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 2,301–2,400 of 14,752
Development of Modular Bio-Inspired Autonomous Underwater Vehicle for Close Subsea Asset Inspection
Gorma, W., Post, M., White, J., Gardner, J., Luo, Y., Kim, J., Mitchell, P., Morozs, N., Wright, M., & Xiao, Q. (2021) · Applied Sciences · doi:10.3390/app11125401 · Cited by 34
Image Retrieval Method Based on Image Feature Fusion and Discrete Cosine Transform
Jiang, D., & Kim, J. (2021) · Applied Sciences · doi:10.3390/app11125701 · Cited by 41
Real-time Geo-localization Using Satellite Imagery and Topography for Unmanned Aerial Vehicles
Chen, S., Wu, X., Mueller, M. W., & Sreenath, K. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636705 · Cited by 36
Energy-Efficient Ground Traversability Mapping Based on UAV-UGV Collaborative System
Li, J., Cheng, Y., Zhou, J., Chen, J., Liu, Z., Hu, S., & Leung, V. C. M. (2021) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2021.3107291 · Cited by 33
Qadeer, W., Hameed, R., Shacham, O., et al. (2013) · ACM SIGARCH Computer Architecture News · doi:10.1145/2508148.2485925 · Cited by 31
Machine Learning and Image Processing Methods for Cetacean Photo Identification: A Systematic Review
Maglietta, R., Carlucci, R., Fanizza, C., & Dimauro, G. (2022) · IEEE Access · doi:10.1109/access.2022.3195218 · Cited by 36
Terrain Aided Planetary UAV Localization Based on Geo-referencing
Wan, X., Shao, Y., Zhang, S., & Li, S. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3198745 · Cited by 32
Liang, T., Ma, S., Ma, X., & You, H. (2022) · Applied Sciences · doi:10.3390/app12178448 · Cited by 36
Huang, X., Li, Z., Zhang, M., & Gao, S. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.994950 · Cited by 43
“In particular, seven hand-crafted features, namely, the SIFT, SURF, and ORB local features, the texture and shape of the cell nuclei, the HOG of the cavities, color of the image, and the DL feature were extracted.”
BackgroundInfluentialEstimating small structural motions from multi-view video measurement
Cai, E., Zhang, Y., Ji, X., Lu, X., Xie, L., Zhuang, Y., Zhao, T., & Lin, G. (2022) · Engineering Structures · doi:10.1016/j.engstruct.2022.115259 · Cited by 32
Zhang, G., Qin, D., Yang, J., Yan, M., Tang, H., Bie, H., & Ma, L. (2022) · Remote Sensing · doi:10.3390/rs14236013 · Cited by 31
Exploiting sublimated deep features for image retrieval
Liu, G., Li, Z., Yang, J.-Y., & Zhang, D. D. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110076 · Cited by 34
Enabling Aircraft Emergency Landings Using Active Visual Site Detection
Warren, M., Mejías, L., Yang, X., Arain, B., Gonzalez, F., & Upcroft, B. (2014) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-07488-7_12 · Cited by 31
Polar Embedding for Aurora Image Retrieval
Yang, X., Gao, X., & Tian, Q. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2442913 · Cited by 30
“Similar choices include SURF [24], PCA-SIFT [25].”
PAIGE: PAirwise Image Geometry Encoding for improved efficiency in Structure-from-Motion
Schönberger, J. L., Berg, A. C., & Frahm, J. (2015) · 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.2015.7298703 · Cited by 37
Feature matching in stereo images encouraging uniform spatial distribution
Tan, X., Sun, C., Sirault, X. R. R., Furbank, R. T., & Pham, T. D. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.02.026 · Cited by 31
“Many advanced feature point detectors have been proposed in the literature, such as the scale invariant feature transform (SIFT) [19] and the speeded up robust features (SURF) [20].”
Terrain Classification From Body-Mounted Cameras During Human Locomotion
Anantrasirichai, N., Burn, J. F., & Bull, D. (2014) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2368353 · Cited by 31
“As locomotion applications generally require real-time processing, speeded up robust features [25] have also used to identify key features in texture areas [8], [26].”
MethodIdentification of ancient coins based on fusion of shape and local features
Huber-Mörk, R., Zambanini, S., Zaharieva, M., et al. (2010) · Machine Vision and Applications · doi:10.1007/s00138-010-0283-y · Cited by 31
Kalia, R., Lee, K., Samir, B., Je, S.-K., & Oh, W.-G. (2011) · Korea-Japan Joint Workshop on Frontiers of Computer Vision · doi:10.1109/fcv.2011.5739756 · Cited by 36
“used box filters as a further approximation to the second order Gaussians, and they used integral images for fast computation [11,12,13].”
MethodMotion artifacts suppression for remote imaging photoplethysmography
Feng, L., Po, L.-M., Xu, X., & Li, Y. (2014) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/icdsp.2014.6900813 · Cited by 33
An image-based intelligent system for pointer instrument reading
Yang, Z., Niu, W., Peng, X., Gao, Y., Qiao, Y., & Dai, Y. (2014) · IEEE International Conference on Information Science and Technology (ICIST) · doi:10.1109/icist.2014.6920593 · Cited by 34
“The registration based on ORB descriptor is fast compared to some other well-known descriptors such as SIFT and SURF.”
MethodClustering near-duplicate images in large collections
Foo, J. J., Zobel, J., & Sinha, R. (2007) · Multimedia Information Retrieval · doi:10.1145/1290082.1290089 · Cited by 33
A study of projections for key point based registration of panoramic terrestrial 3D laser scan
Houshiar, H., Elseberg, J., Borrmann, D., & Nüchter, A. (2015) · Geo-spatial Information Science · doi:10.1080/10095020.2015.1017913 · Cited by 31
Accuracy assessment of minimum control points for UAV photography and georeferencing
Skarlatos, D. P., Procopiou, E., Stavrou, G., et al. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2028988 · Cited by 31
On feature extraction and region matching for forward scan sonar imaging
Aykin, M. D., & Negahdaripour, S. (2012) · doi:10.1109/oceans.2012.6404983 · Cited by 31
“This is exploited by feature matching algorithms that exploit the similarity in the appearance of a feature in the source and destination images [3], [10].”
Automatic sports genre categorization and view-type classification over large-scale dataset
Li, L., Zhang, N., Duan, L., et al. (2009) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1631272.1631380 · Cited by 31
Automatic nuclear cataract grading using image gradients
Srivastava, R., Gao, X., Yin, F., et al. (2014) · Journal of medical imaging · doi:10.1117/1.jmi.1.1.014502 · Cited by 31
Grid-based visual terrain classification for outdoor robots using local features
Khan, Y. N., Komma, P., Bohlmann, K., & Zell, A. (2011) · IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems (CIVTS) · doi:10.1109/civts.2011.5949534 · Cited by 29
“As a second contribution we introduce five further texture descriptors, the Local Ternary Patterns descriptor (LTP) [23], the Local Adaptive Ternary Patterns descriptor (LATP) [1], the SURF descriptor [4], the Daisy descriptor [24] and the Constrast Context Histograms (CCH) descriptor [13], which, to our knowledge, ha…”
BackgroundMethodCoherent Phrase Model for Efficient Image Near-Duplicate Retrieval
Hu, Y., Cheng, X., Chia, L.-T., Xie, X., Rajan, D., & Tan, A. (2009) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2009.2032676 · Cited by 30
Bundle adjustment in large-scale 3D reconstructions based on underwater robotic surveys
Beall, C., Dellaert, F., Mahon, I., & Williams, S. B. (2011) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans-spain.2011.6003631 · Cited by 31
“Features are extracted and matched between all the images [17], [18], and camera poses and landmark locations are optimized to minimize a cost function.”
BackgroundRealidad virtual y realidad aumentada
Guerrero, M. J. A., Manresa-Yee, C., Sansó, R. M., & Vénere, M. (2011) · doi:10.35537/10915/18399 · Cited by 31
Extracting Semantic Information from Visual Data: A Survey
Liu, Q., Li, R., Hu, H., & Gu, D. (2016) · Robotics · doi:10.3390/robotics5010008 · Cited by 34
QuickSpot: a video analytics solution for on-street vacant parking spot detection
Màrmol, E., & Sevillano, X. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3773-8 · Cited by 32
“Based on an integer approximation to the determinant of Hessian blob detector to build a local feature detector partially inspired in SIFT [33] and several times faster [5], SURF descriptors are invariant to image scale and moderate rotations (e.”
MethodSecure Surfing: Privacy-Preserving Speeded-Up Robust Feature Extractor
Wang, Q., Hu, S., Wang, J., & Ren, K. (2016) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2016.84 · Cited by 33
“In [16], the authors considered another famous feature extraction algorithm SURF [17] (which is 2016 IEEE 36th International Conference on Distributed Computing Systems”
BackgroundResultInfluentialData Acquisition for 3D Geometric Recording: State of the Art and Recent Innovations
Georgopoulos, A., & Stathopoulou, E. K. (2017) · Quantitative methods in the humanities and social sciences · doi:10.1007/978-3-319-65370-9_1 · Cited by 43
Loop Closure Detection Based on Multi-Scale Deep Feature Fusion
Chen, B., Yuan, D., Liu, C., & Wu, Q. H. (2019) · Applied Sciences · doi:10.3390/app9061120 · Cited by 31
Hurtado, E. G. (2019) · IntechOpen eBooks · doi:10.5772/intechopen.74181 · Cited by 38
Real‐time geometry‐aware augmented reality in minimally invasive surgery
Chen, L. F., Tang, W. J., & John, N. W. (2017) · Healthcare Technology Letters · doi:10.1049/htl.2017.0068 · Cited by 30
Automatic fetal brain extraction from 2D in utero fetal MRI slices using deep neural network
Li, J., Luo, Y., Shi, L., Zhang, X., Li, M., Zhang, B., & Wang, D. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.10.032 · Cited by 33
Karaman, S., Benois‐Pineau, J., Mégret, R., et al. (2010) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 31
Minimax rates in permutation estimation for feature matchingPreprint
Collier, O., & Dalalyan, A. S. (2013) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.48550/arxiv.1310.4661 · Cited by 31
“Typically, due to the high resolution of most images, the number of features is large and their dimension is relatively large as well (128 for SIFT and 64 for SURF).”
BackgroundPatch Similarity Self-Knowledge Distillation for Cross-View Geo-Localization
Li, S., Hu, M. Q., Xiao, X., & Tu, Z. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3336844 · Cited by 39
“Hand-crafted feature methods widely used the local information for image retrieval, such as SIFT [45], SURF [46], ORB [47], LBP [48].”
MethodWang, S., Laskar, Z., Melekhov, I., Li, X., Zhao, Y., Tolias, G., & Kannala, J. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-023-01982-9 · Cited by 61
“…image, a sparse set of keypoints and their local descriptors are obtained using traditional (Calonder et al., 2010; Lowe, 2004; Rublee et al., 2011; Bay et al., 2006) or learnedCNN-based(DeToneetal.,2018;Revaudetal.,2019; Dusmanu et al., 2019; Melekhov et al., 2021, 2020; Luo et al., 2019; Wang et…”
Video shot-boundary detection: issues, challenges and solutions
Kar, T., Kanungo, P., Mohanty, S. N., et al. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10742-1 · Cited by 30
“Duan and Meng (2020) proposed a combined feature approach using DCT and SURF feature applied to selected frames obtained by non-overlapping interval method followed by coarse and then fine detection of shot boundaries.”
InfluentialKamali, M., Atazadeh, B., Rajabifard, A., & Chen, Y. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102929 · Cited by 45
Beugher, S. D., Brône, G., & Goedemé, T. (2014) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004741606250633 · Cited by 40
Efficient Vessel Feature Detection for Endoscopic Image Analysis
Lin, B., Sun, Y., Sanchez, J. E., & Qian, X. (2014) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2014.2373273 · Cited by 31
“approximated the Gaussian filters with box filters in the calculation of the Hessian matrix, and the obtained speeded up robust features (SURF) detector was typically faster than the DoG detector [20].”
MethodImage matching based on orientation–magnitude histograms and global consistency
Liang, J., Liao, Z., Yang, S., & Wang, Y. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.03.026 · Cited by 30
A real-time visual object tracking system based on Kalman filter and MB-LBP feature matching
Cai, Z., Gu, Z., Yu, Z. L., Liu, H., & Zhang, K. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2411-6 · Cited by 31
Dawood, M., Cappelle, C., Najjar, M. E. E., et al. (2012) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2012.6469511 · Cited by 30
Feature description based on center-symmetric local mapped patterns
Ferraz, C. T., Pereira, O., & Gonzaga, A. (2014) · ACM Symposium on Applied Computing · doi:10.1145/2554850.2554895 · Cited by 30
“SURF approximates SIFT using the Haar wavelet response and using integral images to compute the histograms bins.”
MethodFast stitching of videos captured from freely moving devices by exploiting temporal redundancy
El-Saban, M., Izz, M., & Kaheel, A. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5651811 · Cited by 30
Qadeer, W., Hameed, R., Shacham, O., et al. (2015) · Communications of the ACM · doi:10.1145/2735841 · Cited by 30
Osia, N., & Bourlai, T. (2014) · Image and Vision Computing · doi:10.1016/j.imavis.2014.06.010 · Cited by 31
“• SURF: The SURF method is very similar to SIFT.”
BackgroundMethodInfluentialSocially intelligent surveillance and monitoring: Analysing social dimensions of physical space
Cristani, M., Murino, V., & Vinciarelli, A. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543179 · Cited by 33
Schneider, M., & Schneider, T. H. (2014) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/2600918.2600927 · Cited by 30
Fixed partitioning and salient points with MPEG-7 cluster correlograms for image categorization
Abdullah, A., Veltkamp, R. C., & Wiering, M. (2009) · Pattern Recognition · doi:10.1016/j.patcog.2009.09.007 · Cited by 30
“The most recent algorithm called SURF (Speeded Up Robust Features) [5] is claimed to be comparable to or even better than SIFT in both speed and recognition accuracy.”
MethodInfluentialObject Matching Using Speeded Up Robust Features
Verma, N. K., Goyal, A., Vardhan, A. H., Sevakula, R. K., & Salour, A. (2015) · Proceedings in adaptation, learning and optimization · doi:10.1007/978-3-319-27000-5_34 · Cited by 33
“Scale Invariant Feature Transform (SIFT) [11] and Speeded Up Robust Features (SURF) [2] are local feature descriptors extracted at interest points in an image.”
BackgroundMethodInfluentialSIFT and SURF Performance Evaluation for Mobile Robot-Monocular Visual Odometry
Benseddik, H. E., Djekoune, O., & Belhocine, M. (2014) · Journal of Image and Graphics · doi:10.12720/joig.2.1.70-76 · Cited by 32
Optical Myography: Detecting Finger Movements by Looking at the Forearm
Nissler, C., Mouriki, N., & Castellini, C. (2016) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2016.00003 · Cited by 37
Murtiyoso, A., Grussenmeyer, P., & Fréville, T. (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-2-w3-519-2017 · Cited by 30
“Examples of FBM algorithms include SIFT (Lowe, 2004), SURF (Bay et al., 2006), Harris detectors (Harris and Stephens, 1988), etc.”
MethodRegion duplication detection based on image segmentation and keypoint contexts
Lin, C., Lu, W., Sun, W., Zeng, J., Xu, T., & Lai, J. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5027-9 · Cited by 28
Robotic inspection of ship hull surfaces using a magnetic crawler and a monocular camera
Milella, A., Maglietta, R., Caccia, M., et al. (2017) · Sensor Review · doi:10.1108/sr-02-2017-0021 · Cited by 30
Evaluation of Object Proposals and ConvNet Features for Landmark-based Visual Place Recognition
Hou, Y., Zhang, H., & Zhou, S. (2017) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-017-0735-y · Cited by 28
“By using some local invariant feature extraction methods such as scale-invariant feature transform (SIFT) [12] and speeded-up robust features (SURF) [13], visual BoW first detects a number of interesting keypoints and their local neighbour regions, and then characterizes these detected regions as…”
MethodNandi, D., Saif, A. F. M. S., Paul, P. R.-R., Zubair, K. M., & Shubho, S. A. (2018) · International Journal of Modern Education and Computer Science · doi:10.5815/ijmecs.2018.06.05 · Cited by 35
A video-based object detection and tracking system for weight sensitive UAVs
Abughalieh, K. M., Sababha, B. H., & Rawashdeh, N. A. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6508-1 · Cited by 30
“Speededup Robust Features (SURF) is a similar algorithm and approximates SIFT with a lower computational cost [4].”
MethodA New Dataset and Performance Evaluation of a Region-Based CNN for Urban Object Detection
Dominguez-Sanchez, A., Cazorla, M., & Orts‐Escolano, S. (2018) · Electronics · doi:10.3390/electronics7110301 · Cited by 31
Sekulska-Nalewajko, J., Kornaś, A., Gocławski, J., Miszalski, Z., & Kuźniak, E. (2019) · Plant Methods · doi:10.1186/s13007-019-0401-4 · Cited by 29
Geospatial Object Detection via Deconvolutional Region Proposal Network
Wang, C., Shi, J., Yang, X., Zhou, Y., Wei, S., Li, L., & Zhang, X. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2919382 · Cited by 30
ELF: Embedded Localisation of Features in Pre-Trained CNN
Benbihi, A., Geist, M., & Pradalier, C. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00803 · Cited by 30
“SURF [7] uses image integral to speed up the previous detection and uses a sum of Haar wavelet responses for description.”
MethodSparse graphical representation based discriminant analysis for heterogeneous face recognition
Peng, C., Gao, X., Wang, N., & Li, J. (2018) · Signal Processing · doi:10.1016/j.sigpro.2018.10.015 · Cited by 36
Kim, D., Lee, S., Hong, W., Lee, H., Jeon, S., Han, S. S., & Nam, J. (2019) · Microscopy and Microanalysis · doi:10.1017/s1431927619014752 · Cited by 30
“1) Groups of feature points in f G2 z−1 and f G1 z are extracted using speeded-up robust features (SURF) (Bay et al., 2006) (Supplementary Fig.”
MethodBenchmark of Visual SLAM Algorithms: ORB-SLAM2 vs RTAB-Map
Ragot, N., Khemmar, R., Pokala, A., Rossi, R., & Ertaud, J.-Y. (2019) · International Conference on Emerging Security Technologies · doi:10.1109/est.2019.8806213 · Cited by 37
“Examples of the first category are the SIFT [16] and SURF [17] descriptors, and the second category global descriptors such as HOG [19] and GIST [18]. bag-of-words separates the point of interest space into a finite number of visual words.”
Mapping with Pléiades—End-to-End Workflow
Perko, R., Raggam, H., & Roth, P. M. (2019) · Remote Sensing · doi:10.3390/rs11172052 · Cited by 43
Persistent Stereo Visual Localization on Cross-Modal Invariant Map
Ding, X., Wang, Y., Xiong, R., Li, D., Tang, L., Yin, H., & Zhao, L. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2942760 · Cited by 29
“Many previous works utilized SIFT [37], SURF [38] or binary feature descriptors [39], [40] for data association between current views and the maps.”
MethodMizuno, K., Terayama, K., Tabeta, S., et al. (2019) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2019.2938717 · Cited by 30
“features (SURF) [32], which is a rotation and scale invariant feature and is one of the most widely used descriptors.”
BackgroundFast Object Pose Estimation Using Adaptive Threshold for Bin-Picking
Yan, W., Xu, Z., Zhou, X., Su, Q., Li, S., & Wu, H. (2020) · IEEE Access · doi:10.1109/access.2020.2983173 · Cited by 32
A Robust Copy-Move Forgery Detection In Digital Image Forensics Using SURF
Badr, A., Youssif, A. A. A., & Wafi, M. (2020) · International Symposium on Digital Forensics and Security (ISDFS) · doi:10.1109/isdfs49300.2020.9116433 · Cited by 34
“[29] introduced a Speeded-Up Robust Features (SURF) detector and descriptor which is slightly inspired by the Scale-Invariant Feature Transform (SIFT) descriptor.”
Method3D Digitization of Cultural Heritage
Guidi, G., & Frischer, B. (2020) · Springer eBooks · doi:10.1007/978-3-030-44070-1_13 · Cited by 30
Differential Morphed Face Detection Using Deep Siamese Networks
Soleymani, S., Chaudhary, B., Dabouei, A., Dawson, J. M., & Nasrabadi, N. M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68780-9_44 · Cited by 43
Keypoint based comprehensive copy‐move forgery detection
Diwan, A., Sharma, R., Roy, A., & Mitra, S. K. (2020) · IET Image Processing · doi:10.1049/ipr2.12105 · Cited by 33
“We have experimentally evaluated some of the predominantly used keypoint detectors like SIFT [25], SURF [26], and ORB [27] and compared it with CenSurE.”
MethodInfluentialTouch Modality Classification Using Recurrent Neural Networks
Alameh, M., Abbass, Y., Ibrahim, A., Moser, G., & Valle, M. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3055565 · Cited by 32
“For feature extraction, the first approach uses Speeded-Up Robust Features (SURF) descriptor [17], while the second uses a pre-trained AlexNet CNN [18].”
MethodEnhancing medical image registration via appearance adjustment networks
Meng, M., Bi, L., FULHAM, M. J., Feng, D. D., & Kim, J. (2022) · NeuroImage · doi:10.1016/j.neuroimage.2022.119444 · Cited by 36
“Early image registration employs key points, such as scale-invariant feature transform (SIFT) [44] and speeded up robust features (Surf) [45].”
Combining Optimized SAR-SIFT Features and RD Model for Multisource SAR Image Registration
Wang, M., Zhang, J., Deng, K., & Hua, F. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3074630 · Cited by 31
Detection of Morphed Face Images Using Discriminative Wavelet Sub-bands
Aghdaie, P., Chaudhary, B., Soleymani, S., Dawson, J. M., & Nasrabadi, N. M. (2021) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf50991.2021.9465074 · Cited by 30
Deepfake Image Detection using CNNs and Transfer Learning
Kumar, N., Pranav, P., Nirney, V., & Geetha, V. (2021) · International Conference on Computing, Communication and Green Engineering (CCGE) · doi:10.1109/ccge50943.2021.9776410 · Cited by 39
Tamou, A. B., Benzinou, A., & Nasreddine, K. (2022) · Machine Learning and Knowledge Extraction · doi:10.3390/make4030036 · Cited by 43
Learning-Based Pose Estimation of Non-Cooperative Spacecrafts with Uncertainty Prediction
Li, K., Zhang, H., & Hu, C. (2022) · Aerospace · doi:10.3390/aerospace9100592 · Cited by 34
“The more refined keypoint feature can be calculated through some engineered algorithms [30–33], which seek alternative structures within images to represent the keypoint.”
UKPGAN: A General Self-Supervised Keypoint Detector
You, Y., Liu, W., Ze, Y., Li, Y., Wang, W., & Lu, C. (2022) · 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/cvpr52688.2022.01653 · Cited by 31
TransforMatcher: Match-to-Match Attention for Semantic Correspondence
Kim, S., Min, J., & Cho, M. (2022) · 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/cvpr52688.2022.00850 · Cited by 50
Optical and SAR Image Dense Registration Using a Robust Deep Optical Flow Framework
Zhang, H., Lei, L., Ni, W., Yang, X., Tang, T., Cheng, K., Xiang, D., & Kuang, G. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3235535 · Cited by 38
“Since the classical SIFT [35] or SURF [36] like feature point detector applied separately on optical and SAR images is not able to identify adequate candidate correspondences of high repeatability [7], most of the current feature point detecting and matching methods tend to first apply the Harris…”
MethodVF-SIFT: Very Fast SIFT Feature Matching
Alhwarin, F., Ristić–Durrant, D., & Gräser, A. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15986-2_23 · Cited by 36
Fast Odometry Integration in Local Bundle Adjustment-Based Visual SLAM
Eudes, A., Lhuillier, M., Naudet-Collette, S., & Dhome, M. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.80 · Cited by 30
McManus, C., Furgale, P., & Barfoot, T. D. (2013) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2013.04.008 · Cited by 34
Lin, W.-Y., Liu, L., Matsushita, Y., Low, K., & Liu, S. (2012) · 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.2012.6247651 · Cited by 38
Structured prediction by joint kernel support estimation
Lampert, C. H., & Blaschko, M. B. (2009) · Machine Learning · doi:10.1007/s10994-009-5111-0 · Cited by 29
Learning maps in 3D using attitude and noisy vision sensors
Steder, B., Grisetti, G., Grzonka, S., Stachniss, C., Rottmann, A., & Burgard, W. (2007) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2007.4399414 · Cited by 33
Stereo-Based Visual Odometry for Autonomous Robot Navigation
Kostavelis, I., Boukas, E., Nalpantidis, L., & Gasteratos, A. C. (2016) · International Journal of Advanced Robotic Systems · doi:10.5772/62099 · Cited by 31
“The most common feature detector is the Harris corner detector [19], while more recently developed feature detection methods„ such as SIFT [20], SURF [9] and even CenSurE [21] involve both feature detection and description practices.”
MethodInfluentialTafti, A. P., Baghaie, A., Kirkpatrick, A. B., Holz, J. D., Owen, H. A., D’Souza, R. M., & Yu, Z. (2016) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2016.1152201 · Cited by 32
“For SURF, scale and rotation invariance are intended in the process of design (Bay et al. 2006).”
MethodUlusel, O. C., Picardo, C. B., Harris, C. B., Reda, S., & Bahar, R. I. (2016) · International Conference on Field Programmable Logic and Applications (FPL) · doi:10.1109/fpl.2016.7577310 · Cited by 30
“For instance, Bouris et al. [5] and Svab et al. [6] both presented FPGA implementations for the SURF algorithm.”
MethodInfluential
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.