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 601–700 of 14,752
Chen, Q., Yang, H., Mars, J., & Tang, L. (2016) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/2872362.2872368 · Cited by 120
Retrieval and classification of food images
Farinella, G. M., Allegra, D., Moltisanti, M., Stanco, F., & Battiato, S. (2016) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2016.07.006 · Cited by 122
A machine learning based intelligent vision system for autonomous object detection and recognition
Ramík, D. M., Sabourin, C., Moreno, R. A., & Madani, K. (2013) · Applied Intelligence · doi:10.1007/s10489-013-0461-5 · Cited by 119
“Concerning the implementation, two well known machine-learning based fast recognition methods have been tested: Speededup Robust Features (SURF) introduced in [6] and the ViolaJones object detection framework, presented in [34].”
MethodObject recognition using local invariant features for robotic applications: A survey
Loncomilla, P., Ruíz-del-Solar, J., & Martínez, L. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.05.021 · Cited by 121
Mango Fruit Load Estimation Using a Video Based MangoYOLO—Kalman Filter—Hungarian Algorithm Method
Wang, Z., Walsh, K. B., & Koirala, A. (2019) · Sensors · doi:10.3390/s19122742 · Cited by 120
Jana, D., & Nagarajaiah, S. (2021) · Structural Control and Health Monitoring · doi:10.1002/stc.2713 · Cited by 118
“…of binary strings that compares the image intensities over retinal sampling pattern, and it is found to be more robust than other feature descriptors like Scale-Invariant Feature Transform (SIFT), 58 Speeded Up Robust Features (SURF), 59 or Binary Robust Invariant Scalable Keypoints (BRISK).”
BackgroundLearning and Calibrating Per-Location Classifiers for Visual Place Recognition
Gronát, P., Obozinski, G., Šivic, J., & Pajdla, T. (2013) · 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.2013.122 · Cited by 111
Information from imagery: ISPRS scientific vision and research agenda
Chen, J., Dowman, I. J., Li, S., Li, Z., Madden, M., Mills, J. P., Paparoditis, N., Rottensteiner, F., Sester, M., Toth, C. K., et al. (2015) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2015.09.008 · Cited by 130
An architecture of optimised SIFT feature detection for an FPGA implementation of an image matcher
Yao, L., Feng, H., Zhu, Y., Jiang, Z., Zhao, D., & Feng, W. (2009) · International Conference on Field-Programmable Technology (FPT) · doi:10.1109/fpt.2009.5377651 · Cited by 111
“…of the falsely matched points to the sum of the number of the correctly matched points and the number of the falsely matched points: For the purpose of comparison, the corresponding software models of the original SIFT [4], SURF [5] and polar sampling descriptor [9] have also been implemented.”
BackgroundMethodResultInfluentialKashif, M. I., Deserno, T. M., Haak, D., & Jonas, S. (2015) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2015.11.006 · Cited by 111
Image Registration-Based Bolt Loosening Detection of Steel Joints
Kong, X., & Li, J. (2018) · Sensors · doi:10.3390/s18041000 · Cited by 111
Valero, E., Bosché, F., & Forster, A. M. (2018) · Automation in Construction · doi:10.1016/j.autcon.2018.08.018 · Cited by 112
Local descriptor-based multi-prototype network for few-shot Learning
Huang, H., Wu, Z., Li, W., Huo, J., & Gao, Y. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107935 · Cited by 122
Object Detection in Traffic Videos: A Survey
Ghahremannezhad, H., Shi, H., & Liu, C. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3258683 · Cited by 141
“…as Histogram of Oriented Gradients (HOG) [44], local binary patterns (LBP) [50], scale-invariant feature transform (SIFT) [51], speeded up robust features (SURF) [52], Gabor features [53], Haar-like wavelets [45], and BDF [54] have been proposed that extract valuable information from the images.”
BackgroundRobust and Effective Component-Based Banknote Recognition for the Blind
Hasanuzzaman, F. M., Yang, X., & Tian, Y. (2012) · IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews) · doi:10.1109/tsmcc.2011.2178120 · Cited by 111
Video forgery detection using HOG features and compression properties
Subramanyam, A. V., & Emmanuel, S. (2012) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2012.6343421 · Cited by 110
“Although features such as SIFT give good forgery detection performance [3], [4] owing to there robustness, other features such as SURF [12] or HoG [13] can also be used for detection purpose.”
MethodMultiple target detection and tracking with guaranteed framerates on mobile phones
Wagner, D., Schmalstieg, D., & Bischof, H. (2009) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2009.5336497 · Cited by 113
“In a more recent approach [22] Ta et al. improve speed by tracking SURF features in scale space.”
MethodHybrid Indoor Localization Using IMU Sensors and Smartphone Camera
Poulose, A., & Han, D. S. (2019) · Sensors · doi:10.3390/s19235084 · Cited by 121
Plasmoid formation in global GRMHD simulations and AGN flares
Nathanail, A., Fromm, C. M., Porth, O., Olivares, H., Younsi, Z., Mizuno, Y., & Rezzolla, L. (2020) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staa1165 · Cited by 122
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
Lan, S., Yu, Z., Choy, C., Radhakrishnan, S., Liu, G., Zhu, Y., Davis, L. S., & Anandkumar, A. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00339 · Cited by 146
A detailed analysis of image and video forgery detection techniques
Tyagi, S., & Yadav, D. (2023) · The Visual Computer · doi:10.1007/s00371-021-02347-4 · Cited by 109
Feature learning based on SAE–PCA network for human gesture recognition in RGBD images
Li, S., Yu, B., Wu, W., Su, S., & Ji, R. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.06.086 · Cited by 108
“For example, SIFT [5] and SURF [6] work well for object detection and recognition, while perform poorly on depth image.”
MethodAutomatic Visual Bag-of-Words for Online Robot Navigation and Mapping
Nicosevici, T., & Garcia, R. (2012) · IEEE Transactions on Robotics · doi:10.1109/tro.2012.2192013 · Cited by 106
Object class detection: A survey
Zhang, X., Yang, Y.-H., Han, Z., Wang, H., & Gao, C. (2013) · ACM Computing Surveys · doi:10.1145/2522968.2522978 · Cited by 107
Kanade, T., & Hebert, M. (2012) · Proceedings of the IEEE · doi:10.1109/jproc.2012.2200554 · Cited by 126
Robust local binary pattern feature sets for periocular biometric identification
Xu, J., Cha, M., Heyman, J. L., Venugopalan, S., Abiantun, R., & Savvides, M. (2010) · IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2010.5634504 · Cited by 112
The Case for Mobile Edge-Clouds
Drolia, U., Martins, R., Tan, J., Chheda, A., Sanghavi, M., Gandhi, R., & Narasimhan, P. (2013) · 2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing · doi:10.1109/uic-atc.2013.94 · Cited by 106
A comprehensive study of feature extraction techniques for plant leaf disease detection
Vishnoi, V. K., Kumar, K., & Kumar, B. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11375-0 · Cited by 119
ReDFeat: Recoupling Detection and Description for Multimodal Feature Learning
Deng, Y., & Ma, J. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3231135 · Cited by 144
A fast histogram-based similarity measure for detecting loop closures in 3-D LIDAR data
Röhling, T., Mack, J., & Schulz, D. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353454 · Cited by 104
Deep Learning Image-Based Defect Detection in High Voltage Electrical Equipment
Ullah, I., Khan, R. U., Yang, F., & Wuttisittikulkij, L. (2020) · Energies · doi:10.3390/en13020392 · Cited by 124
Feng, R., Shen, H., Bai, J., & Li, X. (2021) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2021.3081763 · Cited by 115
Deng, X., Liu, E., Li, S., Duan, Y., & Xu, M. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3240024 · Cited by 121
“The commonly used feature matching methods include scale-invariant feature transform (SIFT) [23], speeded up robust features (SURF) [24], and oriented FAST and rotated BRIEF (ORB) [25].”
MethodDetecting Large Repetitive Structures with Salient Boundaries
Wu, C., Frahm, J., & Pollefeys, M. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15552-9_11 · Cited by 108
Local Directional Pattern (LDP) – A Robust Image Descriptor for Object Recognition
Jabid, T., Kabir, M. H., & Chae, O. (2010) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2010.17 · Cited by 107
CAD-based recognition of 3D objects in monocular images
Ulrich, M., Wiedemann, C., & Steger, C. (2009) · 2009 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2009.5152511 · Cited by 106
Near-duplicate keyframe retrieval by nonrigid image matching
Zhu, J., Hoi, S. C. H., Lyu, M. R.-T., & Yan, S. (2008) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1459359.1459366 · Cited by 106
“Instead of using SIFT or PCA-SIFT, we adopt SURF [3], another emerging local feature descriptor to detect and extract local features, which takes advantage of fast feature extraction using integral images for image convolu-tions.”
MethodSemantics for Robotic Mapping, Perception and Interaction: A Survey
Garg, S., Sünderhauf, N., Dayoub, F., Morrison, D., Cosgun, A., Carneiro, G., Wu, Q., Chin, T.-J., Reid, I., Gould, S., et al. (2020) · Foundations and Trends® in Robotics · doi:10.1561/2300000059 · Cited by 105
Real-Time Object Tracking on a Drone With Multi-Inertial Sensing Data
Chen, P., Dang, Y., Liang, R., Zhu, W., & He, X. (2017) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2750091 · Cited by 120
“Speeded up robust features (SURF) [10] is the most significant optimization of scale-invariant feature transform (SIFT).”
BackgroundMoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion
Kentaro, W., Sucar, E., James, S., Lenton, D., & Davison, A. J. (2020) · 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/cvpr42600.2020.01455 · Cited by 117
Fredianelli, L., Carpita, S., Bernardini, M., Pizzo, L. G. D., Brocchi, F., Bianco, F., & Licitra, G. (2022) · Sensors · doi:10.3390/s22051929 · Cited by 120
“Classical machine learning appearance-based methods are based on the recognition of specific local features using descriptors such as the histogram of gradient (HOG) [39,40], Haar-like features [41], Gabor features [42], speedup robust features (SURF) [43], and scale-invariant features transform (SIFT) [44].”
A low-cost airborne velocimetry system: proof of concept
Detert, M., & Weitbrecht, V. (2015) · Journal of Hydraulic Research · doi:10.1080/00221686.2015.1054322 · Cited by 109
Dense reconstruction on-the-fly
Wendel, A., Maurer, M., Graber, G., Pock, T., & Bischof, H. (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.2012.6247833 · Cited by 121
“Once the marker is visible in the image, candidates for the first keyframe are stored and SURF features [2] are extracted.”
MethodFast Wavelet-Based Image Characterization for Highly Adaptive Image Retrieval
Quellec, G., Lamard, M., Cazuguel, G., Cochener, B., & Roux, C. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2180915 · Cited by 104
Improving vehicle localization using semantic and pole-like landmarks
Sefati, M., Daum, M., Sondermann, B., Kreisköther, K., & Kampker, A. (2017) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2017.7995692 · Cited by 108
“[7] H. Bay, T. Tuytelaars, and L. van Gool, “SURF: Speeded Up Robust Features,” in Lecture Notes in Computer Science, Computer Vision – ECCV 2006, D. Hutchison et al., Eds., Berlin, Heidelberg: Springer Berlin Heidelberg, 2006, pp. 404–417.”
MethodAccurate Segmentation and Registration of Skin Lesion Images to Evaluate Lesion Change
Navarro, F., Escudero-Viñolo, M., & Bescós, J. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2825251 · Cited by 111
“technique against two well-known feature detection-description algorithms: SIFT [39] and SURF [44].”
MethodConvolutional Neural Network Architecture for Geometric Matching
Rocco, I., Arandjelović, R., & Šivic, J. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2865351 · Cited by 118
Visual to Text: Survey of Image and Video Captioning
Li, S., Tao, Z., Li, K., & Fu, Y. (2019) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2019.2892755 · Cited by 103
Saxena, S., Shukla, S., & Gyanchandani, M. (2020) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22399 · Cited by 111
Multimodal Remote Sensing Image Registration Methods and Advancements: A Survey
Zhang, X., Leng, C., Hong, Y., Pei, Z., Cheng, I., & Basu, A. (2021) · Remote Sensing · doi:10.3390/rs13245128 · Cited by 123
Detection of Diabetic Retinopathy in Retinal Fundus Images Using CNN Classification Models
Asia, A.-O., Zhu, C., Althubiti, S. A., AL-Alimi, D., Xiao, Y., Ouyang, P., & Al‐qaness, M. A. A. (2022) · Electronics · doi:10.3390/electronics11172740 · Cited by 132
“In [21,22], the BoVW scheme is based on the detection of low-level sparse features with an accelerated enhanced features (i.e., SURF) local descriptor and midlevel features in semisoft encoding with the maximum combination.”
Recent advances in 3D SEM surface reconstruction
Tafti, A. P., Kirkpatrick, A. B., Alavi, Z., Owen, H. A., & Yu, Z. (2015) · Micron · doi:10.1016/j.micron.2015.07.005 · Cited by 121
“We first estimate the rotation and translation from the set of corresponding points between two images in the image set (Lowe, 2004; Bay et al., 2008; Calonder et al., 2010; Rublee, 2011).”
Structural similarity for document image classification and retrieval
Kumar, J., Ye, P., & Doermann, D. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2013.10.030 · Cited by 130
“Compared to SIFT (Lowe, 1999), the SURF descriptors are several times faster and more robust to noise, which often occurs during binarization (Bay et al., 2006).”
MethodLocal shape descriptor selection for object recognition in range data
Taati, B., & Greenspan, M. (2010) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2010.11.021 · Cited by 103
3D reconstruction of underwater structures
Beall, C., Lawrence, B. J., Ila, V., & Dellaert, F. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5649213 · Cited by 109
“Given their scale and local affine invariance properties, we opt to use SIFT [15] or SURF [16] instead, as they constitute a better option for matching visual features”
MethodInfluentialDiscriminative Object Tracking via Sparse Representation and Online Dictionary Learning
Xie, Y., Zhang, W., Li, C., Lin, S., Qu, Y., & Zhang, Y. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2013.2259230 · Cited by 104
Server-side object recognition and client-side object tracking for mobile augmented reality
Gammeter, S., Gassmann, A., Bossard, L., Quack, T., & Gool, L. V. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543248 · Cited by 108
Self-citationSeeland, M., Rzanny, M., Alaqraa, N., Wäldchen, J., & Mäder, P. (2017) · PLoS ONE · doi:10.1371/journal.pone.0170629 · Cited by 111
Normal Assisted Stereo Depth Estimation
Kusupati, U., Cheng, S., Chen, R., & Su, H. (2020) · 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/cvpr42600.2020.00226 · Cited by 123
Tavakkoli, A., Kamran, S. A., Hossain, K. F., & Zuckerbrod, S. L. (2020) · Scientific Reports · doi:10.1038/s41598-020-78696-2 · Cited by 113
SOML: Sparse Online Metric Learning with Application to Image Retrieval
Gao, X., Hoi, S. C. H., Zhang, Y., Wan, J., & Li, J. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8911 · Cited by 102
Chen, C., Wang, B., Lu, C. X., Trigoni, N., & Markham, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.12567 · Cited by 209
“The common pipeline varies from using hand-crafted detectors [202], [203] and descriptors [204], [205], replacing either the descriptor [179], [206], [207], [208], [209], [210] or detector [211], [212], [213] with a learned alternative, or learning both the detector and descriptor [214], [215].”
MethodWang, C., & Cho, Y. K. (2014) · Automation in Construction · doi:10.1016/j.autcon.2014.06.003 · Cited by 102
Research and applications on georeferenced multimedia: a survey
Zheng, Y.-T., Zha, Z.-J., & Chua, T. (2010) · Multimedia Tools and Applications · doi:10.1007/s11042-010-0630-z · Cited by 102
MMSS: Multi-modal Sharable and Specific Feature Learning for RGB-D Object Recognition
Wang, A., Cai, J., Lu, J., & Cham, T. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.134 · Cited by 108
Feature representation for statistical-learning-based object detection: A review
Li, Y., Wang, S., Tian, Q., & Ding, X. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.04.018 · Cited by 102
Usui, H., Subramanian, L., Chang, K. K.-W., et al. (2016) · ACM Transactions on Architecture and Code Optimization · doi:10.1145/2847255 · Cited by 102
“HES-HWA accelerates the fast Hessian detector that is executed in SURF (Speed-Up Robust Features) [Bay et al. 2008], which is used to detect interesting points in images and generate descriptors.”
MethodVision Based Human Activity Recognition: A Review
Bux, A., Angelov, P. P., & Habib, Z. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-46562-3_23 · Cited by 124
Top 10 technologies for indoor positioning on construction sites
Li, C. T., Cheng, J. C. P., & Chen, K. (2020) · Automation in Construction · doi:10.1016/j.autcon.2020.103309 · Cited by 126
Owl eyes: spotting UI display issues via visual understanding
Liu, Z., Chen, C., Wang, J., Huang, Y., Hu, J., & Wang, Q. (2020) · Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering · doi:10.1145/3324884.3416547 · Cited by 102
Feature detection and description for image matching: from hand-crafted design to deep learning
Lin, C., Rottensteiner, F., & Heipke, C. (2020) · Geo-spatial Information Science · doi:10.1080/10095020.2020.1843376 · Cited by 117
“This group contains the well-known descriptors SIFT (scale invariant feature transform [Lowe 2004]) and SURF (speeded-up robust feature [Bay, Tuytelaars, and Van Gool 2006]).”
MethodPhantom of the ADAS: Securing Advanced Driver-Assistance Systems from Split-Second Phantom Attacks
Nassi, B., Mirsky, Y., Nassi, D., Ben-Netanel, R., Drokin, O., & Elovici, Y. (2020) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3372297.3423359 · Cited by 168
“First, the algorithm extracts key points for every frame based on the SURF algorithm [4].”
MethodBag-of-Words and Object-Based Classification for Cloud Extraction From Satellite Imagery
Yuan, Y., & Hu, X. (2015) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2015.2431676 · Cited by 101
Experiences of Aiding Autobiographical Memory Using the SenseCam
Doherty, A. R., Pauly-Takacs, K., Caprani, N., Gurrin, C., Moulin, C. J. A., O'Connor, N. E., & Smeaton, A. F. (2012) · Human–Computer Interaction · doi:10.1080/07370024.2012.656050 · Cited by 100
“…state-of-art multimedia retrieval techniques, we compared our global color based-approach just mentioned to methods for extracting interest point features from images using SIFT [Scale Invariant Feature Transform, (Lowe, 2004)] and SURF [Speeded Up Robust Features, (Bay et al., 2006)] techniques.”
A novel feature descriptor invariant to complex brightness changes
Tang, F., Lim, S., Chang, N. L., & Tao, H. (2009) · 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.2009.5206550 · Cited by 109
Jangid, M., & Srivastava, S. (2018) · Journal of Imaging · doi:10.3390/jimaging4020041 · Cited by 103
Uncertainty Assisted Robust Tuberculosis Identification With Bayesian Convolutional Neural Networks
Abideen, Z. U., Ghafoor, M., Munir, K., Saqib, M., Ullah, A., Zia, T., Tariq, S. A., Ahmed, G., & Zahra, A. (2020) · IEEE Access · doi:10.1109/access.2020.2970023 · Cited by 109
Brain Tumor Segmentation from MRI Images Using Handcrafted Convolutional Neural Network
Ullah, F., Nadeem, M., Abrar, M. Y. B. T., Al‐Razgan, M., Alfakih, T. M., Amin, F., & Salam, A. (2023) · Diagnostics · doi:10.3390/diagnostics13162650 · Cited by 132
“The Speeded Up Robust Features (SURF) is a variation that includes the DSURF descriptor, which is utilized for both feature point detection and description [48].”
MethodIdentifying rice grains using image analysis and sparse-representation-based classification
Kuo, T.-Y., Chung, C., Chen, S., Lin, H., & Kuo, Y. (2016) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2016.07.020 · Cited by 109
LIFT: Learned Invariant Feature Transform
Yi, K. M., Trulls, E., Lepetit, V., & Fua, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.09114 · Cited by 88
MOPED: A scalable and low latency object recognition and pose estimation system
Martinez, M., Collet, A., & Srinivasa, S. S. (2010) · 2010 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2010.5509801 · Cited by 97
HSOG: A Novel Local Image Descriptor Based on Histograms of the Second-Order Gradients
Huang, D., Zhu, C., Wang, Y., & Chen, L. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2353814 · Cited by 104
“…in reinforcing the discriminative power [9], [13], [16], improving the efficiency while decreasing the memory requirements [8], [12], [15], [17], [18], increasing the invariance to lighting changes [10], [14], [19], [20] or scale variations [21], [22], and making them robust to local…”
Global and efficient self-similarity for object classification and detection
Deselaers, T., & Ferrari, V. (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.2010.5539775 · Cited by 108
“We use SURF descriptors [3, 17] and quantize them into 2000 words with k-means.”
MethodBoosting dense SIFT descriptors and shape contexts of face images for gender recognition
Wang, J.-G., Li, J., Yau, W., & Sung, E. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543238 · Cited by 114
“Bay et al. [3] speeded up robust features (SURF) and used integral images for image convolutions and Fast-Hessian detector.”
BackgroundMethodTree Histogram Coding for Mobile Image Matching
Chen, D. M., Tsai, S. S., Chandrasekhar, V., Takacs, G., Singh, J., & Girod, B. (2009) · DCC · doi:10.1109/dcc.2009.33 · Cited by 100
Feature Extraction and Machine Learning for the Classification of Brazilian Savannah Pollen Grains
Gonçalves, A. B., Souza, J. S., da Silva, G. G., et al. (2016) · PLoS ONE · doi:10.1371/journal.pone.0157044 · Cited by 100
“…visual feature can be defined in many different ways, but the one used in this research is based on the Speeded up Robust Features (SURF) technique [19], that detects and describes interest points in an image based on the magnitude and direction of the gradients in and around each pixel of the…”
Sensors and Measurements for UAV Safety: An Overview
Balestrieri, E., Daponte, P., Vito, L. D., Picariello, F., & Tudosa, I. (2021) · Sensors · doi:10.3390/s21248253 · Cited by 118
Unsupervised Image Categorization by Hypergraph Partition
Huang, Y., Liu, Q., Lv, F., Gong, Y., & Metaxas, D. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.25 · Cited by 99
Fusion and binarization of CNN features for robust topological localization across seasons
Arroyo, R., Alcantarilla, P. F., Bergasa, L. M., & Romera, E. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759685 · Cited by 102
Sequential and Patch Analyses for Object Removal Video Forgery Detection and Localization
Aloraini, M., Sharifzadeh, M., & Schonfeld, D. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2993004 · Cited by 99
Texture Analysis and Its Applications in Biomedical Imaging: A Survey
Ghalati, M. K., Nunes, A., Ferreira, H. R. L., Serranho, P., & Bernardes, R. C. (2021) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2021.3115703 · Cited by 130
VizLens: A Robust and Interactive Screen Reader for Interfaces in the Real World
Guo, A., Chen, X. '., Qi, H., White, S., Ghosh, S., Asakawa, C., & Bigham, J. P. (2016) · Proceedings of the 29th Annual Symposium on User Interface Software and Technology · doi:10.1145/2984511.2984518 · Cited by 99
“It uses SURF (Speeded-Up Robust Features) [2] feature detec tor with hessian threshold set to 400 to compute key points and feature vectors in both the reference (Figure 4a) and the input image (Figure 4b).”
MethodCombining global and local features for food identification in dietary assessment
Bosch, M., Zhu, F., Khanna, N., Boushey, C. J., & Delp, E. J. (2011) · 2011 18th IEEE International Conference on Image Processing · doi:10.1109/icip.2011.6115809 · Cited by 98
“In [18], a novel low level descriptor known as SURF was introduced that is based on the 2D Haar wavelet responses and made efficient use of the box filter.”
MethodA comparative study of thermal face recognition methods in unconstrained environments
Hermosilla, G., Ruíz-del-Solar, J., Verschae, R., & Correa, M. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.01.001 · Cited by 109
Automatic Defect Recognition in X-Ray Testing Using Computer Vision
Mery, D., & Arteta, C. (2017) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2017.119 · Cited by 117
DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning
Spencer, J., Bowden, R., & Hadfield, S. (2020) · 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/cvpr42600.2020.01441 · Cited by 138
“Such is the case with SURF [5], BRIEF [6] and BRISK [36].”
MethodSIND: A Drone Dataset at Signalized Intersection in China
Xu, Y., Shao, W., Li, J., Yang, K., Wang, W., Huang, H., Lv, C., & Wang, H. (2022) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc55140.2022.9921959 · Cited by 158
Multithreaded Hybrid Feature Tracking for Markerless Augmented Reality
Lee, T., & Höllerer, T. (2008) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2008.190 · Cited by 93
A review of recent developments in vision-based vehicle detection
Sivaraman, S., & Trivedi, M. M. (2013) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2013.6629487 · Cited by 108
Outdoor place recognition in urban environments using straight lines
Lee, J. H., Lee, S., Zhang, G., Lim, J., Chung, W. K., & Suh, I. H. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907675 · Cited by 100
“Currently, most visual place recognition systems use point features, such as the scale-invariant feature transform (SIFT) [5] or speeded-up robust features (SURF) [6].”
Background
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.