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 3,901–4,000 of 14,752
Combining local and global feature for object recognition using SVM-KNN
Muralidharan, R., & Chandrasekar, C. (2012) · International Conference on Pattern Recognition, Informatics and Mobile Engineering (PRIME) · doi:10.1109/icprime.2012.6208278 · Cited by 17
Weld seam tracking and panorama image generation for on-line quality assurance
Heber, M., Lenz, M., Rüther, M., Bischof, H., Fronthaler, H., & Croonen, G. (2012) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-012-4263-4 · Cited by 16
Humanoid robot navigation: From a visual SLAM to a visual compass
Wirbel, É., Steux, B., Bonnabel, S., et al. (2013) · IEEE International Conference on Networking, Sensing and Control (ICNSC) · doi:10.1109/icnsc.2013.6548820 · Cited by 16
Mosberger, R., Andreasson, H., & Lilienthal, A. J. (2014) · Sensors · doi:10.3390/s141017952 · Cited by 19
Benchmarking template-based tracking algorithms
Lieberknecht, S., Benhimane, S., Meier, P. G., & Navab, N. (2010) · Virtual Reality · doi:10.1007/s10055-010-0185-3 · Cited by 16
“To obtain these correspondences from the algorithms based on SIFT and SURF, we used nearestneighbor matching of the descriptors to generate initial 2D–3D correspondences, then removed outliers via RANSAC.”
MethodInfluentialLearning Optimized Local Difference Binaries for Scalable Augmented Reality on Mobile Devices
Yang, X. Y., & Cheng, K.-T. T. (2014) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2013.260 · Cited by 16
An efficient iris recognition using local feature descriptor
Mehrotra, H., Badrinath, G. S., Majhi, B., et al. (2009) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2009.5413465 · Cited by 16
Registration of multiple stained histological sections
Borovec, J., Kybic, J., Bušta, M., et al. (2013) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2013.6556654 · Cited by 16
RS-SLAM: RANSAC sampling for visual FastSLAM
Lee, G. H., Fraundorfer, F., & Pollefeys, M. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6095048 · Cited by 18
“Image features such as SIFT [11] and SURF [12] could be used where the descriptors for these features can be used for finding correspondences.”
MethodAutomatic multimodal descriptors of rhythmic body movement
Mahmoud, M., Morency, L., & Robinson, P. (2013) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/2522848.2522895 · Cited by 16
A framework for quality-based biometric classifier selection
Bhatt, H. S., Bharadwaj, S., Mayank Vatsa, A., Singh, R., Ross, A. A., & Afzel Noore, B. (2011) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb.2011.6117518 · Cited by 17
Chiu, C., & Wang, H. (2010) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2010.2087471 · Cited by 16
Vision-Based Georeferencing of GPR in Urban Areas
Barzaghi, R., Cazzaniga, N. E., Pagliari, D., & Pinto, L. (2016) · Sensors · doi:10.3390/s16010132 · Cited by 17
A palmprint based recognition system for smartphone
Tiwari, K., Hwang, C. J., & Gupta, P. (2016) · Future Technologies Conference · doi:10.1109/ftc.2016.7821664 · Cited by 16
“In out experiment we have used SURF and ORB features.”
MethodInfluentialAutomatic registration of 2D histological sections to 3D microCT volumes: Trabecular bone
Lundin, E. L., Stauber, M., Papageorgiou, P., Ehrbar, M., Ghayor, C., Weber, F. E., Tanner, C., & Göksel, O. (2017) · Bone · doi:10.1016/j.bone.2017.08.021 · Cited by 18
Rotation Invariant Co-occurrence Matrix Features
Putzu, L., & Ruberto, C. D. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68560-1_35 · Cited by 16
Tingting, H. U., & Ikenaga, T. (2018) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2017mvp0012 · Cited by 16
MARBLE: Mobile Augmented Reality Using a Distributed BLE Beacon Infrastructure
Shao, C., Islam, B., & Nirjon, S. (2018) · IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi.2018.00016 · Cited by 15
“Instead of using ORB features, [30] uses SURF feature for image matching.”
MethodParameter Transfer Extreme Learning Machine based on Projective Model
Chen, C., Jiang, B., & Jin, X. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489244 · Cited by 29
“We consider the SURF-BoW image features (SURF in short) provided by [8], which encode the images with 800-bin histograms with the codebook trained from a subset of Amazon images using SURF descriptors [31].”
MethodU-PC: Unsupervised Planogram Compliance
Ray, A., Kumar, N., Shaw, A. K., & Mukherjee, D. P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01249-6_36 · Cited by 17
Sparsity-regularized feature selection for multi-class remote sensing image classification
Chen, T., Zhao, Y., & Guo, Y. (2019) · Neural Computing and Applications · doi:10.1007/s00521-019-04046-7 · Cited by 16
“SURF is a scale and rotation invariant interest point detector and descriptor, which is well utilized in objects detection, object recognition or image retrieval tasks [12, 13].”
BackgroundManifold Regularization Graph Structure Auto-Encoder to Detect Loop Closure for Visual SLAM
Wang, Z., Peng, Z., Guan, Y., & Wu, L. (2019) · IEEE Access · doi:10.1109/access.2019.2914943 · Cited by 17
“Firstly, selectively extract some interesting or noteworthy parts of the image using sparse key point detection algorithms such as SIFT [21], SURF [22] or ORB [27] feature detection.”
MethodInfluentialA novel video shot boundary detection framework employing DCT and pattern matching
Dhiman, S., Chawla, R., & Gupta, S. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08170-3 · Cited by 16
A Computer Vision Approach to Evaluate Powder Flowability for Metal Additive Manufacturing
Zhang, J., Habibnejad-Korayem, M., Liu, Z., Lyu, T., Sun, Q., & Zou, Y. (2021) · Integrating materials and manufacturing innovation · doi:10.1007/s40192-021-00226-3 · Cited by 19
“The scale-invariant feature transform (SIFT) [37] and speeded up robust feature (SURF) [57] algorithms are two powerful approaches to extract such features they are invariant to scale, rotate, translation, illumination, and blur.”
MethodInfluentialAutomatic Visual Reading of Meters Using Deep Learning
Koščević, K., & Subašić, M. (2019) · Proceedings of the Croatian Computer Vision Workshop · doi:10.20532/ccvw.2018.0002 · Cited by 17
V-SLAM: Vision-based simultaneous localization and map building for an autonomous mobile robot
Savaria, D. T., & Balasubramanian, R. (2010) · doi:10.1109/mfi.2010.5604466 · Cited by 16
“One of the deciding factors was SURF’s quickness.”
MethodInfluentialKim, D. S., Pyeon, M. W., Eo, Y. D., et al. (2012) · GIScience & Remote Sensing · doi:10.2747/1548-1603.49.5.755 · Cited by 16
“Therefore, this algorithm is recognized as the most employed registration method with speeded-up robust features (SURF; Bay et al., 2008) for various types of image (Mikojclyk and Schmid, 2005; El Rube et al., 2011; Stefanik et al., 2011).”
MethodDanger Sign Detection Using Color Histograms and SURF Matching
Gossow, D., Pellenz, J., & Paulus, D. W. R. (2008) · doi:10.1109/ssrr.2008.4745870 · Cited by 16
An efficient approach for recognizing and tracking spontaneous facial expressions
Zraqou, J. S., Alkhadour, W., & Al-Nuaimi, A. (2013) · International Conference on E-Learning and E-Technologies in Education · doi:10.1109/icelete.2013.6644393 · Cited by 16
“Hence, several methods were tested such as the methods proposed by [7], [8] and [9].”
Method3D Disaster Scene Reconstruction Using a Canine-Mounted RGB-D Sensor
Tran, J. Q. M. N., Ufkes, A., Ferworn, A., et al. (2013) · doi:10.1109/crv.2013.15 · Cited by 16
“The proposed system utilizes a GPU implementation of the popular Speeded-Up Robust Features (SURF) [17] algorithm in the Open Computer Vision Library.”
MethodLocal Invariant Feature Tracks for High-Level Video Feature Extraction
Mezaris, V., Dimou, A., & Kompatsiaris, I. Y. (2012) · Lecture notes in electrical engineering · doi:10.1007/978-1-4614-3831-1_10 · Cited by 16
“…} T 0 −1 τ =0 by a factor of a; T = T 0 /a. Application of any of the available combinations of interest point detectors and descriptors (e.g. [1] [4] [5]) on a frame It of S results in the extraction of a set of interest point descriptions Φt = {φm} M t m=1 for every frame, where Mt is the…”
3D Data Segmentation by Local Classification and Markov Random Fields
Tombari, F., & Stefano, L. D. (2011) · International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission · doi:10.1109/3dimpvt.2011.34 · Cited by 16
“Thus, when available, we extract and describe also 2D features from the pixel lattice associated with the range map using the well-known SURF method [26].”
MethodFast stereo-based visual odometry for rover navigation
Cumani, A., & Guiducci, A. (2008) · WSEAS Transactions on Circuits and Systems archive · Cited by 16
Target Driven Instance DetectionPreprint
Ammirato, P., Fu, C.-Y., Shvets, M., Košecká, J., & Berg, A. C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.04610 · Cited by 30
Barnes, D., & Posner, I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.10789 · Cited by 16
An Overview of Perception and Decision-Making in Autonomous Systems in the Era of LearningPreprint
Tang, Y. S., Zhao, C., Wang, J., Zhang, C., Sun, Q., Zheng, W. X., Du, W., Qian, F., & Kurths, J. (2020) · arXiv (Cornell University) · Cited by 16
RCVS: A Unified Registration and Fusion Framework for Video Streams
Xie, H., Sang, M., Zhang, Y., Yang, Y., Zhao, S., & Zhong, J. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3443673 · Cited by 26
Zhang, Y., Wang, J., Chen, J., Shi, D., & Chen, X. (2024) · Remote Sensing · doi:10.3390/rs16183368 · Cited by 17
“Classical feature detection algorithms include invariant feature transform (SIFT) [27], speeded-up robust features (SURF) [28], rotated BRIEF (ORB) [29], binary robust invariant scalable key points (BRISK) [30], AKAZE [31], etc.”
Microscopic aggregated traffic parameter extraction against complex camera motion interference
Chen, X., Zhang, Z., Li, Z., Han, B., Zheng, Y., & Biancardo, S. A. (2025) · Transportation Safety and Environment · doi:10.1093/tse/tdaf056 · Cited by 15
Distributed multi-camera visual mapping using topological maps of planar regions
Montijano, E., & Sagüés, C. (2011) · Pattern Recognition · doi:10.1016/j.patcog.2010.12.022 · Cited by 15
A novel approach to extract hand gesture feature in depth images
Ju, Z., Gao, D., Cao, J., et al. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2609-2 · Cited by 15
A Topological Descriptor of Acoustic Images for Navigation and Mapping
dos Santos, M. M., Ballester, P. L., Zaffari, G. B., Drews, P., & Botelho, S. S. D. C. (2015) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars-sbr.2015.11 · Cited by 15
Filtering Based Adaptive Visual Odometry Sensor Framework Robust to Blurred Images
Zhao, H., Liu, Y., Xie, X., Liao, Y., & Liu, X. (2016) · Sensors · doi:10.3390/s16071040 · Cited by 15
The Bag-of-Words Method with Different Types of Image Features and Dictionary Analysis
Gabryel, M. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.3217/jucs-024-04-0357 · Cited by 15
Pose Estimation Considering an Uncertainty Model of Stereo Vision for In-Water Ship Hull Inspection
Chung, D., & Kim, J. (2018) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2018.09.454 · Cited by 15
GNC & robotics for on orbit servicing with simulated vision in the loop
Rivolta, A., Lunghi, P., & Lavagna, M. (2019) · Acta Astronautica · doi:10.1016/j.actaastro.2019.06.005 · Cited by 14
INTEGRATED PROCESSING OF PHOTOGRAMMETRIC AND LASER SCANNING DATA FOR FRESCOES RESTORATION
Bruno, N., Mikolajewska, S., Roncella, R., et al. (2022) · 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-xlvi-2-w1-2022-105-2022 · Cited by 15
Wang, H., Liu, J., Liu, L., Zhao, M., & Mei, S. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107110 · Cited by 15
Prete, R. D., & Renga, A. (2022) · Aerotecnica Missili & Spazio · doi:10.1007/s42496-022-00139-0 · Cited by 17
Ultrasound Frame-to-Volume Registration via Deep Learning for Interventional Guidance
Guo, H., Xu, X., Song, X., Xu, S. Y., Chao, H., Myers, J., Türkbey, B., Pinto, P. A., Wood, B. J., & Yan, P. (2022) · IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control · doi:10.1109/tuffc.2022.3229903 · Cited by 19
“The most commonly used features for image matching are key points that can be roughly categorized into two folds: 1) corner-based [20], [21], [22] and 2) blob-based [23], [24], [25] feature points.”
Autonomous Asteroid Characterization Through Nanosatellite Swarming
Dennison, K., Stacey, N., & D’Amico, S. (2023) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2023.3245997 · Cited by 16
Rubio, S. E. S., Romero, A. S., Andreo, F. C., et al. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11071339 · Cited by 15
Zhao, K., Yuan, X., Xie, Z., Xiang, Y., Huang, G., & Feng, L. (2023) · Sensors · doi:10.3390/s23146430 · Cited by 17
“SIFT has driven the development of SURF [15].”
Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions
Ren, M., Wang, Y., Zhu, Y., Zhang, K., & Sun, Z. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3298836 · Cited by 17
He, J., Gao, Y., Zhang, T., Zhang, Z., & Wu, F. (2023) · 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/cvpr52729.2023.00284 · Cited by 16
“To achieve high efficiency, we notice that the detector-based matching methods [4, 9, 20, 31] can effectively reduce the matching space by designing keypoint detectors to extract a relatively small keypoint set for matching, thus having high research value.”
BackgroundSPTR: Structure-Preserving Transformer for Unsupervised Indoor Depth Completion
Zhao, L., Zheng, W., Duan, Y., Zhou, J., & Lu, J. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3312664 · Cited by 17
“SF-Net [17] progressively propagates the sparse flow [18] from textured regions to non-texture regions, and uses the rigid flow to synthesize novel images and compute the loss.”
BackgroundA rail fastener defect detection algorithm based on improved YOLOv5
Wang, L., Zang, Q., Zhang, K., & Wu, L. (2024) · Proceedings of the Institution of Mechanical Engineers Part F Journal of Rail and Rapid Transit · doi:10.1177/09544097241234380 · Cited by 15
Binocular Visual Measurement Method Based on Feature Matching
Xie, Z., & Yang, C. (2024) · Sensors · doi:10.3390/s24061807 · Cited by 17
Implicit Neural Image Stitching With Enhanced and Blended Feature Reconstruction
Kim, M., Lee, J., Lee, B., Im, S., & Jin, K. H. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00404 · Cited by 15
“Homography Estimation The feature-based approaches estimate homography using the direct linear transformation (DLT) [11] given feature correspondences [3, 27, 39].”
MethodMulti-Stage Network With Geometric Semantic Attention for Two-View Correspondence Learning
Lin, S., Chen, X., Xiao, G., Wang, H., Huang, F., & Weng, J. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3391002 · Cited by 20
“Initially, either a traditional algorithm [44], [45], [46], [47] or a deep learning-based algorithm [35], [48] is used to acquire a set of feature point coordinates for the images, along with their corresponding descriptors.”
MethodColmap-PCD: An Open-source Tool for Fine Image-to-point cloud Registration
Bai, C., Fu, R., & Gao, X. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611582 · Cited by 25
“In visual reconstruction, feature descriptors such as SIFT [7], SURF [8] and ORB [9] are commonly employed to identify the same features between images.”
MethodA Survey of Landmark Recognition Using the Bag-of-Words Framework
Bhattacharya, P., & Gavrilova, M. L. (2012) · Studies in computational intelligence · doi:10.1007/978-3-642-31745-3_13 · Cited by 17
Lightweight Binary Voxel Shape Features for 3D Data Matching and Retrieval
Matsuda, T., Furuya, T., & Ohbuchi, R. (2015) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2015.66 · Cited by 15
“RELATED WORK In the domain of 2D image analysis, SIFT [17], SURF [4] and other feature descriptors have been used extensively, which is invariant, to varying degrees, to geometrical transformations including scaling, translation, and rotation.”
MethodInfluentialError Aware Monocular Visual Odometry using Vertical Line Pairs for Small Robots in Urban Areas
Zhang, J., & Song, D. (2010) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v24i1.7723 · Cited by 14
“Point features, such as Harris corners, scale-invariant feature transformation (SIFT) points (Lowe 2004), and speed up robust feature (SURF) points (Bay et al. 2008) are the most popular ones since they are readily available and well developed in computer vision literature.”
BackgroundVisual positioning systems — An extension to MoVIPS
Marouane, C., Maier, M., Feld, S., et al. (2014) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2014.7275472 · Cited by 15
“[5], [6] is a similar algorithm which approximates searching for local extrema with a box filter, leading to vastly improved performance at a small expense of accuracy.”
BackgroundSpeeded-Up Robust Feature extraction and matching for fingerprint recognition
Hany, U., & Akter, L. (2015) · International Conference on Electrical Engineering and Information Communication Technology · doi:10.1109/iceeict.2015.7307439 · Cited by 15
Interactive Stereoscopic Video Conversion
Zhang, Z., Zhou, C., Wang, Y., & Gao, W. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2269023 · Cited by 18
A feature descriptor for texture-less object representation using 2D and 3D cues from RGB-D data
Fischer, J., Bormann, R., Arbeiter, G., & Verl, A. W. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630860 · Cited by 19
Beobot 2.0: Cluster architecture for mobile robotics
Siagian, C., Chang, C., Voorhies, R. C., & Itti, L. (2010) · Journal of Field Robotics · doi:10.1002/rob.20379 · Cited by 15
Performance evaluation of keypoint detection and matching techniques on grayscale data
Proença, H. P. M. C. (2013) · Signal Image and Video Processing · doi:10.1007/s11760-013-0535-1 · Cited by 17
“In this work, we evaluate the performance of four of the most popular keypoint detection/matching techniques: SIFT [13], SURF [1], BRIEF [2] and DAISY [21].”
BackgroundMethodExperiencing real 3D gestural interaction with mobile devices
Yousefi, S., Kondori, F. A., & Li, H. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2013.02.004 · Cited by 15
“Among different feature detectors (Lowe, 2004; Harris and Stephens, 1988; Bay et al., 2006), SIFT feature detector is used for its robustness and invariance to image transformation (Lowe, 2004).”
MethodFast Local Self-Similarity for describing interest regions
Liu, J., Zeng, G., & Jianping Fan, B. (2012) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.01.013 · Cited by 15
Mitić, M., & Miljković, Z. (2013) · Soft Computing · doi:10.1007/s00500-013-1121-8 · Cited by 15
“The extraction and matching of the image feature points is conducted using the SURF method (Bay et al. 2008).”
MethodRGB-D object classification using covariance descriptors
Fehr, D., Beksi, W. J., Zermas, D., & Papanikolopoulos, N. P. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907663 · Cited by 19
Learning Spatial Object Localization from Vision on a Humanoid Robot
Leitner, J., Harding, S., Frank, M., Förster, A., & Schmidhuber, J. (2012) · International Journal of Advanced Robotic Systems · doi:10.5772/54657 · Cited by 16
Scaling content-based video copy detection to very large databases
Poullot, S., Buisson, O., & Crucianu, M. (2009) · Multimedia Tools and Applications · doi:10.1007/s11042-009-0323-7 · Cited by 15
“Most of the recent description methods, such as SIFT [24], PCA-SIFT [16], Gradient Location and Orientation Histogram (GLOH) [27] or Speeded-Up Robust Features (SURF) [1], aim at providing strong robustness to general affine transforms and were mainly designed for applications like object recognition and stereo matchi…”
MethodA power-efficient real-time architecture for SURF feature extraction
Wilson, C., Zicari, P., Craciun, S., Gauvin, P., Carlisle, E., George, A. D., & Lam, H. X. (2014) · International Conference on ReConFigurable Computing and FPGAs (ReConFig) · doi:10.1109/reconfig.2014.7032492 · Cited by 14
Stanciu, S. G., Hristu, R., & Stanciu, G. A. (2011) · Ultramicroscopy · doi:10.1016/j.ultramic.2011.01.014 · Cited by 15
Domain Adaptive Classification
Mirrashed, F., & Rastegari, M. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.324 · Cited by 15
Matching of Large Images Through Coupled Decomposition
Sidiropoulos, P., & Müller, J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2409978 · Cited by 14
A real-time mosaicking algorithm using binary features for ROVs
Ferreira, F., Veruggio, G., Caccia, M., Zereik, E., & Bruzzone, G. (2013) · Mediterranean Conference on Control and Automation (MED) · doi:10.1109/med.2013.6608882 · Cited by 15
“That is achieved by a combination of Template correlation [1] and SURF features [2] as it shall be seen.”
MethodLoukas, C., & Georgiou, E. K. (2015) · International Journal of Medical Robotics and Computer Assisted Surgery · doi:10.1002/rcs.1702 · Cited by 15
“We only slightly varied some of the default parameters of the SIFT, SURF and STAR detectors so that the number of features detected in the movable parts of the image (mainly instrument tip and shaft) was roughly equal to that generated by the STIP detector.”
MethodInfluentialLong exposure localization in darkness using consumer cameras
Milford, M. J., Turner, I., & Corke, P. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631105 · Cited by 15
“These side effects are both potentially catastrophic for many types of vision processing techniques, especially those that rely on the now standard gradient-based feature detection algorithms such as Scale- Invariant Feature Transforms (SIFT) [1] and Speeded Up Robust Features (SURF) [2].”
BackgroundMAMPF: An Intelligent Cooking Agent for Zoneless Stoves
Reichel, S., Müller, T., Stamm, O., et al. (2011) · International Conference on Intelligent Environments (IE) · doi:10.1109/ie.2011.18 · Cited by 15
On co-training online biometric classifiers
Bhatt, H. S., Bharadwaj, S., Singh, R., Mayank Vatsa, A., Afzel Noore, B., & Ross, A. A. (2011) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb.2011.6117519 · Cited by 15
“Pointbased Speeded Up Robust Features (SURF) [6] and texturebased Uniform Circular Local Binary Pattern (UCLBP) [3] are used as facial feature extractors along with í µí¼ 2 distance for matching.”
MethodInfluentialEnhancing video concept detection with the use of tomographs
Sidiropoulos, P., Mezaris, V., & Kompatsiaris, I. Y. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738822 · Cited by 15
Real time road edges detection and road signs recognition
Duan, J., & Viktor, M. (2015) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais.2015.7338642 · Cited by 15
Linear distance metric learning for large-scale generic image recognition
中山, 英. (2011) · Medical Entomology and Zoology · Cited by 17
Markatopoulou, F., Mezaris, V., & Patras, I. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351108 · Cited by 15
Feature Based Correspondence: A Comparative Study on Image Matching Algorithms
Muhammad, U., Tanvir, M., & Khurshid, K. (2016) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2016.070329 · Cited by 14
“This algorithm was named Speeded-Up Robust Features (SURF) detector (Bay et al., 2006).”
MethodDETECTION OF GEOMETRIC KEYPOINTS AND ITS APPLICATION TO POINT CLOUD COARSE REGISTRATION
Bueno, M., Martínez-Sánchez, J., González-Jorge, H., & Lorenzo, H. (2016) · 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-xli-b3-187-2016 · Cited by 20
Integration of text and image analysis for flood event image recognition
Jing, M., Scotney, B. W., Coleman, S., et al. (2016) · Irish Signals and Systems Conference · doi:10.1109/issc.2016.7528454 · Cited by 15
ISURE: User authentication in mobile devices using ocular biometrics in visible spectrum
Ahuja, K., Bose, A., Nagar, S., et al. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532374 · Cited by 15
An evaluation of real-time RGB-D visual odometry algorithms on mobile devices
Angladon, V., Gasparini, S., Charvillat, V., Pribanić, T., Petković, T., Đonlić, M., Ahsan, B., & Bruel, F. (2017) · Journal of Real-Time Image Processing · doi:10.1007/s11554-017-0670-y · Cited by 21
“On desktop computers, SIFT [29] and SURF [3] features are commonly used for their high robustness [12].”
MethodLandmark Image Retrieval by Jointing Feature Refinement and Multimodal Classifier Learning
Zhang, X., Wang, S., Li, Z., & Ma, S. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2712798 · Cited by 18
“SURF [47] or ORB [48] can be considered as an efficient alternative to SIFT.”
Hidaka, N., Michikawa, T., Motamedi, A., Yabuki, N., & Fukuda, T. (2017) · Automation in Construction · doi:10.1016/j.autcon.2017.10.014 · Cited by 15
A three-staged approach to medicine box recognition
Magalhães, L., Ribeiro, B., Alves, N., et al. (2017) · doi:10.1109/epcgi.2017.8124317 · Cited by 15
“These method relies on a set of defined feature extractors, such as SURF [6], SIFT [12], or ORB [13].”
MethodContinuous Visual World Modeling for Autonomous Robot Manipulation
İnceoğlu, A., Koc, C., Kanat, B. O., Ersen, M., & Sarıel, S. (2018) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2017.2787482 · Cited by 21
Underwater Robot Navigation for Maintenance and Inspection of Flooded Mine Shafts
Álvarez-Tuñón, O., Rodríguez, Á., Jardón, A., & Balaguer, C. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594445 · Cited by 15
“The main requirements for a descriptor in Visual Odometry are invariability to rotation and scale, which are achieved by SIFT and SURF descriptors.”
MethodJoint Domain Matching and Classification for cross-domain adaptation via ELM
Chen, C., Jiang, B., Cheng, Z., & Jin, X. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.056 · Cited by 15
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.