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 6,901–7,000 of 14,752
Tomită, M.-A., Zaffar, M., Milford, M. J., McDonald-Maier, K. D., & Ehsan, S. (2020) · ePrints Soton (University of Southampton) · doi:10.48550/arxiv.2009.13454 · Cited by 6
A Scene Classification Approach for Augmented Reality Devices
Khurshid, A., Tamayo, S. C., & Grunitzki, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59990-4_14 · Cited by 7
Ohira, G., Kashioka, S., Takao, Y., et al. (2020) · Acta Astronautica · doi:10.1016/j.actaastro.2020.10.013 · Cited by 6
Local feature extracted by the improved bag of features method for person re-identification
Zhang, L., Li, K., Qi, Y., & Wang, F. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.12.142 · Cited by 8
Online Arabic Handwriting Characters Recognition using Deep Learning
Yaagoup, K. M. M., & Mustafa, M. E. (2020) · IJARCCE · doi:10.17148/ijarcce.2020.91014 · Cited by 7
Object Pose Estimation Incorporating Projection Loss and Discriminative Refinement
You, J.-K., Hsu, C.-C. J., Wang, W., & Huang, S.-K. (2021) · IEEE Access · doi:10.1109/access.2021.3054493 · Cited by 6
“Popular methods that extract feature points from RGB images, such as SIFT [25], FAST [26], SURF [27], and ORB [28], have been designed to handle the feature-extracting task under various environmental factors such as different camera viewpoints, lighting conditions, and noisy images.”
MethodImproved ORB Based Image Registration Acceleration Algorithm in Visual-Inertial Navigation System
Zhao, Y., Xiong, Z., Duan, S., et al. (2020) · Chinese Automation Congress · doi:10.1109/cac51589.2020.9326928 · Cited by 6
SAR Image Registration Based on Optimized Ransac Algorithm with Mixed Feature Extraction
Liao, F., Chen, Y., Chen, Y., et al. (2020) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss39084.2020.9323180 · Cited by 6
“SURF approximates or evens outperform previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster [2]-[3].”
BackgroundLearning To Find Good Correspondences Of Multiple Objects
Xie, Y., Tang, Y., Tang, G., et al. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413319 · Cited by 6
A Bucket-Stream rBRIEF Extraction Architecture for SLAM Applications on Embedded Platforms
Chen, H., Li, F., & Zhang, Z. (2020) · International Conference on Field-Programmable Technology (FPT) · doi:10.1109/icfpt51103.2020.00047 · Cited by 6
“Due to the real-time needs of the system, high-quality and hence computation-expensive features such as scale-invariant feature transform (SIFT) [1] or speeded up robust feature (SURF) [2] are less preferred than binary descriptors, such as binary robust independent elementary features (BRIEF).”
BackgroundRapid Multimodal Image Registration Based on the Local Edge Histogram
Zhao, D. (2021) · Mathematical Problems in Engineering · doi:10.1155/2021/5598177 · Cited by 6
Koo, G., Jung, W., & Doh, N. L. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3094412 · Cited by 6
“From the partially measured images, SURF points [14] are detected and matched.”
MethodCrowd estimation using key‐point matching with support vector regression
Ekanayake, E. M. C. L., & Lei, Y. (2021) · IET Image Processing · doi:10.1049/ipr2.12300 · Cited by 6
A Deep Learning Method for Frame Selection in Videos for Structure from Motion Pipelines
Banterle, F., Gong, R., Corsini, M., Ganovelli, F., Gool, L. V., & Cignoni, P. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506227 · Cited by 6
“For example, some works [4] focus on improving the robustness and the effectiveness of the low-level feature extraction and matching to improve both the camera motion and structure estimation performance.”
BackgroundSelf-citationStructure from Motion and Mosaicking for High-Throughput Field-Scale Phenotyping
Aliakbarpour, H., Gao, K., Aktar, R., Suddarth, S., & Palaniappan, K. (2021) · Concepts and strategies in plant sciences · doi:10.1007/978-3-030-73734-4_4 · Cited by 6
Overview of Visual SLAM for Mobile Robots
Chen, W. R. (2021) · International Journal of Frontiers in Engineering Technology · doi:10.25236/ijfet.2021.030701 · Cited by 7
“However, these corner points do not have scale invariance[5] and cannot meet the matching in the case of camera movement, so the researchers designed the famous SIFT[6], SURF[7], ORB[8] feature points.”
MethodSuperline: A Robust Line Segment Feature for Visual SLAM
Qiao, C., Bai, T., Xiang, Z., et al. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636435 · Cited by 6
Garcia‐Fidalgo, E., & Ortiz, A. (2022) · Autonomous Robots · doi:10.1007/s10514-021-10032-7 · Cited by 6
“Among these solutions, binary descriptors (Calonder et al. 2010; Rublee et al. 2011) have progressively emerged as an alternative to real-valued descriptors (Lowe 2004; Bay et al. 2006) given their demonstrated advantages in computational terms.”
BackgroundRajamohan, D., Kim, J., Garratt, M., & Pickering, M. R. (2022) · Autonomous Robots · doi:10.1007/s10514-021-10031-8 · Cited by 6
“Several point feature types like SIFT (Lowe 2004), SURF(Bay et al. 2006), ORB(Rublee et al. 2011) and BRISK(Leutenegger et al. 2011) have been tried independently (Tareen et al. 2018) or in combination with geometric features like lines that connect two point features (Ferber et al. yyy).”
MethodParticle Swarm Optimisation in Practice: Multiple Applications in a Digital Microscope System
Ryan, L., Kühn, S., Colreavy‐Donnelly, S., et al. (2022) · Applied Sciences · doi:10.3390/app12157827 · Cited by 6
STDC-SLAM: A Real-Time Semantic SLAM Detect Object by Short-Term Dense Concatenate Network
Hu, Z., Chen, J., Luo, Y., & Zhang, Y. (2022) · IEEE Access · doi:10.1109/access.2022.3228040 · Cited by 8
“The main feature points extraction algorithms are Scale Invariant Feature Transform (SIFT) [29], Speed-UP Robust Feature (SUFER) [30], ORB, etc.”
MethodIntegrated Image Processing Toolset for Tracking Direction of Metal Grain Deformation
Dharmawan, I. D. M. O., & Lee, J. (2022) · Applied Sciences · doi:10.3390/app13010045 · Cited by 6
Visual Odometry With Point and Line Features Based on Underground Tunnel Environment
Wu, D., Wang, M., Li, Q., et al. (2023) · IEEE Access · doi:10.1109/access.2023.3253510 · Cited by 6
A Monocular SLAM System Based on the ORB Features
Shao, S. (2023) · IEEE International Conference on Power, Electronics and Computer Applications (ICPECA) · doi:10.1109/icpeca56706.2023.10075945 · Cited by 6
“Compared to SIFT [12] or SURF [13], ORB features are more computationally efficient and have strong rotation invariance and scaling invariance.”
MethodWoźniak, P., & Ożóg, D. (2023) · Sensors · doi:10.3390/s23136134 · Cited by 7
“Initially, manual descriptors, such as GIST [16] and SURF [17], were used to solve this.”
MethodLearning with Privileged Information for Improved Target Classification
Ilin, R., Streltsov, S., & Izmailov, R. (2014) · International Journal of Monitoring and Surveillance Technologies Research · doi:10.4018/ijmstr.2014070103 · Cited by 7
Recognizing planar kinematic mechanisms from a single image using evolutionary computation
Eicholtz, M., Kara, L. B., & Lohn, J. D. (2014) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/2576768.2598354 · Cited by 6
Classifier ensemble with incremental learning for disaster victim detection
Soni, B., & Sowmya, A. (2012) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2012.6491007 · Cited by 6
Fast scene recognition based on saliency region and SURF
Chen, S., Wu, C., Yu, X., et al. (2011) · International Conference on Intelligent Control and Information Processing · doi:10.1109/icicip.2011.6008371 · Cited by 6
BIPCO: ultrasound feature points based on phase congruency detector and binary pattern descriptor
Dall’Alba, D., & Fiorini, P. (2015) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-015-1204-3 · Cited by 6
“SURF was introduced as an efficient and faster alternative to other image descriptors [2].”
MethodFull Pixel Matching between Images for Non-linear Registration of Objects
Yaguchi, Y., Iseki, K., & Oka, R. (2010) · IPSJ Transactions on Computer Vision and Applications · doi:10.2197/ipsjtcva.2.1 · Cited by 6
Synthesis of spatio-temporal interest point detectors: Harris 3D, MoSIFT and SURF-MHI
Hendaoui, R., Abdellaoui, M., & Douik, A. (2014) · International Conference on Advanced Technologies for Signal and Image Processing · doi:10.1109/atsip.2014.6834583 · Cited by 6
Matsushita, Y., Kawasaki, H., Ono, S., et al. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025925 · Cited by 6
“Among common feature extraction [14, 15] and tracking methods [16], most of them are”
MethodA Robust Object Tracking Algorithm Based on Surf and Kalman Filter
Yin, H., Peng, C., Chai, Y., et al. (2013) · Intelligent Automation & Soft Computing · doi:10.1080/10798587.2013.869115 · Cited by 6
Feature selection and pose estimation from known planar objects using monocular vision
Xu, S., & Liu, M. (2013) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2013.6739580 · Cited by 6
Audible vision for the blind and visually impaired in indoor open spaces
Yu, X., & Ganz, A. (2012) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2012.6347143 · Cited by 6
Multi‐camera‐based security log management scheme for smart surveillance
Kim, D., Hwang, E., & Rho, S. (2013) · Security and Communication Networks · doi:10.1002/sec.735 · Cited by 6
How Far You Can Get Using Machine Learning Black-Boxes
Rocha, A., Papa, J., & Meira, L. A. A. (2010) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2010.34 · Cited by 6
Mobile robot ego motion estimation using RANSAC-based ceiling vision
Wang, H., Mou, W., Ly, M., et al. (2012) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2012.6244312 · Cited by 6
“SURF has the advantage of speed, which has been claimed to be several times faster and more robust against image transformation than SIFT [9].”
MethodModel-based ego-motion and vehicle parameter estimation using visual odometry
Weydert, M. (2012) · IEEE Mediterranean Electrotechnical Conference (MELECON) · doi:10.1109/melcon.2012.6196577 · Cited by 8
“As illustrated in Figure 1, interest points are detected and matched between consecutive stereo image pairs using the SURF algorithm [9] in the first step.”
MethodRobust Game-Theoretic Inlier Selection for Bundle Adjustment
Albarelli, A., Rodolà, E., & Torsello, A. (2010) · IRIS Research product catalog (Sapienza University of Rome) · Cited by 9
Estimation of flow discharge by an airborne velocimetry system
Detert, M., & Weitbrecht, V. (2016) · La Houille Blanche · doi:10.1051/lhb/2016002 · Cited by 7
ROLE OF TIE-POINTS DISTRIBUTION IN AERIAL PHOTOGRAPHY
Kerner, S., Kaufman, I., & Raizman, Y. (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-xl-3-w4-41-2016 · Cited by 6
Techniques and approaches in Robocup@Home - A review
Mehmood, T., Hashmi, M. U., Akhter, A., & Ajmal, A. (2015) · International Conference on Information and Communication Technologies · doi:10.1109/icict.2015.7469481 · Cited by 7
Salient keypoint selection for object representation
Mukherjee, P., Srivastava, S., & Lall, B. (2016) · National Conference on Communications · doi:10.1109/ncc.2016.7561176 · Cited by 6
Ping, T., Zheng, K., Shan, X., et al. (2016) · National Remote Sensing Bulletin · doi:10.11834/jrs.20166222 · Cited by 6
A Copy-Move Forgery Detection Scheme with Improved Clone Region Estimation
Zhao, F., Shi, W., Qin, B., & Liang, B. (2016) · International Conference on Dependable Systems and Their Applications (DSA) · doi:10.1109/tsa.2016.12 · Cited by 6
Lee, C., Wang, H.-J., Lai, J., et al. (2017) · Scientific Reports · doi:10.1038/srep39834 · Cited by 6
Performance analysis of robust watermarking using linear and nonlinear feature matching
Thanh, T. M., Tanaka, K., Dung, L. H., et al. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4435-1 · Cited by 6
Fast wavelet based image characterization for content based medical image retrieval
Anwar, S. M., Arshad, F., & Majid, M. (2017) · International Conference on Communication, Computing and Digital Systems (C-CODE) · doi:10.1109/c-code.2017.7918956 · Cited by 6
Wei, M., & Singh, K. S. (2017) · ACM Symposium on Computational Fabrication (SCF) · doi:10.1145/3083157.3083164 · Cited by 6
How to speed up outliers removal in image matching
Ramos, J. S., Watanabe, C. Y. V., Traina, C., et al. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.08.010 · Cited by 6
Insulator identification method based on infrared image
Liu, Z., Weiping, F., Zihui, Y., et al. (2017) · doi:10.1109/icsgsc.2017.8038564 · Cited by 6
“The algorithm presented in this paper first computes all the SURF feature points, then, the K nearest neighbor matching is performed with the feature points of the template data to filter out most of the features that are not part of the insulators[3].”
MethodFAST corner detection in polygonal approximation of shape
Rachmawati, E., Supriana, I., & Khodra, M. L. (2017) · International Conference on Science in Information Technology · doi:10.1109/icsitech.2017.8257104 · Cited by 6
“There were many corner detection algorithms have been found, namely Harris [5], Shi-Tomasi [6], FAST [7], Fast-Hessian [8], etc.”
MethodIntegrated navigation system with monocular vision and LIDAR for indoor UAVs
Zheng, W., Xiao, J., & Tong, X. (2017) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2017.8282971 · Cited by 7
“But considering the real-time need and the requirements of robust as scale invariance, affine invariance, illumination invariance, rotation invariance and the like, the better options should be SIFT [16], SURF [17] and ORB [18].”
BackgroundSURF based video summarization and its optimization
Jadhav, D., & Bhosle, U. (2017) · doi:10.1109/iccsp.2017.8286581 · Cited by 6
Age Estimation with Local Ternary Directional Patterns
Angulu, R., Tapamo, J., & Adewumi, A. O. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-75786-5_34 · Cited by 6
Power line-tree conflict detection and 3D mapping using aerial images taken from UAV
Watanabe, J.-I., Ren, S., Zhao, Y., et al. (2018) · doi:10.1117/12.2303480 · Cited by 6
Multipurification of matching pairs based on ORB feature and PCB alignment case study
Ye, F., Zheng, H. Y., Lai, Y., et al. (2018) · Journal of Electronic Imaging · doi:10.1117/1.jei.27.3.033029 · Cited by 6
Engin, M. A., & Çavuşoğlu, B. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6368-8 · Cited by 7
“Recent works describe good performances under various conditions such as, SIFT [30], RIFT [28], GLOH [32] and SURF [3].”
A CBIR Scheme Using GLCM Features in DCT Domain
Kumar, S., Pradhan, J., & Pal, A. K. (2017) · IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) · doi:10.1109/iccic.2017.8524205 · Cited by 7
Chen, H., Dai, Y., Xue, R., Zhong, K., & Li, T. (2018) · IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD) · doi:10.1109/iccd.2018.00066 · Cited by 6
“This stages varies depending on the computation resources, which includes SIFT [18], SURF [19], FAST9 [20], ORB [21].”
MethodVasilakos, C., Chatzistamatis, S., Roussou, O., et al. (2019) · Lecture notes in geoinformation and cartography · doi:10.1007/978-3-030-05330-7_2 · Cited by 6
Mapping Technology in Visual SLAM: A Review
Yang, Z., & Shi, D. (2018) · doi:10.1145/3297156.3297163 · Cited by 7
A New Method of Speeded Up Robust Features Image Registration Based on Image Preprocessing
Wang, X., Lv, X., Li, L., et al. (2018) · International Conference on Information Systems and Computer Aided Education (ICISCAE) · doi:10.1109/iciscae.2018.8666894 · Cited by 6
Minimal Solvers for Mini-Loop Closures in 3D Multi-Scan Alignment
Miraldo, P., Saha, S., & Ramalingam, S. (2019) · 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.2019.00993 · Cited by 6
MFNN: Position and Attitude Measurement Neural Network Based on Multi-Feature Fusion
Man, J., Li, G., Xi, M., Lei, Y., Lu, W. B., & Gao, X. (2019) · IEEE Access · doi:10.1109/access.2019.2933878 · Cited by 6
“Commonly used features are SSD , SIFT , DPM and SURF [26], [27].”
MethodComputer Vision-Based Estimation of Respiration Signals
Reyes, M. E. P., Palmero, J. D., Diaz, J. L., et al. (2019) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-030-30648-9_33 · Cited by 6
Ground Vehicle Monocular Visual Odometry
Sabry, M., Al-Kaff, A., Hussein, A., & Abdennadher, S. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917391 · Cited by 6
“As it is shown in Figure 1, the SURF algorithm [22] is applied on the image to extract and track the features”
MethodInFo: Indoor localization using Fusion of Visual Information from Static and Dynamic Cameras
Kim, C., Bhatt, C., Patel, M., Kimber, D., & Tjahjadi, Y. (2019) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2019.8911805 · Cited by 7
Image-Based Recognition of Individual Trouts in the Wild
Zhao, L., Pedersen, M., Hardeberg, J. Y., et al. (2019) · European Workshop on Visual Information Processing · doi:10.1109/euvip47703.2019.8946137 · Cited by 6
“It is based on SURF (Speeded Up Robust Features) [16], which is regarded as an approximated and fast version of SIFT (Scale Invariance Feature Transform) [17].”
MethodTraining Effective Model for Real-Time Detection of NSFW Photos and Drawings
Zhelonkin, D., & Karpov, N. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-39575-9_31 · Cited by 8
Penerapan Speeded-Up Robust Feature pada Random Forest Untuk Klasifikasi Motif Songket Palembang
Yohannes, Y., Devella, S., & Pandrean, A. H. (2020) · Jurnal Teknik Informatika dan Sistem Informasi · doi:10.28932/jutisi.v5i3.1978 · Cited by 6
“Algoritma SURF didasarkan pada prinsip dan langkah-langkah yang sama dengan SIFT, namun detail setiap langkahnya berbeda [10].”
BackgroundA Comparison of Feature Extractors for Panorama Stitching in an Autonomous Car Architecture
Cortes-Gallardo, E., Moreno‐García, C. F., Zhu, A., et al. (2019) · International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE) · doi:10.1109/icmeae.2019.00017 · Cited by 6
CNN Features vs Classical Features for Largescale Cultural Image Retrieval
Belhi, A., & Bouras, A. (2020) · IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT) · doi:10.1109/iciot48696.2020.9089643 · Cited by 7
3D Object Classification Using 2D Perspectives of Point Clouds
Jansen, L., Liebrecht, N., Soltaninejad, S., & Basu, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-54407-2_38 · Cited by 6
Hajari, N., Lugo, G., Sharma, H. V., & Cheng, I. (2020) · Sensors · doi:10.3390/s20185098 · Cited by 9
Retaining Image Feature Matching Performance Under Low Light Conditions
Shyam, P., Bangunharcana, A., & Kim, K.-S. (2020) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas50221.2020.9268426 · Cited by 12
Multi-Modal Loop Closing in Unstructured Planetary Environments with Visually Enriched Submaps
Giubilato, R., Vayugundla, M., Stürzl, W., Schuster, M. J., Wedler, A., & Triebel, R. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9635915 · Cited by 8
Graph-based reasoning attention pooling with curriculum design for content-based image retrieval
Zhu, X., Wang, H., Liu, P., Yang, Z., & Qian, J. (2021) · Image and Vision Computing · doi:10.1016/j.imavis.2021.104289 · Cited by 8
Robust Image Alignment for Outdoor Teach-and-Repeat Navigation
Broughton, G., Linder, P., Rouček, T., Vintr, T., & Krajník, T. (2021) · European Conference on Mobile Robots · doi:10.1109/ecmr50962.2021.9568832 · Cited by 7
Global-scale object detection using satellite imagery
Hamid, R., O'Hara, S., & Tabb, M. (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-3-107-2014 · Cited by 6
Camera Pose Estimation of a Smartphone at a Field without Interest Points
Miyano, R., Inoue, T., Minagawa, T., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37484-5_44 · Cited by 6
“And an accurate pose is estimated by comparing SURF [13] between a current image and reference images.”
MethodAre Performance Differences of Interest Operators Statistically Significant?
Kanwal, N., Ehsan, S., & Clark, A. F. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23678-5_51 · Cited by 6
Extracting Spatio-temporal Local Features Considering Consecutiveness of Motions
Noguchi, A., & Yanai, . (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-12304-7_43 · Cited by 6
Stabilizing Stereo Correspondence Computation Using Delaunay Triangulation and Planar Homography
Chen, C.-I., Sargent, D., Tsai, C.-M., et al. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-89639-5_80 · Cited by 6
Wide-Baseline Visible Features for Highly Dynamic Scene Recognition
Kawewong, A., Tangruamsub, S., & Hasegawa, O. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03767-2_88 · Cited by 6
“However, other local features, such as SURF [7], are also compatible with our method.”
BackgroundMethodResultInfluentialEssig, K., Sand, N., Schack, T., et al. (2010) · Cited by 6
Improvements in accuracy of single camera terrain classification
Abbas, S. M., Muhammad, A., Mehdi, S. A., et al. (2013) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2013.6766493 · Cited by 6
“SURF relies on FASTHessian detector [8] for detecting key points like corners, blobs and T-junctions at unique locations in the image.”
BackgroundMethodInfluentialGPU acceleration of Eff 2 descriptors using CUDA
Daðason, K., Lejsek, H., Jóhansson, Á. Þ., et al. (2010) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1873951.1874178 · Cited by 6
“Note that since performing this comparison we have become aware of the more recent SURF descriptors [1], which are an even faster variant of SIFT, and a GPU version thereof which is significantly faster than our implementation [2].”
BackgroundRobust local feature extraction algorithm with visual cortex for object recognition
Lee, J., Roh, K. A., Wägner, D., & Ko, H. (2011) · Electronics Letters · doi:10.1049/el.2011.1832 · Cited by 6
Guo-Rong, C., Shaozi, L., Wu, Y., et al. (2011) · International Journal of Computational Intelligence Systems · doi:10.2991/ijcis.2011.4.5.13 · Cited by 6
FPGA Implementation of Exclusive Block Matching for Robust Moving Object Extraction and Tracking
Tomioka, Y., Takasu, R., Aoki, T., et al. (2014) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e97.d.573 · Cited by 6
“…the following three categories according to the resolution of the extracted motions: (a) pixel-level tracking methods, such as optical flow [4]– [7]; (b) tracking methods for obtaining the correspondence between small areas, such as block matching [8]; and (c) object-level tracking methods,…”
MethodInfluentialFast and cheap object recognition by linear combination of views
Revaud, J., Lavoué, G., Ariki, Y., et al. (2007) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1282280.1282313 · Cited by 6
Arslan, O., Demirci, B., Altun, H., & Tunaboylu, N. S. (2013) · International Symposium on Mechatronics and its Applications · doi:10.1109/isma.2013.6547367 · Cited by 7
“The HOG algorithm proposed by Shashua et all [11], Dalal and Triggers [12] and is widely used in object and pattern recognition due to its ability to exhibit superior performance in many applications under different conditions [13,14].”
MethodRobust object tracking combining color and scale invariant features
Zhang, S., Yao, H., & Gao, P. (2010) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.863844 · Cited by 6
Eldirdiri, A., Courivaud, F., Palomar, R., et al. (2013) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-013-0933-4 · Cited by 6
“SURF is a robust image detector and descriptor used in computer vision tasks like object recognition and 3D reconstruction [19,21].”
BackgroundMethodInfluentialSelf-calibration of Large Scale Camera Networks
Goorts, P., Maesen, S., Liu, Y., et al. (2014) · International Conference on Signal Processing and Multimedia Applications · doi:10.5220/0005057201070116 · Cited by 6
Boosted cascade of scattered rectangle features for object detection
Zhang, W., Tong, R., & Dong, J. (2009) · Science in China Series F Information Sciences · doi:10.1007/s11432-009-0034-8 · Cited by 6
Learning efficient policies for vision-based navigation
Hornung, A., Strasdat, H., Bennewitz, M., et al. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354634 · Cited by 6
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.