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 11,701–11,800 of 14,752
Performance Analysis of Coin Matching Using Local Texture Features
Munipalle, V. K., & Nelakuditi, U. R. (2019) · doi:10.1109/icon-cute47290.2019.8991455 · Cited by 1
“,[18].”
Subway 3D Bound Limitation Visualization Method Based on Stereo Vision
Lei, W., Xu, M., Hou, F., et al. (2019) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac47372.2019.8997540 · Cited by 1
Segmentation-based orbiting satellite tracking
Sun, Y., Li, P., & Wan, X. (2020) · International Conference on Multimedia and Image Processing (ICMIP) · doi:10.1145/3381271.3381291 · Cited by 1
“Popular algorithms for edge and key point extraction includes Harris[12], Canny[13], SIFT [14] and SURF [15].”
MethodAn Efficient Approach based on Image Pixel and Semantic Features Towards Video Retrieval
Li, H., Ma, Z., Fan, H., & Liu, J. (2018) · International Conference on Imaging, Signal Processing and Communications (ICISPC) · doi:10.1109/icispc44900.2018.9006689 · Cited by 1
“Common features with local invariance include SIFT [5], ORB [6], SURF [7].”
BackgroundAcceleration of data handling in neural networks by using cascade classification model
Połap, D., & Woźniak, M. (2019) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci44817.2019.9002859 · Cited by 1
New Approach to Improve the Classification Process of Multi-Class Objects
Gafour, Y., & Berrabah, D. (2020) · International Journal of Organizational and Collective Intelligence · doi:10.4018/ijoci.2020040101 · Cited by 1
Wu, L., Wan, W., Yu, X., et al. (2020) · Computer Animation and Virtual Worlds · doi:10.1002/cav.1922 · Cited by 1
A Real-time and Online Multiple-Type Object Tracking Method with Deep Features
Hsu, Y., & Guo, J.-I. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023031 · Cited by 1
Robust Feature Matching via Multi-Scale Grid Structure
Li, Y., Huang, Q., Liu, Y., et al. (2019) · IEEE International Conference on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom) · doi:10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00169 · Cited by 1
“For two-step strategy based methods, they firstly detect key-points by using an off-the-shelf method (e.g. SIFT [13], ORB [14], A-SIFT [15], SURF [16]) and obtain the initial feature correspondences according to a similarity constraint (e.g. near-1187 est neighbor strategy).”
MethodVehicle Feature Point Trajectory Clustering and Vehicle Behavior Analysis in Complex Traffic Scenes
Wang, X., Zhao, J., Wang, Y., et al. (2020) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-44751-9_17 · Cited by 1
Structure Oriented Local Image Feature Description
Yu, W., Qin, X., Wang, P., et al. (2020) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/790/1/012105 · Cited by 1
Localization of Autonomous Robot in an Urban Area Based on SURF Feature Extraction of Images
Yasin, A. S. M., Haque, M. M., Adnan, M. N., et al. (2020) · International Journal of Technology Diffusion · doi:10.4018/ijtd.20201001.oa1 · Cited by 1
Loop Closure Detection for Monocular Visual Odometry: Deep-Learning Approaches Comparison
Sedrine, M. A., Mseddi, W. S., Abdellatif, T., & Attia, R. (2019) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis.2019.00083 · Cited by 1
“In the other hand, from figures 9, 10 and 11 we can see that Siamese ResNet is more accurate than other Siamese Networks, same goes for Multichannel ResNet.”
BackgroundCombination of Salient Object Detection and Image Matching for Object Instance Recognition
Wigati, E. K., Kusuma, G. P., & Utomo, Y. (2020) · Advances in Science Technology and Engineering Systems Journal · doi:10.25046/aj050273 · Cited by 1
“Features extraction will be done using Speeded Up Robust Features (SURF) [22].”
MethodInfluentialImage Clustering and Video Summarization for Efficient 3D Modelling and Reconstruction
Voulodimos, A. S., Protopapadakis, E. E., Doulamis, N. D., & Doulamis, A. D. (2020) · Advances in multimedia and interactive technologies book series · doi:10.4018/978-1-5225-5294-9.ch009 · Cited by 2
Distance Matrix Based Keypoint Selection for Bag-of-Visual Words Model on Image Classification
Mada, U. G., Supriyanto, C., Nugroho, H. A., et al. (2020) · International journal of intelligent engineering and systems · doi:10.22266/ijies2020.0630.31 · Cited by 1
“Some methods have been applied for keypoint extraction, including Scale Invariant Features Transform (SIFT) [9] and Speeded-Up Robust Features (SURF) [10].”
MethodSR-SYBA: A Scale and Rotation Invariant Synthetic Basis Feature Descriptor with Low Memory Usage
Meng, Y., Zhang, D., Lee, D.-J., et al. (2020) · Electronics · doi:10.3390/electronics9050810 · Cited by 1
Research on Panorama Reconstruction Technique of UAV Aerial Image Based on Improved ORB Algorithm
Zhang, Y., Zhang, J., Zhang, L., et al. (2019) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1109/eitce47263.2019.9095113 · Cited by 1
“In terms of calculation speed, it is 100 times that of SIFT and 10 times that of SURF.”
MethodInfluentialA Copy Move Forgery Detection Scheme Based on Dynamic SURF Feature Detection and Block Matching
Pratyusha, D., & Prasad, M. V. N. K. (2018) · doi:10.1109/icinpro43533.2018.9096692 · Cited by 1
“There are two parts to the SURF algorithm [19].”
MethodDetectors and Descriptors of Interest Points
Distante, A., & Distante, C. (2020) · Springer eBooks · doi:10.1007/978-3-030-42374-2_6 · Cited by 1
Maeda, K., Susumu, G., Ogawa, T., & Haseyama, M. (2020) · ITE Transactions on Media Technology and Applications · doi:10.3169/mta.8.140 · Cited by 1
Evaluation of Different Feature Descriptor Algorithms on Classification Task
Gupta, P., Gupta, M., & Gulhane, P. (2019) · International Conference on Computing Communication Control and automation · doi:10.1109/iccubea47591.2019.9128925 · Cited by 1
“While SURF [10] is based on approximation of LoG with Box Filter.”
MethodAn Object Distance Detection Method for Driving Performance Evaluation
Gao, Y., Wang, Z., & Fu, S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-49183-3_23 · Cited by 1
Image-Based Place Recognition Using Semantic Segmentation and Inpainting to Remove Dynamic Objects
Liu, L., Cappelle, C., & Ruichek, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-51935-3_28 · Cited by 1
“Traditional methods design hand-craft local features that are illumination, viewpoint, and scale-invariant, such as speeded-up robust features (SURF) [1] and scale-invariant feature transforms (SIFT) [9].”
MethodSign Language Video Classification Based on Image Recognition of Specified Key Frames
Zhu, Z., Jiang, X., & Zhang, J. (2020) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-51103-6_33 · Cited by 1
Frejlichowski, D. (2020) · Journal of WSCG · doi:10.24132/jwscg.2020.28.8 · Cited by 1
Evaluation of the Automated Testing Framework: A Case Study
Méndez-Porras, A., Alfaro-Velásco, J., & Martínez, A. (2020) · Revista Tecnología en Marcha · doi:10.18845/tm.v33i3.4372 · Cited by 1
Finding robust transfer features for unsupervised domain adaptation
Gao, D., Wu, R., Liu, J., et al. (2020) · International Journal of Applied Mathematics and Computer Science · doi:10.34768/amcs-2020-0008 · Cited by 1
“For this dataset, we considered two types of features: SURF features (Bay et al ., 2006), quantized into an 800-bin histogram with codebooks computed on a subset of Amazon, and 4096-dimensional DeCAF features (Donahue et al ., 2014), which are activations of the sixth fully connected layer of a…”
MethodComparison of Key Points Clouds of Images Using Intuitionistic Fuzzy Sets
Belyakov, S. L., Bozhenyuk, A. V., Morev, K., et al. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-51971-1_30 · Cited by 1
REAL-TIME SLAM FOR THE OFF-ROAD AUTONOMOUS DRIVING
Vishnyakov, B. V., & Sheverdin, V. (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-xliii-b2-2020-631-2020 · Cited by 1
Research on Aerial Image Stitching Technology
Ma, R., Zhang, C., Guo, Q., et al. (2019) · International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC) · doi:10.1109/sdpc.2019.00048 · Cited by 1
“Aiming at the problem that the traditional SIFT constraint is single and the real-time performance is relatively poor, Herbert Bay et al. proposed a new scale and rotation invariant detector and descriptor [5], and created the SURF algorithm.”
BackgroundManeuvers Under Estimation of Human Postures for Autonomous Navigation of Robot KUKA YouBot
Gordón, C., Barahona, S., Cumbajín, M., et al. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-55180-3_25 · Cited by 1
Fast palmprint retrieval using speed up robust features
Kumar, G. (2020) · Indian Journal of Science and Technology · doi:10.17485/ijst/v13i31.404 · Cited by 1
Robust and Efficient Image Alignment Method Using the Student-t Distribution
Zhou, Y., & Maskell, S. R. (2020) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion45008.2020.9190357 · Cited by 1
“The feature-based approaches match features based on the descriptor of features (e.g., SIFT [8], SURF [9]) and then estimate the image background motion given the matched features.”
MethodKLN: A Deep Neural Network Architecture for Keypoint Localization
Hurtík, P., & Tyshchenko, O. K. (2020) · IEEE International Conference on Data Stream Mining & Processing (DSMP) · doi:10.1109/dsmp47368.2020.9204211 · Cited by 1
“The real-time performance has been proposed by the SURF scheme (Speeded Up Robust Features) [4], where the main 978-1-7281-3214-3/20/$31.00 ©2020 European Union concern of the SURF strategy is its high-speed calculation of operators applying box filters for tracking and object recognition.”
MethodInfluentialThe comparison between two methods of object detection: Fast Yolo model and Delaunay Triangulation
Benjelloun, F., Elmanaa, I., Sabri, M. A., Yahyaouy, A., & Aarab, A. (2020) · International Symposium on Computer Vision · doi:10.1109/iscv49265.2020.9204197 · Cited by 1
Logo Based Amphetamines Classification using SURF and Bag-of-features model
Nitijiramon, T., Cooharojananone, N., & Saiseng, S. (2020) · International Conference on Mathematics and Computers in Science and Engineering (MACISE) · doi:10.1109/macise49704.2020.00023 · Cited by 1
“SURF was first published by Herbert Bay, Tinne Tuytelaars, and Luc Van Gool [4].”
MethodSTED-Net: Self-taught encoder-decoder network for unsupervised feature representation
Ду, С., & Ikenaga, T. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09734-4 · Cited by 1
“Early feature representation methods [1, 2, 4, 15, 27] were manually designed to extract information from low-level image textures.”
MethodExtracting Handwritten Regions In Japanese Document Images
Nguyen, K., & Do, T.-H. (2020) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr49794.2020.9237784 · Cited by 1
“SURF was claimed to perform faster than SIFT without reducing the quality of detected points [17].”
BackgroundMethodFeature-Less Stitching of Cylindrical Cable for Surface Inspection of Cable-Stayed Bridges
Zhang, K., Zhou, L., & Xiao, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60639-8_18 · Cited by 1
Image Matching Algorithm Based on Improved ORB Feature Extraction
Yang, Q., & Chuang, S. (2020) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-62483-5_21 · Cited by 1
Progressive Refinement Imaging
Kluge, M., Weyrich, T., & Kolb, A. (2019) · UCL Discovery (University College London) · Cited by 1
Automated Calculation of Fundamental Matrix from Stereo Images from a Different Point of View
Chater, A., & Lasfar, A. (2020) · Springer eBooks · doi:10.1007/978-3-030-48378-4_7 · Cited by 1
SAFFIRE: System for Autonomous Feature Filtering and Intelligent ROI Estimation
Boschi, M., Stefano, L. D., & Alessandrini, M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68799-1_40 · Cited by 1
“ges. For instance, SIFT is arguably the most popular approach [6] for textured objects, although a number of alternative solutions have been 4 M. Boschi et al. also proposed, such as ORB [9] and SURF [1]. However, approaches based on segments [3] and combination of segments [10] have been shown to be more appropriate…”
InfluentialSketch Based Data Retrieval Using Reversible Data Hiding on Images
Birari, D. R., Hiran, D., & Narawade, V. E. (2020) · Journal of University of Shanghai for Science and Technology · doi:10.51201/jusst12511 · Cited by 1
Pikramenos, G., Kechagias, K., Psallidas, T., Smyrnis, G., Spyrou, E., & Perantonis, S. J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-66125-0_3 · Cited by 2
The Use of Input Words Vectorsto Detect Crowd Region in Images
Abdulateef, S. A., Kadhim, L. M., & Ghandawi, E. W. (2021) · International Journal of Engineering Research and Advanced Technology · doi:10.31695/ijerat.2021.3678 · Cited by 1
Monitoring Technique Using a Vision-based Single-Camera System for Reinforced Soil Retaining Wall
Ha, Y.-S., Kweon, G.-C., & Kim, Y.-T. (2020) · Korean Society of Hazard Mitigation · doi:10.9798/kosham.2020.20.6.209 · Cited by 1
6D Pose Estimation for Texture-Less Industrial Parts in the Crowd
Zhou, D., Chai, Z., Liu, C., Li, P., & Xiong, Z. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-66645-3_35 · Cited by 1
The loop closure Detection Algorithm Based on Bag of Semantic Word For Robot Navigation
Yu, P., Ruan, X., & Zhu, X. (2020) · IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) · doi:10.1109/iciba50161.2020.9277317 · Cited by 1
“Most of the current loop closure detection is based on the traditional feature (such as ORB) visual bag model (BoW) method [4], At present, traditional SIFT [5], SURF [6] and ORB [7] are often used as image representations.”
MethodCombining Region-Based and Point-Based Algorithm to Detect Vehicle Plate Location
Maulana, H., Kartika, I. S. Y., Saputra, W. S. J., et al. (2020) · doi:10.1109/itis50118.2020.9321000 · Cited by 1
Automatic Event Detection in User-Generated Video Content: A Survey
Alamuru, S., Jain, S., & Mohnaty, M. N. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-8752-8_29 · Cited by 1
Self-Supervised Rigid Registration for Small Images
Ma, R., Zhao, S., & Cheng, S. S. M. (2021) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2021.01.011 · Cited by 1
“The feature detectors we use include SIFT [13], SURF [14], ORB [15], and AKAZE [16] algorithms.”
MethodImage Registration Improved by Generative Adversarial Networks
Jiang, S., Wang, C., & Huang, C. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-67835-7_3 · Cited by 1
Model Quality Aware RANSAC: A Robust Camera Motion Estimator
Yeh, S.-H., Lu, Y., & Song, D. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341345 · Cited by 1
Relationship between Grasping Actions and Object Attributes: A Survey
Le, V.-H. (2021) · Journal of Advances in Information Technology · doi:10.12720/jait.12.1.6-13 · Cited by 1
Richer Aggregated Features for Optical Flow Estimation with Edge-aware Refinement
Wang, X., Zhu, D., Song, J., Liu, Y., Li, J., & Zhang, X. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341544 · Cited by 1
“Many researchers have utilized it to design feature descriptors [18], [19], [20].”
MethodOgawara, K., & Iseki, K. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340771 · Cited by 1
“However, they rely on manually designed image features such as HOG [5] and SURF [6] that are not optimal compared with the statistically learned image features.”
MethodORB-SLAM2 Based Teach-and-Repeat System
Pivoňka, T., & Přeučil, L. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-70740-8_19 · Cited by 1
Co-Attention for Conditioned Image Matching
Wiles, O., Ehrhardt, S., & Zisserman, A. (2021) · 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/cvpr46437.2021.01566 · Cited by 65
“Methods that solve the correspondence task typically follow a detect-and-describe approach: first they detect distinctive regions [5, 15, 30, 34, 49] and then describe these regions using descriptors [5, 6, 21, 26, 30, 49] with varying degrees of invariance to scale, illumination, rotation, and affine transformations.”
Toward Improving Image Retrieval via Global Saliency Weighted Feature
Zhao, H., Wu, J., Zhang, D., & Liu, P. (2021) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi10040249 · Cited by 2
González, Y., Millán, A., Sánchez, Y. V. C., et al. (2020) · Memoria Investigaciones en Ingeniería · doi:10.36561/ng.19.4 · Cited by 1
Binary GAN based Approach for Unsupervised Loop Closure Detection in Autonomous Unmanned Systems
Jin, S., Yang, H., Chen, L., et al. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.2626 · Cited by 1
“…by hand-crafted feature extraction methods, such as scale-invariant feature transform (SIFT) (Lowe et al. (2004)), speeded-up robust feature (SURF) (Bay et al. (2006)), oriented features from accelerated segment test, rotated binary robust-independent elementary feature (ORB) (Rublee et al.…”
BackgroundMethodInfluentialCho, H. (2021) · Turkish Journal of Computer and Mathematics Education (TURCOMAT) · doi:10.17762/turcomat.v12i9.4773 · Cited by 1
Patel, P., & Patel, N. M. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-33-6981-8_55 · Cited by 1
ADAS algorithm for creating a wider view of the environment with a blind spot display for the driver
Kundid, J., Vranješ, M., Lukač, Ž., et al. (2021) · Zooming Innovation in Consumer Technologies Conference (ZINC) · doi:10.1109/zinc52049.2021.9499264 · Cited by 1
Candidate box fusion based approach to adjust position of the candidate box for object detection
Cao, J., Ren, W., Zhang, H., & Chen, Z. (2021) · IET Image Processing · doi:10.1049/ipr2.12264 · Cited by 1
“IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology Gradient), SURF [12] (Speeded up Robust Features) and DPM [13] (Deformable Parts Model).”
MethodISM Band Multi-source Signal Perception Based on Time-Frequency Image Feature Analysis
Deng, Z., Qi, H., Hu, E., et al. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-3142-9_57 · Cited by 1
Research and Implementation of ORB-SLAM in Drastically Changing Scenes
Wang, Z., Wang, M., Yu, Y., & Ye, X. (2021) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec51613.2021.9482292 · Cited by 1
Image Matching Using Enhancement Offsets With Adaptive Parameter Selection Via Histogram Analysis
Psaila, J., Hong-Phuoc, T., & Guan, L. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506798 · Cited by 1
“Poor colour contrast significantly impacts the detection of keypoints [4, 8].”
BackgroundMethodInfluentialData Augmentation for Writer Identification Using a Cognitive Inspired Model
Pignelli, F., Costa, Y. M. G., Oliveira, L. S., et al. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86337-1_17 · Cited by 1
Analysis of Optical Mapping Data with Neural Network
Doleží, V., & Gajdoš, P. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-84910-8_26 · Cited by 1
Yin, X., Ma, L., Sun, P., & Tan, X. (2021) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-021-00795-7 · Cited by 1
Shivanna, V. M., Chen, K., Wu, B.-X., & Guo, J.-I. (2021) · Artificial intelligence · doi:10.5772/intechopen.99416 · Cited by 1
Efficient Parameter Based Online Object Tracking
Rahman, M. H., Ali, S., & Bouguila, N. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533905 · Cited by 1
Chakravarty, P., Roussel, T., Pandey, G. S., et al. (2021) · Journal of Autonomous Vehicles and Systems · doi:10.1115/1.4052604 · Cited by 1
Self-citationLi, C., You, Y., Cao, J., et al. (2021) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss47720.2021.9553197 · Cited by 1
Computer vision monitoring and detection for landslides
Chen, T., Kuo, C.-H., & Chen, J. C. Y. (2019) · Structural Monitoring and Maintenance · doi:10.12989/smm.2019.6.2.161 · Cited by 1
Monocular Localization in Feature-Annotated 3D Polygon Maps
Mock, A., Wiemann, T., & Hertzberg, J. (2021) · European Conference on Mobile Robots · doi:10.1109/ecmr50962.2021.9568810 · Cited by 1
“For that, we created a high resolution reference data set to evaluate SIFT [18], SURF [19], ORB [9], and AKAZE [20] with respect to our requirements.”
MethodChen, W., Wang, Z., & Li, H. (2021) · IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00088 · Cited by 1
“Hand-craft features such as SIFT[21], ASIFT[24], HOG[4] and SURF[1] are used by classical methods before deep learning methods.”
MethodMotorbike Counting in Heavily Crowded Scenes
Huynh, C. K., Dang, T. K., & Nguyen, C. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-91387-8_12 · Cited by 2
Bag of Groups of Convolutional Features Model for Visual Object Recognition
Singh, J., & Singh, C. (2021) · Machine learning for signal processing ... · doi:10.1109/mlsp52302.2021.9596432 · Cited by 1
An Analysis of Feature Detectors Usage in the Task of Lunar Crater Detection
Kuzmenko, N., & Ostroumov, I. (2021) · IEEE International Conference Actual Problems of Unmanned Aerial Vehicles Developments (APUAVD) · doi:10.1109/apuavd53804.2021.9615411 · Cited by 1
Descriptor Sampling VLSI Design Based on BRIEF Algorithm for Surrounding View Application
Lin, J.-Y., Chou, H.-S., Su, K.-Z., et al. (2021) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-tw52618.2021.9603183 · Cited by 1
“There are several main methods for the feature detection, such as Oriented FAST Rotated BRIEF (ORB) [1], Scale Invariant Feature Transform (SIFT) [2] , and Speeded-Up Robust Features (SURF) [3].”
MethodRobust Optimized Structural Feature-Based Transformation Parameter Estimation for Image Registration
Hazra, J., Chowdhury, A. R., Dasgupta, K., & Dutta, P. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-5207-3_44 · Cited by 1
Quaternion-Based Non-Linear Motion Estimation Method
Петрович, К. А., & Goshin, Y. V. (2021) · International Conference on Information Technology and Nanotechnology (ITNT) · doi:10.1109/itnt52450.2021.9649162 · Cited by 1
Ye, J. C. (2021) · Mathematics in industry · doi:10.1007/978-981-16-6046-7_2 · Cited by 1
AN EFFICIENT KEYPOINT FEATURE EXTRACTION TECHNIQUES TO DETECT COPY MOVE IMAGE FORGERY
Gayatri, M., & Rao, C. S. (2021) · IJARCCE · doi:10.17148/ijarcce.2021.101208 · Cited by 1
Vision-Based Safe Landing of UAV using Tiny-SURF Algorithm
Gupta, P., Pareek, B., Kumar, R., & Aeron, A. C. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9658927 · Cited by 1
Interpolation-Based Smart Video Stabilization
Dervişoğlu, S., Sarıgül, M., & Karacan, L. (2021) · Journal of Intelligent Systems with Applications · doi:10.54856/jiswa.202112185 · Cited by 1
“SIFT does direction-independent feature extraction [2]– [4], SURF approach is an optimized version of the SIFT algorithm [5], and FAST is a corner detection algorithm reported to give more successful results than alternatives [2].”
Multi-Scale, Super-Resolution Remote Imaging via Deep Conditional Normalizing Flows
Heintz, A. M., Peck, M. A., & Mackey, I. (2022) · AIAA SciTech Forum · doi:10.2514/6.2022-2499 · Cited by 1
360ViewPET: View Based Pose EsTimation for Ultra-Sparse 360-Degree Cameras
Zhou, Q., Chen, B., Yang, Z., et al. (2021) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism52913.2021.00008 · Cited by 1
Liu, J., & Liu, X. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9658589 · Cited by 1
“Feature-based methods usually use various invariant feature descriptors for matching, such as SIFT [4], SURF [5], Hu’s seven moments, Zernike moments [6], and orientation codes [7].”
MethodSign Language Recognition Using Convexity Defects and Hough Line
Cheok, M. J., Omar, Z., & Jaward, M. H. (2020) · International Journal of Computer & Software Engineering · doi:10.15344/2456-4451/2020/158 · Cited by 1
Japanese Kana and Brazilian Portuguese Manuscript Database
Pereira, L. F. M., Pignelli, F., Cizeski, E. M. A., et al. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-93420-0_17 · Cited by 1
Object class-agnostic segmentation for practical CNN utilization in industry
Gouda, A., Ghanem, A., Kaiser, P., & ten Hompel, M. (2021) · International Conference on Mechanical Engineering and Robotics Research (ICMERR) · doi:10.1109/icmerr54363.2021.9680821 · Cited by 1
Image Anomaly Detection Based on Adaptive Iteration and Feature Extraction in Edge‐Cloud IoT
Zhang, W., Tang, X., & Zhang, J. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/7715753 · Cited by 1
“Subsequently, an accelerated version called speeded up robust features (SURF) was proposed [30].”
MethodInformation Extraction and Object Tracking in Digital Video
Neves, A. J. R., & Gallegos-Funes, F. J. (2022) · Artificial intelligence · doi:10.5772/intechopen.94616
Basu, S., Li, C., & Cohen, F. S. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12284-6 · Cited by 1
“Hand-crafted features such as SIFT [28], SURF [3] and corner points have been extensively used for key point localization.”
MethodFeature Classification‐Based Inclination Measurement for Industrial Assembly Platform
Meng, Z., Meng, L., & Tomiyama, H. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/5911031 · Cited by 1
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.