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 1,501–1,600 of 14,752
An Efficient Near-Duplicate Video Shot Detection Method Using Shot-Based Interest Points
Zhou, X., Zhou, X., Chen, L., Bouguettaya, A., Xiao, N., & Taylor, J. (2009) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2009.2021794 · Cited by 51
A General Dense Image Matching Framework Combining Direct and Feature-Based Costs
Braux-Zin, J., Dupont, R., & Bartoli, A. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.30 · Cited by 52
“Most point descriptors such as SIFT [18] and SURF [3] use the concept of histograms of gradient.”
BackgroundMethodInfluentialPose Estimation for Robot Manipulators via Keypoint Optimization and Sim-to-Real Transfer
Lu, J., Richter, F., & Yip, M. C. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3151981 · Cited by 64
Entropic image thresholding based on GLGM histogram
Xiao, Y., Cao, Z., & Yuan, J. (2014) · Pattern Recognition Letters · doi:10.1016/j.patrec.2013.12.017 · Cited by 48
The latent words language model
Deschacht, K., Belder, J. D., & Moens, M. (2012) · Computer Speech & Language · doi:10.1016/j.csl.2012.04.001 · Cited by 53
Dynamic surface matching by geodesic mapping for 3D animation transfer
Tung, T., & Matsuyama, T. (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.2010.5539806 · Cited by 50
Bruno, F., Gallo, A., Filippo, F. D., et al. (2013) · Digital Heritage International Congress · doi:10.1109/digitalheritage.2013.6743719 · Cited by 47
Local Polar DCT Features for Image Description
Song, T., & Li, H. (2012) · IEEE Signal Processing Letters · doi:10.1109/lsp.2012.2229273 · Cited by 48
“Representative work tackling this problem is SURF [18].”
BackgroundToussaint, M., Plath, N., Lang, T., & Jetchev, N. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509831 · Cited by 52
“The identification and localization of objects is based on SURF interest points and descriptors [29] using the OpenSURF library [30].”
MethodKeyframe extraction in endoscopic video
Schoeffmann, K., Fabro, M. D., Szkaliczki, T., Böszörményi, L., & Keckstein, J. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2224-7 · Cited by 48
Hasan, M. M., Pickering, M. R., & Jia, X. (2012) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2012.2187456 · Cited by 47
Finding objects for blind people based on SURF features
Chincha, R., & Tian, Y. (2011) · IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW) · doi:10.1109/bibmw.2011.6112423 · Cited by 48
Streaming mobile augmented reality on mobile phones
Chen, D. M., Tsai, S. S., Vedantham, R., et al. (2009) · IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2009.5336472 · Cited by 47
Ozturk, O., Yamasaki, T., & Aizawa, K. (2009) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2009.5457590 · Cited by 49
“In our work, SIFT features were chosen to be utilized in the algorithm after several experiments with Kanade-LucasThomasi(KLT) features or recently popular SURF[6] features.”
MethodA robust, multi-hypothesis approach to matching occupancy grid maps
Blanco, J., González-Jiménez, J., & Fernández‐Madrigal, J. (2013) · Robotica · doi:10.1017/s0263574712000732 · Cited by 48
“[1].”
Good match exploration using triangle constraint
Guo, X., & Cao, X. (2011) · Pattern Recognition Letters · doi:10.1016/j.patrec.2011.08.021 · Cited by 47
“…around ll rights reserved. x: +86 22 27406538. every interest point for point-based schemes or every interest region for region-based is represented by a feature descriptor based on the concentrated information (for instance, gradient (Lowe, 2004) and Haar-Wavelet response (Bay et al., 2006)).”
BackgroundMethodInfluentialFast Image Classification for Monument Recognition
Amato, G. M., Falchi, F., & Gennaro, C. (2015) · Journal on Computing and Cultural Heritage · doi:10.1145/2724727 · Cited by 54
Urban, S., & Weinmann, M. (2015) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-ii-3-w5-121-2015 · Cited by 46
Minimally disruptive needle insertion: a biologically inspired solution
Leibinger, A., Oldfield, M. J., & y Baena, F. R. (2016) · Interface Focus · doi:10.1098/rsfs.2015.0107 · Cited by 48
Cross-Spectral Local Descriptors via Quadruplet Network
Aguilera, C., Aguilera, C. A., Sappa, A. D., et al. (2017) · Sensors · doi:10.3390/s17040873 · Cited by 47
Yang, H., Chen, Q., Riaz, M., Luan, Z., Tang, L., & Mars, J. (2017) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1145/3079856.3080224 · Cited by 48
“For instance, as shown in Figure 1 a query to an IPA application flows through Automatic Speech Recognition (ASR) [23, 46], Natural Language Processing (NLP) [11], Image Matching (IMM) [7] and Question-Answering (QA) [50] stages to generate an intelligent response.”
BackgroundA Vision-Based System for In-Bed Posture Tracking
Liu, S., & Ostadabbas, S. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.163 · Cited by 56
“There are some feature descriptors which meet this requirement such as multi-scale oriented patches (MOPS) [7], scale invariant feature transform (SIFT) [18], and speeded-up robust features (SURF) [3].”
BackgroundColor Homography: Theory and Applications
Finlayson, G. D., Gong, H., & Fisher, R. B. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2760833 · Cited by 54
“Among other popular feature point matching algorithms, such as SIFT [20], MSER [49], SURF [50], and Harris corner feature [51], we”
MethodCARS: Collaborative Augmented Reality for Socialization
Zhang, W., Han, B., Hui, P., Gopalakrishnan, V., Zavesky, E., & Qian, F. (2018) · IEEE Workshop on Mobile Computing Systems and Applications (WMCSA) · doi:10.1145/3177102.3177107 · Cited by 59
“SIFT [18] and SURF [4] have been used extensively in cloud-based AR (e.g., Overlay [11] uses SURF and VisualPrint [12] uses SIFT).”
MethodInfluentialLu, S., Liu, Z., & Shen, Y. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2790498 · Cited by 50
“We compare our approach with other classical methods, which include the original SIFT [22], edge-SIFT [24], and SURF [44].”
Fusion of Domain-Specific and Trainable Features for Gender Recognition From Face Images
Azzopardi, G., Greco, A., Saggese, A., & Vento, M. (2018) · IEEE Access · doi:10.1109/access.2018.2823378 · Cited by 47
A FAST-BRISK Feature Detector with Depth Information
Liu, Y., Zhang, H., Guo, H., & Xiong, N. N. (2018) · Sensors · doi:10.3390/s18113908 · Cited by 51
Esmaeilpour, M., Cardinal, P., & Koerich, A. L. (2019) · Applied Soft Computing · doi:10.1016/j.asoc.2019.105912 · Cited by 51
“For extracting feature from the spectrograms, the speeded up robust feature (SURF [62]) is implemented, which is the modified version of the scale invariant feature transform (SIFT) [63] by fast approximation of Hessian matrix (for encoding principal curvatures at each point of interest) and…”
MethodHomography From Two Orientation- and Scale-Covariant Features
Baráth, D., & Kúkelová, Z. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00118 · Cited by 53
FrameNet: Learning Local Canonical Frames of 3D Surfaces From a Single RGB Image
Huang, J., Zhou, Y., Funkhouser, T. A., & Guibas, L. J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00873 · Cited by 62
Aliaga, I. J., Vera, V., Rodríguez, M. V., Barbero, Á. E. G., Pedrera-Cana, M., & Pájares, G. (2020) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2020.101816 · Cited by 61
Traffic-Aware Multi-Camera Tracking of Vehicles Based on ReID and Camera Link Model
Hsu, H.-M., Wang, Y., & Hwang, J. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413863 · Cited by 51
“One is traditional handcrafted methods, such as SURF [1] and ORB [26].”
MethodA comprehensive review of vehicle detection using computer vision
Abbas, A. F., Sheikh, U. U., AL-Dhief, F. T., & Mohd, M. N. H. (2021) · TELKOMNIKA (Telecommunication Computing Electronics and Control) · doi:10.12928/telkomnika.v19i3.12880 · Cited by 48
Unaligned Hyperspectral Image Fusion via Registration and Interpolation Modeling
Ying, J., Shen, H., & Cao, S.-Y. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3081136 · Cited by 49
Quaternionic Weber Local Descriptor of Color Images
Lan, R., Zhou, Y., & Tang, Y. Y. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2492839 · Cited by 46
A Review of Object Detection Techniques
Li, K., & Cao, L. (2020) · International Conference on Electromechanical Control Technology and Transportation (ICECTT) · doi:10.1109/icectt50890.2020.00091 · Cited by 64
“It first came out of Herbert Bay et al. [8] in 2006.”
BackgroundMethodAttention-SLAM: A Visual Monocular SLAM Learning From Human Gaze
Li, J., Pei, L., Zou, D., Xia, S., Wu, Q., Li, T., Sun, Z., & Yu, W. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3038432 · Cited by 49
A Review of Vision-Laser-Based Civil Infrastructure Inspection and Monitoring
Zhou, H., Xu, C., Tang, X., Wang, S., & Zhang, Z. (2022) · Sensors · doi:10.3390/s22155882 · Cited by 56
TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation
Chen, H., Manhardt, F., Navab, N., & Busam, B. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00469 · Cited by 58
Hand-Crafted Features or Machine Learnt Features? Together They Improve RGB-D Object Recognition
Jin, L., Gao, S., Li, Z., & Tang, J. (2014) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2014.56 · Cited by 45
“In feature extraction module, the local features are used to characterize the local regions, and commonly used features include SIFT [28], HOG [9], SURF [1], etc.”
MethodRGBD object recognition and visual texture classification for indoor semantic mapping
Filliat, D., Battesti, E., Bazeille, S., Duceux, G., Gepperth, A., Harrath, L., Jebari, I., Pereira, R., Tapus, A., Meyer, C., et al. (2012) · IEEE International Conference on Technologies for Practical Robot Applications · doi:10.1109/tepra.2012.6215666 · Cited by 48
Retinal Image Quality Analysis for Automatic Diabetic Retinopathy Detection
Pires, R., Jelinek, H. F., Wainer, J., & Rocha, A. D. R. (2012) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2012.39 · Cited by 46
“To detect the points, we use the Speeded Up Robust Features (SURF) [22] as it is a good feature detector with reasonable speed.”
MethodSurvey on modeling and indexing events in multimedia
Scherp, A., & Mezaris, V. (2013) · Multimedia Tools and Applications · doi:10.1007/s11042-013-1427-7 · Cited by 48
“…texture features [46], local neighborhood features expressed with the use of the scale-invariant feature transform (SIFT) [44] or similar local descriptors, e.g., speeded-up robust features (SURF) [9], color-variants of SIFT [80]), mel-frequency cepstral coefficients (MFCC) for audio, and others.”
MethodAirplane detection based on rotation invariant and sparse coding in remote sensing images
Liu, L., & Shi, Z. (2014) · Optik · doi:10.1016/j.ijleo.2014.06.062 · Cited by 47
“Typical feature descriptors, such as SIFT [7] and speeded up robust feature (SURF) [15], assign an orientation to interest points before extracting descriptor.”
MethodSkyStitch: A Cooperative Multi-UAV-based Real-time Video Surveillance System with Stitching
Meng, X., Wang, W., & Leong, B. (2015) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2733373.2806225 · Cited by 59
“We adopted the latest ORB method [25] for feature extraction, as it has been shown to achieve comparable accuracy to other methods such as SIFT [23] and SURF [11] but at a much lower computational cost.”
MethodRobust face recognition after plastic surgery using region-based approaches
Marsico, M. D., Nappi, M., Riccio, D., & Wechsler, H. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.10.004 · Cited by 47
Compression of image patches for local feature extraction
Makar, M. A., Chang, C.-L., Chen, D. M., Tsai, S. S., & Girod, B. (2009) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2009.4959710 · Cited by 44
Bootstrapping Boosted Random Ferns for discriminative and efficient object classification
Villamizar, M., Andrade‐Cetto, J., Sanfeliu, A., & Moreno-Noguer, F. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.03.025 · Cited by 50
6-DoF model-based tracking of arbitrarily shaped 3D objects
Azad, P., Münch, D., Asfour, T., et al. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979950 · Cited by 46
Textureless Macula Swelling Detection With Multiple Retinal Fundus Images
Giancardo, L., Mériaudeau, F., Karnowski, T. P., Tobin, K. W., Grisan, E., Favaro, P., Ruggeri, A., & Chaum, E. (2010) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2010.2095852 · Cited by 46
Stückler, J., & Behnke, S. (2009) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/ichr.2009.5379529 · Cited by 47
Beyond Bits: Reconstructing Images from Local Binary Descriptors
d'Angelo, E., Alahi, A., & Vandergheynst, P. (2012) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 51
Action recognition based on overcomplete independent components analysis
Zhang, S., Yao, H., Sun, X., Wang, K., Zhang, J., Lu, X., & Zhang, Y. (2014) · Information Sciences · doi:10.1016/j.ins.2013.12.052 · Cited by 44
“[53] extends the SURF descriptor [4] to extract features from a video.”
BackgroundAutomated detection in complex objects using a tracking algorithm in multiple X-ray views
Mery, D. (2011) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2011.5981715 · Cited by 48
“…example, methods based on saliency maps [20], Haar basis features [30], histogram of oriented gradients [4], corner detectors [9], SURF descriptors [2], Maximally Stable regions [14], Local Binary Patterns [21], etc. Description [step 2b]: Each segmented potential region r is characterized using a…”
MethodVisual indoor positioning with a single camera using PnP
Deretey, E., Ahmed, M. T., Marshall, J. A., & Greenspan, M. (2015) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2015.7346756 · Cited by 57
“First 2D features in the query image are computed using OpenCV’s [25] SURF detector and extractor, which was selected for its speed and accuracy.”
MethodInfluentialMulti-pose facial expression recognition based on SURF boosting
Rao, Q., Qu, X. H., Mao, Q., & Zhan, Y. (2015) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii.2015.7344635 · Cited by 52
“2) Feature Extraction and Representation: SURF is a scale and rotation invariant detector and descriptor [21].”
MethodAutomatic detection of referral patients due to retinal pathologies through data mining
Quellec, G., Lamard, M., Erginay, A., Chabouis, A., Massin, P., Cochener, B., & Cazuguel, G. (2016) · Medical Image Anal. · doi:10.1016/j.media.2015.12.006 · Cited by 49
3D Mapping for Visualization of Rigid Structures: A Review and Comparative Study
Santoso, F., Garratt, M., Pickering, M. R., & Asikuzzaman, M. (2015) · IEEE Sensors Journal · doi:10.1109/jsen.2015.2498940 · Cited by 50
Spatial-Hessian-Feature-Guided Variational Model for Pan-Sharpening
Liu, P., Xiao, L., Zhang, J., et al. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2015.2497966 · Cited by 46
“1(a) detected by the fast Hessian detector [41].”
BackgroundMethodInfluentialK Nearest Neighbour Joins for Big Data on MapReduce: A Theoretical and Experimental Analysis
Song, G., Rochas, J., Beze, L. E., et al. (2016) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2016.2562627 · Cited by 46
Local structure learning in high resolution remote sensing image retrieval
Du, Z., Li, X., & Lu, X. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.05.061 · Cited by 46
“As there is a mean average precision (MAP) gap [38] while using the SIFT300 features in image retrieval, to achieve a better performance, in the future work, the low-level features can be acquired by descriptor learning or auto-encoder instead of directly using the SIFT or SURF.”
Detection of Copy-Move Forgery in Images Using Segmentation and SURF
Manu, V. T., & Mehtre, B. M. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-28658-7_55 · Cited by 50
Evaluating features and classifiers for road weather condition analysis
Qian, Y., Almazán, E. J., & Elder, J. H. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7533192 · Cited by 55
“Our algorithm was compared with dense SURF feature [12] and different pooling methods (Improved Fisher Vector[13] and Bag of Visual Words[14], Textons[10]) to measure the effectiveness of algorithm.”
MethodHybrid soft computing approaches to content based video retrieval: A brief review
Bhaumik, H., Bhattacharyya, S., Nath, M. D., & Chakraborty, S. (2016) · Applied Soft Computing · doi:10.1016/j.asoc.2016.03.022 · Cited by 48
Bochinski, E., Eiselein, V., & Sikora, T. (2016) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2016.7738056 · Cited by 58
“The basic principle is to extract image features like HOG, SIFT, SURF [6, 30, 1] which are useful for a generic description of instances of specific object classes.”
BackgroundA Vegetable Category Recognition System Using Deep Neural Network
Sakai, Y., Oda, T., Ikeda, M., & Barolli, L. (2016) · International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS) · doi:10.1109/imis.2016.84 · Cited by 50
“The system was based on local feature extraction methods, such as Scale Invariant Feature Transform (SIFT) [18]–[20] and Speed Up Robust Features (SURF) [21], [22] methods for extracting the feature points.”
MethodAction recognition based on hierarchical dynamic Bayesian network
Xiao, Q., & Song, R. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4614-0 · Cited by 46
“The local feature always describes patches independently, and the patches are combined together to build space–time model [17], such as HOG [4] and SURF [1].”
MethodMultiscale gigapixel video: A cross resolution image matching and warping approach
Yuan, X., Fang, L., Dai, Q., Brady, D. J., & Liu, Y. (2017) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccphot.2017.7951481 · Cited by 49
“(e) SIFT [26] (f) SURF [2] (g) DAISY [37] (h) LATCH [21]”
MethodInfluentialProgressive Large Scale-Invariant Image Matching in Scale Space
Zhou, L., Zhu, S., Shen, T., Wang, J., Fang, T., & Quan, L. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.259 · Cited by 44
“A number of extensions, including SURF [3] for speed, ASIFT [28] for full affine invariance, are proposed.”
BackgroundMethodInfluentialA comprehensive review on iris image-based biometric system
Winston, J. J., & Hemanth, D. J. (2018) · Soft Computing · doi:10.1007/s00500-018-3497-y · Cited by 55
Joint Feature and Texture Coding: Toward Smart Video Representation via Front-End Intelligence
Ma, S., Zhang, X., Wang, S., Zhang, X., Jia, C., & Wang, S. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2873102 · Cited by 52
Distinctive image features from illumination and scale invariant keypoints
Tang, G., Liu, Z., & Xiong, J. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7566-8 · Cited by 52
“In order to evaluate the matching score of iSIFT, we compared the proposed iSIFT with SIFT [23], SURF [4], FAST [34], MSER [29] and ORB [36] on the standard DTU datasets [1] and on the captured images by ourselves.”
BackgroundMethodInfluentialDetection of copy-move forgery using AKAZE and SIFT keypoint extraction
Prakash, C. S., Panzade, P. P., Om, H., & Maheshkar, S. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7629-x · Cited by 49
How Deep Features Have Improved Event Recognition in Multimedia: A Survey
Ahmad, K., & Conci, N. (2019) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3306240 · Cited by 51
“The initial efforts in this regard mainly focus on handcrafted static visual features, such as SIFT [96] and SURF [21], spatio-temporal features, such as Motion SIFT (MoSIFT) [34], and dense trajectories [143, 144].”
BackgroundMulti-image Semantic Matching by Mining Consistent Features
Wang, Q., Zhou, X., & Daniilidis, K. (2018) · 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.2018.00078 · Cited by 45
Zhang, H., Tang, Z., Xie, Y., Gao, X., Chen, Q., & Gui, W. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2960051 · Cited by 45
“, SURF [25]) for image registration.”
Roggi, G., Niccolai, A., Grimaccia, F., & Lovera, M. (2020) · Energies · doi:10.3390/en13040838 · Cited by 48
A Novel Depth and Color Feature Fusion Framework for 6D Object Pose Estimation
Zhou, G., Yan, Y., Wang, D., & Chen, Q. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3001533 · Cited by 48
Plikynas, D., Žvironas, A., Gudauskis, M., Budrionis, A., Daniušis, P., & Sliesoraitytė, I. (2020) · IEEE Instrumentation & Measurement Magazine · doi:10.1109/mim.2020.9126068 · Cited by 51
XGBoost: 2D-Object Recognition Using Shape Descriptors and Extreme Gradient Boosting Classifier
Monika, M., Kumar, M., & Kumar, M. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-6876-3_16 · Cited by 46
Detection of threat objects in baggage inspection with X-ray images using deep learning
Saavedra, D., Banerjee, S., & Mery, D. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05521-2 · Cited by 56
VNIR–NIR hyperspectral imaging fusion targeting intraoperative brain cancer detection
León, R., Fabelo, H. A., Ortega, S., Piñeiro, J. F., Szołna, A., Hernandez, M., Espino, C., Jiménez-O’Shanahan, A., Carrera, D., Bisshopp, S., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-99220-0 · Cited by 49
Towards interactive, intelligent, and integrated multimedia analytics
Zahálka, J., & Worring, M. (2014) · IEEE Conference on Visual Analytics Science and Technology (VAST) · doi:10.1109/vast.2014.7042476 · Cited by 57
Visual Model Feature Tracking For UAV Control
Mondragon, I. F., Campoy, P., Correa, J. F., & Mejías, L. (2007) · IEEE International Symposium on Intelligent Signal Processing, · doi:10.1109/wisp.2007.4447629 · Cited by 46
Image Retrieval based on Bag-of-Words modelPreprint
Liu, J. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1304.5168 · Cited by 56
HFF6D: Hierarchical Feature Fusion Network for Robust 6D Object Pose Tracking
Liu, J., Sun, W., Liu, C., Zhang, X., Fan, S., & Wu, W. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3181597 · Cited by 56
Image Stitching Techniques Applied to Plane or 3-D Models: A Review
Fu, M., Liang, H. Z., Zhu, C., Dong, Z., Sun, R., Yue, Y., & Yang, Y. M. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3251661 · Cited by 54
“Common point feature descriptors include SIFT [4], SURF [35], ORB [36], AKAZE [37], and so on, and line feature descriptors include LSD [38] and so on.”
BackgroundMethodYang, L., & Cai, H. (2023) · Advanced Engineering Informatics · doi:10.1016/j.aei.2023.102313 · Cited by 59
Robust semi-blind video watermarking based on frame-patch matching
Thanh, T. M., Hiệp, P. T., Tam, T. M., et al. (2014) · AEU - International Journal of Electronics and Communications · doi:10.1016/j.aeue.2014.05.004 · Cited by 44
Cube2Video: Navigate Between Cubic Panoramas in Real-Time
Zhao, Q., Wan, L., Feng, W., et al. (2013) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2013.2280249 · Cited by 44
A Fast and Accurate Video Semantic-Indexing System Using Fast MAP Adaptation and GMM Supervectors
Inoue, N., & Shinoda, K. (2012) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2012.2191395 · Cited by 50
Feature Point Descriptors: Infrared and Visible Spectra
Ricaurte, P., Chilán, C., Aguilera-Carrasco, C., Vintimilla, B. X., & Sappa, A. D. (2014) · Sensors · doi:10.3390/s140203690 · Cited by 54
Fast Traffic Sign Recognition with a Rotation Invariant Binary Pattern Based Feature
Yin, S., Ouyang, P., Liu, L., et al. (2015) · Sensors · doi:10.3390/s150102161 · Cited by 45
A Branch-and-Bound Approach to Correspondence and Grouping Problems
Bazin, J., Li, H., Kweon, I., Demonceaux, C., Vasseur, P., & Ikeuchi, K. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.264 · Cited by 44
Evolutionary learning of local descriptor operators for object recognition
Pérez, C. B., & Gustavo Olague, A. (2009) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1569901.1570043 · Cited by 45
“Bay et al. [2] also designed a descriptor called SURF, which is a SIFT version specially designed for real time applications.”
BackgroundEnhanced disparity estimation in stereo images
Kordelas, G., Alexiadis, D. S., Daras, P., et al. (2015) · Image and Vision Computing · doi:10.1016/j.imavis.2014.12.001 · Cited by 45
Fusing Multiple Features for Depth-Based Action Recognition
Zhu, Y. M., Chen, W., & Guo, G. (2015) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2629483 · Cited by 43
“2008] is an extension of the SURF [Bay et al. 2006] for action representation.”
BackgroundRed Blood Cell Tracking Using Optical Flow Methods
Guo, D., van de Ven, A. L., & Zhou, X. (2013) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2013.2281915 · Cited by 52
Stop helping me - I'm bored!: why assembly assistance needs to be adaptive
Funk, M., Dingler, T., Cooper, J., & Schmidt, A. (2015) · Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2015 ACM International Symposium on Wearable Computers - UbiComp '15 · doi:10.1145/2800835.2807942 · Cited by 45
GeoCDX: An Automated Change Detection and Exploitation System for High-Resolution Satellite Imagery
Klaric, M. N., Claywell, B. C., Scott, G. J., et al. (2013) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2013.2243840 · Cited by 45
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.