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 4,401–4,500 of 14,752
3D Point Cloud Initial Registration Using Surface Curvature and SURF Matching
Tong, L., & Ying, X. (2018) · 3D Research · doi:10.1007/s13319-018-0193-8 · Cited by 13
A probabilistic topic model for event-based image classification and multi-label annotation
Laib, L., Allili, M. S., & Ait-Aoudia, S. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.05.012 · Cited by 15
Robust template matching with large angle localization
Yang, Y., Chen, Z., Li, X., Guan, W., Zhong, D., & Xu, M. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.05.105 · Cited by 13
Event retrieval using motion barcodes
Ben-Artzi, G., Werman, M., & Peleg, S. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351277 · Cited by 14
Enhancing Video Recommendation Using Multimedia Content
Deldjoo, Y. (2019) · SpringerBriefs in applied sciences and technology · doi:10.1007/978-3-030-32094-2_6 · Cited by 13
“They include for instance scale invariant feature transform ( SIFT ) [36], speeded up robust features ( SURF ) [6], local binary patterns ( LBP ) [41], discrete Wavelet transform ( DWT ), such as Gabor filters [37], discrete Fourier transform ( DFT ), and histogram of oriented gradients ( HOG ) [8].”
Reliable object recognition system for cloud video data based on LDP features
Nayagam, M. G., & Ramar, K. (2019) · Computer Communications · doi:10.1016/j.comcom.2019.10.027 · Cited by 13
Content Based Image Retrieval Approach using Deep Learning
Abdel-Nabi, H., Al‐Naymat, G., & Awajan, A. (2019) · International Conference on New Trends in Computing Sciences (ICTCS) · doi:10.1109/ictcs.2019.8923042 · Cited by 14
IMAGE MOSAIC ALGORITHM BASED ON PCA-ORB FEATURE MATCHING
Zhu, J., Gong, C., Zhao, M. X., et al. (2020) · 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-w10-83-2020 · Cited by 13
Food recognition using neural network classifier and multiple hypotheses image segmentation
Minija, S. J., & Emmanuel, W. R. S. (2020) · The Imaging Science Journal · doi:10.1080/13682199.2020.1742416 · Cited by 13
“Moreover, SIFT [11] and SURF [12] feature descriptors are used for the detection of the local feature information.”
MethodOnline Monitoring for Neural Network Based Monocular Pedestrian Pose Estimation
Gupta, A. K., & Carlone, L. (2020) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294609 · Cited by 20
Mutual Information Based Feature Selection for Stereo Visual Odometry
Kottath, R., Poddar, S., Sardana, R., Bhondekar, A. P., & Karar, V. (2020) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-020-01206-z · Cited by 13
“With the introduction of SIFT (Scale Invariant Feature Transform) [16], several robust detector-descriptor schemes have been proposed in the literature, such as Speeded up Robust Features (SURF) [17], Oriented FAST and rotated BRIEF (ORB) [18].”
MethodVurchio, F., Orsini, F., Scorza, A., et al. (2020) · IEEE International Symposium on Medical Measurements and Applications (MeMeA) · doi:10.1109/memea49120.2020.9137249 · Cited by 13
A Feature Points Extraction Algorithm Based on Adaptive Information Entropy
Yin, D., Si-wei, Z., Wang, P., Lin, M., Song, H., Ke, F., & Luo, K. (2020) · IEEE Access · doi:10.1109/access.2020.3008457 · Cited by 12
“Herbert Bay, on the basis of the SIFT algorithm, improved it and realized Speed Up Robust Features (SURF) algoritm [12] which runs three times faster than SIFT; Murray and Klein proposed the Parallel Tracking And Mapping (PTAM) system.”
MethodJoshua Bapu, J., & Florinabel, D. J. (2020) · Earth Science Informatics · doi:10.1007/s12145-020-00486-1 · Cited by 13
“discussed in (Lowe 2004; Bay et al. 2006; Nyoungui et al. 2002; Baraldi and Parmiggiani 1995) that the various kind of target detection techniques with feature extraction and classification of the images.”
BackgroundAccurate Chronic Wound Area Measurement using Structure from Motion
Barbosa, F. M. C., de Carvalho, B. M., & Gomes, R. B. (2020) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms49503.2020.00047 · Cited by 13
3D Scene Geometry-Aware Constraint for Camera Localization with Deep Learning
Tian, M., Nie, Q., & Shen, H. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196940 · Cited by 18
DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction
Jin, J., Patil, A. G., Xiong, Z., & Zhang, H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58589-1_18 · Cited by 15
Lattice-Point Mutually Guided Ground-to-Aerial Feature Matching for Urban Scene Images
Zheng, X., Li, H., Xiong, H., et al. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3069222 · Cited by 13
“Its variants, such as speeded-up robust features (SURF) [18], affine SIFT (ASIFT) [19], and perspective SIFT (PSIFT) [20], also attempt to improve its speed or invariance to affine or perspective transformations.”
BackgroundOkuboyejo, D. A., & Olugbara, O. O. (2021) · Diagnostics · doi:10.3390/diagnostics11081366 · Cited by 14
DGFNet: Dual Gate Fusion Network for Land Cover Classification in Very High-Resolution Images
Guo, Y., Wang, F., Xiang, Y., & You, H. (2021) · Remote Sensing · doi:10.3390/rs13183755 · Cited by 14
Gradient-Aligned convolution neural network
Hao, Y., Hu, P., Li, S., Udupa, J. K., Tong, Y., & Li, H. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108354 · Cited by 17
SymbioLCD: Ensemble-Based Loop Closure Detection using CNN-Extracted Objects and Visual Bag-of-Words
Kim, J. J. Y., Urschler, M., Riddle, P., & Wicker, J. S. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636622 · Cited by 18
Palanisamy, P. A., Elara, M. R., Semwal, A., et al. (2021) · Sensors · doi:10.3390/s21217287 · Cited by 13
Traffic Sign Recognition Based on CNN and Twin Support Vector Machine Hybrid Model
Sun, Y., & Chen, L. (2021) · Journal of Applied Mathematics and Physics · doi:10.4236/jamp.2021.912204 · Cited by 13
Recent Approaches for Image Colorization
Pierre, F., & Aujol, J. (2021) · Springer eBooks · doi:10.1007/978-3-030-03009-4_55-1 · Cited by 14
Sunitha, K., Krishna, A., & Prasad, B. G. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03207-x · Cited by 15
Data Acquisition and Preparation for Dual-Reference Deep Learning of Image Super-Resolution
Guo, Y., Wu, X., & Shu, X. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3184819 · Cited by 13
An, S.-Y., & Kim, J.-Y. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3151154 · Cited by 14
“The keypoints and their descriptors can be extracted using SIFT [8] and SURF [9] which are representative methods in the field of visual object recognition.”
MethodAutomated and Miniaturized Pico-Liter Metabolite Extraction System for Single-Cell Mass Spectrometry
Zhao, P., Cheng, S., Feng, Y., et al. (2022) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2022.3194255 · Cited by 13
The applications of machine vision in raw material and production of wood products
Wang, Q., Zhan, X., Wu, Z., Liu, X., & Feng, X. (2022) · BioResources · doi:10.15376/biores.17.3.wang · Cited by 16
Semantic Correlation Transfer for Heterogeneous Domain Adaptation
Zhao, Y., Li, S., Zhang, R., Liu, C. H., Cao, W., Wang, X., & Tian, S. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3199619 · Cited by 17
“D SURF features [67], 4096-”
A survey for image based methods in construction: from images to digital twins
Koulalis, I., Dourvas, N. I., Triantafyllidis, T., Ioannidis, K., Vrochidis, S., & Kompatsiaris, I. Y. (2022) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1145/3549555.3549594 · Cited by 15
“During the first years object detection methods used feature extraction, where the researchers had to define manually which features describe better specific classes of objects [6, 33].”
MethodMulti-Neighborhood Guided Kendall Rank Correlation Coefficient for Feature Matching
Chen, J., Yang, M., Gong, W., & Yu, Y. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3217410 · Cited by 17
AutoMatch: Leveraging Traffic Camera to Improve Perception and Localization of Autonomous Vehicles
He, Y., Ma, L., Cui, J., Yan, Z., Xing, G., Wang, S., Hu, Q., & Chen, P. (2022) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3560905.3568519 · Cited by 25
On Making SIFT Features Affine Covariant
Baráth, D. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01802-0 · Cited by 13
“2005) fromorientationand scale-covariant ones obtained by, for instance, SIFT (Lowe 1999) or SURF (Bay et al. 2006) detectors.”
MethodSupervised Scale-Invariant Segmentation (and Detection)
Li, Y., Tax, D. M. J., & Loog, M. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-24785-9_30 · Cited by 13
A Robust Mosaicing Method with Super-Resolution for Optical Medical Images
Hu, M., Penney, G., Rueckert, D., Edwards, P., Bello, F., Figl, M., Casula, R., Cen, Y., Liu, J., Miao, Z., et al. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15699-1_39 · Cited by 12
“A common solution to this problem is to build a 2D mosaicing image and a lot of research work has been done in the medical imaging community [1-8].”
BackgroundMethodAutomatic Coin Classification and Identification
Huber-Mörk, R., Nlle, M., Rubik, M., Hdlmoser, M., Kampel, M., & Zambanini, S. (2012) · InTech eBooks · doi:10.5772/35795 · Cited by 15
Fusion of face and periocular information for improved authentication on smartphones
Raja, K. B., Ramachandra, R., Stokkenes, M., & Busch, C. (2015) · Cited by 18
Sidiropoulos, P., Mezaris, V., & Kompatsiaris, I. Y. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2302554 · Cited by 13
Communication Technologies for People With Sensory Disabilities
Ladner, R. E. (2012) · Proceedings of the IEEE · doi:10.1109/jproc.2011.2182090 · Cited by 18
A unified framework for concurrent detection of anatomical landmarks for medical image understanding
Nemoto, M., Masutani, Y., Hanaoka, S., et al. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.878327 · Cited by 13
“In recent years, SIFT (Scale Invariant Feature Transform) [8] and SURF (Speeded-Up Robust Features) [9] have received more attention in that research field.”
BackgroundMethodChowdhury, M., & Kundu, M. K. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2252-3 · Cited by 14
Camera motion estimation for 3-D structure reconstruction of moving objects
Chwa, D., Dani, A. P., Kim, H., et al. (2012) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2012.6377997 · Cited by 13
“It is necessary to know the point correspondences between consecutive camera images, which can be computed using the existing feature tracking techniques [8]-[10].”
MethodBB-Homography: Joint Binary Features and Bipartite Graph Matching for Homography Estimation
Liu, S., Wang, H., Wei, Y., & Pan, C. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2339591 · Cited by 14
“Unlike SIFT or SURF, binary descriptor is a string of 0–1 codes; therefore, extracting and matching the descriptor only involves fast bitwise operations.”
BackgroundInfluentialTamper detection for active surveillance systems
Tsesmelis, T., Christensen, L., Fihl, P., & Moeslund, T. B. (2013) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2013.6636616 · Cited by 13
“In the proposed system we apply SURF [2] to detect key points (f1).”
MethodFeedback-based gameplay metrics: measuring player experience via automatic visual analysis
Marczak, R., van Vught, J., Schott, G. R., & Nacke, L. E. (2012) · Australasian Conference On Interactive Entertainment · doi:10.1145/2336727.2336733 · Cited by 24
Outdoor augmented reality tracking using 3D city models and game engine
Li, J., & Fan, X. (2014) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2014.7003758 · Cited by 13
“SURF (Speeded Up Robust Features) , which is a performance scale- and rotation-invariant interest point detector and descriptor [6], is adopted for finding corresponding points between the video frame and the rendered 3D model in the game engine on a frame by frame basis.”
Method3D visual SLAM for an assistive robot in indoor environments using RGB-D cameras
Meng, L., de Silva, C. W., & Zhang, J. (2014) · International Conference on Computer Science & Education (ICCSE) · doi:10.1109/iccse.2014.6926426 · Cited by 13
Keypoint-Based Analysis of Sonar Images: Application to Seabed Recognition
Nguyen, H.-G., Fablet, R., Ehrhold, A., & Boucher, J. (2011) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2011.2165848 · Cited by 15
A spherical representation for efficient visual loop closing
Chapoulie, A., Rives, P., & Filliat, D. (2011) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2011.6130261 · Cited by 20
“Detectors/descriptors like SIFT [19] or SURF [15] present very good results in terms of robustness; i.”
BackgroundRobot robust object recognition based on fast SURF feature matching
Du, M., Wang, J., Li, J., et al. (2013) · Chinese Automation Congress · doi:10.1109/cac.2013.6775802 · Cited by 13
“The results of Bay’s article suggested that the number of interest point rapidly decayed with the increase of scale, and the interest points concentrated in the first 8 layers[4], as shown in Figure 1.”
BackgroundMethodPerspective correction for improved visual registration using natural features.
Clark, A., Green, R. D., & Grant, R. N. (2008) · doi:10.1109/ivcnz.2008.4762073 · Cited by 13
“The two most popular natural feature registration algorithms, SIFT and SURF, were tested to examine the effect of varying algorithms on the success of the perspective correction technique.”
MethodInfluentialAn analysis of scale-space sampling in SIFT
Rey-Otero, I., Morel, J., & Delbracio, M. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025982 · Cited by 13
Adaptive iterative closest keypoint
Ekekrantz, J., Pronobis, A., Folkesson, J. B., & Jensfelt, P. (2013) · European Conference on Mobile Robots · doi:10.1109/ecmr.2013.6698824 · Cited by 13
“The algorithm tends to converge well after the fifth iteration using SURF keypoints given a suitable α value as is apparent in fig.”
MethodInfluentialRemote Sensing Image Automatic Registration on Multi-scale Harris-Laplacian
Weixing, W., Ting, C., Liu, S., et al. (2015) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-014-0432-2 · Cited by 13
Cratering studies in Polyvinylidene Fluoride (PVDF) thin films
Shu, A., Bugiel, S., Grün, E., et al. (2013) · Planetary and Space Science · doi:10.1016/j.pss.2013.05.001 · Cited by 13
Interactive ads recommendation with contextual search on product topic space
Wang, J., Wang, B., Duan, L., et al. (2011) · Multimedia Tools and Applications · doi:10.1007/s11042-011-0866-2 · Cited by 13
Contour-based iterative pose estimation of 3D rigid object
Leng, D., & Sun, W. (2011) · IET Computer Vision · doi:10.1049/iet-cvi.2010.0098 · Cited by 13
Zhao, F., Huang, Q., Wang, H., & Gao, W. (2010) · EURASIP Journal on Advances in Signal Processing · doi:10.1155/2010/410628 · Cited by 13
Active 3D shape acquisition using smartphones
Won, J.-H., Lee, M. H., & Park, I. K. (2012) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2012.6239196 · Cited by 13
Speech control of a teleoperated mobile humanoid robot
Wang, B., Li, Z., & Ding, N. (2011) · IEEE International Conference on Automation and Logistics (ICAL) · doi:10.1109/ical.2011.6024739 · Cited by 13
Food Image Recognition by Using Bag-of-SURF Features and HOG Features
Ahmed, A., & Ozeki, T. (2015) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/2814940.2814968 · Cited by 13
Li, Y., & Davis, C. H. (2010) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2010.2062490 · Cited by 13
A Design of an Optimized ORB Accelerator for Real-Time Feature Detection
Lee, K.-Y. (2014) · International Journal of Control and Automation · doi:10.14257/ijca.2014.7.3.20 · Cited by 13
“In this paper, we propose a method to design an optimized ORB algorithm [2] that fits the embedded environment instead of SIFT and SURF algorithms.”
MethodInfluentialWildlife@Home: Combining Crowd Sourcing and Volunteer Computing to Analyze Avian Nesting Video
Desell, T., Bergman, R., Goehner, K., Marsh, R. A., VanderClute, R., & Ellis‐Felege, S. N. (2013) · IEEE International Conference on eScience · doi:10.1109/escience.2013.50 · Cited by 16
Stereo Vision Obstacle Detection Based on Scale Invariant Feature Transform Algorithm
Pollini, L., Greco, F., Mati, R., et al. (2007) · AIAA Guidance, Navigation, and Control Conference and Exhibit · doi:10.2514/6.2007-6612 · Cited by 13
An Adaptive Image-stitching Algorithm for an Underwater Monitoring System
Hengyu, L., Luo, J. T., Huang, C., et al. (2014) · International Journal of Advanced Robotic Systems · doi:10.5772/58988 · Cited by 13
“In the view of current study, the phase correlation method [5-7] is the most popular algorithm in the field of the frequency power spectrum algorithm while the SIFT (scale invariant feature transform) [8], FAST (features from accelerated segment test) [9] and ORB (oriented FAST and rotated BRIEF) [10] and SURF [11-13]…”
MethodEvidential combination of SVM road obstacle classifiers in visible and far infrared images
Besbes, B., Ammar, S., Kessentini, Y., et al. (2011) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2011.5940529 · Cited by 13
Image feature extraction for mobile processors
Murphy, M., Keutzer, K., & Wang, H. (2009) · IEEE International Symposium on Workload Characterization · doi:10.1109/iiswc.2009.5306789 · Cited by 12
The feature and spatial covariant kernel: adding implicit spatial constraints to histogram
Liu, X., Wang, D., Li, J., & Zhang, B. (2007) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1282280.1282361 · Cited by 13
Diminished Reality for Hiding a Pedestrian using Hand-Held Camera
Hasegawa, K., & Saitô, H. (2015) · doi:10.1109/ismarw.2015.18 · Cited by 13
Attributed Relational SIFT-Based Regions Graph for Art Painting Retrieval
Manzo, M., & Petrosino, A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41181-6_84 · Cited by 11
Integrated visual information for maritime surveillance
Bloisi, D. D., Iocchi, L., Nardi, D., & Fiorini, M. (2015) · Institution of Engineering and Technology eBooks · doi:10.1049/pbtr001e_ch11 · Cited by 13
Robust visual odometry to irregular illumination changes with RGB-D camera
Kim, P., Lim, H., & Kim, H. J. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353893 · Cited by 15
“It can be achieved by utilizing the blob detector like LoG, DoG, SURF [26] and the plane model based RANSAC algorithm [28].”
MethodHuman Action Recognition Using Multi-Velocity STIPs and Motion Energy Orientation Histogram *
Li, C., Su, B., Wang, J., Wang, H., & Zhang, Q. (2014) · Journal of information science and engineering · doi:10.6688/jise.2014.30.2.2 · Cited by 11
Ground Vehicle Detection and Classification by an Unmanned Aerial Vehicle
Montanari, R., Tozadore, D. C., Fraccaroli, E. S., et al. (2015) · Latin American Robotics Symposium and Brazilian Symposium on Robotics (LARS-SBR) · doi:10.1109/lars-sbr.2015.64 · Cited by 13
Monocular Vision based Navigation in GPS-Denied Riverine Environments
Yang, J., Rao, D., Chung, S., et al. (2011) · AIAA Infotech@Aerospace Conference · doi:10.2514/6.2011-1403 · Cited by 13
Video Key Frame Detection Based on SURF Algorithm
Grycuk, R., Knop, M., & Mandal, S. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19324-3_50 · Cited by 13
Video-Story Composition via Plot Analysis
Choi, J., Oh, T.-H., & Kweon, I. S. (2016) · 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.2016.340 · Cited by 13
ARTAR-Artistic Augmented Reality
Nithin, G., & Bhooshan, R. S. (2016) · Procedia Technology · doi:10.1016/j.protcy.2016.05.183 · Cited by 13
“SURF (Speed Up Robust Features) algorithm [2] is an approximation of SIFT in which DoG is approximated to box filters.”
MethodOnline Background-Subtraction with Motion Compensation for Freely Moving Camera
Kurnianggoro, L., Wahyono, W., Yu, Y., et al. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-42294-7_51 · Cited by 13
Object tracking using improved Camshift with SURF method
Li, J., Ji, Z., Zhou, Z., et al. (2011) · doi:10.1109/ossc.2011.6184709 · Cited by 13
Improving SURF Based Copy-Move Forgery Detection Using Super Resolution
Al-Hammadi, M. M., & Emmanuel, S. (2016) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2016.0075 · Cited by 14
“Integral image can calculate the sum of intensities inside any rectangular region in time independent of its size [1].”
BackgroundMethodMulti target tracking on aerial videos
Máttyus, G., Benedek, C., & Szirányi, T. (2010) · Cited by 13
Fiber Defect Detection of Inhomogeneous Voluminous Textiles
Siegmund, D., Samartzidis, T., Fu, B., Braun, A., & Kuijper, A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59226-8_27 · Cited by 15
Copy and Paste: Temporally Consistent Stereoscopic Video Blending
Wang, Z., Chen, X., & Zou, D. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2706197 · Cited by 13
“In this experiment, we compare SIFT flow with SURF matching [39], FREAK matching [40] and block matching methods (Simply extracts the square neighborhood around a pixel location as feature.”
Methoddos Santos, C. G. R., de Araujo, T. D. O., Morais, J. M. D., & Meiguins, B. S. (2017) · International Journal of Multimedia and Ubiquitous Engineering · doi:10.14257/ijmue.2017.12.4.10 · Cited by 13
“The AKAZE algorithm, as the previously mentioned algorithms, has faster computing than the established SURF and SIFT and is also faster than its predecessor KAZE [15], and maintains a good precision in variations of viewpoint and noise in the image.”
MethodInfluentialAir-SSLAM: A Visual Stereo Indoor SLAM for Aerial Quadrotors
Araujo, P., Miranda, R., do Carmo, D. S., Alves, R., & de Oliveira, L. R. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2730883 · Cited by 13
“…region around the keypoints, providing feature vectors, which are compared across the stereo images; rBRIEF is a binary-based feature descriptor, which runs faster than the scale-invariant feature transform (SIFT) [17] and speeded up robust features (SURF) [18], keeping good rotation invariance.”
BackgroundRegistration of 3D scan data using image reprojection
Byun, S., Jung, K., Im, S., & Chang, M. (2017) · International Journal of Precision Engineering and Manufacturing · doi:10.1007/s12541-017-0143-z · Cited by 13
“Most of these use 2D feature point matching algorithms like Scale Invariant Feature Transform (SIFT)(23) or Speeded Up Robust Features (SURF).(24) A 2D feature point matching algorithm has less calculation complexity than a corresponding 3D algorithm, thus improving the speed of registration.”
MethodSidiropoulos, P., Müller, J., Watson, G., Michael, G., & Walter, S. H. G. (2017) · Planetary and Space Science · doi:10.1016/j.pss.2017.10.012 · Cited by 13
“…a large volume of multi-instrument images in one pass is the fact that the employed image matching techniques (Lowe, 2004), (Mount et al., 1999) (Bay et al., 2006), are the ones developed for a “generic” image type, i.e. they ignore the specific properties of high-resolution planetary images…”
Robotic hand grasping of objects classified by using support vector machine and bag of visual words
Ergene, M. C., & Durdu, A. (2017) · International Artificial Intelligence and Data Processing Symposium (IDAP) · doi:10.1109/idap.2017.8090228 · Cited by 14
A Secure Mobile Authentication Alternative to Biometrics
Azimpourkivi, M., Topkara, U., & Cărbunar, B. (2017) · Annual Computer Security Applications Conference · doi:10.1145/3134600.3134619 · Cited by 13
Simultaneous object detection and localization using convolutional neural networks
Ouadiay, F. Z., Bouftaih, H., Bouyakhf, E. H., & Himmi, M. M. (2018) · International Conference on Intelligent Systems and Computer Vision (ISCV) · doi:10.1109/isacv.2018.8354045 · Cited by 14
Schmid, B. J., & Adhami, R. R. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2859594 · Cited by 13
Real-Time Augmented Reality for Ear Surgery
Hussain, R., Lalande, A., Marroquin, R., Girum, K. B., Guigou, C., & Grayeli, A. B. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00937-3_38 · Cited by 18
Single crater-aided inertial navigation for autonomous asteroid landing
Meng, Y., Li, S., Wang, S., & Huang, X. (2018) · Advances in Space Research · doi:10.1016/j.asr.2018.09.035 · Cited by 13
LUIFT: LUminance Invariant Feature Transform
Diaz-Escobar, J., Kober, V. I., & Gonzalez-Fraga, J. A. (2018) · Mathematical Problems in Engineering · doi:10.1155/2018/3758102 · Cited by 13
“The SURF [11, 36] (Speed Up Robust Features) and the KAZE [12] descriptors are a couple of examples.”
MethodAn almost complete curvature scale space representation: Euclidean case
Benkhlifa, A., & Ghorbel, F. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.03.009 · Cited by 15
Liu, S., & Jiang, J. (2019) · Remote Sensing · doi:10.3390/rs11121400 · Cited by 13
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.