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 8,001–8,100 of 14,752
Performance Analysis of Vehicle Detection Algorithm in Aerial Traffic Videos
Liu, S., Liu, H., Shi, W., et al. (2019) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv47840.2019.00018 · Cited by 4
“For ViBe, to eliminate the impact of video jitter as far as possible, we used SURF [2] to register the image.”
MethodHandwritten Text Recognition Using Reconstructed Pen Trace with Medial Representation
Arseev, S., & Mestetsky, L. (2020) · International Conference on Information Technology and Nanotechnology (ITNT) · doi:10.1109/itnt49337.2020.9253330 · Cited by 4
“Classic image recognition methods encompass a wide variety of descriptors, such as LBP [2], SIFT [3], SURF [4], HOG [5] and others.”
BackgroundA Multi‐Person Selfie System via Augmented Reality
Jie, L., & Yang, C. (2020) · Computer Graphics Forum · doi:10.1111/cgf.14167 · Cited by 4
“Speeded Up Robust Feature , or SURF for short, proposed by Bay et al. [BTVG06], denotes another effort to find features, where SURF can be shown to be easier or faster to compute and is often more robust compared with SIFT.”
ResultRobust tracking of moving objects using thermal camera and speeded up robust features descriptor
Vlahović, N., & Djurovic, Z. M. (2020) · International Journal of Adaptive Control and Signal Processing · doi:10.1002/acs.3212 · Cited by 4
“Descriptor extraction consists of forming a square region centered around the point of interest, whose orientation was computed in the previous step.”
BackgroundMethodInfluentialBone Age Assessment based on SuperPoint Features
Miao, J., Yue, H., Wu, X., Xu, D., & Chen, W. (2020) · Chinese Automation Congress · doi:10.1109/cac51589.2020.9327736 · Cited by 4
“According to the features used, these algorithms can be categorized into two kinds, i.e. global feature-based algorithms [31], [35] and local feature-based algorithms [5], [8], [25], [28].”
MethodBhowmick, A., Saharia, S., & Hazarika, S. M. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10491-7 · Cited by 5
“Since they are based on the local SIFT [29] or Speeded-Up Robust Features (SURF) [7] features, they automatically inherit scale, rotation, and illumination invariance.”
3D mesh transformation preprocessing system in the real space for augmented reality services
Yoon, Y.-S., Hwang, S., Lee, D., et al. (2021) · ICT Express · doi:10.1016/j.icte.2021.02.001 · Cited by 4
Half-edge composite structure: good performance in motion matching
Qian, J., Luo, X., & Xue, Y. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03073-4 · Cited by 4
Sequence-based visual place recognition: a scale-space approach for boundary detection
Bampis, L., & Gasteratos, A. C. (2021) · Autonomous Robots · doi:10.1007/s10514-021-09984-7 · Cited by 4
“The approach was based on a visual vocabulary of SURF (Bay et al. 2006) and a Chow-Liu tree measuring the visual words’ co-visibility relationship.”
MethodStitching Strip Determination for Optimal Seamline Search
Garg, A., & Dung, L.-R. (2020) · International Conference on Imaging, Signal Processing and Communications (ICISPC) · doi:10.1109/icispc51671.2020.00013 · Cited by 4
“Some popular feature detectors such as Harris Corner[11], Speeded Up Robust Features (SURF)[12], and Scale-Invariant Feature Transform (SIFT)[13] are more often used strategies.”
MethodSTATE OF THE ART IN DENSE IMAGE MATCHING COST COMPUTATION FOR HIGH-RESOLUTION SATELLITE STEREO
Wang, Y., Wang, Y., Gong, D., et al. (2021) · 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-xliii-b2-2021-109-2021 · Cited by 4
Three-Dimensional Stitching of Binocular Endoscopic Images Based on Feature Points
Zhou, C., Yu, H. Y., Yuan, B., et al. (2021) · Photonics · doi:10.3390/photonics8080330 · Cited by 4
Robotic arm grasping through 3D point clouds recognition
Ji, S., Li, W., Zhang, Z., et al. (2021) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar52367.2021.9517680 · Cited by 4
Real-Time Facial Recognition Using SURF-FAST
Setta, S., Sinha, S., Mishra, M., et al. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-16-2937-2_32 · Cited by 4
Towards An Indoor Navigation System Using Monocular Visual SLAM
Bajpai, A., & Amir-Mohammadian, S. (2021) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac51774.2021.00077 · Cited by 5
SAL‐Net: Self‐Supervised Attribute Learning for Object Recognition and Segmentation
Yang, S., Wang, J., Arif, S., Jia, M., & Zhong, S. (2021) · Wireless Communications and Mobile Computing · doi:10.1155/2021/2891303 · Cited by 4
Evaluating Registrations of Serial Sections With Distortions of the Ground Truths
Lobachev, O., Funatomi, T., Pfaffenroth, A., Förster, R., Knudsen, L., Wrede, C., Guthe, M., Haberthür, D., Hlushchuk, R., Salaets, T., et al. (2021) · IEEE Access · doi:10.1109/access.2021.3124341 · Cited by 4
“The actual detectors and descriptors include SIFT [27], [28], SURF [29], [30], AKAZE [31], [32].”
BackgroundMethodThe Relocalization of SLAM Tracking Based on Spherical Cameras
Chang, Q., Liu, Q., Xin, Y., Huang, Y., Ren, F., & Cui, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3130928 · Cited by 4
“Other renowned solutions are SURF [23], ORB [24], and AKAZE [25].”
BackgroundTemporalFusion: Temporal Motion Reasoning with Multi-Frame Fusion for 6D Object Pose Estimation
Mu, F., Huang, R., Luo, A., Li, X. S., Qiu, J., & Cheng, H. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636583 · Cited by 4
“Traditional sparse feature-based methods extract scale invariant points of interest, such as SIFT [25] or SURF [26], and then estimate object poses with a method such as RANSAC [27] or P n P [28].”
MethodLi, J., Wu, D. M., Jiang, P., et al. (2021) · IEEE Access · doi:10.1109/access.2021.3134887 · Cited by 4
Bio-Inspired Multimodal Imaging in Reduced Visibility
Lapray, P., Thomas, J., & Farup, I. (2022) · Frontiers in Computer Science · doi:10.3389/fcomp.2021.737144 · Cited by 4
“Finally, we register all the bands using the speeded up robust features (SURF) method (Bay et al., 2006) to compensate for any misalignment induced by fi eld of view or optical assembly.”
MethodWELDMAP: A Photogrammetric Suite Applied to the Inspection of Welds
de Oña, E. R., Rodríguez‐Martín, M., Rodríguez‐Gonzálvez, P., Mora, R., & González‐Aguilera, D. (2022) · Applied Sciences · doi:10.3390/app12052553 · Cited by 5
Retinal Image Lesions Assisted Diabetic Retinopathy Screening System Through Machine Learning
(2022) · International journal of intelligent engineering and systems · doi:10.22266/ijies2022.0430.17 · Cited by 6
“Atlas and parasuraman [8] applied three feature extraction methods namely gray level co-occurrence matrix (GLCM) [10], speed up robust features (SURF) [11] and gary level run length matrix (GLRLM) [9] for the classification of normal retinal images from DR effected retinal images.”
MethodDiscriminative Shape Feature Pooling in Deep Neural Networks
Hu, G., Dixit, C., & Qi, G. (2022) · Journal of Imaging · doi:10.3390/jimaging8050118 · Cited by 4
STCDesc: Learning deep local descriptor using similar triangle constraint
Yin, J., Liu, Q., Meng, F., & He, Z. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108799 · Cited by 6
Learning General Feature Descriptor for Visual Measurement With Hierarchical View Consistency
Rao, Y., Yang, J., Ju, Y., Li, C., Rigall, E., Fan, H., & Dong, J. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3169563 · Cited by 5
The Icosahedron Marker for Robots 6-Dof Pose Estimation
Duan, L., Sun, H., Xuan, B., Tan, Y., Cui, R., & Wu, M. (2021) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio54168.2021.9739580 · Cited by 4
“Feature descriptors like SURF, ORB[3,4] are used to describe the features of the robots in RGB images, and find correspondences between the observed descriptors and the 3D model, finally the PnP solver was used to estimate the pose.”
MethodKadam, P., & Phansalkar, S. (2021) · Journal of Engineering Science and Technology Review · doi:10.25103/jestr.142.20 · Cited by 4
“However, due to complex appearances of the real food images, using a single descriptor in isolation is not sufficient to effectively represent the large variation of foods [35].”
DIRECT IMAGE-TO-GEOMETRY REGISTRATION USING MOBILE SENSOR DATA
Kehl, C., Buckley, S. J., Gawthorpe, R. L., et al. (2016) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-iii-2-121-2016 · Cited by 4
A Novel Approach to Extract Hand Gesture Feature in Depth Images
Liu, H., Ju, Z., Ji, X., et al. (2017) · Studies in computational intelligence · doi:10.1007/978-3-662-53692-6_9 · Cited by 4
An improved YOLOv5s for protective gear detection
Cheng, X., & Lü, T. (2022) · International Conference on Intelligent Computing and Signal Processing (ICSP) · doi:10.1109/icsp54964.2022.9778822 · Cited by 4
Enhanced Feature Matching Algorithm for Medical Image Registration
Samantaray, M., Panigrahi, M., & Patra, K. C. (2022) · Advances in sustainability science and technology · doi:10.1007/978-981-19-2277-0_33 · Cited by 4
Wang, Y., Yan, X., Ye, Z., Xie, H., Liu, S., Xu, X., & Tong, X. (2022) · Astrodynamics · doi:10.1007/s42064-022-0146-0 · Cited by 7
Pal, S., Gupta, S., Das, N., & Ghosh, K. (2022) · Journal of Autonomous Vehicles and Systems · doi:10.1115/1.4055161 · Cited by 4
Revisiting the Receptive Field of Conv-GRU in DROID-SLAM
Bangunharcana, A., Kim, S., & Kim, K.-S. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00207 · Cited by 4
“In geometric BA [5, 32, 34], optimization is performed over the reprojection error of points correspondences, commonly obtained via keypoint detector-descriptor scheme [3, 28, 38].”
MethodContext‐aware Siamese network for object tracking
Zhang, J., Wang, J., Zhang, H., Miao, M., & Wu, D. (2022) · IET Image Processing · doi:10.1049/ipr2.12629 · Cited by 4
Wu, B.-X., Shivanna, V. M., Hung, H.-H., & Guo, J.-I. (2022) · Sensors · doi:10.3390/s22197371 · Cited by 5
IFLNET: Image Forgery Localization Using Dual Attention Network
(2022) · International journal of intelligent engineering and systems · doi:10.22266/ijies2022.1231.17 · Cited by 4
Multi-L: A Novel Multi-Robot Cooperative Localization Method in Indoor Environment
Zhu, Z., Zhu, K., Zheng, Z., Chen, S., & Zheng, N. (2022) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc55140.2022.9922050 · Cited by 5
“These methods use descriptors generated from the surrounding environment features, such as SIFT [11],SURF [12] and ORB [13], to represent images, each associated with a global location.”
MethodExplainable computer vision analysis for embryo selection on blastocyst images
Kallipolitis, A., Τζιομάκα, Μ., Papadopoulos, D. P., & Maglogiannis, I. G. (2022) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi56158.2022.9926740 · Cited by 4
“Speeded Up Robust Features (SURF) [19] is employed as a local descriptor due to its efficiency and speed.”
MethodZhuang, Y., Jiang, X., Gao, Y., Fang, Z., & Fujita, H. (2022) · Sensors · doi:10.3390/s22249647 · Cited by 4
“Famous feature point extractors, such as, SIFT [2] and SURF [3], which is faster than SIFT, are the basis for accurate feature matching.”
MethodMegaPose: 6D Pose Estimation of Novel Objects via Render & Compare
Labbé, Y., Manuelli, L., Mousavian, A., Tyree, S., Birchfield, S. T., Tremblay, J., Carpentier, J., Aubry, M., Fox, D., & Šivic, J. (2022) · HAL · Cited by 4
A 3D Scene Information Enhancement Method Applied in Augmented Reality
Li, B., Wang, X., Gao, Q., et al. (2022) · Electronics · doi:10.3390/electronics11244123 · Cited by 4
Zhang, J., Yu, X., Liu, Y., Yu, J., & Gao, H. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3224539 · Cited by 6
“The feature-based approaches, such as speeded-up robust features (SURF) [10], scale-invariant feature transform (SIFT), and oriented features from accelerated segment test and rotated binary robust independent elementary feature (ORB) [11], extract robust feature points using a feature point…”
MethodMultimodal Colored Point Cloud to Image Alignment
Rotstein, N., Bracha, A., & Kimmel, R. (2022) · 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/cvpr52688.2022.00654 · Cited by 4
“Featurebased methods extract features in each image [1, 3, 42, 54] and then match them.”
MethodBeam-Domain Image Mosaic of Forward-Looking Sonar Using Expression Domain Mapping Model
Wei, M., Bian, H., Zhang, F., et al. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3207986 · Cited by 4
“…The content alignment of the two images to be mosaicked is completed through feature extraction and geometric deformation [3], [4], [5] or grayscale registration to compensate for rotation and translation [6], and then the seam removal and overlapping part fusion functions are…”
New Scheme of Image Matching for The Power Transmission Line Icing
Nusantika, N. R., Xiao, J., & Hu, X. (2022) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea54703.2022.10006260 · Cited by 4
“The FAST algorithm detects feature points with a more straight-forward operation than SIFT or SURF.”
MethodInfluentialAutomatic Identification and Geo-Validation of Event-Related Images for Emergency Management
Vernier, M., Farinosi, M., Foresti, A., & Foresti, G. L. (2023) · Information · doi:10.3390/info14020078 · Cited by 4
A Robust Pedestrian Detection Approach for Autonomous Vehicles
Ghari, B., Tourani, A., & Shahbahrami, A. (2022) · Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS) · doi:10.1109/icspis56952.2022.10043934 · Cited by 6
Biometric-Based Key Handling Using Speeded Up Robust Features
Kaur, P., Kumar, N., & Singh, M. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-19-9228-5_52 · Cited by 4
Analysis of schizophrenia using support vector machine classifier
Jiji, G. W., Rajesh, A., & Kanagaraj, A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14513-y · Cited by 5
Towards Reconstruction of 3D Geometry of Underwater Rubble Mounds via Structure from Motion
Takao, S., Kita, T., & Hirabayashi, T. (2023) · IEEE Underwater Technology (UT) · doi:10.1109/ut49729.2023.10103396 · Cited by 4
(2023) · International Journal of Advanced Technology and Engineering Exploration · doi:10.19101/ijatee.2022.10100139 · Cited by 4
Traffic Sign Detection Using Hybrid Network Of Yolo And Resnet
Vinothkumar, S., Varadhaganapathy, S., Shanthakumari, R., Pradeev, S., Pragatheeswaran, S., & Annamalai, K. (2023) · International Conference on Computer Communication and Informatics (ICCCI) · doi:10.1109/iccci56745.2023.10128337 · Cited by 4
(MARGOT) Monocular Camera-Based Robot Grasping Strategy for Metallic Objects
Almagro, C. V., Orrego, R. M., González, Á. G., Matheson, E., Marín, R., Castro, M. D., & Ferré, M. (2023) · Sensors · doi:10.3390/s23115344 · Cited by 5
Kurul, M., Aydın, N., & Şen, Ö. (2023) · Medical Bulletin of Haseki · doi:10.4274/haseki.galenos.2023.9005 · Cited by 4
Visual Quality Assessment of Point Clouds Compared to Natural Reference Images
Baek, A., Kim, M., Son, S., et al. (2023) · Journal of Web Engineering · doi:10.13052/jwe1540-9589.2232 · Cited by 4
“Here, a feature detection algorithm, e.g., scale-invariant feature transform (SIFT) and speed-up robust features (SURF), is employed to increase the detection accuracy of the ROI and a corresponding region [52, 53].”
MethodWu, T.-H., & Chen, K. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160290 · Cited by 4
Multi-scale fusion transformer based weakly supervised hashing learning for instance retrieval
Lv, Y., Jiao, C., Zhao, W., et al. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-01907-5 · Cited by 4
DENSE SWIN-UNET: DENSE SWIN TRANSFORMERS FOR SEMANTIC SEGMENTATION OF PNEUMOTHORAX IN CT IMAGES
Tang, Z., Zhang, J., Bai, C., Zhang, Y., Liang, K., & Yao, X. (2023) · Journal of Mechanics in Medicine and Biology · doi:10.1142/s0219519423400699 · Cited by 6
PanoPoint: Self-Supervised Feature Points Detection and Description for 360° Panorama
Zhang, H., Hong, Y., Jia, H., et al. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00686 · Cited by 4
MISC210K: A Large-Scale Dataset for Multi-Instance Semantic Correspondence
Sun, Y., Huang, Y., Guo, H., Zhao, Y., Wu, R., Yu, Y., Ge, W., & Zhang, W. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00688 · Cited by 9
“Methods for semantic correspondence can be roughly categorized into several groups: handcrafted feature based methods [2, 5, 23, 35, 38], learnable feature based meth-ods [18,19,28,39], graph matching and optimization based methods [22,41,46,47], methods focusing on geometry displacement [3, 8, 9,…”
MethodZheng, D., Wei, L., Lv, W., Liu, Y., & Wang, Y. (2023) · Remote Sensing · doi:10.3390/rs15184388 · Cited by 6
An End‐to‐End Robotic Visual Localization Algorithm Based on Deep Learning
Chen, N., Wang, H., Fan, G., Yang, D., & Rao, L. (2023) · Journal of Sensors · doi:10.1155/2023/2396911 · Cited by 5
Hi-SIGIR: Hierachical Semantic-Guided Image-to-image Retrieval via Scene Graph
Wang, Y., Dai, P., Jia, X., Zeng, Z., Li, R., & Cao, X. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612283 · Cited by 13
Towards automated remote sizing and hot steel manufacturing with image registration and fusion
Lin, Y., Wang, P., Wang, Z., Ali, S., & Mihaylova, L. S. (2023) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-023-02251-9 · Cited by 5
“…many other algorithms were developed with highly accurate performance, such as the Speeded Up Robust Features (SURF) method, which reduce the amount of calculation and speed up the feature extraction process so that it can meet the real-time requirements (Bay et al., 2006; Tafti et al., 2018).”
Innovative Cucumber Phenotyping: A Smartphone-Based and Data-Labeling-Free Model
Nguyen, L. Q., Shin, J., Ryu, S., Dang, L. M., Park, H. Y., Lee, O. N., & Moon, H. (2023) · Electronics · doi:10.3390/electronics12234775 · Cited by 4
Huang, Y., Sun, Y., Lai, C., Xu, Q., Wang, X., Shen, X., & Ge, W. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01489 · Cited by 4
“Before calculating the similarity matrix and generating correspondence, several selection [27] or calculation [24, 4, 23] based preprocessing are often used to improve the discriminative of semantic representation among patches.”
MethodAlzoubi, Y. I., Topcu, A. E., & Özdemir, E. (2024) · Applied Sciences · doi:10.3390/app14020751 · Cited by 4
Face Recognition using CNN and Amazon S3: An Expandable and Safe Integration for Various Uses
Dasaraju, S. P. V., Bandaru, D. S., Ravella, A., et al. (2023) · International Conference on Automation, Computing and Renewable Systems (ICACRS) · doi:10.1109/icacrs58579.2023.10404736 · Cited by 4
Lee, H., Carriquiry, A. L., & Park, S. (2024) · Statistical Analysis and Data Mining The ASA Data Science Journal · doi:10.1002/sam.11659 · Cited by 4
“SURF is a patented local feature detector and descriptor invariant to scale and rotation transformations [3], and we use it to automatically choose interest points from the two images.”
MethodPark, J., Kim, S., Hong, K., et al. (2024) · NAVIGATION Journal of the Institute of Navigation · doi:10.33012/navi.634 · Cited by 4
GPU Accelerated Processing Method for Feature Point Extraction and Matching in Satellite SAR Images
Dong, L., Jiao, N., Zhang, T., Liu, F., & You, H. (2024) · Applied Sciences · doi:10.3390/app14041528 · Cited by 4
Chlubna, T., Milet, T., & Zemčík, P. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18573-6 · Cited by 4
“Anotheroption istousefeaturematchingalgorithmswithdescriptorssuchasSIFT[13],SURF[14],KAZE [15]orORB[16]andfindthedisplacementofthefoundfeatures.”
Target Research Based on BLIP Model
Song, H., & Song, Y. (2024) · Academic Journal of Science and Technology · doi:10.54097/ak59r592 · Cited by 4
DCL-depth: monocular depth estimation network based on iam and depth consistency loss
Han, C., Lv, C., Kou, Q., Jiang, H., & Cheng, D. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18877-7 · Cited by 5
“By the optical flow field propagate, sparse SURF [3] was utilized for guided training on textured regions through a self-supervised network.”
Zhang, C., Xue, H., Nie, K., et al. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2024.103735 · Cited by 4
Joint Attention Detection Using First-Person Points-of-View Video
Bise, K., Saitoh, T., Tsuchiya, K., et al. (2024) · International Conference on Computer Graphics and Image Processing (CGIP) · doi:10.1109/cgip62525.2024.00029 · Cited by 4
“Typical methods for detection and descriptors of local features corresponding to 1) and 2) above include SIFT (Scale-Invariant Feature Transform) [5], SURF (speed up robust feature) [6] and ORB ( rotated robust independent elementary features) [7].”
MethodHardware Accelerator for Feature Matching with Binary Search Tree
Thathsara, M., Lam, S.-K., Kawshan, D., et al. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10558431 · Cited by 4
“Previous works used FPGAs to accelerate feature matching for binary descriptors, e.g., BRIEF [4], ORB [5], BRISK [6], and non-binary descriptors e.g., SIFT [7], SURF [8].”
MethodZhong, J., Gan, Y., & Yang, J. (2024) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2024.103863 · Cited by 4
An image-based bridge displacement field measurement method with self-vibration elimination
Liu, Y.-F., Liu, J., Wei, X.-C., Liu, X., & Li, B. (2024) · Advances in Structural Engineering · doi:10.1177/13694332241286535 · Cited by 4
“The most well-known algorithms include scale-invariant feature transformation (SIFT) (Lowe, 2004) and speed-up robust feature (SURF) (Bay et al., 2006), which was improved from SIFT.”
Improving Integrality of Detected Moving Objects Based on Image Matting
Zhang, L., Wang, H., Deng, T., et al. (2014) · Chinese Journal of Electronics · doi:10.23919/cje.2014.10851933 · Cited by 4
Unrotating images in laparoscopy with an application for 30° laparoscopes
Moll, M., Koninckx, T. P., Gool, L. J. V., et al. (2009) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-540-89208-3_230 · Cited by 4
Self-citationComparison of feature detectors for rover navigation
Cumani, A., & Guiducci, A. (2009) · International Conference on Mathematical Methods and Computational Techniques in Electrical Engineering · Cited by 4
Le, T.-N., Le, Y.-T., & Tran, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-07464-1_5 · Cited by 4
“…roposed process with the original method which does other state-of-the-art saliency detection methods. xist-ds d Since pendent of the keypoint extraction and recognition al nducted to evaluate our approach using four popular lo SK [18], SIFT [19], and SURF [20]. ed in a system using CPU Core i3 3.”
MethodVisual Approaches for Handle Recognition
Jauregi, E., Lazkano, E., Martínez‐Otzeta, J. M., & Sierra, B. (2008) · Springer eBooks · doi:10.1007/978-3-540-78317-6_32 · Cited by 4
Markov-Vetter, D., & Staadt, O. (2013) · elib (German Aerospace Center) · Cited by 4
Pose estimation and trajectory calculation for autonomous close-range rendezvous and docking
Priggemeyer, M., Dimartino, M., & Roßmann, J. (2015) · IEEE International Conference on Advanced Intelligent Mechatronics (AIM) · doi:10.1109/aim.2015.7222501 · Cited by 4
“Speeded Up Robust Feature (SURF) descriptors deliver both, scale and rotational invariance [15] and are very suitable for these low rates.”
BackgroundDirectional Votes of Optical Flow Projections for Independent Motion Detection
Czúni, L., & Gál, M. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33564-8_40 · Cited by 4
A Graph-Based Hierarchical SLAM Framework for Large-Scale Mapping
Zhang, H., Hou, Z., Li, N., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33515-0_44 · Cited by 4
“FE usually means extracting visual features [8][9] or geometry traits [10] from sensor observation.”
MethodImproved Vision-Based Algorithm for Unmanned Aerial Vehicles Autonomous Landing
Zhao, Y., Pei, H., & Zhou, H. (2013) · Journal of Multimedia · doi:10.4304/jmm.8.2.90-97 · Cited by 4
IMU-aided SURF feature matching for relative pose estimation
Wong, D., Hayes, M., & Bainbridge-Smith, A. (2010) · doi:10.1109/ivcnz.2010.6148873 · Cited by 4
“The Hessian threshold [7] was varied between 500 and 8000 to extract a different number of features.”
BackgroundMethodBehera, A., Cohn, A. G., & Hogg, D. (2014) · British Machine Vision Conference (BMVC) · doi:10.5244/c.28.100 · Cited by 3
“T is processed to extract a set of visual features using one of the available approaches such as SIFT [23], STIP [19], SURF [3] and CUBOID [10].”
MethodObject recognition for vision-based navigation in indoor environments without using image database
Lee, H., Kim, J., Kim, C., et al. (2014) · doi:10.1109/isce.2014.6884460 · Cited by 4
A modified feature point descriptor based on binary robust independent elementary features
Zhang, F., Ye, F., & Su, Z. (2014) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2014.7003788 · Cited by 5
Finding logos in real-world images with point-context representation-based region search
Wang, J., Fu, J., & Lu, H. (2013) · Multimedia Systems · doi:10.1007/s00530-013-0349-6 · Cited by 4
Automatic toxic granulation detection and grading based on speeded up robust features
Qiao, G., Zong, G., Wang, J., et al. (2011) · Cytometry Part A · doi:10.1002/cyto.a.21113 · Cited by 4
Autonomous Self-Localization of Mobile Robots through Reference Point Based Computer Vision
Couto, L. N., & Osório, F. S. (2012) · doi:10.1109/cbsec.2012.12 · Cited by 4
“The chosen method for this particular problem is SURF [7], which is itself inspired by and generally improves upon SIFT [8].”
BackgroundMethod3D Reconstruction of Chinese Hickory Trees for Mechanical Harvest
He, L., Du, X., Qiu, G., & Wu, C. (2012) · 2012 Dallas, Texas, July 29 - August 1, 2012 · doi:10.13031/2013.41936 · Cited by 7
An efficient framework for location-based scene matching in image databases
Chen, X., Das, M., & Loui, A. C. P. (2012) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-012-0011-7 · Cited by 4
“SURF (Speeded Up Robust Features) [1] is a faster performing scale- and rotation-invariant interest point detector and descriptor.”
BackgroundMethodInfluential
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.