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 2,901–3,000 of 14,752
Vaškevičius, N., Pathak, K., Ichim, A.-E., & Birk, A. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6225335 · Cited by 23
“Speeded Up Robust Features (SURF) [8], [9], the Scale Invariant Feature Transform (SIFT) [10], etc.”
MethodStraub, J., Berk, J., Nervold, A., et al. (2013) · Cited by 23
Comparative Study of Part-Based Handwritten Character Recognition Methods
Song, W., Uchida, S., & Liwicki, M. (2011) · Proceedings of the International Conference on Document Analysis and Recognition · doi:10.1109/icdar.2011.167 · Cited by 23
Learning invariant structure for object identification by using graph methods
Bai, X. P., Song, Y.-Z., & Hall, P. M. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2010.12.016 · Cited by 22
“Patches can be described in several ways: Gaussian derivative jets [6] and shape contexts [4] have been used, as have the recently proposed SURF features [3], but SIFT features [22] are perhaps the most common.”
MethodBoosted random contextual semantic space based representation for visual recognition
Zhang, C., Xue, Z., Zhu, X., Wang, H., Huang, Q., & Tian, Q. (2016) · Information Sciences · doi:10.1016/j.ins.2016.06.029 · Cited by 24
Shleymovich, M. P., Medvedev, M. V., & Lyasheva, S. A. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2270141 · Cited by 23
“Based on equality (18) it is possible to obtain energy estimation for each image point using the following algorithm.”
BackgroundMethodInfluentialShleymovich, M. P., Medvedev, M. V., & Lyasheva, S. A. (2016) · International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM) · doi:10.1109/icieam.2016.7911633 · Cited by 23
“In SURF method [11] salient points are detected with the help of Hesse matrix.”
MethodAccurate image registration method for PCB defects detection
Hua, G.-L., Huang, W.-P., & Liu, H. (2018) · Jurnal Engineering · doi:10.1049/joe.2018.8272 · Cited by 25
“The part of this description of SURF has two parts: determine the main orientation of feature points and generate SURF descriptors.”
MethodInfluentialTransductive Transfer Learning Based on Broad Learning System
Yang, L., Song, S., & Chen, C. L. P. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00162 · Cited by 30
“We follow the the feature extraction method in [21] and speeded up robust features (SURF) [23] are utilized to describe the samples, which are summarized in Table I.”
MethodPanetta, K. A., Wan, Q., Kaszowska, A., Taylor, H. A., & Agaian, S. С. (2019) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2019.2892919 · Cited by 23
“For instance, in Step 1, we chose the SIFT feature extraction algorithm over the regular dense [55] feature, SURF [56] feature, and random sampling [57] feature extraction be- cause it provided more accurate classification for eye tracker data with regard to the participants’ movement that resulted in frequent zoom-in…”
MethodCivera, M., Fragonara, L. Z., & Surace, C. (2019) · Sensors · doi:10.3390/s19102345 · Cited by 23
Miah, S. J., Vu, H., & Gammack, J. G. (2019) · Information Technology and Management · doi:10.1007/s10799-019-00303-2 · Cited by 26
“Local region descriptors, named Speeded Up Robust Features (SURF) [37], are first extracted from each photo.”
BackgroundEsfahani, M. A., Wu, K., Yuan, S., & Wang, H. (2019) · Image and Vision Computing · doi:10.1016/j.imavis.2019.06.014 · Cited by 21
Loss Switching Fusion with Similarity Search for Video Classification
Wang, L., Huynh, D. Q., & Mansour, M. R. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803051 · Cited by 32
6DoF Pose-Estimation Pipeline for Texture-less Industrial Components in Bin Picking Applications
Blank, A., Hiller, M., Zhang, S., Leser, A., Metzner, M., Lieret, M., Thielecke, J., & Franke, J. E. (2019) · European Conference on Mobile Robots · doi:10.1109/ecmr.2019.8870920 · Cited by 27
Unsupervised Extraction of Local Image Descriptors via Relative Distance Ranking Loss
Yu, X., Tian, Y., Porikli, F., Hartley, R. I., Li, H., Heijnen, H., & Balntas, V. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00351 · Cited by 24
“The evolution of local descriptors has achieved remarkable progress over the past three decades, including differential filter based [24], moment invariant based [52], and histograms of gradients based features, such as HOG [11], LBP [31], DAISY [54], SIFT [29] and SURF [5].”
BackgroundMethodInfluentialTracking feature extraction techniques with improved SIFT for video identification
Jin, R., & Kim, J. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2694-2 · Cited by 22
SuperPointVO: A Lightweight Visual Odometry based on CNN Feature Extraction
Xiao, H., Tao, Y., Li, Z., Cen, R., & Xue, F. (2020) · International Conference on Automation, Control and Robotics Engineering (CACRE) · doi:10.1109/cacre50138.2020.9230348 · Cited by 31
“Until recently, hand-engineered feature extraction methods (SIFT[1], SURF[2], ORB[3]) were still widely used.”
MethodUsing SURF to Improve ResNet-50 Model for Poultry Disease Recognition Algorithm
Quach, L.-D., Quoc, N. P., Thi, N. H., et al. (2020) · doi:10.1109/icci51257.2020.9247698 · Cited by 23
“~ 318 ~ hypothesis could improve the accuracy of the ResNet-50 model by enhancing the data preprocessing with Speeded Up Robust Features (SURF) [10].”
MethodAdditive deep feature optimization for semantic image retrieval
Hussain, S., Zia, M. A., & Arshad, W. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114545 · Cited by 24
Zaatari, S. E., Wang, Y., Hu, Y., & Li, W. (2021) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-021-01743-w · Cited by 29
“The vectors are scale and rotation invariant, which allows them to be matched robustly from different images (Bay et al. 2006).”
BackgroundFSD-SLAM: a fast semi-direct SLAM algorithm
Dong, X. L., Cheng, L., Hu, P., & Li, T. (2021) · Complex & Intelligent Systems · doi:10.1007/s40747-021-00323-y · Cited by 28
“In 2014, Artal and Tardos et al. [16] designed ORB-SLAM system.”
BackgroundSun, L., & Deng, L. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3152837 · Cited by 28
Virtual Correspondence: Humans as a Cue for Extreme-View Geometry
Ma, W.-C., Yang, A., Wang, S., Urtasun, R., & Torralba, A. B. (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/cvpr52688.2022.01546 · Cited by 33
“Prevalent approaches focus on hand-crafted [7, 13, 50, 55, 65, 77] or learned [20,23,60,81–84] robust visual features that can distinguish one pixel from the others in diverse scenarios.”
BackgroundTree Segmentation and Parameter Measurement from Point Clouds Using Deep and Handcrafted Features
Wang, F., & Bryson, M. (2023) · Remote Sensing · doi:10.3390/rs15041086 · Cited by 30
A Review of Navigation Algorithms for Unmanned Aerial Vehicles Based on Computer Vision Systems
Ali, B., Наилевич, С. Р., & Владимировна, Ц. В. (2022) · Gyroscopy and Navigation · doi:10.1134/s2075108722040022 · Cited by 28
“SURF algorithm was used as a key point detector [48], while the navigation algo-rithm was based on RANSAC [43].”
MethodStructNeRF: Neural Radiance Fields for Indoor Scenes With Structural Hints
Chen, Z., Wang, C., Guo, Y.-C., & Zhang, S. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3305295 · Cited by 32
Patruno, C., Renò, V., Nitti, M., et al. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e26042 · Cited by 23
“The downward-looking vision-based odometer uses the speeded-up robust features (SURF) [21] approach to detect distinctive, invariant, and robust 2D points locally.”
MethodA novel image multitasking enhancement model for underwater crack detection
Cao, W., & Li, J. (2024) · Structural Health Monitoring · doi:10.1177/14759217241228780 · Cited by 30
“44 Therefore, image feature point detection is an important downstream task.”
VL-MFL: UAV Visual Localization Based on Multisource Image Feature Learning
Liu, G., Li, C., Zhang, S., & Yuan, Y. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3383509 · Cited by 34
“Generally, they detect specific keypoints from an image in the first, such as line/edge [15], corner [16], blob [17], [18], [19], and morphological region [20].”
BackgroundŠlapak, E., Pardo, E., Dopiriak, M., Maksymyuk, T., & Gazda, J. (2024) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2024.102810 · Cited by 37
“The growth in image feature extraction capabilities in robotics began with the appearance of the scale-invariant feature transform (SIFT) [2] and speeded up robust features (SURF) [3] approaches.”
BackgroundA REAL-TIME TRACKING SYSTEM COMBINING TEMPLATE-BASED AND FEATURE-BASED APPROACHES
Ladikos, A., Benhimane, S., & Navab, N. (2007) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0002042303250332 · Cited by 30
Altadmri, A., & Ahmed, A. A. (2013) · Multimedia Tools and Applications · doi:10.1007/s11042-013-1363-6 · Cited by 23
License plate localization in complex scenes based on oriented FAST and rotated BRIEF feature
Wang, R., Xia, Y., Wang, G., et al. (2015) · Journal of Electronic Imaging · doi:10.1117/1.jei.24.5.053011 · Cited by 23
RFID tag bearing estimation for mobile robot localization
Milella, A., Paola, D. D., Cicirelli, G., & D’Orazio, T. (2009) · International Conference on Advanced Robotics (ICAR) · Cited by 23
Intelligent Traffic System: Cooperation of MANET and Image Processing
Badura, S., & Lieskovsky, A. (2010) · doi:10.1109/iciic.2010.41 · Cited by 23
Many-to-many feature matching in object recognition: a review of three approaches
Shokoufandeh, A., Keselman, Y., Demirci, M. F., Macrini, D., & Dickinson, S. (2012) · IET Computer Vision · doi:10.1049/iet-cvi.2012.0030 · Cited by 24
Real-World Re-Identification in an Airport Camera Network
Li, Y., Wu, Z., Karanam, S., et al. (2014) · International Conference on Distributed Smart Cameras · doi:10.1145/2659021.2659039 · Cited by 23
“SURF: Speeded up robust features.”
Evaluation of stereo algorithms for 3D object recognition
Tombari, F., & Gori, F. (2011) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2011.6130359 · Cited by 24
“Feature matching is a common approach for object recognition that has been particularly successful in the past years and has been used for both 3D point clouds [12, 28, 19, 20, 35] as well as images [16, 3].”
BackgroundLocal image region description using orthogonal symmetric local ternary pattern
Huang, M., Mu, Z., Zeng, H., & Huang, S. (2014) · Pattern Recognition Letters · doi:10.1016/j.patrec.2014.12.001 · Cited by 23
Online Robust 3D Mapping Using Structure from Motion Cues
Nicosevici, T., & García, R. (2008) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceanskobe.2008.4531022 · Cited by 24
“The features are encoded using either SIFT [9] or SURF descriptors [10].”
BackgroundMethodBlur Invariant Translational Image Registration for $N$-fold Symmetric Blurs
Pedone, M., Flusser, J., & Heikkilä, J. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2268972 · Cited by 23
Avrithis, Y., Tolias, G., & Kalantidis, Y. (2010) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1873951.1873985 · Cited by 22
“We have measured the alignment score of Hessian-affine [17] and SURF [1] features on 50 pairs of images depicting the same scene from different viewpoints.”
MethodHuman Body Parts Tracking Using Torso Tracking: Applications to Activity Recognition
Dargazany, A., & Nicolescu, M. (2012) · International Conference on Information Technology: New Generations · doi:10.1109/itng.2012.132 · Cited by 26
Lee, T., & Soatto, S. (2011) · 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.2011.5995453 · Cited by 22
“similarity [13] or affine [16]), and then “blur” everything else by various binning or averaging mechanisms [2, 13, 19].”
BackgroundExploiting Text-Related Features for Content-based Image Retrieval
Schroth, G., Hilsenbeck, S., Huitl, R., Schweiger, F., & Steinbach, E. G. (2011) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2011.21 · Cited by 22
“To describe the appearance of the characters, upright SURF [10] descriptors are extracted on each of the patches, where the rotation is estimated based on the detected baseline.”
MethodInfluentialIndoor navigation system using image and sensor data processing on a smartphone
Atzori, L., Dessì, T., & Popescu, V. (2012) · International Conference on Optimization of Electrical and Electronic Equipment · doi:10.1109/optim.2012.6231975 · Cited by 23
3-D Head Tracking via Invariant Keypoint Learning
Wang, H., Davoine, F., Lepetit, V., Chaillou, C., & Pan, C. (2012) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2012.2190474 · Cited by 26
Using maximum consistency context for multiple target association in wide area traffic scenes
Shi, X., Li, P., Ling, H., Hu, W., & Blasch, E. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6638042 · Cited by 24
“In particular, Speeded Up Robust Features (SURF) [18] features are used for the efficiency and we then fit affine models for image warping.”
MethodWang, Y., Mei, T., Wang, J., Li, H., & Li, S. (2011) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2072298.2072310 · Cited by 23
“For example, local features such as Scale-Invariant Feature Transform (SIFT) feature [18], MPEG-7 image signature, and Speeded Up Robust Feature (SURF) [2] have been devised to handle luminance and geometry variances.”
MethodA novel system for automatic detection and classification of animal
Matúška, S., Hudec, R., Benčo, M., et al. (2014) · doi:10.1109/elektro.2014.6847875 · Cited by 23
“More information about key point descriptors can be found in [5], [6] for SIFT, [7],[8] for SURF and [9] for Opponent colour descriptors.”
MethodEnhanced local binary covariance matrices (ELBCM) for texture analysis and object tracking
Romero, A., Gouiffès, M., & Lacassagne, L. (2013) · doi:10.1145/2466715.2466733 · Cited by 23
“, Harris [5], SIFT [11], SURF [2]) or over dense grid of points evenly distributed over the image’s region of interest [10] and [3].”
BackgroundCombining SURF-based local and global features for road obstacle recognition in far infrared images
Besbes, B., Apatean, A., Rogozan, A., et al. (2010) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2010.5625285 · Cited by 23
Real-time SIFT-based object recognition system
Wang, Z., Han, X., He, W., Wen, F., & Yuan, K. (2013) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2013.6618111 · Cited by 27
Efficient image retrieval using advanced SURF and DCD on mobile platform
Lee, Y.-H., & Kim, Y. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2129-5 · Cited by 23
Pixel-Wise Spatial Pyramid-Based Hybrid Tracking
Lu, H., Lu, S., Wang, D., Wang, S., & Leung, H. (2012) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2012.2201794 · Cited by 24
PRISM: PRincipled Implicit Shape Model
Lehmann, A., Leibe, B., & Gool, L. V. (2009) · British Machine Vision Conference (BMVC) · doi:10.5244/c.23.64 · Cited by 23
Self-citationVisual textures as realizations of multivariate log-Gaussian Cox processes
Nguyen, H.-G., Fablet, R., & Boucher, J. (2011) · 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.2011.5995340 · Cited by 26
“From these reviews, we investigate five robust detector/descriptor types reported with the best score performance in [1, 3, 16, 24, 28], respectively: FH+Surf, FH+Brief, DoG+Sift, (Hes-Lap)+Daisy and (HarLap)+(Sift-Spin).”
BackgroundMethodInfluentialEfficient on-line data summarization using extremum summaries
Girdhar, Y., & Dudek, G. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6224657 · Cited by 31
3D modelling of trompe l'oeil decorated vaults using dense matching techniques
Chiabrando, F., Lingua, A. M., Noardo, F., & Spano, A. T. (2014) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-ii-5-97-2014 · Cited by 22
“In the keypoint matching step, the nearest neighbour is defined as the keypoint with the minimum Euclidean distance for the invariant descriptor vector (Bay et al., 2006, Bay et al., 2008).”
Large-scale, dense city reconstruction from user-contributed photos
Irschara, A., Zach, C., Klopschitz, M., & Bischof, H. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.07.010 · Cited by 22
Visual terrain classification by flying robots
Khan, Y. N., Masselli, A., & Zell, A. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6224988 · Cited by 25
“Speeded Up Robust Features (SURF) [2] are a modification of the famous SIFT features .”
MethodBelimpasakis, P., & Walsh, R. (2011) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2011.5735494 · Cited by 23
“A Robust image detection and description techniques, such as the non-proprietary SURF (Speeded Up Robust Features) [2], which is used to identify the object.”
MethodReal-time adaptive blur for reducing eye strain in stereoscopic displays
Leroy, L., Fuchs, P., & Moreau, G. (2012) · ACM Transactions on Applied Perception · doi:10.1145/2207216.2207220 · Cited by 27
Görgü, L., Campbell, A. G., McCusker, K., Dragone, M., O’Grady, M. J., O'Connor, N. E., & O’Hare, G. M. P. (2010) · International Conference on Advances in Mobile Computing and Multimedia (MoMM) · doi:10.1145/1971519.1971550 · Cited by 23
“To generate the augmented photos, the Speeded Up Robust Features (SURF) [9] algorithm is utilised, features can be tracked from a template image onto an image taken by the phone.”
MethodInfluentialOn the Affinity between 3D Detectors and Descriptors
Salti, S., Petrelli, A., Tombari, F., & Stefano, L. D. (2012) · International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission · doi:10.1109/3dimpvt.2012.10 · Cited by 25
“DoG and SIFT [1], FastHessian and SURF [2].”
MethodInfluentialHand Gesture Recognition Using Fast Multi-scale Analysis
Fang, Y., Cheng, J., Wang, K., et al. (2007) · International Conference on Image and Graphics · doi:10.1109/icig.2007.52 · Cited by 23
Robot planning with a semantic map
Rogers, J. G., & Christensen, H. I. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630879 · Cited by 23
“The Examine action is selected by the planner to look at a previously segmented or categorized object and try to identify it directly with the SURF-based recognition module.”
MethodS-AKAZE: An effective point-based method for image matching
Liu, Y., Lan, C., Li, C., Mo, F., & Wang, H. (2016) · Optik · doi:10.1016/j.ijleo.2016.03.072 · Cited by 23
Visual EKF-SLAM from Heterogeneous Landmarks
Esparza-Jiménez, J. O., Devy, M., & Gordillo, J. L. (2016) · Sensors · doi:10.3390/s16040489 · Cited by 24
Rotation and scale invariant upsampled log-polar fourier descriptor for copy-move forgery detection
Park, C., Kim, C., Lee, J., & Kwon, G. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3575-z · Cited by 24
Real‐time transmission tower detection from video based on a feature descriptor
Cerón, A., Mondragon, I. F., & Prieto, F. (2016) · IET Computer Vision · doi:10.1049/iet-cvi.2015.0477 · Cited by 22
A person re-identification algorithm based on pyramid color topology feature
Hu, H., Fang, W., Zeng, G., et al. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-4188-2 · Cited by 23
Indoor Place Recognition System for Localization of Mobile Robots
Sahdev, R., & Tsotsos, J. K. (2016) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2016.38 · Cited by 25
“Other local features based approaches include the works of Bay et al. [26] and Dallal and Triggs [27].”
MethodPoor textural image tie point matching via graph theory
Xiuxiao Yuan, A., Chen, S., Yuan, W., & Cai, Y. (2017) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.04.015 · Cited by 27
Vehicle trajectory clustering based on 3D information via a coarse-to-fine strategy
Song, H., Wang, X., Hua, C., Wang, W., Guan, Q., & Zhang, Z. (2017) · Soft Computing · doi:10.1007/s00500-017-2831-0 · Cited by 23
“Figure 2 shows the results of ORB algorithm which is applied in different traffic scenes with differently viewing angles, and Table 1 presents the measured running time compared with other feature descriptors, such as SIFT (Lowe 2004), SURF (Bay et al. 2006), MSER (Forssén and Lowe 2007), BRISK (Leutenegger et al. 2011…”
MethodToews, M., & Wells, W. M. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2750978 · Cited by 23
FEATURE MATCHING OF HISTORICAL IMAGES BASED ON GEOMETRY OF QUADRILATERALS
Maiwald, F., Schneider, D., Henze, F., et al. (2018) · 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-2-643-2018 · Cited by 23
“Using conventional gradient-based descriptors like SIFT (Lowe, 2004), SURF (Bay et al., 2006) and ORB (Rublee et al.”
MethodSentas, A., Tashiev, I., Küçükayvaz, F., Kul, S., Eken, S., Sayar, A., & Becerikli, Y. (2018) · International Conference on Emerging Intelligent Data and Web Technologies · doi:10.1007/978-3-319-75928-9_86 · Cited by 12
Data Augmentation on Synthetic Images for Transfer Learning using Deep CNNs
Talukdar, J., Biswas, A., & Gupta, S. (2018) · International Conference on Signal Processing and Integrated Networks (SPIN) · doi:10.1109/spin.2018.8474209 · Cited by 22
“[2] H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded up robust features,” in Lecture Notes in Computer Science, 2006, vol. 3951 LNCS, pp. 404–417.”
MethodEfficient parallel optimizations of a high-performance SIFT on GPUs
Li, Z., Jia, H., Zhang, Y., Liu, S., Li, S., Wang, X., & Zhang, H. (2018) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2018.10.012 · Cited by 25
An Intelligent Object Detection and Measurement System Based on Trinocular Vision
Ma, Y., Li, Q.-W., Xing, J.-Y., Huo, G.-Y., & Liu, Y. (2020) · IEEE transactions on circuits and systems for video technology (Print) · doi:10.1109/tcsvt.2019.2897482 · Cited by 22
“To provide high accuracy of the object detection, the feature point matching strategy in the Speed-up Robust Features (SURF) algorithm [68] was improved in this section.”
MethodMethod for 3-D Scene Reconstruction Using Fused LiDAR and Imagery From a Texel Camera
Bybee, T. C., & Budge, S. E. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2923551 · Cited by 24
A generic codebook based approach for gait recognition
Khan, M. H., Farid, M. S., & Grzegorzek, M. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08007-z · Cited by 22
“Numerous feature computation techniques have been proposed in recent years and have been successfully exploited in various computer vision problems; SIFT (Scale Invariant Feature Transform) [49], SURF (Speeded-Up Robust Feature) [5], HOG (Histogram of Oriented Gradient) [18], HOF (Histogram of Optical Flow) [44], MBH…”
MethodA Review on SIFT and SURF for Underwater Image Feature Detection and Matching
Ansari, S. (2019) · International Conference on Electrical, Computer and Communication Technologies (ICECCT) · doi:10.1109/icecct.2019.8869489 · Cited by 23
“It is based on the Hessian matrix but uses a very basic approximation, just as DoG [1, 2, 11].”
MethodImage classification using SLIC superpixel and FAAGKFCM image segmentation
Singh, N. K., Singh, N. J., & Kumar, W. K. (2019) · IET Image Processing · doi:10.1049/iet-ipr.2019.0255 · Cited by 24
“Furthermore, other factors are needed to be dealt, such as the change in illumination, viewpoint, scale, and rotation [5, 6].”
BackgroundZhou, Y., & Maskell, S. R. (2019) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion43075.2019.9011271 · Cited by 23
“The feature points can be generated by, for example, Harris corner or SIFT-like [19] detectors.”
MethodBinol, H., Moberly, A. C., Niazi, M. K. K., Essig, G., Shah, J., Elmaraghy, C., Teknos, T. N., Taj‐Schaal, N., Yu, L., & Gürcan, M. N. (2020) · Applied Sciences · doi:10.3390/app10175894 · Cited by 27
Synthesized View Quality Assessment Using Feature Matching and Superpixel Difference
Mahmoudpour, S., & Schelkens, P. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.3024109 · Cited by 18
“We used the Speed Up Robust Features (SURF) [17] for feature point detection and feature matching.”
MethodPyramid regional graph representation learning for content-based video retrieval
Zhao, G., Zhang, M., Li, Y., Liu, J., Zhang, B., & Wen, J.-R. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2020.102488 · Cited by 27
Scale Normalized Image Pyramids with AutoFocus for Object Detection
Singh, B., Najibi, M., Sharma, A., & Davis, L. S. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3058945 · Cited by 36
Comparison of image matching techniques
(2016) · International Journal of Latest Trends in Engineering and Technology · doi:10.21172/1.73.552 · Cited by 23
Local Keypoints and Global Affine Geometry: Triangles and Ellipses for Image Fragment Matching
Paradowski, M., & Sluzek, A. S. (2011) · Studies in computational intelligence · doi:10.1007/978-3-642-17934-1_9 · Cited by 23
Accurate Registration Using Adaptive Block Processing for Multispectral Images
Lee, I.-H., & Choi, T. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2248594 · Cited by 23
“The Hessian threshold was also modified to 500; more details of the parameters can be found in [36] and [37].”
BackgroundCamera pose estimation using Visual Servoing for aerial video change detection
Bourdis, N., Marraud, D., & Sahbi, H. (2012) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2012.6350676 · Cited by 23
“This processing time is dominated by the registration step, which consists of extracting SURF features [9] from two given images and computing a homography using RANSAC.”
MethodA novel clique formulation for the visual feature matching problem
Segundo, P. S., & Artieda, J. (2015) · Applied Intelligence · doi:10.1007/s10489-015-0646-1 · Cited by 25
“Thus, given a set of interest points and descriptors computed locally via state of the art algorithms such as SIFT (Scale Invariant Feature Transform) [27] or SURF (Speeded Up Robust Features) [32], robust algorithms are required which filter out as many incorrect associations as possible.”
MethodFast object detection for robots in a cluttered indoor environment using integral 3D feature table
Kanezaki, A., Suzuki, T., Harada, T., et al. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980129 · Cited by 23
DARTs: Efficient scale-space extraction of DAISY keypoints
Marimón, D., Bonnin, A., Adamek, T., & Gimeno, R. (2010) · 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.2010.5539936 · Cited by 24
Object recognition combining vision and touch
Corradi, T., Hall, P. M., & Iravani, P. (2017) · Robotics and Biomimetics · doi:10.1186/s40638-017-0058-2 · Cited by 25
“The visual model is a simple bag-of-words model, using SURF [5] as features.”
MethodTorki, M., Hussein, M. E., Elsallamy, A., et al. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.3519 · Cited by 23
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.