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








Verification
Claims the paper makes
0 Valid · 2 Not valid · 12 Not checked · 30 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The number of interest points found is on average very similar for all detectors.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 4 × 4 sub-region division solution provided the best results.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SURF outperformed the other descriptors for almost all the comparisons.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The SURF descriptor outperforms the other descriptors in a systematic and significant way, with sometimes more than 10% improvement in recall for the same level of precision.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in the results section, the performance is comparable to the one using the discretised and cropped Gaussians.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
8 more claims
Create a free account to see all 44 claims and every source verdict.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This transition marked a new era, where we moved beyond the classic approaches and task-specific feature engineering of earlier days [Lowe 2004; Bay et al. 2006; Rosten and Drummond 2006] towards models that could be trained once over large amounts of data, and then adapted for a broad variety of tasks, such as image recognition, object detection, and image segmentation [Krizhevsky et al. 2012; Sz”
From On the Opportunities and Risks of Foundation Models (2021) · cites this paper as Bay et al. 2006
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · cited 14×
“This PCA-SIFT yields a 36-dimensional descriptor which is fast for matching, but proved to be less distinctive than SIFT in a second comparative study by Mikolajczyk et al. [8] and slower feature computation reduces the effect of fast matching.”
BackgroundMethodResultInfluentialMarr, D., & Hildreth, E. (1980) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1980.0020 · Cited by 6,510
PCA-SIFT: a more distinctive representation for local image descriptors
Ke, Y., & Sukthankar, R. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.183 · Cited by 3,932
Robust wide-baseline stereo from maximally stable extremal regions
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.02.006 · Cited by 3,686
Scalable Recognition with a Vocabulary Tree
Nister, D., & Stewenius, H. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.264 · Cited by 3,579
Scale & Affine Invariant Interest Point Detectors
Mikolajczyk, K., & Schmid, C. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000027790.02288.f2 · Cited by 3,436
Cited by
Items 5,501–5,600 of 14,752
Image super-resolution via feature-based affine transform
Hsu, C., & Lin, C. (2011) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2011.6093845 · Cited by 9
SURF algorithm with color and global characteristics
Yoon, H.-S., Chung, H., & Hahn, H. (2009) · 2009 ICCAS-SICE · Cited by 9
Efficient video summarization and retrieval tools
Valdés, V., & Martínez, J. M. (2011) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2011.5972518 · Cited by 9
“The proposed approach makes use of a two-level search mechanism for fast access to the indexed video content and such mechanism relies in the combination of HSV histograms and SURF features [1].”
MethodLinking video ADS with product or service information by web search
Wang, J., Duan, L., Wang, B., et al. (2009) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2009.5202488 · Cited by 9
“As local image features, SURF has been successfully applied to object recognition and classification [10].”
Wang, R., Zhu, Z., & Zhang, L. (2015) · Journal of Electronic Imaging · doi:10.1117/1.jei.24.3.033002 · Cited by 9
Segmentation Based Features for Wide-Baseline Multi-view Reconstruction
Mustafa, A., Kim, H., İmre, E., & Hilton, A. (2015) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2015.39 · Cited by 9
Sketch-Based Retrieval Using Content-Aware Hashing
Liang, S., Zhao, L., Wei, Y., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13168-9_14 · Cited by 9
Online learning the consensus of multiple correspondences between sets
Moreno‐García, C. F., & Serratosa, F. (2015) · Knowledge-Based Systems · doi:10.1016/j.knosys.2015.09.034 · Cited by 9
“ SURF [29]: It is composed of a vector of features obtained from the Speeded-up robust features algorithm.”
MethodCharacterizing objects with SIKA features for multiclass classification
Srivastava, S., Mukherjee, P., & Lall, B. (2015) · Applied Soft Computing · doi:10.1016/j.asoc.2015.12.014 · Cited by 9
“Scale Invariant Feature Transform (SIFT) [5], Speeded Up Robust Features (SURF) [6], Histogram of Oriented Gradients (HOG) [7], Oriented and Rotated Brief (ORB) [8], KAZE [9] etc. have been widely used for solving the former issue.”
Ono, S., Maehara, T., & Minami, K. (2016) · Applied Soft Computing · doi:10.1016/j.asoc.2015.11.001 · Cited by 9
Adaptive Cloud Resource Allocation for Analysing Many Video Streams
Chen, W., Lu, Y.-H., & Hacker, T. J. (2015) · IEEE International Conference on Cloud Computing Technology and Science · doi:10.1109/cloudcom.2015.79 · Cited by 9
“SURF is also a local feature detector and descriptor and it is partially inspired by SIFT.”
MethodInfluentialVideo-Based Action Detection Using Multiple Wearable Cameras
Zheng, K., Lin, Y., Zhou, Y., Salvi, D., Fan, X., Guo, D., Meng, Z., & Wang, S. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16178-5_51 · Cited by 8
“Specifically, we first extract the SURF features [3] and match them between neighboring frames using nearest neighbor search.”
MethodAutonomous exploration of indoor environments with a micro-aerial vehicle
Pepe, G., Satler, M., & Tripicchio, P. (2015) · Workshop on Research, Education and Development of Unmanned Aerial Systems (RED-UAS) · doi:10.1109/red-uas.2015.7440989 · Cited by 9
Exploration and Mapping Technique Suited for Visual-features Based Localization of MAVs
Chudoba, J., Kulich, M., Saska, M., Báča, T., & Přeučil, L. (2016) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-016-0358-8 · Cited by 9
“From the available image features, the speeded-up robust features (SURF, [4]) are used in the experiments described in this article.”
Visual Data Driven Approach for Metric Localization in Substation
Wu, H. R., Wu, Y., Liu, C., & Yang, G. (2015) · Chinese Journal of Electronics · doi:10.1049/cje.2015.10.022 · Cited by 9
Fast Underwater Image Mosaicing through Submapping
Elibol, A., Kim, J., Gracias, N., et al. (2016) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-016-0380-x · Cited by 9
Two Dimensionality Reduction Techniques for SURF Based Face Recognition
Vinay, A., Vasuki, V., Bhat, S., Jayanth, K. S., Murthy, K. N. B., & Natarajan, S. (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.05.222 · Cited by 9
Emotion Recognition Using Facial Expression
Kumar, S., Jaiswal, S., Kumar, R., & Singh, S. K. (2015) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-4666-8723-3.ch013 · Cited by 9
KUKA robot control based Kinect image analysis
Belhadj, H., Hassen, S. B., Kaâniche, K., et al. (2013) · doi:10.1109/icbr.2013.6729264 · Cited by 9
“Then we apply the recognition algorithm SIFT [6].”
MethodJung, M., & Song, J.-B. (2016) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.1109/iccas.2016.7832411 · Cited by 9
Yanagawa, Y., Echigo, T., Vu, H. A., et al. (2017) · IPSJ Transactions on Computer Vision and Applications · doi:10.1186/s41074-017-0015-6 · Cited by 9
Scaramuzzino, S., Carallo, C., Pileggi, G., et al. (2017) · Annals of Biomedical Engineering · doi:10.1007/s10439-017-1829-1 · Cited by 9
Chai, Z., & Matsumaru, T. (2017) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2017.p0365 · Cited by 8
Moura, G. M., & da Silva, R. L. D. S. (2017) · Journal of Multimedia · Cited by 9
A hyperspectral vessel image registration method for blood oxygenation mapping
Wang, Q., Li, Q., Zhou, M., et al. (2017) · PLoS ONE · doi:10.1371/journal.pone.0178499 · Cited by 9
Murtza, I., Khan, A., & Akhtar, N. (2017) · Neural Computing and Applications · doi:10.1007/s00521-017-3050-4 · Cited by 11
Drought Stress Classification Using 3D Plant Models
Srivastava, S., Bhugra, S., Lall, B., & Chaudhury, S. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.240 · Cited by 14
“We performed experiments with Speeded-Up Robust features (SURF) [2] as well, and observed the same problems (holes).”
Your Privacy Is in Your Hand: Interactive Visual Privacy Control with Tags and Gestures
Shu, J., Zheng, R., & Hui, P. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67235-9_3 · Cited by 11
“We use Speeded-Up Robust Features (SURF) [7] implemented in OpenCV library [3] for tag detection.”
MethodInfluentialImage classification using bag of visual words model with FAST and FREAK
Singhal, N., Singhal, N., & Kalaichelvi, V. (2017) · International Conference on Electrical, Computer and Communication Technologies (ICECCT) · doi:10.1109/icecct.2017.8117861 · Cited by 9
“Examples of a few image the detectors are as follows: SIFT (Scale-invariant feature transform), FAST[1], SURF[2], BRIEF[3], ORB[4], BRISK[5].”
MethodFOV Expansion of Bioinspired Multiband Polarimetric Imagers With Convolutional Neural Networks
Zhao, Y., Wang, M., Yang, G., et al. (2017) · IEEE photonics journal · doi:10.1109/jphot.2017.2783039 · Cited by 9
Content Based Image Retrieval with Graphical Processing Unit
Kaur, B., & Jindal, S. (2014) · Cited by 9
A Survey on Visual Place Recognition for Mobile Robots Localization
Chen, Y., Gan, W., Zhang, L., Liu, C., & Wang, X. (2017) · Web Information Systems and Applications Conference (WISA) · doi:10.1109/wisa.2017.7 · Cited by 11
“H Badino [29] developed SURF as a whole-image descriptor named WI-SURF.”
MethodInfluentialMulti-View Audio-Articulatory Features for Phonetic Recognition on RTMRI-TIMIT Database
Douros, I., Katsamanis, A., & Maragos, P. A. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461612 · Cited by 9
“Another interesting choice of features to use, which are also robust and scale invariant, are the Speed Up Robust Features (SURF) features [11].”
BackgroundAN IMPROVED IMAGE MATCHING METHOD BASED ON SURF ALGORITHM
Chen, S., Zheng, S. Z., Xu, Z., Guo, C., & Ma, X. L. (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-3-179-2018 · Cited by 13
Social computing for image matching
Chamoso, P., Rivas, A., Sánchez-Torres, R., et al. (2018) · PLoS ONE · doi:10.1371/journal.pone.0197576 · Cited by 9
“• Corners and points of interest : Harris & Stephens, SUSAN, Shi & Tomasi, Level curve curvature, FAST [19], Laplacian of Gaussian, Difference of Gaussians, Determinant of Hessian, SURF [20], ORB [21].”
BackgroundGiang, N. T., Muller, J.-M., Rupnik, E., et al. (2018) · Sensors · doi:10.3390/s18072150 · Cited by 9
Explorations on visual localization from active to passive
Yang, Y., Wu, Y., & Chen, N. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6347-0 · Cited by 8
“Many progresses have been made in the literature, such as famous corner detector Harris [53], Hessian [54], stable region detector LoG [55], stable point detector DoG [56], scale-invariant blob-like feature detector SURF [57], extremely efficient FAST [58] detector and its extension AGAST [59].”
BackgroundMethodResearch on an Image Mosaic Algorithm Based on Improved ORB Feature Combined with SURF
Feng, Y., & Li, S. (2018) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2018.8407963 · Cited by 9
Touchless typing with head movements captured in thermal spectrum
Nowosielski, A., & Forczmański, P. (2018) · Pattern Analysis and Applications · doi:10.1007/s10044-018-0741-0 · Cited by 9
“We considered corners detected using FAST algorithm (green squares) [29], Harris–Stephens features (blue x) [15] and SURF features (red circle) [4].”
MethodWarren, M., Schoellig, A. P., & Barfoot, T. D. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460961 · Cited by 7
“A large and well-known number of visual feature detectors and descriptors exist [2], [3], [4], [5] for robustly matching keypoints in imagery.”
BackgroundA novel inertial-aided feature detection model for autonomous navigation in planetary landing
Yu, M., Li, S., Huang, X., & Wang, S. (2018) · Acta Astronautica · doi:10.1016/j.actaastro.2018.09.022 · Cited by 9
SConE: Siamese Constellation Embedding Descriptor for Image Matching
Trzcinski, T. P., Komorowski, J., Dąbała, Ł., Czarnota, K., Kurzejamski, G., & Lynen, S. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11009-3_24 · Cited by 10
Detection and tracking of a landing platform for aerial robotics applications
Ruiz, M. S., Vargas, A. M. P., & Romero-Cano, V. (2018) · doi:10.1109/ccra.2018.8588112 · Cited by 9
Addressing facial dynamics using k-medoids cohort selection algorithm for face recognition
Garain, J., Kumar, R. K., Kisku, D. R., & Sanyal, G. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-018-7132-9 · Cited by 10
“First the SURF points [5] and SIFT points [27] are detected and localized on both the probe and gallery images.”
BackgroundEnhanced Gradient-Based Local Feature Descriptors by Saliency Map for Egocentric Action Recognition
Zuo, Z., Wei, B. W., Chao, F., Qu, Y., Peng, Y., & Yang, L. (2019) · Applied System Innovation · doi:10.3390/asi2010007 · Cited by 10
A Versatile Visual Navigation System for Autonomous Vehicles
Majer, F., Halodová, L., Vintr, T., Dlouhý, M., Merenda, L., Fentanes, J. P., Portugal, D., Couceiro, M. S., & Krajník, T. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-14984-0_8 · Cited by 12
Discriminative multi-source adaptation multi-feature co-regression for visual classification
Tao, J., & Dai, W. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.02.007 · Cited by 9
Bakas, S., Doulgerakis-Kontoudis, M., Hunter, G., Sidhu, P., Makris, D., & Chatzimichail, K. (2019) · Ultrasound in Medicine and Biology · doi:10.1016/j.ultrasmedbio.2019.01.023 · Cited by 9
UAVS ENHANCED NAVIGATION IN OUTDOOR GNSS DENIED ENVIRONMENT USING UWB AND MONOCULAR CAMERA SYSTEMS
Zahran, S., Masiero, A., Mostafa, M. M. R., et al. (2019) · 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-w13-665-2019 · Cited by 9
“The camera is attached to the belly of the drone (nadir), the implemented VO is based on the optical flow approach shown in (Heinrich, 2017), where features are detected in consecutive frames (30 FPS) through the Speeded Up Robust Features (SURF) detector (Bay et al., 2006), which has been chosen because of its low co…”
MethodSmart Walker V: Implementation of RTAB-Map Algorithm
Ramachandran, S., & Sahin, F. (2019) · doi:10.1109/sysose.2019.8753827 · Cited by 9
“This paper concentrates on SIFT [3] and SURF [2] feature methods in terms of matching keypoints for loop closure detection from the known vocabulary of words detected.”
MethodReal-Time Downward View Generation of a Vehicle Using Around View Monitor System
Lee, J.-K., Kim, M., Lee, S., et al. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2929532 · Cited by 9
Content-oriented image quality assessment with multi-label SVM classifier
Cao, J., Wang, S., Wang, R., Zhang, X., & Kwong, S. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.07.018 · Cited by 9
Unconstrained self-calibration of stereo camera on visually impaired assistance devices
Li, H., Wang, K., Yang, K., Cheng, R., Wang, C., & Fei, L. (2019) · Applied Optics · doi:10.1364/ao.58.006377 · Cited by 10
Improving Keypoint Matching Using a Landmark-Based Image Representation
Huang, X., Dai, Z., Chen, W., He, L., & Zhang, H. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794420 · Cited by 9
Zhao, C., Ding, R., & Key, H. L. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8802931 · Cited by 11
Khemmar, R., Gouveia, M., Decoux, B., & Ertaud, J.-Y. (2019) · Computer Science Research Notes · doi:10.24132/csrn.2019.2902.2.5 · Cited by 10
Heterogeneous Image Matching via a Novel Feature Describing Model
Zhou, B., Duan, X., Ye, D., et al. (2019) · Applied Sciences · doi:10.3390/app9224792 · Cited by 9
A Novel Fast Retina Keypoint Extraction Algorithm for Multispectral Images Using Geometric Algebra
Li, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2954081 · Cited by 9
“The speeded up robust feature (SURF) [15] proposed by Bay is a computationally-efficient replacement to SIFT, which outperforms SIFT in robustness and speed [16].”
MethodImproved feature point extraction and mismatch eliminating algorithm
Sun, D., Zhang, S., & Wang, Y. (2020) · Systems Science & Control Engineering · doi:10.1080/21642583.2019.1707725 · Cited by 9
Li, Z., Zhou, A., Wang, M., & Shen, Y. (2019) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio49542.2019.8961602 · Cited by 9
“FAB-MAP [2] is an advanced visual place recognition algorithm, which builds on local features such as SIFT [3] or SURF [4], and matches the appearance of the current scene to a place where robots previously visited by converting the image into bag-of-words representations.”
MethodSemi-Autonomous Interventional Manipulation using Pneumatically Attachable Flexible Rails
Ettorre, C. D., Stilli, A., Dwyer, G., et al. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967789 · Cited by 9
“Hence, the kidney is segmented both in the left and right frame, following which local features are extracted using SURF algorithm [32] for both frames.”
MethodHybrid Method for Moving Object Exploration in Video Surveillance
Krishna, R. S. B., Bharathi, B., Ayoobkhan, M. U. A., et al. (2019) · International Conference on Computational Intelligence and Knowledge Economy (ICCIKE) · doi:10.1109/iccike47802.2019.9004330 · Cited by 9
Analysis of Suitable Natural Feature Computer Vision Algorithms for Augmented Reality Services
Cīrulis, A., Brigmanis-Briģis, K., & Zvejnieks, G. (2020) · Baltic Journal of Modern Computing · doi:10.22364/bjmc.2020.8.1.10 · Cited by 9
Feature Matching and Heat Flow in Centro-Affine Geometry
Olver, P. J., Qu, C., & Yang, Y. Y. (2020) · Symmetry Integrability and Geometry Methods and Applications · doi:10.3842/sigma.2020.093 · Cited by 9
Automatic food recognition system for middle‐eastern cuisines
Qaraqe, M., Usman, M., Ahmad, K., Sohail, A., & Boyaci, A. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2019.1051 · Cited by 8
“In this regard, the initial efforts are based on hand-crafted visual features, such as scale-invariant feature transforms (SIFTs) [5], speed-ed up robust features (SURFs) [6], local binary patterns (LBPs) [7], and colour-based visual features.”
BackgroundGround Control Point Automatic Extraction for Spaceborne Georeferencing Based on FPGA
Liu, D., Zhou, G., Zhang, D., et al. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.2998838 · Cited by 9
“Bay et al. [23] proposed approximation to the LoG by using box filter representations of the respective kernels based on SIFT.”
BackgroundMethodInfluentialMaltar, J., Marković, I., & Petrovic, I. K. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103598 · Cited by 12
“In the context of visual place recognition SURF [4] is used in FAB-MAP [12], while ORB features [6, 42] are used in ORB-SLAM [34].”
MethodHybrid Capsule Network Architecture Estimation for Melanoma Detection
Boaro, J. M. C., dos Santos, P. T. C., Rocha, C. V. M., Fontenele, T., Bráz, G., de Almeida, J. D. S., de Paiva, A. C., & da Rocha, S. V. (2020) · International Conference on Systems, Signals and Image Processing · doi:10.1109/iwssip48289.2020.9145127 · Cited by 9
“The first one using RSurf features [14] and Local Binary Patterns (LBP) and the second one using features from a convolutional neural network, in this specific study, the AlexNet network [15].”
MethodInterior dense 3D reconstruction system with RGB-D camera for complex large scenes
Fu, X., Li, G., & Yu, L. (2020) · Measurement Science and Technology · doi:10.1088/1361-6501/abaa67 · Cited by 9
Attributed Relational SIFT-Based Regions Graph: Concepts and Applications
Manzo, M. (2020) · Machine Learning and Knowledge Extraction · doi:10.3390/make2030013 · Cited by 9
“Quantitative comparison using the Mean Reciprocal Rank (MRR) measure among SIFT [8], SURF [29], ORB [30], FREAK [31], BRIEF [32], and the Attributed Relational SIFT-based Regions Graph (ARSRG) matching on the dataset in [26].”
MethodHu, K., Huang, G., Yang, Y., Pun, C., Ling, B. W., & Cheng, L. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09566-2 · Cited by 10
“SURF algorithm was a fast scale-invariant feature detector and descriptor for feature matching and was proposed by Herbert Bay in 2006 [2].”
MethodA Systematic Review on Product Recognition for Aiding Visually Impaired People
Machado, A., Veras, R. D. M. S., Aires, K. R. T., & Neto, L. D. S. B. (2021) · IEEE Latin America Transactions · doi:10.1109/tla.2021.9448542 · Cited by 12
“As primeiras pesquisas encontradas en-volvem a utilização de descritores de características, tais como Scale-Invariant Feature Transform (SIFT) [56] e Speeded Up Robust Features (SURF) [57].”
BackgroundImage Boundary, Corner, and Edge Detection: Past, Present, and Future
Zakariah, M., & Al-Shalfan, K. (2020) · International Journal of Computer and Electrical Engineering · doi:10.17706/ijcee.2020.12.2.39-57 · Cited by 9
Diabetic retinopathy grading based on Lesion correlation graph
Luo, D., & Kamata, S. (2020) · International Conference on Informatics, Electronics & Vision (ICIEV) · doi:10.1109/icievicivpr48672.2020.9306664 · Cited by 11
“Furthermore, Speeded Up Robust Features (SURF) [16] improves detection accuracy and reduce the detection time.”
BackgroundMatching Intensity for Image Visibility Graphs: A New Method to Extract Image Features
Zhu, D., Semba, S., & Yang, H. (2021) · IEEE Access · doi:10.1109/access.2021.3050747 · Cited by 8
Realtime flicker removal for fast video streaming and detection of moving objects
Nowisz, J., Kopania, M., & Przelaskowski, A. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10385-8 · Cited by 9
“Optical flow methods, like Lucas-Kanade [14] or Farneback [6] or feature detection methods like SURF [2], SIFT [13], or ORB [20] can be used.”
MethodMultiscale Image Matching for Automated Calibration of UAV-Based Frame and Line Camera Systems
Hasheminasab, S. M., Zhou, T., LaForest, L., et al. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3062573 · Cited by 9
“…several scale invariant image matching algorithms such as scale invariant feature transform (SIFT) [11] and speeded-up robust features (SURF) [12] have been developed, when dealing with UAV-based images with significant scale differences, these algorithms would result in high percentage of…”
Image Retrieval using Bag-of-Features for Lung Cancer Classification
Bhatt, S. D., & Soni, H. B. (2021) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict50816.2021.9358499 · Cited by 11
Goal oriented image quality assessment
Kiruthika, S. U., & Masilamani, V. (2021) · IET Image Processing · doi:10.1049/ipr2.12209 · Cited by 9
“The second set of features is obtained from SURF [30].”
MethodInfluentialPanoramic Imaging Assessment of Different Bladder Phantoms – An Evaluation Study
Hackner, R., Suarez-Ibarrola, R., Qiu, T., et al. (2021) · Urology · doi:10.1016/j.urology.2021.05.036 · Cited by 9
Real-Time Violence Detection in Videos Using Dynamic Images
Guedes, A. R. M., & Cámara-Chávez, G. (2020) · Latin American Computer Conference (CLEI) · doi:10.1109/clei52000.2020.00065 · Cited by 10
Learning local descriptors with multi-level feature aggregation and spatial context pyramid
Liang, P., Ji, H., Cheng, E., Chai, Y., Wang, L., & Ling, H. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.030 · Cited by 11
Graph matching based on fast normalized cut and multiplicative update mapping
Yang, J., Yang, X., Zhou, Z., & Liu, Z. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108228 · Cited by 8
Ahmed, S., Frikha, M., Hussein, T. D. H., & Rahebi, J. (2021) · International Conference on Electrical, Communication, and Computer Engineering (ICECCE) · doi:10.1109/icecce52056.2021.9514139 · Cited by 9
RetractedCheng, M., & Matsuoka, M. (2021) · Sensors · doi:10.3390/s21186035 · Cited by 11
Effective methods of diabetic retinopathy detection based on deep convolutional neural networks
Gu, Y., Wang, X., Pan, J., Yong, Z., Guo, S., Pan, T., Jiao, Y., & Zhou, Z. (2021) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-021-02498-8 · Cited by 9
“Reference [27] designed a Bag-of-Visual-Words scheme that based on SURF [4] local descriptor.”
MethodBrahmi Script Recognition System using Deep Learning Techniques
Devi, P. D., & Sathiyapriya, V. (2021) · International Conference on Inventive Research in Computing Applications (ICIRCA) · doi:10.1109/icirca51532.2021.9544978 · Cited by 9
Loop Closure Detection Using KPCA and CNN for Visual SLAM
Dai, K., Cheng, L., Yang, R., & Yan, G. (2021) · Chinese Control Conference (CCC) · doi:10.23919/ccc52363.2021.9550432 · Cited by 11
“Various feature extraction methods, such as SIFT, SURF, FAST and ORB [13,1,16,17], are used in previous methods.”
MethodHuber, M., Mitchell, J. B., Henry, R., et al. (2021) · International Symposium on Medical Robotics · doi:10.1109/ismr48346.2021.9661563 · Cited by 9
“To compute the homography, we extract image features and their descriptors with a SURF feature detector [32].”
MethodLoop Closure Detection by Using Global and Local Features With Photometric and Viewpoint Invariance
Yu, M., Zhang, L., Wang, W., & Huang, H. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3116898 · Cited by 9
Efficient probability-oriented feature matching using wide field-of-view imaging
Flores, M., Valiente, D., Gil, A., Reinoso, Ó., & Payá, L. (2021) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2021.104539 · Cited by 10
Automatic Satellite Image Stitching Based on Speeded Up Robust Feature
Megha, V., & K, R. K. (2021) · International Conference on Artificial Intelligence and Machine Vision (AIMV) · doi:10.1109/aimv53313.2021.9670954 · Cited by 9
ImPos: An Image-Based Indoor Positioning System
Li, Y., Kambhamettu, R. H., Hu, Y., & Zhang, R. (2022) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc49033.2022.9700699 · Cited by 10
“We adopt the standard feature matching techniques [27] to determine whether every pair of feature points are a match.”
MethodHa, Y.-S., Lee, J., & Kim, Y.-T. (2022) · Remote Sensing · doi:10.3390/rs14071697 · Cited by 9
Efficient hand vein recognition using local keypoint descriptors and directional gradients
Alshayeji, M. H., Al‐Roomi, S. A., & Abed, S. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12608-6 · Cited by 9
A Very Fast Copy-Move Forgery Detection Method for 4K Ultra HD Images
Bertojo, L., Néraud, C., & Puech, W. (2022) · Frontiers in Signal Processing · doi:10.3389/frsip.2022.906304 · Cited by 13
“Shivakumar and Baboo (2011) proposed a method based on the Speed Up Robust Feature [SURF (Bay et al., 2006)] which is a descriptor inspired by SIFT but faster.”
MethodLTSR: Long-term Semantic Relocalization based on HD Map for Autonomous Vehicles
Wang, H., Xue, C., Tang, Y., Li, W., Wen, F., & Zhang, H. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811855 · Cited by 9
Detection of Android Malware App through Feature Extraction and Classification of Android Image
Khan, M. A. R., Kumar, N., & Tripathi, R. C. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.01305103 · Cited by 10
Boosting vision transformer for low-resolution borehole image stitching through algebraic multigrid
Chen, J., Fu, Z., Huang, J., et al. (2022) · The Visual Computer · doi:10.1007/s00371-022-02564-5 · Cited by 9
A Parallel Convolution and Decision Fusion-Based Flower Classification Method
Jia, L., Zhai, H., Yuan, X., Jiang, Y. L., & Ding, J. (2022) · Mathematics · doi:10.3390/math10152767 · Cited by 11
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.