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








Verification
Claims the paper makes
0 Valid · 2 Not valid · 12 Not checked · 30 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The number of interest points found is on average very similar for all detectors.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 4 × 4 sub-region division solution provided the best results.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SURF outperformed the other descriptors for almost all the comparisons.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The SURF descriptor outperforms the other descriptors in a systematic and significant way, with sometimes more than 10% improvement in recall for the same level of precision.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in the results section, the performance is comparable to the one using the discretised and cropped Gaussians.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
8 more claims
Create a free account to see all 44 claims and every source verdict.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This transition marked a new era, where we moved beyond the classic approaches and task-specific feature engineering of earlier days [Lowe 2004; Bay et al. 2006; Rosten and Drummond 2006] towards models that could be trained once over large amounts of data, and then adapted for a broad variety of tasks, such as image recognition, object detection, and image segmentation [Krizhevsky et al. 2012; Sz”
From On the Opportunities and Risks of Foundation Models (2021) · cites this paper as Bay et al. 2006
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · cited 14×
“This PCA-SIFT yields a 36-dimensional descriptor which is fast for matching, but proved to be less distinctive than SIFT in a second comparative study by Mikolajczyk et al. [8] and slower feature computation reduces the effect of fast matching.”
BackgroundMethodResultInfluentialMarr, D., & Hildreth, E. (1980) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1980.0020 · Cited by 6,510
PCA-SIFT: a more distinctive representation for local image descriptors
Ke, Y., & Sukthankar, R. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.183 · Cited by 3,932
Robust wide-baseline stereo from maximally stable extremal regions
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.02.006 · Cited by 3,686
Scalable Recognition with a Vocabulary Tree
Nister, D., & Stewenius, H. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.264 · Cited by 3,579
Scale & Affine Invariant Interest Point Detectors
Mikolajczyk, K., & Schmid, C. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000027790.02288.f2 · Cited by 3,436
Cited by
Items 5,601–5,700 of 14,752
Automatic Matching of Multimodal Remote Sensing Images via Learned Unstructured Road Feature
Yu, K., Xu, C., Ma, J., et al. (2022) · Remote Sensing · doi:10.3390/rs14184595 · Cited by 9
Бобков, В. А., Kudryashov, A. P., & Inzartsev, A. (2022) · Remote Sensing · doi:10.3390/rs14205123 · Cited by 11
Repeatable adaptive keypoint detection via self-supervised learning
Yan, P., Tan, Y., & Tai, Y. (2022) · Science China Information Sciences · doi:10.1007/s11432-021-3364-5 · Cited by 9
“SURF [16] and KAZE [17] are also based on scale space.”
BackgroundCRBeDaSet: A Benchmark Dataset for High Accuracy Close Range 3D Object Reconstruction
Gabara, G., & Sawicki, P. (2023) · Remote Sensing · doi:10.3390/rs15041116 · Cited by 12
Morphological Analysis of the Left Ventricular Endocardial Surface and Its Clinical Implications
Mukhopadhyay, A., Qian, Z. Y., Bhandarkar, S. M., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33418-4_62 · Cited by 9
Keygraphs for Sign Detection in Indoor Environments by Mobile Phones
Morimitsu, H., Hashimoto, M., Pimentel, R. B., Junior, R. M. C., & Hirata, R. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-20844-7_32 · Cited by 9
Localization and object recognition for mobile robots
Arnau Ramisa, A. (2009) · TDX (Tesis Doctorals en Xarxa) · Cited by 9
Single Camera Structure and Motion Estimation
Dani, A. P., & Dixon, W. E. (2010) · Lecture notes in control and information sciences · doi:10.1007/978-1-84996-089-2_12 · Cited by 9
Exploring real-time video interactivity with Scratch
Hwang, T.-H. T. (2012) · Cited by 9
Vision-Guided Robot Control for 3D Object Recognition and Manipulation
Sun, Q., Haemmerle, E., Cheng, Y., & Gamage, P. B. (2008) · InTech eBooks · doi:10.5772/6223 · Cited by 11
Reconstructing Shape and Motion from Asynchronous Cameras
Klose, F., Lipski, C., & Magnor, M. A. (2010) · Eurographics · doi:10.2312/pe/vmv/vmv10/171-177 · Cited by 9
Visual Bearing-Only Simultaneous Localization and Mapping with Improved Feature Matching
Strasdat, H., Stachniss, C., Bennewitz, M., et al. (2007) · Informatik aktuell · doi:10.1007/978-3-540-74764-2_3 · Cited by 9
Triantafyllidis, G. A., Dimitriou, M., Kounalakis, T., et al. (2013) · ELCVIA Electronic Letters on Computer Vision and Image Analysis · doi:10.5565/rev/elcvia.523 · Cited by 9
Clustering Using Class Specific Hyper Graphs
Xia, S., & Hancock, E. R. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-89689-0_36 · Cited by 9
“Hence, local invariant feature based methods[3][6][8], e.g. SIFT, PCA-SIFT, GLOH and SURF, have recently been developed and have been successfully and widely used for object classification [3][7], scene classification [2][5] and video clustering or retrieval [9].”
MethodLandmark Recognition in VISITO Tuscany
Amato, G. M., Falchi, F., & Rabitti, F. (2012) · Communications in computer and information science · doi:10.1007/978-3-642-27978-2_1 · Cited by 9
“The basic idea of Speeded Up Robust Features (SURF) [7] is quite similar to SIFT.”
MethodInfluentialMultiple object identification using grid voting of object center estimated from keypoint matches
Higa, K., Iwamoto, K., & Nomura, T. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738612 · Cited by 9
“Various local descriptors, such as SIFT [1] and SURF [2] which are robust to scaling and rotation of an object, have been proposed for identifying objects between query and database images.”
MethodInfluentialOpenCV Performance Measurements on Mobile Devices
Hudelist, M. A., Cobârzan, C., & Schoeffmann, K. (2014) · doi:10.1145/2578726.2578798 · Cited by 9
“In the next phase we group functions calls to common keypoint detection and descriptor extraction operations like SIFT [7] and SURF [3].”
MethodA pose graph based visual SLAM algorithm for robot pose estimation
Hong, S., & Ye, C. (2014) · World Automation Congress (WAC) · doi:10.1109/wac.2014.6936197 · Cited by 9
Authenticating Lossy Surveillance Video
Ren, Y. J., O’Gorman, L., Wu, L. J., Chang, F., Wood, T. L., & Zhang, J. R. (2013) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2013.2279542 · Cited by 8
Annotating Dance Posture Images Using Multi Kernel Feature Combination
Hassan, E., Chaudhury, S., & Gopal, M. (2011) · National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) · doi:10.1109/ncvpripg.2011.16 · Cited by 9
“Various efficient low-level feature extraction algorithms have been developed which are able to capture subtle variations in colors, color layouts and textures of images [1], [2].”
BackgroundSuzuki, T., & Ikenaga, T. (2013) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.e96.a.1376 · Cited by 9
Tasaki, T., Tokura, S., Sonoura, T., et al. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5649848 · Cited by 9
“Some works [3] use scale and rotation invariant (Local Invariant: LI) feature points like SIFT [4] or SURF [5] without calibrating mirror parameters.”
MethodA new Method for Shot Identification in Basketball Video
Liu, Y., Liu, X., & Huang, C. (2011) · Journal of Software · doi:10.4304/jsw.6.8.1468-1475 · Cited by 9
Automated Detection of Damaged Areas after Hurricane Sandy using Aerial Color Images
Ye, S., Nourzad, S. H. H., Pradhan, A. R., et al. (2014) · Computing in Civil and Building Engineering (2014) · doi:10.1061/9780784413616.223 · Cited by 9
Feng, S., Lotz, T., Chase, J. G., et al. (2010) · Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/iembs.2010.5626070 · Cited by 9
“[58] is another scale and rotation-invariant interest point detector and it employs a slightly different way to detect features [59].”
BackgroundA mapreduce approach for processing large-scale remote sensing images
Liu, Y., Chen, L., Xiong, W., et al. (2012) · International Conference on Geoinformatics · doi:10.1109/geoinformatics.2012.6270312 · Cited by 9
Li, Z., Yu, X., Li, P., & Hashem, M. (2014) · The Visual Computer · doi:10.1007/s00371-014-1044-0 · Cited by 9
Weighted Local Bundle Adjustment and Application to Odometry and Visual SLAM Fusion
Eudes, A., Naudet-Collette, S., Lhuillier, M., et al. (2010) · British Machine Vision Conference (BMVC) · doi:10.5244/c.24.25 · Cited by 9
Image matching techniques for vision-based indoor navigation systems: a 3D map-based approach1
Li, X., & Wang, J. (2014) · Journal of Location Based Services · doi:10.1080/17489725.2013.837201 · Cited by 9
“Then, these newly developed invariant features were applied to image matching systems (e.g. Bay, Tuytelaars, and Gool 2006; Boris, Effrosyni, and Marcin 2008; Se, Lowe, and Little 2002) for accurate location estimation.”
MethodLearning a bag of features based nonlinear metric for facial similarity
Lefebvre, G., & García, C. (2013) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2013.6636646 · Cited by 12
“) while local image descriptors computes invariant features to geometric transforms [19, 15, 4, 23].”
Bai, Y., & Qi, H. (2010) · EURASIP Journal on Image and Video Processing · doi:10.1155/2010/469563 · Cited by 9
Robust L∞convex optimisation for monocular visual odometry trajectory estimation
Boulekchour, M., Aouf, N., & Richardson, M. A. (2014) · Robotica · doi:10.1017/s0263574714001829 · Cited by 9
“It is worthy as well to mention here that each image measurement adds one conical constraint in (24).”
BackgroundRotation and affine-invariant SIFT descriptor for matching UAV images with satellite images
Mingguo, Z., Wu, C., Chen, D., et al. (2014) · doi:10.1109/cgncc.2014.7007582 · Cited by 9
Stereo vision based tree planting spot detection
Kemppainen, T., & Visala, A. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630655 · Cited by 9
Robust features for 2‐DE gel image registration
Möller, B., & Posch, S. (2009) · Electrophoresis · doi:10.1002/elps.200900293 · Cited by 9
“The study shows that among detectors based on image derivatives (Hessian or moment matrices), Harris corners [23], and SUSAN [24], the more recently published scale invariant detectors, the SIFT [25] and SURF [26], are superior in a general context.”
BackgroundMethodMulti-spectral image registration and evaluation based on edge-enhanced MSER
Liu, L., Tuo, H., Xu, T., & Jing, Z. L. (2013) · The Imaging Science Journal · doi:10.1179/1743131x12y.0000000046 · Cited by 9
“Hessian-Affine, SIFT and speeded up robust feature (SURF) belong to blob detectors.(5,6) Maximally stable extremal region (MSER),(7) which we focus on in this article, is a region detector.”
MethodEstimating correspondence between arbitrarily selected points in two widely-separated views
Podbreznik, P., & Potočnik, B. (2010) · Advanced Engineering Informatics · doi:10.1016/j.aei.2010.03.001 · Cited by 9
Mobile media communication, processing, and analysis: A review of recent advances
Gao, W., Duan, L., Sun, J., et al. (2013) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2013.6571985 · Cited by 9
Template Matching Technique for Panoramic Image Stitching
Bhat, A. S., Shivaprakash, A. V., Prasad, N. S., et al. (2013) · Asia Modelling Symposium · doi:10.1109/ams.2013.22 · Cited by 9
“Corners are good keypoints, and are retained using the Hessian matrix.[6] An orientation is calculated for each keypoint, Read the images”
MethodA novel framework for motion segmentation and tracking by clustering incomplete trajectories
Karavasilis, V., Blekas, K., & Nikou, C. (2012) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2012.07.004 · Cited by 10
Contour Propagation Using Feature-Based Deformable Registration for Lung Cancer
Yang, Y., Zhou, S., Shang, P., et al. (2013) · BioMed Research International · doi:10.1155/2013/701514 · Cited by 9
Motion based vehicle identification in car video
Jazayeri, A., Cai, H., Zheng, J. Y., et al. (2010) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2010.5548082 · Cited by 9
Multi-cue Discriminative Place Recognition
Li, X., & Pronobis, A. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15751-6_41 · Cited by 9
Fast image blurring using Lookup Table for real time feature extraction
Ryu, J., & Nishimura, T. H. (2009) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie.2009.5213780 · Cited by 9
“Bay [2] applied the box filter for fast implementation of feature extraction, called Speed Up Robust Feature (SURF).”
MethodStatic hand sign recognition using linear projection methods
Gamage, N., Chow, K. Y., & Akmeliawati, R. (2009) · doi:10.1109/icara.2000.4803982 · Cited by 9
Retinal image registration based on salient feature regions
Zheng, J., Tian, J., Dai, Y., et al. (2009) · doi:10.1109/iembs.2009.5334778 · Cited by 9
Inertial sensors aided image alignment and stitching for panorama on mobile phones
Yang, Q., Wang, C., Gao, Y., et al. (2011) · doi:10.1145/2025876.2025882 · Cited by 9
Fast pose estimation for visual navigation using homographies
Mont, E., & Sagüés, C. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354409 · Cited by 9
“The appearance of invariant descriptors like SIFT [12] or SURF [1] in computer vision has made possible to achieve these tasks in a more precise and robust way.”
BackgroundMethodBody-relative navigation guidance using uncalibrated cameras
Koch, O., & Teller, S. J. (2009) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2009.5459327 · Cited by 10
Sorting local descriptors for lowbit rate mobile visual search
Chen, J., Duan, L., Ji, R., et al. (2011) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2011.5946582 · Cited by 9
MEDIACYCLE: BROWSING AND PERFORMING WITH SOUND AND IMAGE LIBRARIES
Siebert, X., Dupont, S., Fortemps, P., et al. (2009) · ORBi UMONS · Cited by 9
From pixels to objects: Enabling a spatial model for humanoid social robots
Figueira, D., Lopes, M. C., Ventura, R., et al. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152551 · Cited by 9
“…different approaches have been used in computer vision to enable recognition, for instance, eigenspace matching has been used successfully by Schiele [7], others have used Speeded Up Robust Features (SURF) [8], and many have benefited from David Lowe’s Scale Invariant Feature Transform (SIFT) [5].”
MethodVision-Based Terrestrial Surface Monitoring
Paar, G., Huber, N. B., Bauer, A., et al. (2012) · Springer eBooks · doi:10.1007/978-3-642-25495-6_10 · Cited by 9
Tiling of Satellite Images to Capture an Island Object
Sayar, A., Eken, S., & Mert, Ü. (2014) · Communications in computer and information science · doi:10.1007/978-3-319-11071-4_19 · Cited by 9
“[2] proposed a SIFT [3] based multi-spectral remote image registration technique which is actually similar to the SURF technique [4].”
MethodLee, T.-J., Bahn, W., Jang, B.-M., et al. (2012) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2012.6491053 · Cited by 9
Luo, R. C., Huang, C. Y., & Lin, P. H. (2011) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2011.6027077 · Cited by 9
An Architecture for Prototyping and Application Development of Visual Tracking Systems
Becker, M., Bleser, G., Pagani, A., Stricker, D., & Wuest, H. (2007) · 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video · doi:10.1109/3dtv.2007.4379440 · Cited by 9
A comparative study of grayscale conversion techniques applied to SIFT descriptors
Macêdo, S., Melo, G., & Kelner, J. (2015) · Journal on Interactive Systems · doi:10.5753/jis.2015.662 · Cited by 15
“The influences of these methods were also presented using SIFT and SURF descriptors ([12] and [2], respectively), Local Binary Patterns (LBP)[15] and Geometric Blur[3].”
BackgroundMethodFuzzy Controller based Biped Robot Balance Control using 3D Image
Park, S., Han, Y., & Hahn, H. (2009) · International Journal of Fuzzy Systems · doi:10.30000/ijfs.200909.0008 · Cited by 9
FPGA-Based Stereo Vision System Using Gradient Feature Correspondence
Hagiwara, H., Touma, Y., Asami, K., et al. (2015) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2015.p0681 · Cited by 9
Moreń, K., & Göhringer, D. (2016) · Journal of Real-Time Image Processing · doi:10.1007/s11554-016-0576-0 · Cited by 9
“The first one is a construction of simplified feature extraction algorithms like PCA-SIFT [14] or SURF [6].”
MethodGlobal and Local Image Descriptors for Content Based Image Retrieval and Object Recognition
Raoui, Y., Bouyakhf, E. H., & Devy, M. (2011) · Cited by 9
Vehicle Classification Based on Hierarchical Support Vector Machine
Jiang, M., & Li, H. (2013) · Lecture notes in electrical engineering · doi:10.1007/978-3-319-01766-2_68 · Cited by 9
imPlag: Detecting image plagiarism using hierarchical near duplicate retrieval
Srivastava, S., Mukherjee, P., & Lall, B. (2015) · IEEE India Conference · doi:10.1109/indicon.2015.7443541 · Cited by 15
“Apart from the traditionally proven SIFT [8], SURF [9] and PCA-SIFT [10], ORB [11], FREAK [12] and KAZE [13] have become popular.”
MethodA Multiscale Method for HOG-Based Face Recognition
Wei, X., Guo, G., Wang, H., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-22879-2_49 · Cited by 9
Comparison of feature extraction methods for landmine detection using Ground Penetrating Radar
Temlioğlu, E., Dağ, M., & Gürcan, R. (2016) · doi:10.1109/siu.2016.7495827 · Cited by 9
A Hybrid Local Feature for Face Recognition
Gou, G., Huang, D., & Wang, Y. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-32695-0_8 · Cited by 9
Aggregating binary local descriptors for image retrieval
Amato, G. M., Falchi, F., & Vadicamo, L. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4450-2 · Cited by 14
Autonomous learning of robust visual object detection and identification on a humanoid
Leitner, J., Chandrashekhariah, P., Harding, S., Frank, M., Spina, G., Förster, A., Triesch, J., & Schmidhuber, J. (2012) · IEEE International Conference on Development and Learning (ICDL) · doi:10.1109/devlrn.2012.6400826 · Cited by 9
Recent trends in content-based video copy detection
Roopalakshmi, R., & Reddy, G. R. M. (2010) · IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) · doi:10.1109/iccic.2010.5705802 · Cited by 9
Liang, L., Wei, M., Szymczak, A., Pang, W., & Wang, M. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2614219 · Cited by 10
Event recognition in egocentric videos using a novel trajectory based feature
Buddubariki, V., Tulluri, S. G., & Mukherjee, S. (2016) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/3009977.3010011 · Cited by 9
Stereo-camera visual odometry for outdoor areas and in dark indoor environments
Ruppelt, J. P., & Trommer, G. F. (2016) · IEEE Aerospace and Electronic Systems Magazine · doi:10.1109/maes.2016.150255 · Cited by 8
“The best results were achieved with the image processing setup MfFI, SURF-detector, FREAKdescriptor, and the SOF tracker.”
MethodInfluentialPeople Reidentification in a Camera Network
de Oliveira, Í. O., & Pio, J. L. D. S. (2009) · doi:10.1109/csa.2009.5404259 · Cited by 9
Comparison of spatial reconstruction software packages using DSLR images
Somogyi, J., Lovas, T., & Barsi, Á. (2017) · Pollack Periodica · doi:10.1556/606.2017.12.2.2 · Cited by 8
Di, K., Liu, B., Peng, M., Xin, X., Jia, M., Zuo, W., Ping, J., Wu, B., & Oberst, J. (2017) · 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-xlii-3-w1-29-2017 · Cited by 11
“Other scale-invariant features, such as SURF (Bay et al., 2008) and AKAZE (Alcantarilla et al.”
BackgroundMethodda Silva, C. F., & Siebra, C. (2017) · IEEE Latin American Conference on Computational Intelligence (LA-CCI) · doi:10.1109/la-cci.2017.8285727 · Cited by 10
A Coarse-to-Fine Strategy for Vehicle Logo Recognition from Frontal-View Car Images
Sotheeswaran, S., & Ramanan, A. (2018) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661818010170 · Cited by 9
“Hsieh et al. [14] have proposed a system to detect vehicle and to recognize the make and model of the vehicle using a novel symmetrical SURF descriptor [15].”
MethodChatbri, H., Kameyama, K., Kwan, P., et al. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6054-x · Cited by 9
Detection of Dust Deposition Using Convolutional Neural Network for Heritage Images
Sharma, T., Agrawal, P., & Verma, N. K. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-1135-2_27 · Cited by 13
Human Identification System Based on Statistical Gait Features
Htun, K. Z., & Zaw, S. M. M. (2018) · IEEE/ACIS International Conference on Computer and Information Science (ICIS) · doi:10.1109/icis.2018.8466396 · Cited by 9
Quantization of the Space of Structural Image Features as a Way to Increase Recognition Performance
Gorokhovatskyi, V., Gorokhovatskyi, O., Yevgenyi, P., et al. (2018) · IEEE International Conference on Data Stream Mining & Processing (DSMP) · doi:10.1109/dsmp.2018.8478434 · Cited by 9
“Table 1 shows an example of the distribution of CF SURF for each of the 4 etalons (images of dolphins) in the cluster system.”
BackgroundMethodInfluentialChen, L., Huang, P., & Cai, J. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2879286 · Cited by 9
A New Probabilistic Representation of Color Image Pixels and Its Applications
Lin, Z., Qin, H., & Chan, S. C. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2883580 · Cited by 9
Phua, B., Hsiao, P., Wang, X., et al. (2018) · Solar Energy · doi:10.1016/j.solener.2018.12.004 · Cited by 9
Joint Exploitation of Features and Optical Flow for Real-Time Moving Object Detection on Drones
Lezki, H., Ozturk, I. A., Akpınar, M., Yucel, M. K., Loğoğlu, K. B., Erdem, A., & Erdem, E. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11012-3_8 · Cited by 9
Label guided correlation hashing for large-scale cross-modal retrieval
Dong, G., Zhang, X., Lan, L., Wang, S., & Luo, Z. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7192-5 · Cited by 9
Zeng, Y., Ning, Z., Liu, P., Luo, P., Zhang, Y., & He, G. (2019) · Computing · doi:10.1007/s00607-019-00716-5 · Cited by 10
A multi-level descriptor using ultra-deep feature for image retrieval
Wu, Z., & Yu, J. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07771-2 · Cited by 10
ORBDeepOdometry - A Feature-Based Deep Learning Approach to Monocular Visual Odometry
Krishnan, K. S., & Sahin, F. (2019) · International Conference on System of Systems Engineering · doi:10.1109/sysose.2019.8753848 · Cited by 11
Image Based Localization Using Semantic Segmentation for Autonomous Driving
Çınaroğlu, İ., & Baştanlar, Y. (2019) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2019.8806570 · Cited by 11
Heterogeneous domain adaptation with label and structural consistency
Huang, J., Zhou, Z., Shang, J., & Niu, C. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08731-x · Cited by 9
“Two different types of features are considered: SURF [3] which are encoded with 800-bin histograms and DeCAF6 [10] which are the 4,096-dimensional activations of the FC6-layer extracted by the deep convolutional neural network.”
MethodA Smart-Decision System for Realtime Mobile AR Applications
Huang, S., Han, T., & Xie, J. L. (2019) · Globecom · doi:10.1109/globecom38437.2019.9014186 · Cited by 10
“This technique is used by many feature detection and extraction techniques such as SIFT [10], SURF [11] and ORB [12].”
MethodReal-Time Iris Tracking Using Deep Regression Networks for Robotic Ophthalmic Surgery
Qiu, H., Li, Z., Yang, Y., Chen, X., & Bian, G. (2020) · IEEE Access · doi:10.1109/access.2020.2980005 · Cited by 15
An End-to-End Trainable Multi-Column CNN for Scene Recognition in Extremely Changing Environment
Li, Z., Zhou, A., & Shen, Y. (2020) · Sensors · doi:10.3390/s20061556 · Cited by 10
Yuen, H. P., Choi, Y. W., & Kim, Y. B. (2020) · IEEE International Colloquium on Signal Processing & Its Applications (CSPA) · doi:10.1109/cspa48992.2020.9068705 · Cited by 9
“Here, a GPU-based SURF (Speeded Up Robust Features) algorithm [11] for detection and extraction of the feature points correspondence between the input images is used.”
MethodLearning-Based Affine Registration of Histological Images
Wodziński, M., & Müller, H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-50120-4_2 · Cited by 17
“We compare the proposed method to the most popular computer vision descriptors (SURF [25] and SIFT [26]) as well as the intensity-based, iterative affine registration [27].”
MethodA local feature extraction method for UAV-based image registration based on virtual line descriptors
Xing, L., & Dai, W. (2020) · Signal Image and Video Processing · doi:10.1007/s11760-020-01788-z · Cited by 10
“In recent years, the research on invariant detectors has gradually emerged within rapid development, of which the SIFT (scale invariant feature transformation) algorithm and its variants are the most representatives [3, 4].”
BackgroundSize-invariant Detection of Marine Vessels From Visual Time Series
Marques, T. P., Albu, A. B., O’Hara, P. D., Serra-Sogas, N., Morrow, B., McWhinnie, L., & Canessa, R. R. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00049 · Cited by 13
Self-supervised Simultaneous Alignment and Change Detection
Furukawa, Y., Suzuki, K., Hamaguchi, R., et al. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340840 · Cited by 9
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.