariance and rotation, while being highly robust against several deformations.”
MethodInfluentialFeature-Based 6-DoF Camera Localization Using Prior Point Cloud and Images
Kim, H., Lee, D., Oh, T., et al. (2014) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-05582-4_1 · Cited by 8
3D reconstruction model of underwater environment in stereo vision system
Wu, Y., Nian, R., & He, B. (2013) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.23919/oceans.2013.6741275 · Cited by 8
A Comparative Evaluation of Feature Detectors on Historic Repeat Photography
Gat, C., Albu, A. B., Germán, D. M., & Higgs, E. S. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24031-7_70 · Cited by 11
Narumi, T., Kasai, T., Honda, T., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39226-9_27 · Cited by 8
A Low-Cost Head and Eye Tracking System for Realistic Eye Movements in Virtual Avatars
Li, Y., Wei, H., Monaghan, D. S., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-04114-8_39 · Cited by 8
“On the other hand, if isolated segmentation of an eye pair from each camera system is used, real time performance is achieved but insufficient matching points (via SURF descriptors [16].”
Projected Transfer Sparse Coding for cross domain image representation
Li, X., Fang, M., & Zhang, J.-J. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.09.018 · Cited by 8
An Effective Color Addition to Feature Detection and Description for Book Spine Image Matching
Fowers, S. G., & Lee, D.-J. (2011) · ISRN Machine Vision · doi:10.5402/2012/945973 · Cited by 8
Ehsan, S., Kanwal, N., Clark, A. F., et al. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2160869 · Cited by 8
Binary feature from intensity quantization and weakly spatial contextual coding for image search
Zhuang, D., Zhang, D., Li, J., et al. (2014) · Information Sciences · doi:10.1016/j.ins.2014.08.064 · Cited by 8
Vision-based navigation with efficient scene recognition
Kim, J., Park, C., & Kweon, I. S. (2011) · Intelligent Service Robotics · doi:10.1007/s11370-011-0091-x · Cited by 9
Image-based global localization using VG-RAM Weightless Neural Networks
Junior, L. J. L., Oliveira-Santos, T., Forechi, A., Veronese, L. D. P., Badue, C. S., & Souza, A. F. D. (2014) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2014.6889888 · Cited by 10
“Much of the work in Robotics Vision in the last decade relied in visual features with certain degree of invariance to affine transformations [3, 4] (e.”
BackgroundA Quasi-Dense Matching Approach and its Calibration Application with Internet Photos
Wan, Y., Miao, Z., Wu, Q. M. J., Wang, X., Tang, Z., & Wang, Z. (2014) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2326255 · Cited by 8
Topological and Metric Robot Localization through Computer Vision Techniques
Murillo, A. C., Guerrero, J. J., & Saguüés, C. (2008) · Lecture notes in electrical engineering · doi:10.1007/978-0-387-75523-6_8 · Cited by 8
Visual tracking for non-rigid objects using Rao-Blackwellized particle filter
Kim, J., Park, C., & Kweon, I.-S. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509949 · Cited by 8
“The integral images have been used for face detection and feature detection to reduce the computation time, as introduced in [22][23].”
MethodSpringer, D., Simmet, F., Niederkorn, D., et al. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6637877 · Cited by 8
“This eliminates the need to use SIFT [2] or SURF [9] for precise motion estimations while at the same time provides real-time performance with an average of 10.”
MethodLocalizability of unicycle mobiles robots: An algebraic point of view
Sert, H., Perruquetti, W., Kökösy, A., Jin, X., & Palos, J. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385855 · Cited by 10
Leitner, J., Frank, M., Förster, A., & Schmidhuber, J. (2014) · International Conference on Informatics in Control, Automation and Robotics (ICINCO) · doi:10.5220/0005113401020109 · Cited by 8
Challenge of multi-camera tracking
Wang, Y., Lü, K., & Zhai, R. (2014) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2014.7003745 · Cited by 8
Research of Image Matching Based on Improved SURF Algorithm
Qi, F., Xu, W., & Li, Q. (2013) · TELKOMNIKA Indonesian Journal of Electrical Engineering · doi:10.11591/telkomnika.v12i2.3951 · Cited by 9
“Bay, etc. [10] an algorithm called SURF, it is the improved SIFT algorithm, the algorithm of SURF and GLOH (Gradient Locationand Orientation Histogram and GLOH), SIFT, and PCA-SIFT are all compared, the results showed that SURF are close to or exceed SIFT in all aspects of performance, and the…”
MethodBoosting histograms of descriptor distances for scalable multiclass specific scene recognition
Chin, T.-J., Suter, D., & Wang, H. (2010) · Image and Vision Computing · doi:10.1016/j.imavis.2010.11.002 · Cited by 8
Heterogeneous Visual Codebook Integration Via Consensus Clustering for Visual Categorization
López-Sastre, R. J., Renes-Olalla, J., Gil-Jiménez, P., et al. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2243058 · Cited by 8
I-BRIEF: A Fast Feature Point Descriptor with More Robust Features
Liu, J., & Liang, X. (2011) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis.2011.11 · Cited by 8
“Signatures by Michael Calonder et al. [8], [9], [10] can be computed much faster than SIFT or SURF.”
MethodInfluentialRobust image watermarking for camera-captured image using image registration technique
Thongkor, K., & Amornraksa, T. (2014) · International Symposium on Communications and Information Technologies · doi:10.1109/iscit.2014.7011959 · Cited by 8
Registering landsat-8 mosaic images: A case study on the Marmara sea
Sayar, A., Eken, S., & Mert, Ü. (2013) · International Conference on Electronics, Computer and Computation · doi:10.1109/icecco.2013.6718306 · Cited by 8
“[4] proposed a SIFT [5] based multi-spectral remote image registration technique which is actually similar to the SURF technique [6].”
MethodVaškevičius, N., Mueller, C. A., Bonilla, M., et al. (2014) · 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2014.6899490 · Cited by 8
Discrete Multiwavelet–Based Video Watermarking Scheme Using SURF
Leelavathy, N., Evani, V. P., & Samayamantula, S. K. (2015) · ETRI Journal · doi:10.4218/etrij.15.0114.0012 · Cited by 8
“SURF features are invariant to translation, rotation, and scaling [17].”
BackgroundEfficient object detection and tracking in video sequences
Dornaika, F., & Chakik, F. (2012) · Journal of the Optical Society of America A · doi:10.1364/josaa.29.000928 · Cited by 8
“Obviously, in the domain of computer vision, there are other feature extraction methods such as Speeded Up Robust Features (SURF) and Center Surround Extremas (CenSurE) that are described in [26,27].”
MethodPalmer, R., WEST, G. A. W., & Tan, T. (2012) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2012.6411699 · Cited by 8
“Some of the more successful and widely used include Harris keypoints [2], SIFT [3], SURF [4], and FAST [5]; all of which try to detect stable keypoints for use in matching the same locations across images.”
MethodHuman Machine Interface in Weld Seam Detection Using an RGB-D Camera
Silvers, G. A., & Fang, G. (2014) · Advanced materials research · doi:10.4028/www.scientific.net/amr.875-877.1967 · Cited by 8
Content-based synchronization for multiple photos galleries
Broilo, M., Boato, G., & Natale, F. G. B. D. (2012) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2012.6467267 · Cited by 8
Improved Vision-Based Algorithm for Unmanned Aerial Vehicles Autonomous Landing
Zhao, Y., & Pei, H. L. (2013) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.273.560 · Cited by 8
Panoramic image generation with lens distortions
Ju, M.-H., & Kang, H.-B. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738267 · Cited by 8
A Robust Method for Mosaicking Sequence Images Obtained from UAV
Cheng, X., Wang, J., & Xu, Y. (2010) · International Conference on Information Engineering and Computer Science · doi:10.1109/iciecs.2010.5678358 · Cited by 8
Reflection removal in smart devices using a prior assisted independent components analysis
Kalwad, P., Prakash, D., Peddigari, V. R., et al. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2083105 · Cited by 8
Intelligent visual mouse system based on hand pose trajectory recognition in video sequences
Maleki, B., & Ebrahimnezhad, H. (2014) · Multimedia Systems · doi:10.1007/s00530-014-0420-y · Cited by 8
“Bao et al. [13] used SURF (Speeded Up Robust Features) [14] points to spot the hand motion direction and its trajectory.”
Production of high-resolution digital terrain models in mountain regions to support risk assessment
Forlani, G., Roncella, R., & DIOTRI, F. (2013) · Geomatics Natural Hazards and Risk · doi:10.1080/19475705.2013.862746 · Cited by 8
A new descriptor resistant to affine transformation and monotonic intensity change
Huang, Z., Kang, W., Wu, Q., & Chen, X. (2013) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2013.10.010 · Cited by 8
Newborn Verification Using Headprint
Tiwari, S., & Singh, S. K. (2012) · Journal of Information Technology Research · doi:10.4018/jitr.2012040102 · Cited by 8
Pohl, M., Schaeferling, M., & Kiefer, G. (2014) · International Conference on Field Programmable Logic and Applications (FPL) · doi:10.1109/fpl.2014.6927463 · Cited by 8
AR City Representation System Based on Map Recognition Using Topological Information
Uchiyama, H., Saitô, H., Servieres, M. C. J., et al. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02771-0_15 · Cited by 8
“The feature points can be described using rich descriptors such as SIFT [7] or SURF [8], that typically use image patches.”
MethodCritical Advancement in Telerobotic Servicing Vision Technology
Miller, K., Masciarelli, J., Rohrschneider, R. R., & Gravseth, I. J. (2010) · AIAA SPACE Conference & Exposition · doi:10.2514/6.2010-8919 · Cited by 8
Joint Solution for the Online 3D Photorealistic Mapping Using SfM and SLAM
Choi, H., Jun, C., Yuen, S. L., Cho, H., & Doh, N. L. (2013) · International Journal of Advanced Robotic Systems · doi:10.5772/52854 · Cited by 8
Edge-Based Multi-modal Registration and Application for Night Vision Devices
Sutour, C., Aujol, J., Deledalle, C., & de Senneville, B. D. (2015) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-014-0554-8 · Cited by 8
“These descriptors have been widely studied and adapted [3,16], combined with classical matching algorithms such as the RANSAC algorithm [7], in order to estimate the optimal transformation.”
MethodAffine Stable Characteristic based sample expansion for object detection
Gao, K., Zhang, Y., Zhang, W., & Lin, S. (2010) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1816041.1816103 · Cited by 8
“As shown in the following subsection, with the small feature set comparable with traditional methods [16, 19], we can achieve much better detection performance than them.”
A lowbit rate vocabulary coding scheme for mobile landmark search
Ji, R., Duan, L., Chen, J., et al. (2011) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2011.5946946 · Cited by 8
“Comparing with previous works in compact local descriptors e.g. SURF [14] and PCA-SIFT [15], more recent works in [2][3][4][6] aim to achieve compression rates that are suitable for wireless transmission in mobile visual search scenarios.”
ResultExtend point descriptors for line, curve and region matching
Liu, H., Wang, Z., & Deng, C. (2010) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc.2010.5581065 · Cited by 8
“Also using sample gradients in local regions to characterize local texture information, many other methods, such as Shape Context [2], GLOH [3] and SURF [4] are developed.”
MethodRobust recognition of planar mirrored walls using a single view
Agha–mohammadi, A., & Song, D. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980211 · Cited by 11
Automatic Image Annotation using SURF Features
Shukla, T., Mishra, N., & Sharma, S. (2013) · International Journal of Computer Applications · doi:10.5120/11567-6868 · Cited by 8
Towards AUV Route Following Using Qualitative Navigation
Vandrish, P., Vardy, A., & King, P. (2012) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2012.63 · Cited by 8
THE USE OF MOBILE LASER SCANNING DATA AND UNMANNED AERIAL VEHICLE IMAGES FOR 3D MODEL RECONSTRUCTION
Zhu, L., Jaakkola, A., & Hyyppa, J. M. (2013) · 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-1-w2-419-2013 · Cited by 8
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.