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 9,301–9,400 of 14,752
Deeply Activated Salient Region for Instance SearchPreprint
Xiao, H.-C., Zhao, W., Lin, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.00185 · Cited by 3
“Hand-crafted features such as SIFT [5] and SURF [6] that are superior in local image matching were de-facto descriptors at that time.”
MethodFeatures for Ground Texture Based Localization -- A SurveyPreprint
Schmid, J. F., Simon, S. F., & Mester, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.11948 · Cited by 13
Khaliq, A., Ehsan, S., Milford, M. J., & McDonald-Maier, K. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.08153 · Cited by 11
“Feature extraction technique can either be handcraft-based (such as SURF [2], SIFT [3] and HOG [4]) or deep neural networks with rich spatial information from middle and late convolutional layers [5]; both have made an attempt to solve the VPR problem.”
MethodHomography Estimation with Convolutional Neural Networks Under Conditions of VariancePreprint
Niblick, D. K., & Kak, A. C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.01041 · Cited by 3
“Commonly used algorithms for feature detection and description include Scale Invariant Feature Transform (SIFT) [13], Speeded Up Robust Features (SURF) [1], and Oriented FAST and Rotated BRIEF (ORB) [17].”
MethodUKPGAN: Unsupervised KeyPoint GANeration.Preprint
You, Y., Liu, W., Li, Y., Wang, W., & Lu, C. (2020) · arXiv (Cornell University) · Cited by 3
Convolutional neural network-based vision systems for unmanned aerial vehicles
Verbickas, R. (2013) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2013-06787 · Cited by 3
Sequential Place Learning: Heuristic-Free High-Performance Long-Term Place RecognitionPreprint
Chancán, M., & Milford, M. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02074 · Cited by 6
Learning Camera Localization via Dense Scene MatchingPreprint
Tang, S., Tang, C., Huang, R., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.16792 · Cited by 3
Graph-Based Thermal–Inertial SLAM With Probabilistic Neural NetworksPreprint
Saputra, M. R. U., Lu, C. X., de Gusmão, P. P. B., Wang, B., Markham, A., & Trigoni, N. (2021) · IEEE Transactions on robotics · doi:10.48550/arxiv.2104.07196 · Cited by 51
Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace ProjectionPreprint
Ye, N., Wang, C., Fan, H., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.15346 · Cited by 3
Computer vision application in tracking grooming behaviour in arthropodsPreprint
Munshi, C., Sadhu, A., Chatterjee, S. K., & Bhattacharya, S. (2021) · Research Square · doi:10.21203/rs.3.rs-631124/v1 · Cited by 3
Telefonica Research Content-Based Copy Detection TRECVID Submission.
Anguera, X., Obrador, P., Adamek, T., et al. (2009) · TRECVID · Cited by 3
On Forecasting Lung Cancer Patients’ Survival Rates Using 3D Feature Engineering
Ghani, T. (2019) · doi:10.22215/etd/2019-13731 · Cited by 3
Deep Metric Learning for Ground ImagesPreprint
Radhakrishnan, R., Schmid, J. F., Scholz, R., & Schmidt-Thieme, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.01569 · Cited by 4
No way to crop: On robust image crop localization.Preprint
Ying, Q., Hu, X., Zhou, H., Zhang, X., You, Z., & Qian, Z. (2021) · arXiv (Cornell University) · Cited by 2
AI-supported Framework of Semi-Automatic Monoplotting for Monocular Oblique Visual Data AnalysisPreprint
Golparvar, B., & Wang, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.14021 · Cited by 3
Andrade‐Cetto, J., & Villamizar, M. (1999) · Wiley Encyclopedia of Electrical and Electronics Engineering · doi:10.1002/047134608x.w5512 · Cited by 3
A Comprehensive Literature Review on Convolutional Neural NetworksPreprint
Mohammed, E. U. R., Reddy, S. N., & Waseem, M. S. (2022) · doi:10.36227/techrxiv.21746237 · Cited by 6
A Comprehensive Literature Review on Convolutional Neural NetworksPreprint
Mohammed, E. U. R., Reddy, S. N., & Waseem, M. S. (2022) · doi:10.36227/techrxiv.21746237.v1 · Cited by 5
Into Darkness: Visual Navigation Based on a Lidar-Intensity-Image PipelinePreprint
Barfoot, T. D., McManus, C., Anderson, S., Dong, H., Beerepoot, E., Tong, C. H., Furgale, P., Gammell, J. D., & Enright, J. P. (2023) · doi:10.32920/23796135 · Cited by 2
Evaluating SLAM algorithms for Autonomous Helicopters
Skoglund, M. A. (2008) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 3
y Terán, A. R. M. (2013) · theses.fr (ABES) · doi:10.70675/ec3de82azbd4cz4035zafeaz6134de504570 · Cited by 6
Room layout estimation on mobile devices
Angladon, V. (2018) · theses.fr (ABES) · doi:10.70675/16e4b911z377bz47d8zac58z5a0fea7f57d8 · Cited by 4
Hypergraph based visual categorization and segmentation
Huang, Y. (2010) · Rutgers University Community Repository (Rutgers University) · doi:10.7282/t3tt4qqf · Cited by 3
Salarian, M., & Ansari, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.00319 · Cited by 3
Object Detection and Tracking with Occlusion Handling in Maritime Surveillance-A Review
Banu, R., & Sidram, M. H. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9181-1_8 · Cited by 2
Comparative evaluation of keypoint detectors for 3d digital avatar reconstruction
GAJIĆ, D. B., Gojić, G., Драган, Д., et al. (2020) · Facta universitatis - series Electronics and Energetics · doi:10.2298/fuee2003379g · Cited by 2
Fully Leveraging Deep Learning Methods for Constructing Retinal Fundus Photomontages
Kim, J., Go, S., Noh, K. J., Park, S. J., & Lee, S. (2021) · Applied Sciences · doi:10.3390/app11041754 · Cited by 3
Advanced Environment Modelling for Remote Teleoperation to Improve Operator Experience
Jin, Y., Soto, D. A. P., Rossiter, J. A., et al. (2021) · doi:10.1145/3487923.3487939 · Cited by 2
“For feature extraction, traditional approaches in the image domain (SIFT [16] and SURF [2]) used at Bundle-Fusion [8] perform poorly in homogeneous surfaces, such as metal, which can be observed from TABLE 1.”
MethodHistogram of Low-Level Visual Features for Salient Feature Extraction
Mehboob, R., Javed, A., Dawood, H., & Dawood, H. (2022) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-022-06644-5 · Cited by 2
PERFORMANCE OF LOCALIZATION BASED ON VISUAL SLAM AND LIDAR POINT CLOUD REGISTRATION
Lu, P. R., Chiang, K., Lin, Y.-J., et al. (2023) · 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/isprs-archives-xlviii-1-w1-2023-257-2023 · Cited by 2
AMFF-net: adaptive multi-modal feature fusion network for image classification
Liu, W., Lu, X., & Wei, Y. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16217-9 · Cited by 2
Comparing Screen-Based Version Control to Augmented Artifact Version Control for Physical Objects
Letter, M., Kurzweg, M., & Wolf, K. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42280-5_25 · Cited by 2
Video Quality Assessment System Using Deep Optical Flow and Fourier Property
Kang, D., Kim, Y., Kwon, S., Kim, H., Kim, J., & Paik, J. (2023) · IEEE Access · doi:10.1109/access.2023.3335352 · Cited by 2
Speed Matters, a robust infrared and visible image matching method at real-time speed
Chang, R., Yang, C., Zhang, H., et al. (2024) · Journal of Real-Time Image Processing · doi:10.1007/s11554-023-01395-4 · Cited by 2
Analyzing the Domain Shift Immunity of Deep Homography Estimation
Shao, M., Taşdizen, T., & Joshi, S. C. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00473 · Cited by 3
“Traditional homography estimation methods typically rely on matched image feature points, such as SIFT [17], SURF [3], ORB [22], LPM [19], GMS [4], SOSNet [26], LIFT [25], and OAN [28].”
MethodKim, H.-W., Noh, S.-C., Kim, S., Chu, H.-W., Jung, C.-H., & Kang, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-69153-5 · Cited by 3
“These functions can be addressed using relatively classical algorithms 12–14 .”
BackgroundLiang, Z., Gabrieli, F., Pol, A., et al. (2024) · Remote Sensing · doi:10.3390/rs16173233 · Cited by 2
Li, F., Zou, C., Yun, J., Huang, L., Liu, Y., Tao, B., & Xie, Y. (2024) · Sensors · doi:10.3390/s24206680 · Cited by 3
“They often used feature detection and description algorithms, such as scale-invariant feature transform (SIFT) [17] and sped-up robust features (SURF) [18], to obtain descriptors and perform matching.”
MethodRelative pose estimation from panoramic images using a hybrid neural network architecture
Offermann, L. (2024) · Scientific Reports · doi:10.1038/s41598-024-75124-7 · Cited by 2
“Examples for manually designed feature detectors and descriptors are SIFT 11 , SURF 12 , and ORB 13 .”
MethodSpecular Region Detection and Covariant Feature Extraction
Bappy, D. M., Kang, D., Lee, J., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78198-8_12 · Cited by 2
UAVs-Based Visual Localization via Attention-Driven Image Registration Across Varying Texture Levels
Ren, Y., Dong, G., Zhang, T., et al. (2024) · Drones · doi:10.3390/drones8120739 · Cited by 2
A Novel Approach to Fire Detection With Enhanced Target Localisation and Recognition
Zou, L., Sun, Q., Jiang, F., Wu, Z., Sun, L., Wang, X., Gogate, M., Dashtipour, K. K., & Hussain, A. (2025) · Expert Systems · doi:10.1111/exsy.70006 · Cited by 2
Automated intrinsic/extrinsic PTZ camera calibration using mobile LiDAR data
Hany, Y., Abdelghany, A. A., Eissa, A. M., Hodaei, M., Liu, J., Shin, S.-Y., Mathew, J. K., Cox, E., Wells, T., Bullock, D. M., et al. (2025) · Measurement · doi:10.1016/j.measurement.2025.117023 · Cited by 3
Grid-Guided Sparse Laplacian Consensus for Robust Feature Matching
Xia, Y., & Ma, J. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3539469 · Cited by 20
“Classical feature extraction and description methods, such as SIFT [6], SURF [33], and KAZE [34], are widely used due to their low implementation cost.”
A Feature Disentanglement Method for Image Stitching of Printed Circuit Boards
Zhou, Z., Zhu, Q. X., Luo, J., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3547509 · Cited by 2
“Lever-aging SIFT [6], SURF [7], and SOSNet [20], we selected RANSAC [4] and MAGSAC [26] as the most effective out-lier removal algorithms.”
Zhang, S., Wu, J., Wang, K., & Deng, S. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3550799 · Cited by 2
Lin, L., Lin, C., Nie, L., et al. (2025) · The Visual Computer · doi:10.1007/s00371-025-03889-7 · Cited by 2
“Image-to-image registration has traditionally relied on hand-crafted local feature descriptors such as SIFT [10], SURF [11], and ORB [12].”
RWZC: A Model-Driven Approach for Learning-Based Robust Wyner-Ziv Coding
Shi, Y., Shao, S., Wu, Y., et al. (2025) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3559128 · Cited by 2
“First, feature points of each image pair are extracted by conventional algorithm, e.g. SIFT/SURF/FAST/ORB [18], [19], [20], [21].”
Measuring marine hydrodynamics from space using planet satellite imagery
Tlhomole, J. B., Alosairi, Y., Hughes, G. O., & Piggott, M. D. (2025) · Remote Sensing of Environment · doi:10.1016/j.rse.2025.114741 · Cited by 2
SOR-YOLO: a strip-shaped object detection network for traffic columns and traffic cones
Wang, J., Wang, Y., Zhou, C., & Wang, H. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04017-7 · Cited by 2
“…robustness of autonomous driving systems under adverse weather conditions and complex lighting environments [19], as well as improving their ability to respond to temporary and unpredictable situations such as road construction [20], traffic accidents, and temporary traffic control facilities [21].”
Bharti, D., & Venkatesh, K. S. (2025) · IEEE Access · doi:10.1109/access.2025.3567010 · Cited by 2
“Notable feature descriptors such as SIFT, SURF, and ORB [7], [8], [9] are well-known for their robustness to variations in lighting, scale, and rotation.”
Real-Time Gesture Recognition and Segmentation with High Accuracy for Complex Gestures
He, Y., Quan, H., Wu, G., et al. (2025) · Journal of Shanghai Jiaotong University (Science) · doi:10.1007/s12204-025-2828-2 · Cited by 2
Dense point-wise line voting for robust 6D Pose estimation in industrial bin-picking
Wang, J., Yi, G., Zhang, S., Wang, Y., Wang, Z., Zhang, X., Zhou, Z., & Xu, J. (2025) · The Visual Computer · doi:10.1007/s00371-025-04052-y · Cited by 3
“Given an input image, the hand-crafted feature-based methods [1, 19, 30] extract corners of interest and then construct the associated local descriptors for the subsequent matching.”
Zhang, P., Lai, S., Wang, D., & Lu, H. (2025) · Machine Intelligence Research · doi:10.1007/s11633-023-1477-x · Cited by 2
In situ 3D tracking method of electrical tree growth in polymers
Bu, Q., Wu, Z., Zhou, J., et al. (2025) · Journal of Applied Physics · doi:10.1063/5.0284906 · Cited by 2
Xi, Y., Liu, D., Kou, R., et al. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3600996 · Cited by 2
“1, including the MSE-based method, SURF [20], optical flow, and enhanced correlation coe ffi cient (ECC) [14].”
VoxDepth : Rectification of Depth Images on Edge Devices
Chakrabarty, Y., Dixit, A., & Sarangi, S. R. (2025) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3763793 · Cited by 2
“We present the related work in Section V-C3 and finally conclude in Section VII.”
Occlusion-robust multi-object tracking against viewpoint changing for UAV
Zhai, Y., Lu, D., Li, J., & Wang, Y. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132440 · Cited by 3
FACA v1 – Fully Automated Co-Alignment of UAV point clouds
Schüßler, N., Torizin, J., Gunkel, C., et al. (2025) · Geoscientific model development · doi:10.5194/gmd-18-5913-2025 · Cited by 2
Multimodal Content Alignment with LLM for Visual Presentation of Papers
Hu, H., He, Z., Zhou, Y., Zhang, T., & Lyu, X. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04624-6_14 · Cited by 2
Automatic defect localization method based on BIM projected image
Xu, L., Feng, X., Liu, J., Qi, H., & Wang, Y. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103874 · Cited by 2
Empirical Evaluation of Invariances in Deep Vision Models
Keremis, K., Vrochidou, Ε., & Papakostas, G. A. (2025) · Journal of Imaging · doi:10.3390/jimaging11090322 · Cited by 6
Creating nasal cycle simulations by processing MRI and CT scan data with image morphing algorithms
Vithanage, I. A. W., Ginat, D. T., & Dixon, A. R. (2025) · Scientific Reports · doi:10.1038/s41598-025-14023-x · Cited by 2
Yoon, Y., Jeon, Y., Kim, J., Han, S., Kim, H., & Kwon, S. (2025) · Computer Applications in Engineering Education · doi:10.1002/cae.70096 · Cited by 3
“Feature extraction algorithms such as SIFT [23], SURF [24], and ORB [25] can be utilized.”
Semantic Digital Twin Modeling of Urban Elements: Methods and Applications in Smart Cities
Li, Y., Yang, J. Y., Zhang, S., Li, Y., Ye, S., Qin, Z., & Guan, Y. (2025) · Transactions in GIS · doi:10.1111/tgis.70144 · Cited by 2
Deep blueprint: A literature review and guide to automated image classification for ecologists
Game, C. A., Piechaud, N., & Howell, K. L. (2026) · Journal of Animal Ecology · doi:10.1111/1365-2656.70271 · Cited by 3
“Thus a traditional ap - proach is to extract image characteristics linked to colour, textural and geometric patterns (Ahonen et al., 2006 ; Bay et al., 2006; Dalal & Triggs, 2005 ; Haralick et al., 1973; Lowe, 2004 ; Matas et al., 2004 ; Mikolajczyk & Schmid, 2005 ) and classify with algo - rithms…”
A Self-Supervised Learning Approach for Pairwise Matching of Ancient Dunhuang Fragments
Chen, M., Xiang, Y., & Zheng, Y. (2025) · Journal on Computing and Cultural Heritage · doi:10.1145/3776642 · Cited by 2
“This process can be divided into three main steps: feature detection[16, 17, 31, 56, 57], feature description[1, 5, 10, 27, 33, 35, 38, 39], and matching alignment[3, 32, 36, 45, 54], ultimately achieving the rejoining of the fragments.”
A Rotation and Scale Invariant Map Matching Method for UAV Visual Geolocalization
Liu, Y., Bai, J., Xiao, Z. Q., Lian, Y., & Jiao, L. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3639900 · Cited by 3
“Traditional template matching and feature matching algorithms are based on artificial features, such as speeded-up robust features [14] and mutual information [15].”
Non-contact sensing methods for wave measurement: current research and challenge
Zhou, Z., Liu, J., Wu, R., & Guo, A. (2025) · Intelligent Transportation Infrastructure · doi:10.1093/iti/liaf003 · Cited by 6
UMOS-Net: Unsupervised Multi-stage Online Video Stabilization Network
Wang, P., Qin, P., Qin, J., et al. (2025) · doi:10.1109/ijcnn64981.2025.11229204 · Cited by 2
“In traditional methods, the feature point extraction during the trajectory estimation primarily depend on mathematical formulas [21], such as ORB [28], SIFT [22], and SURF [3].”
He, K. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3652103 · Cited by 3
“3(a). b) Feature description: A speeded-up robust feature (SURF) algorithm [23] was employed for the feature detection due to its capability of handling the image rotation, scale, and illumination variation, fast computation [24], and robustness against ultrasound probe shift. c) Vector…”
Pereira, T., Viegas, C. X. P., Soares, S., & Ferreira, N. (2026) · Robotics · doi:10.3390/robotics15020035 · Cited by 7
“Subsequent techniques such as SURF [33], BRIEF [34], and ORB [35] were introduced, with ORB emerging as an efficient alternative to SIFT and SURF.”
Wan, T., Qi, F., Yang, Y., et al. (2026) · npj Heritage Science · doi:10.1038/s40494-026-02368-z · Cited by 2
“Scale-Invariant Feature Transform (SIFT) 32 – 34 and Speeded Up Robust Features (SURF) 35 have been extensively employed for nat-ural image registration.”
Hosseini, K., Zubareva, S. S., Hummelsberger, J., et al. (2026) · Natural Hazards · doi:10.1007/s11069-025-07939-0 · Cited by 2
“It is important to note that this study compares only five of the most well-known feature extraction algorithms, including SURF(Bay et al. 2006), SIFT(Lowe 2004), ORB(Rublee et al. 2011), KAZE(Alcantarilla et al. 2012), and BRISK(Leutenegger et al. 2011 ).”
Öksüz, C., Narter, A., Ece, B., et al. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109857 · Cited by 2
Xie, P., Lu, Z.-R., Liu, J., & Wang, L. G. (2026) · Experimental Mechanics · doi:10.1007/s11340-026-01282-6 · Cited by 3
StructGCN: A structure-aware graph convolutional network for spacecraft pose estimation
Yongqi, M. U., Zhi, X., Gong, J., JIANG, S., Jianming, H. U., Xinkai, W. A. N. G., & Bao, G. (2026) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2026.104204 · Cited by 3
Affine SIFT Based on Particle Swarm Optimization
Cao, X., Cai, G., & Chen, S.-L. (2013) · Advances in intelligent systems and computing · doi:10.1007/978-3-642-38667-1_7 · Cited by 2
Stable estimation of horizontal velocity for planetary lander with motion constraints
Shao, W., Sui, S., Meng, L., & Yue, Y. (2015) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2015.7081659 · Cited by 2
“ASIFT can handle much higher transition tilts than scale-invariant feature transform (SIFT)([15]) or speeded up robust feature (SURF)([16]), and it has characteristics of translation, scale, rotation and affine invariant.”
BackgroundEnchev, I., Pfingsthorn, M. F., Łuczyński, T., et al. (2015) · doi:10.1109/oceans-genova.2015.7271561 · Cited by 2
“In order to represent image data we use one of the most successful and efficient descriptors - SURF [36].”
MethodA method of semi-quantifying β-AP in brain PET-CT 11 C-PiB images
Jiang, J., Lin, X., Wen, J., Huang, Z., & Yan, Z. (2014) · Bio-Medical Materials and Engineering · doi:10.3233/bme-130940 · Cited by 2
“SURF is a fast interest point detector and descriptor, which is derived from scale-invariant feature transform [7].”
Tracking a Moving Target from a Moving Camera with Rotation-Compensated Imagery
Mirisola, L. G. B., & Dias, J. M. M. (2009) · InTech eBooks · doi:10.5772/6498 · Cited by 2
Methods for recovering the dislocations contour line of gallium arsenide wafer of digital image
Samoilov, A., & Шевченко, И. В. (2015) · Eastern-European Journal of Enterprise Technologies · doi:10.15587/1729-4061.2015.43326 · Cited by 2
A new interest point extraction method
Hong, C. H., Wu, C., Chen, D., et al. (2015) · doi:10.1109/ccdc.2015.7161761 · Cited by 2
Panorama images stitching on android phones
Gansawat, D., & Sinthupinyo, W. (2011) · Cited by 2
Affine Invariant Feature Description
Bulla, C., & Weissenburger, A. (2015) · International symposium on image and signal processing and analysis/ISPA ... · doi:10.1109/ispa.2015.7306059 · Cited by 2
Tomasev, N., & Mladenič, D. (2013) · Multimedia tools and applications · doi:10.1007/s11042-014-2254-1 · Cited by 7
“While the classification experiments in Section 5 have been performed on quantized SIFT feature representations [33], use cases of Image Hub Explorer in Section 4 have also been demonstrated on SURF [5], BRIEF [10] and ORB [49] quantized representations.”
MethodMoving Objects Detection Based on the Precise Background Compensation Under Dynamic Scene
Wang, Y., Yu, Y., Yan, G., et al. (2014) · International Journal of Advanced Pervasive and Ubiquitous Computing · doi:10.4018/ijapuc.2014010104 · Cited by 2
Towards ambient communication support for power grid maintenance and repair
Kume, N., & Rissanena, M. J. (2011) · Procedia Computer Science · doi:10.1016/j.procs.2011.07.015 · Cited by 2
Kazlouski, A., & Sadykhov, R. K. (2014) · IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) · doi:10.1109/inista.2014.6873621 · Cited by 2
“In the first step control points are determined from the registered images based on the SURF method [11,12] or the vertices detection method [13,14].”
MethodVision-based Localization for AUVs using Weighted Template Matching in a Structured Environment
Kim, D., Lee, D., Myung, H., et al. (2013) · Journal of Institute of Control Robotics and Systems · doi:10.5302/j.icros.2013.13.9012 · Cited by 2
Spatially consistent partial matching for intra- and inter-image prototype selection
Kosinov, S., Bruno, E., & Marchand‐Maillet, S. (2008) · Signal Processing Image Communication · doi:10.1016/j.image.2008.04.017 · Cited by 2
New Compound Method for Target Recognition and Tracking
Sun, K. (2013) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.273.790 · Cited by 2
“In recent years, target tracking based on local features matching achieved great success [1,2,3].”
BackgroundKinect-Derived Augmentation of the Real World for Cultural Heritage
Bostancı, E., Kanwal, N., & Clark, A. F. (2013) · UKSim International Conference on Computer Modelling and Simulation (UKSim) · doi:10.1109/uksim.2013.10 · Cited by 2
Modulating vision with motor plans: A biologically-inspired efficient allocation of visual resources
Lukic, L., Billard, A., & Santos-Victor, J. (2013) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2013.7029971 · Cited by 2
“For the second detector, we selected SURF [30].”
MethodCharacteristic Point Match Algorithm Based on the SURF in Binocular Stereo Vision
Xiaoli, W., Lei, Y., Lirong, W., et al. (2012) · International Conference on Intelligent Networks and Intelligent Systems · doi:10.1109/icinis.2012.72 · Cited by 2
Comparing Proposed Signature with SURF in Object Detection Process
Elsalamony, H. A. (2015) · IETE Journal of Research · doi:10.1080/03772063.2015.1023371 · Cited by 2
“The determinant of the Hessian matrix is where w is recommended at 0.9 that is the relative weight of the fi lter responses [18,19].”
BackgroundMethodInfluentialAutomatic chaptering of VoD content based on DVD content
Thudor, F., Autier, I., Chupeau, B., et al. (2012) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2012.6269812 · Cited by 2
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.