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








Verification
Claims the paper makes
0 Valid · 2 Not valid · 12 Not checked · 30 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The number of interest points found is on average very similar for all detectors.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 4 × 4 sub-region division solution provided the best results.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SURF outperformed the other descriptors for almost all the comparisons.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The SURF descriptor outperforms the other descriptors in a systematic and significant way, with sometimes more than 10% improvement in recall for the same level of precision.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in the results section, the performance is comparable to the one using the discretised and cropped Gaussians.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
8 more claims
Create a free account to see all 44 claims and every source verdict.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This transition marked a new era, where we moved beyond the classic approaches and task-specific feature engineering of earlier days [Lowe 2004; Bay et al. 2006; Rosten and Drummond 2006] towards models that could be trained once over large amounts of data, and then adapted for a broad variety of tasks, such as image recognition, object detection, and image segmentation [Krizhevsky et al. 2012; Sz”
From On the Opportunities and Risks of Foundation Models (2021) · cites this paper as Bay et al. 2006
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · cited 14×
“This PCA-SIFT yields a 36-dimensional descriptor which is fast for matching, but proved to be less distinctive than SIFT in a second comparative study by Mikolajczyk et al. [8] and slower feature computation reduces the effect of fast matching.”
BackgroundMethodResultInfluentialMarr, D., & Hildreth, E. (1980) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1980.0020 · Cited by 6,510
PCA-SIFT: a more distinctive representation for local image descriptors
Ke, Y., & Sukthankar, R. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.183 · Cited by 3,932
Robust wide-baseline stereo from maximally stable extremal regions
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.02.006 · Cited by 3,686
Scalable Recognition with a Vocabulary Tree
Nister, D., & Stewenius, H. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.264 · Cited by 3,579
Scale & Affine Invariant Interest Point Detectors
Mikolajczyk, K., & Schmid, C. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000027790.02288.f2 · Cited by 3,436
Cited by
Items 1,301–1,400 of 14,752
City brain: practice of large‐scale artificial intelligence in the real world
Zhang, J., Hua, X., Huang, J., Shen, X., Chen, J., Zhou, Q., Fu, Z., & Zhao, Y. (2019) · IET Smart Cities · doi:10.1049/iet-smc.2019.0034 · Cited by 55
“There have been various algorithms to detect and describe image local key-points, which is divided into two categories: hand-crafted methods [26, 27] and neural network methods [28, 29].”
MethodSelf-Supervised deep homography estimation with invertibility constraints
Wang, C., Wang, X., Bai, X. P., Liu, Y., & Zhou, J. W. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2019.09.021 · Cited by 54
Fast and incremental loop closure detection with deep features and proximity graphs
An, S., Zhu, H., Wei, D., Tsintotas, K. A., & Gasteratos, A. C. (2022) · Journal of Field Robotics · doi:10.1002/rob.22060 · Cited by 61
“This local feature extraction process is totally different from the traditional hand-crafted methods, such as SIFT [21] or SURF [22], which firstly detect keypoints and subsequently they describe them.”
MethodInfluentialOne-stage CNN detector-based benthonic organisms detection with limited training dataset
Chen, T., Wang, N., Wang, R., Zhao, H., & Zhang, G. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.08.014 · Cited by 54
A Bottom-Up Review of Image Analysis Methods for Suspicious Region Detection in Mammograms
Oza, P. R., Sharma, P., Patel, S., & Bruno, A. (2021) · Journal of Imaging · doi:10.3390/jimaging7090190 · Cited by 57
“Local keypoints and their corresponding descriptors, such as SIFT [64] and SURF [65], have been widely adopted over many computer vision topics [66].”
InfluentialGuetari, R., Ayari, H., & Sakly, H. (2023) · Knowledge and Information Systems · doi:10.1007/s10115-023-01894-7 · Cited by 79
“ComparedwithSIFTandSURF,thecomputationalcostofORBislessanditsmagnitude isfasterthanSURF.”
MethodInfluentialVehicle Detection Algorithms for Autonomous Driving: A Review
Liang, L., Ma, H., Zhao, L., Xie, X., Hua, C., Zhang, M., & Zhang, Y. (2024) · Sensors · doi:10.3390/s24103088 · Cited by 80
“Some other feature extraction methods are also frequently used for vehicle detection, such as a local binary pattern (LBP) [60], Gabor filters [61], and sped-up robust features (SURFs) [62].”
MethodA Probabilistic Framework for Tracking Deformable Soft Tissue in Minimally Invasive Surgery
Mountney, P., Lo, B. P. L., Thiemjarus, S., Stoyanov, D. V., & Guang, Z.-Y. (2007) · Springer eBooks · doi:10.1007/978-3-540-75759-7_5 · Cited by 55
“Detailed performance analysis has shown that for MIS images, the best performing individual descriptors are Spin, SIFT, SURF, DIH and GLOH.”
MethodOn 3-D Motion Estimation From Feature Tracks in 2-D FS Sonar Video
Negahdaripour, S. (2013) · IEEE Transactions on Robotics · doi:10.1109/tro.2013.2260952 · Cited by 54
Integrating Graph Partitioning and Matching for Trajectory Analysis in Video Surveillance
Lin, L., Lu, Y., Pan, Y., & Chen, X. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2211373 · Cited by 56
Gesture Recognition using Wearable Vision Sensors to Enhance Visitors' Museum Experiences
Baraldi, L., Paci, F., Serra, G., Benini, L., & Cucchiara, R. (2015) · IEEE Sensors Journal · doi:10.1109/jsen.2015.2411994 · Cited by 63
“between two consecutive frames is estimated running the RANSAC [23] algorithm on densely sampled features points: SURF [24] features and sample motion vector are extracted from the Farneback’s optical flow [25] to get dense matches between frames.”
MethodVideo stabilization with moving object detecting and tracking for aerial video surveillance
Walha, A., Wali, A., & Alimi, A. M. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-1928-z · Cited by 60
Barazzetti, L., & Scaioni, M. (2010) · Sensors · doi:10.3390/s100807469 · Cited by 53
A Comparison of Dense Region Detectors for Image Search and Fine-Grained Classification
İşcen, A., Tolias, G., Gosselin, P.-H., & Jeǵou, H. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2423557 · Cited by 56
“proaches aim at extracting distinctive and repeatable image parts, such as blobs and corners [29][35][31][6], offering covariance properties: the same regions should be detected under some geometrical transformations.”
BackgroundHierarchical Ensemble of Background Models for PTZ-Based Video Surveillance
Liu, N., Wu, H., & Lin, L. (2014) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2320493 · Cited by 56
Learning Visual Contexts for Image Annotation From Flickr Groups
Ulges, A., Worring, M., & Breuel, T. M. (2010) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2010.2101051 · Cited by 54
“In all experiments, images are represented by bag-of-visual-words features obtained from a dense sampling of patches and their description using SURF [2] (Corel-Small, Corel-Big, Flickr-Small) or DCT coefficients [41] (Corel-5K).”
Event Recognition in Photo Collections with a Stopwatch HMM
Bossard, L., Guillaumin, M., & Gool, L. V. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.151 · Cited by 59
“As visual features, we use densely sampled SURF [2] descriptors and code them into a Bag-of-Words representation using a vocabulary of 1024 words, which is then max pooled.”
MethodDriver head pose estimation using efficient descriptor fusion
Alioua, N., Amine, A., Rogozan, A., Bensrhair, A., & Rziza, M. (2016) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-016-0103-z · Cited by 58
Object detection and identification for blind people in video scene
Jabnoun, H., Benzarti, F., & Amiri, H. (2015) · International Conference on Intelligent Systems Design and Applications (ISDA) · doi:10.1109/isda.2015.7489256 · Cited by 55
“Each octave is computed by convolution between down sampled images with different Gaussian kernels The Difference of Gaussian is obtained from the difference of two adjacent scales that are separated by a factor of k [14].”
MethodFast and robust 3D feature extraction from sparse point clouds
Serafin, J., Olson, E., & Grisetti, G. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759604 · Cited by 61
Face Morphing Detection: An Approach Based on Image Degradation Analysis
Neubert, T. (2017) · International Workshop on Digital Watermarking · doi:10.1007/978-3-319-64185-0_8 · Cited by 50
“Other feature detectors, for example SIFT [13] or SURF [14], are more robust to the degradation based on JPEG compression and therefore not well suited for our purpose.”
MethodSparse Online Learning of Image Similarity
Gao, X., Hoi, S. C. H., Zhang, Y., Zhou, J., Wan, J., Chen, Z., Li, J., & Zhu, J. (2017) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3065950 · Cited by 54
“…2000], and local features, SIFT feature descriptors [Lowe 2004; Mikolajczyk and Schmid 2005; Quelhas et al. 2007] and SURF feature descriptors [Bay et al. 2006], as well as their Bag-of-Words (BoW) representations [Fergus et al. 2005; Wang et al. 2006; Bosch et al. 2007; Wu et al. 2010; Jegou…”
BackgroundVandaele, R., Aceto, J., Müller, M., Peronnet, F., Debat, V., Wang, C., Huang, C.-T., Jodogne, S., Martinive, P., Geurts, P., et al. (2018) · Scientific Reports · doi:10.1038/s41598-017-18993-5 · Cited by 52
“• SURF: each window is described by the extended SURF descriptor 27 , a descriptor previously proven to show robustness against rotations, scaling and noise.”
MethodWound area measurement with 3D transformation and smartphone images
Liu, C., Fan, X., Guo, Z., Mo, Z., Chang, E., & Xu, Y. L. (2019) · BMC Bioinformatics · doi:10.1186/s12859-019-3308-1 · Cited by 65
“Besides the SIFT method, researchers have also proposed some faster methods, such as principal component analysis scale-invariant feature transform (PCA-SIFT) [28], gradient location-orientation histogram (GLOH) [29], and speed up robust features (SURF) [30].”
MethodMulti-camera visual SLAM for off-road navigation
Yang, Y. M., Tang, D., Wang, D., Song, W., Wang, J., & Fu, M. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103505 · Cited by 57
A Traffic-Sign Detection Algorithm Based on Improved Sparse R-cnn
Cao, J., Zhang, J., & Jin, X. (2021) · IEEE Access · doi:10.1109/access.2021.3109606 · Cited by 65
Multiple Vehicles Detection and Tracking based on Scale-Invariant Feature Transform
Choi, J.-Y., Sung, K.-S., & Yang, Y.-K. (2007) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2007.4357684 · Cited by 57
Depth map guided triplet network for deepfake face detection
Liang, B., Wang, Z., Huang, B., Zou, Q., Wang, Q., & Liang, J. (2023) · Neural Networks · doi:10.1016/j.neunet.2022.11.031 · Cited by 54
Compact Video Description for Copy Detection with Precise Temporal Alignment
Douze, M., Jégou, H., Schmid, C., & Pérez, P. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15549-9_38 · Cited by 53
BSIFT: Toward Data-Independent Codebook for Large Scale Image Search
Zhou, W., Li, H., Hong, R., Lu, Y., & Tian, Q. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2389624 · Cited by 57
“As a variation, SURF [25] is demonstrated with comparable performance but better efficiency.”
Comprehensive Feature-Based Robust Video Fingerprinting Using Tensor Model
Nie, X., Yin, Y., Sun, J., Liu, J., & Cui, C. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2629758 · Cited by 56
SDC – Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks
Schuster, R., Wasenmüller, O., Unger, C., & Stricker, D. (2019) · 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.2019.00266 · Cited by 60
“Robustness is also a problem for faster hand-crafted feature extractors like SURF [5] and DAISY [38].”
BackgroundDual-Camera Super-Resolution with Aligned Attention Modules
Wang, T., Xie, J., Sun, W., Yan, Q., & Chen, Q. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00201 · Cited by 75
Soft Exemplar Highlighting for Cross-View Image-Based Geo-Localization
Guo, Y., Choi, M., Li, K., Boussaïd, F., & Bennamoun, M. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3152046 · Cited by 72
Barazzetti, L., Forlani, G., Fabio Remondino, A., Roncella, R., & Scaioni, M. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.890116 · Cited by 51
Alonso‐Fernandez, F., & Bigün, J. (2015) · IET Biometrics · doi:10.1049/iet-bmt.2014.0038 · Cited by 54
Sloop: A pattern retrieval engine for individual animal identification
Duyck, J., Finn, C., Hutcheon, A., Vera, P., Salas, J., & Ravela, S. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.07.017 · Cited by 60
Following human guidance to cooperatively carry a large object
Stückler, J., & Behnke, S. (2011) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2011.6100917 · Cited by 64
Object classification in 3D baggage security computed tomography imagery using visual codebooks
Flitton, G. T., Mouton, A., & Breckon, T. P. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.02.006 · Cited by 51
“[30] present a BoW model using the Speeded-Up Robust Features (SURF) [31] and a Support Vector Machine (SVM) [32] classifier for automated object recognition within 2D X-ray baggage imagery.”
MethodLim, J., Frahm, J.-M., & Pollefeys, M. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995511 · Cited by 53
A comparison of feature descriptors for visual SLAM
Hartmann, J., Klüssendorff, J. H., & Maehle, E. (2013) · European Conference on Mobile Robots · doi:10.1109/ecmr.2013.6698820 · Cited by 59
“The Speeded-Up Robust Features (SURF, [5]) is largely inspired by SIFT and specifically aimed to improve the computation time.”
MethodDetection of interest points in turbid underwater images
García, R., & Gracias, N. (2011) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans-spain.2011.6003605 · Cited by 55
Content based image retrieval with LIRe
Lux, M. (2011) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2072298.2072432 · Cited by 57
Alcantarilla, P. F., Bergasa, L. M., & Davison, A. J. (2012) · Image and Vision Computing · doi:10.1016/j.imavis.2012.11.001 · Cited by 60
Comparison of local image descriptors for full 6 degree-of-freedom pose estimation
Vikstén, F., Forssén, P.-E., Johansson, B., & Moe, A. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152360 · Cited by 53
A review of quadruped robots and environment perception
Meng, X., Wang, S., Cao, Z., & Zhang, L. (2016) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2016.7554355 · Cited by 58
Cheng, H.-Y., & Lin, C.-L. (2017) · Atmospheric measurement techniques · doi:10.5194/amt-10-199-2017 · Cited by 53
Comparison of photo‐matching algorithms commonly used for photographic capture–recapture studies
Matthé, M., Sannolo, M., Winiarski, K. J., der Sluijs, A. S., Goedbloed, D. J., Steinfartz, S., & Stachow, U. (2017) · Ecology and Evolution · doi:10.1002/ece3.3140 · Cited by 58
Automated detection of retinal health using PHOG and SURF features extracted from fundus images
Koh, J. E. W., Ng, E. Y. K., Bhandary, S. V., et al. (2017) · Applied Intelligence · doi:10.1007/s10489-017-1048-3 · Cited by 53
Mechanical assembly assistance using marker-less augmented reality system
Wang, Y., Zhang, S., Yang, S., He, W., & Bai, X. (2018) · Assembly Automation · doi:10.1108/aa-11-2016-152 · Cited by 59
“To improve its tracking performance, there have been numerous feature descriptor algorithms used including scale invariant feature transform (SIFT) (Lowe, 2004), speed-up robust feature (SURF) (Bay et al., 2006), binary robust invariant scalable keypoints (BRISK) (Leutenegger et al., 2011) and ORB (Rublee et al., 2011…”
MethodVehicle classification based on images from visible light and thermal cameras
Nam, Y., & Nam, Y.-C. (2018) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-018-0245-2 · Cited by 55
Discrete Curvature Representations for Noise Robust Image Corner Detection
Zhang, W., Sun, C., Breckon, T. P., & AlShammari, N. K. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2910655 · Cited by 56
Deep Sclera Segmentation and Recognition
Rot, P., Vitek, M., Grm, K., Emeršič, Ž., Peer, P., & Štruc, V. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-27731-4_13 · Cited by 69
“For the latter, we compute SIFT [80], SURF [81] and ORB [82] descriptors using their corresponding keypoint detectors.”
MethodA review on food recognition technology for health applications
Allegra, D., Battiato, S., Ortis, A., Urso, S., & Polosa, R. (2020) · Health Psychology Research · doi:10.4081/hpr.2020.9297 · Cited by 64
Long‐range rover localization by matching LIDAR scans to orbital elevation maps
Carle, P. J. F., Furgale, P., & Barfoot, T. D. (2010) · Journal of Field Robotics · doi:10.1002/rob.20336 · Cited by 62
Scalable Feature Matching by Dual Cascaded Scalar Quantization for Image Retrieval
Zhou, W., Yang, M., Wang, X., Li, H., Lin, Y., & Tian, Q. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2430329 · Cited by 51
“In many algorithms [1], [2], [3], [4], [5], [6], [7], invariant local features [8], [9] are exploited to represent images and the bag-of-visual-words (BoW) model [1] has been popularly adopted to represent an image as a group of visual words.”
A novel point cloud registration using 2D image features
Lin, C.-C., Tai, Y.-C., Lee, J.-J., & Chen, Y. (2017) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-016-0435-y · Cited by 57
“[26, 27] is a descriptor of feature points of images.”
BackgroundMultiRes-NetVLAD: Augmenting Place Recognition Training With Low-Resolution Imagery
Khaliq, A., Milford, M. J., & Garg, S. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3147257 · Cited by 57
Rafiei, M., Raitoharju, J., & Iosifidis, A. (2023) · IEEE Access · doi:10.1109/access.2023.3234187 · Cited by 66
Wang, G., Chen, H., Chen, L., Zhuang, Y., Zhang, S., Zhang, T., Dong, H., & Gao, P. (2023) · Remote Sensing · doi:10.3390/rs15071773 · Cited by 61
Glaucoma diagnosis in the era of deep learning: A survey
Ashtari-Majlan, M., Dehshibi, M. M., & Masip, D. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124888 · Cited by 69
Towards relative continuous-time SLAM
Anderson, S., & Barfoot, T. D. (2013) · 2013 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2013.6630700 · Cited by 51
Towards a robust affect recognition: Automatic facial expression recognition in 3D faces
Azazi, A., Lutfi, S. L., Venkat, I., & Fernández-Martínez, F. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.10.042 · Cited by 59
“SURF (Bay et al., 2006) is a feature extraction technique that returns the most robust keypoints and their features.”
MethodVisual terrain classification for selecting energy efficient gaits of a hexapod robot
Zenker, S., Aksoy, E. E., Goldschmidt, D., Wörgötter, F., & Manoonpong, P. (2013) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2013.6584154 · Cited by 52
“Here, we apply two well known feature descriptors: Scale Invariant Feature Transform (SIFT) [9] and Speed Up Robust Feature (SURF) [10], details of which are provided below.”
MethodMonitoring shoreline change on Djerba Island using GIS and multi-temporal satellite data
Bouchahma, M., & Yan, W. (2013) · Arabian Journal of Geosciences · doi:10.1007/s12517-013-1052-9 · Cited by 52
“SURF presented by Herbert et al. 2008.”
Robust place recognition with stereo cameras
Cadena, C., Gálvez-López, D., Ramos, F., Tardós, J. D., & Neira, J. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5650234 · Cited by 54
“For this purpose, we use SURF features [14].”
MethodOnline loop closure for real-time interactive 3D scanning
Weise, T., Wismer, T., Leibe, B., & Gool, L. V. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2010.11.023 · Cited by 54
“To a certain extent the extracted SURF feature descriptors are viewpoint invariant [3].”
BackgroundMethodSelf-citationFPGA-Based Parallel Hardware Architecture for Real-Time Image Classification
Qasaimeh, M., Sagahyroon, A. A., & Shanableh, T. (2015) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2015.2424077 · Cited by 55
“To address the complexity problem, a number of simplified versions of the SIFT algorithm have been proposed, such as SURF[5]and the fastSIFT[6]algorithms.”
MethodInfluentialRobust Feature Matching with Alternate Hough and Inverted Hough Transforms
Chen, H., Lin, Y., & Chen, B. (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.2013.356 · Cited by 52
“, [3, 4, 6, 21], have brought about significant progress in this area.”
BackgroundEfficient algorithms for subwindow search in object detection and localization
An, S., Peursum, P., Liu, W., & Venkatesh, S. (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.2009.5206822 · Cited by 55
Pedestrian Counting with Occlusion Handling Using Stereo Thermal Cameras
Kristoffersen, M. S., Dueholm, J. V., Gade, R., & Moeslund, T. B. (2016) · Sensors · doi:10.3390/s16010062 · Cited by 58
Graph-Based Place Recognition in Image Sequences with CNN Features
Zhang, X., Wang, L., Zhao, Y. C., & Su, Y. L. (2018) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-018-0917-2 · Cited by 56
“First, the features used, such as SIFT [27], SURF [4] and BRIEF [7], are empirically designed, which could be vulnerable to occlusion and illumination variation.”
MethodA novel measurement model based on abBRIEF for global localization of a UAV over satellite images
Mantelli, M., Pittol, D., Neuland, R., Ribacki, A., Maffei, R. D. Q., Jorge, V. A. M., Prestes, E., & Kolberg, M. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.12.006 · Cited by 57
MagicHand: Interact with IoT Devices in Augmented Reality Environment
Sun, Y., Armengol-Urpi, A., Kantareddy, S. N. R., Siegel, J. E., & Sarma, S. E. (2019) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr.2019.8798053 · Cited by 59
“A key challenge in AR is the design of accurate object detection [11] [12] and 3D pose estimation algorithms [13] [14].”
BackgroundAutonomous Target Tracking of UAV Using High-Speed Visual Feedback
Chuang, H.-M., He, D., & Namiki, A. (2019) · Applied Sciences · doi:10.3390/app9214552 · Cited by 51
Discriminative distribution alignment: A unified framework for heterogeneous domain adaptation
Yao, Y., Zhang, Y., Li, X., & Ye, Y. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2019.107165 · Cited by 49
Monocular Localization with Vector HD Map (MLVHM): A Low-Cost Method for Commercial IVs
Xiao, Z., Yang, D., Wen, T., Jiang, K., & Yan, R. (2020) · Sensors · doi:10.3390/s20071870 · Cited by 64
“Among them, there are many works based on local features, and many of them have made great basic contributions to robot positioning and mapping, such as Scale-Invariant Feature Transform (SIFT) [19,20], Speeded Up Robust Features (SURF) [21] and ORB [22,23].”
Computer Aided Breast Cancer Detection Using Ensembling of Texture and Statistical Image Features
Roy, S. D., Das, S., Kar, D., Schwenker, F., & Sarkar, R. (2021) · Sensors · doi:10.3390/s21113628 · Cited by 62
“The accuracy of texture features, such as Scale Invariant Feature Transform (SIFT) [3], SURF [4], Oriented FAST and rotated BRIEF (ORB) [5] and Gray Level Co-Occurrence Matrix (GLCM), as well as statistical features, such as Haralick features [6] are computed using various standard ML algorithms, such as Random Forest…”
MethodFeature based person detection beyond the visible spectrum
Jüngling, K., & Arens, M. (2009) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2009.5204085 · Cited by 61
Toward Real-World Single Image Super-Resolution: A New Benchmark and A New ModelPreprint
Cai, J., Zeng, H., Yong, H., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.00523 · Cited by 52
Inertial sensor-aligned visual feature descriptors
Kurz, D., & Benhimane, S. (2011) · doi:10.1109/cvpr.2011.5995339 · Cited by 52
“Bay et al. [2] showed that omitting the spatial normalization for Upright-SURF, outperforms regular SURF descriptors in terms of discriminative power while at the same time, the user is forced to keep the camera in an upright orientation which limits the field of possible applications.”
MethodInfluentialMining Compact Bag-of-Patterns for Low Bit Rate Mobile Visual Search
Ji, R., Duan, L., Chen, J., Huang, T., & Gao, W. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2324291 · Cited by 51
“To this end, local descriptors in the literature like SIFT [37], SURF [38] or PCA-SIFT [39] are “over sized”.”
MethodAPIBot: Question answering bot for API documentation
Tian, Y., Thung, F., Sharma, A. B., & Lo, D. (2017) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase.2017.8115628 · Cited by 63
A novel system of SSVEP-based human–robot coordination
Han, X., Lin, K. C., Gao, S., & Gao, X. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aae1ba · Cited by 54
“Details on the detector and descriptor of SURF were followed by the literature (Bay et al 2006).”
MethodProbabilistic Appearance-Based Place Recognition Through Bag of Tracked Words
Tsintotas, K. A., Bampis, L., & Gasteratos, A. C. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2897151 · Cited by 50
Convolutional neural network architecture for geometric matching
Rocco, I., Arandjelović, R., & Šivic, J. (2017) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.48550/arxiv.1703.05593 · Cited by 51
Secure video retrieval using image query on an untrusted cloud
Yan, H., Chen, M., Hu, L. F., & Jia, C. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106782 · Cited by 53
A scalable and modular automated pipeline for stitching of large electron microscopy datasets
Mahalingam, G., Torres, R., Kapner, D., Trautman, E. T., Fliss, T. P., Seshamani, S., Perlman, E., Young, R., Kinn, S., Buchanan, J., et al. (2022) · eLife · doi:10.7554/elife.76534 · Cited by 53
Chen, L., Huang, Y., Dong, J., Xu, Q., Kwong, S., Lu, H., Lu, H., & Li, C. (2025) · ACM Computing Surveys · doi:10.1145/3759243 · Cited by 120
GNSS integration with vision-based navigation for low GNSS visibility conditions
Won, D. H., Lee, E., Heo, M.-B., Sung, S., Lee, J., & Lee, Y. J. (2013) · GPS Solutions · doi:10.1007/s10291-013-0318-8 · Cited by 53
Fast image matching based-on improved SURF algorithm
Huijuan, Z., & Qiong, H. (2011) · International Conference on Electronics, Communications and Control · doi:10.1109/icecc.2011.6066546 · Cited by 53
“In order to implement real-time match on computer, we choose the fast feature-based algorithm SURF [4].”
MethodMulti-spectral Satellite Image Registration Using Scale-Restricted SURF
Teke, M., & Temizel, A. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.565 · Cited by 52
Towards low bit rate mobile visual search with multiple-channel coding
Ji, R., Duan, L., Chen, J., Yao, H., Rui, Y., Chang, S., & Gao, W. (2011) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2072298.2072372 · Cited by 50
Visually bootstrapped generalized ICP
Pandey, G., Savarese, S., McBride, J. R., & Eustice, R. M. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980322 · Cited by 54
Histogram-based interest point detectors
Lee, W.-T., & Chen, H.-T. (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.2009.5206521 · Cited by 53
“Assume that the discrete quantity has L levels (bins) in the interval [1 , L ] .”
BackgroundMethodLothe, P., Bourgeois, S., Dekeyser, F., Royer, E., & Dhome, M. (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.2009.5206662 · Cited by 52
Towards a more effective method for analyzing mobile eye-tracking data
Brône, G., Oben, B., & Goedemé, T. (2011) · doi:10.1145/2029956.2029971 · Cited by 51
Deceiving faces: When plastic surgery challenges face recognition
Nappi, M., Ricciardi, S., & Massimo Tistarelli, A. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.08.012 · Cited by 51
Compositional Model-Based Sketch Generator in Facial Entertainment
Zhang, M., Li, J., Wang, N., & Gao, X. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2664499 · Cited by 54
“In light of the speed up robust feature (SURF) [34] describing photometric differences with the spatial distribution of gradient information, we propose a feature, namely, QSURF.”
BackgroundMokatren, M., Kuflik, T., & Shimshoni, I. (2017) · Future Generation Computer Systems · doi:10.1016/j.future.2017.07.007 · Cited by 56
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.