SURF: Speeded Up Robust Features
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index; none of the 18 sources its claims cite is checked for support yet.
Overview
CoChat Summary
TL;DR
SURF is a scale- and rotation-invariant interest point detector and descriptor that uses integral images, Hessian-based detection, and Haar-wavelet responses to be faster than prior methods while matching or exceeding their repeatability and distinctiveness. It reports strong results on standard benchmarks and a museum object recognition task.
Key findings
- The Fast-Hessian detector is more than 3× faster than DoG and 5× faster than Hessian-Laplace, with comparable or better repeatability on Graffiti, Leuven, Boat, and Wall; on the first Graffiti image (800×640), computation times were 120 ms for Fast-Hessian, 400 ms for DoG, 650 ms for Hessian-Laplace, and 1800 ms for Harris-Laplace.
- SURF’s 64-dimensional descriptor outperformed GLOH, SIFT, and PCA-SIFT in most comparisons, sometimes by more than 10% improvement in recall for the same precision; SURF-128 was slightly better but slower to match.
- Joint detector-descriptor computation times on the first Graffiti image were 255 ms for U-SURF, 354 ms for SURF, 391 ms for SURF-128, and 1036 ms for SIFT.
- In museum object recognition, recognition rates were 85.7% for SURF-128, 83.8% for U-SURF, 82.6% for SURF, 78.3% for GLOH, 78.1% for SIFT, and 72.3% for PCA-SIFT.
Methods
- Design: a scale- and rotation-invariant detector/descriptor. The detector uses the determinant of the Hessian with box-filter approximations evaluated via integral images; the descriptor uses Haar-wavelet responses in a 4×4 subregion grid, producing a 64-dimensional vector, with an upright U-SURF variant and an extended SURF-128 variant.
- Data: standard evaluation sequences from Mikolajczyk (including Graffiti, Wall, Boat, Leuven, Bikes, Trees, and Ubc; Bark excluded from descriptor evaluations) and a real-life museum object recognition database of 216 images of 22 objects, with 116 test images at 320×240.
- Analysis: detector repeatability scores, descriptor recall-(1-precision) graphs under similarity-threshold and nearest-neighbour-ratio matching, recognition rates, and computation timings on a standard Linux PC (Pentium IV, 3 GHz).
Limitations
- The paper has no explicit limitations section. It states that space limitations prevent showing results on all sequences, and it assumes skew, anisotropic scaling, and perspective effects are second-order effects covered only by overall descriptor robustness.
- Evident from the text: the method is scale- and rotation-invariant but not affine-invariant; Fig. 4 notes the interest points are not affine invariant, and the descriptor does not use colour.
- Evident from the text: the object recognition experiment uses small 320×240 test images and matching without additional geometric constraints, which the authors say would reduce false positives but were omitted for comparison purposes.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
0 Valid · 2 Not valid · 12 Not checked · 30 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The number of interest points found is on average very similar for all detectors.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 4 × 4 sub-region division solution provided the best results.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SURF outperformed the other descriptors for almost all the comparisons.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The SURF descriptor outperforms the other descriptors in a systematic and significant way, with sometimes more than 10% improvement in recall for the same level of precision.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in the results section, the performance is comparable to the one using the discretised and cropped Gaussians.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
8 more claims
Create a free account to see all 44 claims and every source verdict.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This transition marked a new era, where we moved beyond the classic approaches and task-specific feature engineering of earlier days [Lowe 2004; Bay et al. 2006; Rosten and Drummond 2006] towards models that could be trained once over large amounts of data, and then adapted for a broad variety of tasks, such as image recognition, object detection, and image segmentation [Krizhevsky et al. 2012; Sz”
From On the Opportunities and Risks of Foundation Models (2021) · cites this paper as Bay et al. 2006
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · cited 14×
“This PCA-SIFT yields a 36-dimensional descriptor which is fast for matching, but proved to be less distinctive than SIFT in a second comparative study by Mikolajczyk et al. [8] and slower feature computation reduces the effect of fast matching.”
BackgroundMethodResultInfluentialMarr, D., & Hildreth, E. (1980) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1980.0020 · Cited by 6,510
PCA-SIFT: a more distinctive representation for local image descriptors
Ke, Y., & Sukthankar, R. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.183 · Cited by 3,932
Robust wide-baseline stereo from maximally stable extremal regions
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.02.006 · Cited by 3,686
Scalable Recognition with a Vocabulary Tree
Nister, D., & Stewenius, H. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.264 · Cited by 3,579
Scale & Affine Invariant Interest Point Detectors
Mikolajczyk, K., & Schmid, C. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000027790.02288.f2 · Cited by 3,436
Cited by
Items 4,301–4,400 of 14,752
Human identification by gait from event-based camera
Sokolova, A., & Konushin, A. (2019) · Machine Vision Applications · doi:10.23919/mva.2019.8758019 · Cited by 17
“The features are extracted from these maps using Speeded Up Robust Features (SURF) [3] and than clusterized and classified.”
MethodScale, translation and rotation invariant Wavelet Local Feature Descriptor
Barajas-García, C., Solorza-Calderón, S., & Gutiérrez-López, E. (2019) · Applied Mathematics and Computation · doi:10.1016/j.amc.2019.124594 · Cited by 15
Analyzing periodicity and saliency for adult video detection
Liu, Y., Gu, X., Huang, L., Ouyang, J., Liao, M., & Wu, L. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7576-6 · Cited by 15
Object Detection Based on Multiple Information Fusion Net
Zhang, Y., Kong, J., Qi, M., Liu, Y., Wang, J., & Lu, Y. (2020) · Applied Sciences · doi:10.3390/app10010418 · Cited by 14
“Several techniques can be used in this step for feature extraction, such as scale-invariant feature transform (SIFT) [2], histogram of oriented gradients (HOG) [3] and speeded-up robust features (SURF) [4].”
MethodSuzuki, K., Yokota, Y., Kanazawa, Y., & Takebayashi, T. (2020) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii46433.2020.9025845 · Cited by 17
“One solution is to weight each trial sample by the success degree of the sample, but the success estimation requires a detailed image processing of each object, which is extremely costly [10].”
BackgroundZhao, Y., Liu, G., Xu, S., Bu, S., Jiang, H., & Wan, G. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3008517 · Cited by 16
Diabetic retinopathy identification using autoML
Harikrishnan, V. K., Vijarania, M., & Gambhir, A. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-820604-1.00012-1 · Cited by 14
Stereo Vision-Based Depth Estimation
Meng, Z., Kong, X., Meng, L., et al. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-3514-7_90 · Cited by 14
Volume Sweeping: Learning Photoconsistency for Multi-View Shape Reconstruction
Leroy, V., Franco, J.-S., & Boyer, E. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-020-01377-0 · Cited by 18
Deep Local Feature Descriptor Learning With Dual Hard Batch Construction
Wang, S., Guo, X., Tie, Y., Qi, L., & Guan, L. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3029424 · Cited by 15
“The most representative ones are Scale Invariant Feature Transform (SIFT) [3] and its derivatives [5]–[9], which estimate the correspondence of features by exploring the gradient magnitudes and directions.”
BackgroundFeature Detection and Matching With Linear Adjustment and Adaptive Thresholding
Cai, Z., Ou, Y., Ling, Y., Dong, J., Lü, J., & Lee, H. (2020) · IEEE Access · doi:10.1109/access.2020.3030183 · Cited by 14
“The SURF [10] algorithm is improved on the basis of SIFT algorithm.”
MethodJiang, Z., Wang, X., Huang, X., & Li, H. (2021) · Image and Vision Computing · doi:10.1016/j.imavis.2021.104127 · Cited by 14
Gonzalez-Soler, L. J., Gomez‐Barrero, M., Kolberg, J., Chang, L., Pérez‐Suárez, A., & Busch, C. (2021) · IET Biometrics · doi:10.1049/bme2.12023 · Cited by 15
“In summary, the main contributions of this work with respect to our preliminary study in [22] are as follows: � New fingerprint representation to accurately identify artefacts produced by materials used in the fabrication of PAIs, which combines the generalisation capability of FV with different well‐known descriptors…”
MethodInfluentialAll around the map: Online spherical panorama construction
DiVerdi, S., Wither, J., & Höllerer, T. (2008) · Computers & Graphics · doi:10.1016/j.cag.2008.11.002 · Cited by 14
Context-based object recognition for door detection
Kim, S., Cheong, H., Kim, D. H., & Park, S.-K. (2011) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2011.6088578 · Cited by 17
Abdel-Wahab, M., Wenzel, K., & Fritsch, D. (2012) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-i-3-1-2012 · Cited by 14
Detecting Markers in Blurred and Defocused Images
Toyoura, M., Aruga, H., Turk, M., & Mao, X. (2013) · International Conference on Cyberworlds (CW) · doi:10.1109/cw.2013.58 · Cited by 14
Improving HySpex Sensor Co-registration Accuracy using BRISK and Sensor-model based RANSAC
Schwind, P., Schneider, M., & Müller, R. (2014) · 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-1-371-2014 · Cited by 14
Evaluation of local features and classifiers in BOW model for image classification
Qu, Y., Wu, S., Liu, H., Xie, Y., & Wang, H. (2012) · Multimedia Tools and Applications · doi:10.1007/s11042-012-1107-z · Cited by 12
Fast reciprocal nearest neighbors clustering
López-Sastre, R. J., Oñoro-Rubio, D., Gil-Jiménez, P., & Maldonado-Bascón, S. (2011) · Signal Processing · doi:10.1016/j.sigpro.2011.07.023 · Cited by 13
Visual attention guided features selection with foveated images
Gomes, R. B., de Carvalho, B. M., & Gonçalves, L. M. G. (2013) · Neurocomputing · doi:10.1016/j.neucom.2012.10.033 · Cited by 14
Simultaneous Camera Pose and Correspondence Estimation with Motion Coherence
Lin, W.-Y., Cheong, L., Tan, P., et al. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-011-0456-9 · Cited by 14
“However, despite many advances in matching techniques (Bay et al. 2006; Harris and Stephens 1988; Lowe 2004), obtaining correspondences across two images remains a non-trivial problem and contains a strong underlying assumption that the features are sufficiently distinct to enable unique point to point correspondence.”
BackgroundMulti-camera based real-time configuration estimation of continuum robots
Weber, B., Zeller, P., & Kühnlenz, K. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385944 · Cited by 14
Dang, Q. B., Le, V. P., Luqman, M. M., et al. (2015) · Proceedings of the International Conference on Document Analysis and Recognition · doi:10.1109/icdar.2015.7333956 · Cited by 14
Detection and tracking of objects with direct integration of perception and expectation
Jüngling, K., & Arens, M. (2009) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2009.5457576 · Cited by 14
Redundancy removal through semantic neighbor selection in Visual Sensor Networks
Bai, Y., & Qi, H. (2009) · ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC) · doi:10.1109/icdsc.2009.5289402 · Cited by 14
Accurate map merging with virtual emphasis for multi‐robot systems
Lee, H. C., Cho, Y. J., & Lee, B.-U. (2013) · Electronics Letters · doi:10.1049/el.2013.1572 · Cited by 14
Local distortion resistant image watermarking relying on salient feature extraction
Nikolaidis, A. (2012) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/1687-6180-2012-97 · Cited by 14
“As one can see in Figure 23, the technique by Dong et al. is flawless for all values of standard deviation, followed in order of performance by the SIFT-based and the SURF-based versions of our method, with RST-based and FAST-based following.”
InfluentialMonzó, D., Albiol, A., Sastre, J., et al. (2008) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2008.4712085 · Cited by 14
AR GIS on a Physical Map based on Map Image Retrieval using LLAH Tracking
Uchiyama, H., Saitô, H., Servieres, M. C. J., et al. (2009) · Cited by 14
SURF-Based SLAM Scheme using Octree Occupancy Grid for Autonomous Landing on Asteroids
Cocaud, C., & Kubota, T. (2010) · Cited by 14
A survey of simultaneous localization and mapping on unstructured lunar complex environment
Wang, Y., Zhang, W., & An, P. (2017) · AIP conference proceedings · doi:10.1063/1.5005198 · Cited by 17
A Fast and Power-Efficient Hardware Architecture for Visual Feature Detection in Affine-SIFT
Ouyang, P., Yin, S., Liu, L., Zhang, Y., Zhao, W. S., & Wei, S. (2018) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2018.2806447 · Cited by 15
GPU-based Image Analysis on Mobile DevicesPreprint
Ensor, A., & Hall, S. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1112.3110 · Cited by 16
Grounding Spatio-Semantic Referring Expressions for Human-Robot InteractionPreprint
Shridhar, M., & Hsu, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.05720 · Cited by 17
“Lastly, the process of encoding visual information usually involves hand-picking feature extractors such as SIFT [24] or SURF [3].”
Multi-Modal Data and Model Reduction for Enabling Edge Fusion in Connected Vehicle Environments
Thornton, S., & Dey, S. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3378182 · Cited by 20
“…histograms as our low complexity model to provide very low computation inference time as well as data size but could have chosen lightweight multi-layer perceptron (MLP) DNN models as well as other image descriptors [78] [79] or image transforms [80] [81] if a larger decision space was needed.”
BackgroundRobot Manipulation Based on Embodied Visual Perception: A Survey
Wang, S., Nikolić, M. N., Lam, T. L., Gao, Q. H., Ding, R., & Zhang, T. (2025) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70022 · Cited by 28
AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
Vuong, K., Ghosh, A., Ramanan, D., Narasimhan, S. G., & Tulsiani, S. (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/cvpr52734.2025.02019 · Cited by 62
“While classical pipelines [50, 51] leveraged hand-designed features [3, 35, 44] and matching mechanisms, their subsequent incarnations [7, 39, 63] have incorporated several learning-based components e.g . learned features [13, 32] or learned “doppelganger” detectors [8].”
Exploiting ground plane constraints for visual-inertial navigation
Panahandeh, G., Zachariah, D., & Jansson, M. (2012) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans.2012.6236923 · Cited by 15
“We used the speeded up robust features (SURF) [27], which is invariant to image scale and rotation.”
MethodA Robust Image Matching Method based on Optimized BaySAC
Kang, Z., Jia, F., & Zhang, L. (2014) · Photogrammetric Engineering & Remote Sensing · doi:10.14358/pers.80.11.1041 · Cited by 13
Optical Flow Requires Multiple Strategies (but Only One Network)
Schuster, T., Wolf, L., & Gadot, D. (2017) · 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.2017.732 · Cited by 16
Real-Time Monocular Visual Odometry for Turbid and Dynamic Underwater Environments
Ferrera, M., Moras, J., Trouvé-Peloux, P., & Creuze, V. (2019) · Sensors · doi:10.3390/s19030687 · Cited by 100
“The following combination of features detector and descriptor are compared: ORB [22], BRISK [50], FAST [51] + BRIEF [21], FAST + FREAK [52], SIFT [53] and SURF [18].”
MethodModern approaches to computer vision
Tymchyshyn, R. M., Volkov, O. Y., Gospodarchuk, O. Y., & Bogachuk, Y. P. (2018) · Control Systems and Computers · doi:10.15407/usim.2018.06.046 · Cited by 30
Full Direction Local Neighbors Pattern (FDLNP)
Alrahhal, M., & Supreethi, K. P. (2021) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2021.0120116 · Cited by 19
Automatic feature type selection in digital photogrammetry of piping
Tian, Y., Ding, C., Lin, Y.-F., Ma, S., & Li, L. (2022) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12840 · Cited by 12
Choi, I., Kim, J., & JungHoon, S. (2022) · Measurement · doi:10.1016/j.measurement.2022.111062 · Cited by 13
Pose Estimation Method for Non-Cooperative Target Based on Deep Learning
Deng, L., Suo, H., Jia, Y., & Huang, C. (2022) · Aerospace · doi:10.3390/aerospace9120770 · Cited by 12
ImTooth: Neural Implicit Tooth for Dental Augmented Reality
Li, H., Zhai, H., Yang, X., Wu, Z., Zheng, Y., Wang, H., Wu, J.-C., Bao, H., & Zhang, G. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3247459 · Cited by 20
Deep learning for face mask detection: a survey
Sharma, A., Gautam, R., & Singh, J. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14686-6 · Cited by 19
Universal high spatial resolution hyperspectral imaging using hybrid-resolution image fusion
Cao, X., Lian, Y., Liu, Z., et al. (2023) · Optical Engineering · doi:10.1117/1.oe.62.3.033107 · Cited by 13
Optical and SAR Image Registration Based on the Phase Congruency Framework
Xie, Z., Zhang, W., Wang, L., et al. (2023) · Applied Sciences · doi:10.3390/app13105887 · Cited by 13
Choi, J., Ma, Z., Kim, K., et al. (2023) · Measurement · doi:10.1016/j.measurement.2023.113158 · Cited by 13
“3(a) and (b), using speeded-up robust features (SURF) [26], a feature matching algorithm with a relatively lower computational cost Fig.”
MethodChoi, J., Chung, J., Kim, K., et al. (2023) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2023.110504 · Cited by 13
An effective stereo SLAM with high-level primitives in underwater environment
Xu, S., Ma, T., Li, Y., Ding, S., Gao, J., Xia, J., Qi, H., & Gu, H. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/ace645 · Cited by 13
“They also developed an online word bag model to enhance loop closure accuracy, using a combination of scale-invariant feature transform (SIFT) [16] and speeded up robust features (SURF) [17] features.”
Multi-View Clustering via Triplex Information Maximization
Zhang, C., Lou, Z., Zhou, Q., & Hu, S. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3297410 · Cited by 19
“Two kinds of features are used for describing these images, i.e., 800D-SIFT [32] and 800D-SURF [40] features.”
MethodSubramanian, J. A., Asirvadam, V. S., Zulkifli, S. A. B. M., Singh, N. S. S., Shanthi, N., & Lagisetty, R. K. (2023) · Drones · doi:10.3390/drones7080509 · Cited by 16
“SURF (Speeded-Up Robust Features) is a faster version of SIFT that uses a Hessian matrix approximation to identify key points and extract descriptors [90].”
MethodPark, J. S., & Park, H. S. (2023) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13083 · Cited by 13
“Proposed techniques for object detection encompass template matching, Hough transform (Duda & Hart, 1972), scale-invariant feature transform (Lowe, 1999), and speeded-up robust features (Bay et al., 2006).”
MethodFeature-based Visual Odometry for Bronchoscopy: A Dataset and Benchmark
Deng, J., Li, P., Dhaliwal, K., Lu, C. X., & Khadem, M. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342034 · Cited by 14
A Deep Learning Model to Inspect Image Forgery on SURF Keypoints of SLIC Segmented Regions
Uliyan, D. M. (2024) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.6622 · Cited by 13
Robust Heterogeneous Model Fitting for Multi-source Image Correspondences
Lin, S., Huang, F., Lai, T., Lai, J., Wang, H., & Weng, J. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02023-9 · Cited by 17
Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks
Jiang, Z., Li, X. R., Liu, J., Fan, X., & Liu, R. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i3.28036 · Cited by 26
Fast Double-Channel Aggregated Feature Transform for Matching Planetary Remote Sensing Images
Huang, R., Wan, G., Zhou, Y., Ye, Z., Xie, H., Xu, Y., & Tong, X. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3390432 · Cited by 14
Zheng, L., Zhao, X., Xu, S., Ren, Y., & Zheng, Y. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109640 · Cited by 15
Liu, C.-W., Zhang, Y., Chen, Q., Pitas, I., & Fan, R. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3540283 · Cited by 15
“Conventional hand-crafted sparse correspondence matching approaches [30], [31], [32] first extract keypoints using explicitly designed local feature detectors and descriptors.”
Saliency-constrained semantic learning for airport target recognition of aerial images
Zhao, D., Shi, J., Wang, J., et al. (2015) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.9.096058 · Cited by 13
Junior, L. J. L., Oliveira-Santos, T., Badue, C. S., & Souza, A. F. D. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139699 · Cited by 14
Feature-Based Methods in 3D Shape Analysis
Bronstein, A. M., Bronstein, M. M., & Ovsjanikov, M. (2012) · Springer eBooks · doi:10.1007/978-1-4471-4063-4_5 · Cited by 16
LOIND: An illumination and scale invariant RGB-D descriptor
Feng, G., Liu, Y., & Liao, Y. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139445 · Cited by 14
Image based Monument Recognition using Graph based Visual Saliency
Triantafyllidis, G. A., & Kalliatakis, G. (2013) · ELCVIA Electronic Letters on Computer Vision and Image Analysis · doi:10.5565/rev/elcvia.524 · Cited by 13
Symbol recognition with a new autonomously evolving classifier autoclass
Angelov, P. P., Kangin, D., Zhou, X., et al. (2014) · IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS) · doi:10.1109/eais.2014.6867482 · Cited by 13
“BRISK [21], SIFT [22], SURF [23], HOG [24], gist [4], based on Gabor filters [25], are amongst them.”
MethodOn the accuracy of 3D landscapes from UAV image data
Douterloigne, K., Gautama, S., & Philips, W. R. (2010) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2010.5651391 · Cited by 13
“First feature points are extracted in all images (e.g. SURF [3]) and are matched with each other.”
BackgroundRecognition of facial sketch styles
Zhang, M., Li, J., Wang, N., & Gao, X. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.09.009 · Cited by 12
RGB-D sensor based SLAM and human tracking with Bayesian framework for wheelchair robots
Wu, B., Jen, C.-L., Li, W.-F., Tsou, T.-Y., Tseng, P.-Y., & Hsiao, K.-T. (2013) · International Conference on Advanced Robotics and Intelligent Systems (ARIS) · doi:10.1109/aris.2013.6573544 · Cited by 13
Scene classification using multiple features in a two-stage probabilistic classification framework
Sun, Z.-L., Rajan, D., & Chia, L.-T. (2010) · Neurocomputing · doi:10.1016/j.neucom.2010.07.004 · Cited by 13
Toward mutual information based automatic registration of 3D point clouds
Pandey, G., McBride, J. R., Savarese, S., & Eustice, R. M. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386053 · Cited by 13
People Locator: A System for Family Reunification
Thoma, G. R., Antani, S., Gill, M., Pearson, G., & Neve, L. (2012) · IT Professional · doi:10.1109/mitp.2012.25 · Cited by 12
Emergency medicine training with gesture driven interactive 3D simulations
Bartoli, G., Bimbo, A. D., Faconti, M., et al. (2012) · doi:10.1145/2390895.2390903 · Cited by 13
Visual context identification for privacy-respecting video analytics
Badii, A., Einig, M., Tiemann, M., et al. (2012) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2012.6343470 · Cited by 13
A probabilistic definition of salient regions for image matching
Maybank, S. J. (2013) · Neurocomputing · doi:10.1016/j.neucom.2012.06.060 · Cited by 13
Image classification using boosted local features with random orientation and location selection
Zhang, C., Cheng, J., Zhang, Y., Liu, J., Liang, C., Pang, J., Huang, Q., & Tian, Q. (2015) · Information Sciences · doi:10.1016/j.ins.2015.03.011 · Cited by 14
Improved keypoint descriptors based on Delaunay triangulation for image matching
Zhao, X., He, Z., & Zhang, S. (2014) · Optik · doi:10.1016/j.ijleo.2013.12.022 · Cited by 13
Kim, A., & Eustice, R. M. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094820 · Cited by 20
Optimizing Camera Perspective for Stereo Visual Odometry
Peretroukhin, V., Kelly, J. W., & Barfoot, T. D. (2014) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2014.9 · Cited by 15
“Stereo matching was performed by matching SURF descriptors and aided by epipolar constraints.”
MethodFusing matching and biometric similarity measures for face diarization in video
Khoury, E., Gay, P., & Odobez, J. (2013) · doi:10.1145/2461466.2461484 · Cited by 13
“SIFT and SURF [2] features computed on regions around automatically detected points-of-interest are known to be robust to scale, rotation, and illumination variations.”
BackgroundInfluentialTubeTagger - YouTube-based Concept Detection
Ulges, A., Koch, M., Borth, D., et al. (2009) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2009.41 · Cited by 13
Jin, F., & Feng, D. (2014) · PLoS ONE · doi:10.1371/journal.pone.0095576 · Cited by 13
Sketch retrieval via local dense stroke features
Ma, C., Yang, X., Zhang, C., Ruan, X., & Yang, M. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2015.11.007 · Cited by 13
Bag of Features Model Using the New Approaches: A Comprehensive Study
Chougrad, H., Zouaki, H., & Alheyane, O. (2016) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2016.070132 · Cited by 18
Robust Ego-Motion Estimation with ToF Cameras.
Droeschel, D., May, S., Holz, D., Plöger, P.-G., & Behnke, S. (2009) · Cited by 13
A comparison of key-point descriptors for the stereo matching algorithm
Satnik, A., Hudec, R., Kamencay, P., Hlubík, J., & Benčo, M. (2016) · International Conference Radioelektronika · doi:10.1109/radioelek.2016.7477419 · Cited by 13
“The SURF descriptor [4] is closely related to the SIFT descriptor in the sense that it is also a feature vector derived from receptive-field-like responses in a neighborhood of an interest point.”
MethodReal-time facial feature tracking in poor quality thermal imagery
Kwaśniewska, A., & Rumiński, J. (2016) · International Conference on Human System Interaction · doi:10.1109/hsi.2016.7529681 · Cited by 12
Video shot boundary detection method using histogram differences and local image descriptor
Bendraou, Y., Essannouni, F., Aboutajdine, D., et al. (2014) · World Conference on Complex Systems · doi:10.1109/icocs.2014.7060883 · Cited by 13
Lee, S., Wei, L., & Naguib, A. M. (2016) · IEEE International Symposium on Assembly and Manufacturing · doi:10.1109/isam.2016.7750717 · Cited by 13
“The appearance based approach exploits the uniqueness of photometric appearance by adopting invariant features such as SURF [3], SIFT [4] and HOG [5] and/or by exploring eigenspaces [1] and color histograms [2].”
MethodDung, L., & Mizukawa, M. (2009) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2009.p0726 · Cited by 13
Off the Shelf Cloud Robotics for the Smart Home: Empowering a Wireless Robot through Cloud Computing
de la Pinta, J. R., Torreblanca, J. M., Jurado, I., & Cozar, S. R. D. (2017) · Sensors · doi:10.3390/s17030525 · Cited by 13
Learning-based tone mapping operator for image matching
Rana, A., Valenzise, G., & Dufaux, F. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296707 · Cited by 13
Adaptive representation-based face sketch-photo synthesis
Li, J., Yu, X., Peng, C., et al. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.10.095 · Cited by 13
A fast stochastic framework for automatic MR brain images segmentation
Ismail, M., Soliman, A., Ghazal, M. A., Switala, A. E., Gimel’farb, G., Barnes, G. N., Khalil, A., & El-Baz, A. S. (2017) · PLoS ONE · doi:10.1371/journal.pone.0187391 · Cited by 14
A Non-Cooperative Satellite Feature Point Selection Method for Vision-Based Navigation System
Ning, M., Zhang, S., & Wang, S. (2018) · Sensors · doi:10.3390/s18030854 · Cited by 13
Visual–inertial estimation of velocity for multicopters based on vision motion constraint
Deng, H., Arif, U., Fu, Q., Xi, Z., Quan, Q., & Cai, K. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.06.010 · Cited by 13
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.