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 10,501–10,600 of 14,752
Mechanical Identification of Extra Large Hydraulic Engineering Vehicles Based on Video Big Data
Wu, S.-Q., Wang, Y., & Zhang, Z.-Y. (2019) · IEEE International Conference on Big Data Computing Service and Applications (BigDataService) · doi:10.1109/bigdataservice.2019.00047 · Cited by 1
“The SURF algorithm consists of the following steps: (1) The construction of the Hessian matrix Hessian.”
MethodInfluentialReal-time Online UAV Images Mosaic with Robustness to Cumulative Errors
Xia, X., Wang, B., Li, J., et al. (2020) · International Conference on Computing, Networks and Internet of Things (CNIOT) · doi:10.1145/3398329.3398361 · Cited by 1
“The main algorithms for extracting the feature points are SIFT [6], SURF [7], and ORB [8].”
MethodBrachyView: development of an algorithm for real-time automatic LDR brachytherapy seed detection
Brennen, T., Galli, L., Cutajar, D. L., et al. (2020) · Physics in Medicine and Biology · doi:10.1088/1361-6560/abac9e · Cited by 1
Crowdsourcing Trajectory Based Indoor Positioning Multisource Database Construction on Smartphones
Zhang, X., Liu, T., Li, Q., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60952-8_15 · Cited by 1
Sarasa, C. C. G., & Pabón, J. D. O. (2020) · Revista Universidad Católica de Oriente · doi:10.47286/01211463.285 · Cited by 1
Can We Detect Harmony in Artistic Compositions? A Machine Learning Approach
Vandor, A., van Vollenhoven, M., Weiß, G., & Spanakis, G. (2021) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0010244901870195 · Cited by 2
OSN: Onion-ring support neighbors for correspondence selection
Gong, C., Lu, Y., Song, C., et al. (2021) · Information Sciences · doi:10.1016/j.ins.2021.01.042 · Cited by 1
Meng, Y., Sun, Q., Zhang, C., & Tang, Y. S. (2020) · Cyber-Physical Systems · doi:10.1080/23335777.2020.1811386 · Cited by 1
“In order to improve accuracy, SIFT [22], SURF [23], ORB [24], etc., are used to extract feature points, which contain information such as illumination, scale, rotation and other information from different views.”
MethodOn the Comparison of Mono Visual Odometry Front End in Low Texture Environment
Wang, X., Li, Q., & Lin, Z. (2020) · International Conference on Mechatronics, Robotics and Automation (ICMRA) · doi:10.1109/icmra51221.2020.9398353 · Cited by 1
“Numerous image features, such as SIFT [14], SURF [15], ORB[5], have been proposed by researchers of graphic algorithms.”
MethodSrinath, R., Aishwarya, P., Suman, B., et al. (2021) · International Conference on Computer Communication and Informatics (ICCCI) · doi:10.1109/iccci50826.2021.9402604 · Cited by 1
Adaptive Real-Time Loop Closure Detection Based on Image Feature Concatenation
Liu, J., Xiao, M., Lin, X., et al. (2021) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas51556.2021.9401368 · Cited by 1
Small Infrared Aerial Target Detection Using Spatial and Temporal Cues
Guo, L., Zhang, W., Sun, X., et al. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87355-4_12 · Cited by 1
Design of a SLAM Map Building System for a Ground-Based Robot Using ROS
Shinde, S. V., Tailor, P., Mahajan, T., et al. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-2543-5_23 · Cited by 1
Machine Learning for Measuring and Analyzing Online Social Communications
Bronk, C., Lendasse, A., Lindner, P., Wallach, D. S., & Hammer, B. (2021) · European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) · doi:10.14428/esann/2021.es2021-3 · Cited by 1
A Stitching Method for Large Document Images
Paulhac, L., & Domenger, J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-44854-0_12 · Cited by 1
Illumination-Invariant Feature Detection based on Shallow Hybrid Network Model
Wang, R., Zhang, M., Zeng, L., et al. (2021) · International Conference on Frontiers of Electronics, Information and Computation Technologies · doi:10.1145/3474198.3478273 · Cited by 1
“Many classic detection methods have emerged, such as SIFT [7], SURF [8], FAST [9], ORB [10], TILDE [6], LIFT [11], Key.”
MethodInfluentialImage Geolocation Method Based on Attention Mechanism Front Loading and Feature Fusion
Lu, H., Yang, C., Qi, B., Zhu, M., & Xu, J. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/7168451 · Cited by 1
ASA-Net: Deep representation learning between object silhouette and attributes
Yang, S., Wang, J., Yang, L., & Fei, Z. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.06.071 · Cited by 1
Brand Logo Detection Using Slim YOLO-V4
Dwivedi, P., Saritha, S. K., & Jain, S. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-2535-1_4 · Cited by 1
An early screening method of the diabetic foot based on infrared thermography
Hu, T., Gao, L., Zhang, X., et al. (2022) · International Conference on Signal Image Processing and Communication (ICSIPC) · doi:10.1117/12.2643906 · Cited by 1
Semi-supervised Bolt Anomaly Detection in Haphazard Environment
Liu, C.-W., Yan, Y., Ma, N., Peng, Y., Liu, C., & Chen, Q. (2022) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case49997.2022.9926716 · Cited by 2
“In the field of keypoint detection, some classic but still prevalent methods [16], [17] can accurately detect keypoints in a chaotic scene.”
BackgroundAutomated Honduran Banknote Image Classification using Machine Learning
Castelar, S., Banegas, L. A., Mendoza, D. A., Soto, J. C., & Davila, K. (2022) · IEEE Central America and Panama Convention (CONCAPAN) · doi:10.1109/concapan48024.2022.9997703 · Cited by 1
Semantic-assisted Unified Network for Feature Point Extraction and Matching
Ji, D., You, W., Chen, Y., et al. (2022) · ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry (VRCAI) · doi:10.1145/3574131.3574433 · Cited by 1
“In recent years, hand-crafted feature points (such as SIFT [Lowe 2004], SURF [Bay et al. 2006], etc.) have been adopted by many mainstream open-source systems and commercial software due to their outstanding scale and rotation invariance.”
BackgroundImproved Feature Point and Descriptor Extraction Network for SuperPoint
Suo, Q., Yan, C., Liu, C., & Ma, C. (2022) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec55388.2022.10019834 · Cited by 1
Real Time Victim Detection with Mobile Robot in Smoky Environments
Gelfert, S. (2022) · doi:10.1109/compauto55930.2022.00025 · Cited by 1
“[10] investigate the challenge of victim detection by using the histogram of oriented gradients (HOG) feature descriptor, which is well known in the domain of pedestrian detection [11], and the speeded up robust features descriptor (SURF) for object detection by [12] as a comparative analysis.”
MethodDecision Fusion Based Multi-type Shot Boundary Detection in Real Time
Shi, H., Zhang, Y., & Li, Y. (2022) · International Conference on Information Communication and Signal Processing (ICICSP) · doi:10.1109/icicsp55539.2022.10050708 · Cited by 1
“In [4] [5] [6], the color space histogram combined with canny edge features [7], gradient features, and speeded-up robust features (SURF) [8] is applied to shot boundary detection respectively, which eliminated the influence of fast motion and illumination variation.”
MethodElectron Microscopy Image Registration with Transformers
Feng, F., Zhang, T., Sun, R., He, J., Xiong, Z., & Wu, F. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-30111-7_2 · Cited by 3
Hardware architecture design for real-time SIFT extraction with reduced memory usage
Tsai, T., Wang, R., & Tung, N.-C. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15789-w · Cited by 1
“Due to the good performance of SIFT in feature extraction from the image, many improved methods have been proposed based on SIFT, such as PCA-SIFT [23], SURF [6], GLOH [33], etc.”
Automated Financial Documents Processing System Using Machine Learning
Deshmukh, G. A. (2023) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2023.53905 · Cited by 1
SSML-QNet: Scale-Separative Metric Learning Quadruplet Network for Multi-modal Image Patch Matching
Zhang, X., Sun, Y., Han, Y., et al. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/511 · Cited by 1
A Novel Learning Dictionary for Sparse Coding-Based Key Point Detection
Hong-Phuoc, T., & Guan, L. (2023) · IEEE Multimedia · doi:10.1109/mmul.2023.3285853 · Cited by 1
Preliminary study on the impact of acoustic emissions on fish
Ferreira, F., Diamant, R., Shachar, I., et al. (2023) · doi:10.1109/oceanslimerick52467.2023.10244726 · Cited by 1
DESPP-DETR: A Dense Connection Efficient Spatial Pooling DEtection TRansformer for Vehicle Detection
Krishnendhu, S. P., & Mohandas, P. (2023) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3628426 · Cited by 1
Incorporating Global Correlation and Local Aggregation for Efficient Visual Localization
Xie, D., Lu, J., Song, Z., & Chen, X. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-46308-2_6 · Cited by 1
Image Feature Detectors in Agricultural Harvesting: An Evaluation
Cui, Z., Xu, L., Yang, Y., et al. (2023) · Sensors · doi:10.3390/s23239497 · Cited by 1
Abdollahinejad, G., & Hashemi, M. (2023) · doi:10.1109/icee59167.2023.10334862 · Cited by 1
Real time anatomical landmarks and abnormalities detection in gastrointestinal tract
Khan, Z., & Tahir, M. A. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1685 · Cited by 6
“SURF is a scale-invariant and rotation-invariant descriptor of image ( Bay, Tuytelaars & Gool, 2006 ).”
BackgroundAssessing Local Descriptors for Feature-Based Registration of Whole-Slide Images
Elskens, A., Foucart, A., Zindy, E., Debeir, O., & Decaestecker, C. (2023) · International Symposium on Medical Information Processing and Analysis (SIPAIM) · doi:10.1109/sipaim56729.2023.10373514 · Cited by 2
Towards Content-based Pixel Retrieval in Revisited Oxford and Paris
An, G., Kim, W. J., Yang, S., Li, R., Huo, Y., & Yoon, S. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01875 · Cited by 6
“The classical local features have SIFT [23], SUFT [3], and rootSIFT [2].”
BackgroundWang, Z., Shen, M., & Chen, Q. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18382-x · Cited by 1
“Traditional methods are ORB [21], SURF [39], BRISK [40], and SIFT [20].”
A Real-Time Localization Algorithm for Unmanned Aerial Vehicle Based on Continuous Images Processing
Geng, P., Yang, A., & Liu, Y. (2024) · Journal on artificial intelligence · doi:10.32604/jai.2024.047642 · Cited by 1
Humanoid robot action using multi-mode fusion based on frame expert system
Juang, L. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19058-2 · Cited by 1
Pest Density Classification using MobileNet Architecture
Hegde, C., Shylashree, N., & Raghu, B. N. (2024) · IEEE International Conference for Women in Innovation, Technology & Entrepreneurship (ICWITE) · doi:10.1109/icwite59797.2024.10503567 · Cited by 1
“The most recent works that have used hand-crafted features like GIST, HOG, SIFT and SURF to build traditional machine learning models [8 – 11].”
MethodCai, Z., Zhang, S., Zhang, J., et al. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01461-9 · Cited by 1
“…point matching, but fewer matching pairs are obtained [14]; (3) these methods lack consideration of the distribution of matching feature points [15]; (4) these methods are only improved from the perspective of the descriptors [12, 16], and it is difficult to distinguish true and false matches.”
A visual area detection algorithm based on mirror splicing for motorcycle indirect vision test
Li, Y., Liu, Z., Jiang, S., et al. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad4b52 · Cited by 1
“Feature points were matched using SURF [21] because of their invariance to scale, illumination changes, and rotation.”
Line Fitting-Based Corner-Like Detector for 2D Laser Scanners Data*
Sousa, R. B., Sobreira, H., Silva, M. F., et al. (2024) · International Conference on Automation, Robotics and Applications · doi:10.1109/icara60736.2024.10553006 · Cited by 1
“The proposed algorithm performs local line fitting evaluated in multiple distance-based scales around a certain point, similar to Speeded Up Robust Features (SURF) [23].”
MethodSelf‐supervised binocular depth estimation algorithm with self‐rectification for autonomous driving
Bao, J., Yu, H., Zou, Y., Lv, J., Liu, W., & Cao, Y. (2024) · IET Intelligent Transport Systems · doi:10.1049/itr2.12522 · Cited by 1
BinVPR: Binary Neural Networks towards Real-Valued for Visual Place Recognition
Wang, J., Han, J., Dong, R., & Kan, J. (2024) · Sensors · doi:10.3390/s24134130 · Cited by 1
“VPR based on local feature descriptors requires a detection phase that determines individual patches or key points within the image to retain as local features, including SIFT [32], SURF [33], and ORB [34].”
Method2D3D-DescNet: Jointly Learning 2D and 3D Local Feature Descriptors for Cross-Dimensional Matching
Chen, S., Su, Y., Lai, B., Cai, L., Hong, C., Li, L., Qiu, X., Jia, H. L., & Liu, W. (2024) · Remote Sensing · doi:10.3390/rs16132493 · Cited by 1
“On the one hand, the description strategies of 2D handcrafted feature descriptors are usually classified into gradient statistics (SIFT [5], SURF [6]), local binary pattern statistics (LBP [26], RLBP [27]), local intensity comparison (BRIEF [28], ORB [29]), and…”
Chen, S., Guo, P., Wang, J., Xu, X., Meng, L., & Zhang, X. (2024) · Journal of Aerospace Engineering · doi:10.1061/jaeeez.aseng-5695 · Cited by 1
Fingerphoto morphing attack generation using texture descriptors based landmarks
Li, H., & Ramachandra, R. (2024) · Scientific Reports · doi:10.1038/s41598-024-66790-8 · Cited by 1
A 6D Object Pose Estimation Method combining Self-attention Mechanism
Sun, Y., Dai, S., Dang, J., & Yong, J. (2024) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea62105.2024.10604264 · Cited by 2
“Representative algorithms include Scale Invariant Feature Transform (SIFT) algorithm [5], Speeded Up Robust Features (SURF) algorithm [6], FAST (Features from Accelerated Segment Test) algorithm [7], and ORB (Oriented Fast and Rotated Brief) algorithm [8].”
MethodKosykh, V. P., Gromilin, G. I., & Yakovenko, N. S. (2024) · Optoelectronics Instrumentation and Data Processing · doi:10.3103/s8756699024700195 · Cited by 1
DL-PoseNet: A Differential Lightweight Network for Pose Regression over SE(3)
Li, W., Liu, J., Wang, Y., Hao, W., Ren, D., & Chen, L. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611375 · Cited by 5
“The majority of these techniques follow the same pipeline: keypoints are extracted using several mathematic tools such as the SURF [11], ORB [12], then a quadratic error function is derived which is generally solved using the Gauss-Newton method [13], Levenberg-Marquardt method [14] and their…”
MethodYan-xi, L., Song, A., Liu, G., et al. (2024) · Remote Sensing · doi:10.3390/rs16162966 · Cited by 1
Repetitive Patterns Recognition in Textures of Ancient Peruvian Pottery
Sepulveda, S., Bustos, B., & Sipiran, I. (2024) · Journal on Computing and Cultural Heritage · doi:10.1145/3694789 · Cited by 1
“Under certain assumptions about the transformations that could occur between the instances to be matched, one could detect matches using methods such as Scale Invariant Feature Transform [31], Speeded-Up Robust Features [1], and the variations that occurred later [5, 39].”
Zhou, Y., Cui, J., Lian, B., Zhao, X., Zhang, Z., & Wan, Z. (2024) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea61579.2024.10664843 · Cited by 1
“…feature extraction algorithms such as Harris corner detection [3], Scale-Invariant Feature Transform (SIFT) [4], Speeded Up Robust Features (SURF) [5], and Histogram of Oriented Gradients (HOG) [6] are implemented to delineate diverse image characteristics, encompassing color, texture, region,…”
MethodGastrointestinal image stitching based on improved unsupervised algorithm
Yan, R., Jiang, Y. Y., Zhang, C., et al. (2024) · PLoS ONE · doi:10.1371/journal.pone.0310214 · Cited by 1
“SURF [11] offers faster feature extraction and matching than SIFT, but at the cost of reduced matching points and lower tolerance to scaling and rotation changes, problematic in endoscopic applications with frequent viewpoint variations.”
BackgroundUnifying Building Instance Extraction and Recognition in UAV Images
Hu, X., Zhou, Y., Lan, C., et al. (2024) · Remote Sensing · doi:10.3390/rs16183449 · Cited by 1
Co-registration of PRISMA Hyperspectral Imagery for Accurate Land Cover Classification
Xu, Q., Yordanov, V., Tran, X. T., et al. (2024) · Lecture notes in civil engineering · doi:10.1007/978-3-031-71000-1_15 · Cited by 1
Tooth Motion Monitoring in Orthodontic Treatment by Mobile Device-Based Multi-View Stereo
Xie, J., Zhang, C., Wei, G., Wang, P., Wei, G., Liu, W., Gu, M., Luo, P., & Wang, W. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3470992 · Cited by 5
Multi-modal CrossViT using 3D spatial information for visual localization
Kang, J., Mark, M., & Hong, H.-K. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20382-w · Cited by 1
“Algorithms that are invariant to transformations such as scale-invariant feature transform (SIFT) [16], speeded-up robust features (SURF) [17], as well as oriented fast and rotated brief (ORB) [18] are widely used for generating local key-point descriptors.”
Kammel, F., & Reiterer, A. (2024) · Forests · doi:10.3390/f15111846 · Cited by 1
Yu, H., Song, W., Zhang, B., et al. (2024) · Land · doi:10.3390/land13111842 · Cited by 1
Enhancing Image Stitching Algorithms with SIFT Feature Detection
Wang, M. (2024) · Applied and Computational Engineering · doi:10.54254/2755-2721/105/2024tj0069 · Cited by 1
“Researchers have achieved many results in feature point extraction (e.g., SIFT, SURF), image alignment (e.g., RANSAC), and image fusion (e.g., seamless cloning) [4,5].”
Exploiting deep cross-semantic features for image retrieval
Lu, Z., Liu, G., Hu, J.-K., & Li, Z. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.126157 · Cited by 2
Real-Time Beach Monitoring: Addressing Beach Safety with UAVs and Computer Vision
Da‐Silva‐Gomez, R., Rodríguez-Ramos, A., Pérez-Saura, D., et al. (2024) · doi:10.1109/robot61475.2024.10797412 · Cited by 1
“Classical methods such as SIFT (Scale-Invariant Feature Transform) [3] and SURF (Speeded-Up Robust Features) [4] are commonly used for feature extraction in images.”
An Improved Registration Method for UAV-Based Linear Variable Filter Hyperspectral Data
Wang, X., Yu, C., Zhang, X., et al. (2024) · Remote Sensing · doi:10.3390/rs17010055 · Cited by 1
Noda, E., Huang, L., Chong, T., Jain, S., Madestam, A., Tompsett, A., Druckenmiller, H., & Hsiang, S. (2024) · BigData Congress [Services Society] · doi:10.1109/bigdata62323.2024.10825635 · Cited by 1
Performance Evaluation of Feature Detectors and Descriptors with Close-Range Solar Panel Images
Ansar, E., Sewil, S., Maksood, F. Z., et al. (2024) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip63160.2024.10849783 · Cited by 1
YOLOOI: YOLO with Robustness to Outliers and Illumination
Jiang, H., & Cheng, X. (2024) · International Conference on Computer, Vision and Intelligent Technology (ICCVIT) · doi:10.1109/iccvit63928.2024.10872438 · Cited by 1
“Nonetheless, these techniques heavily rely on manually crafted feature extraction methods like SIFT [12] and SURF [13], which often struggle to cope with the wide range of defect types encountered in real-world scenarios.”
Liu, Y., Wu, X., Ren, J., Wang, J., Bo, Y., & Wang, Y. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3546970 · Cited by 2
“The handcrafted features include color histogram, scale-invariant feature transform [1], histogram of oriented gradient [2], local binary patterns [3], speeded up robust features [4], and so on.”
Yuxiang, 林. L., Xiaojun, 韩. H., Xiufeng, 李. L., et al. (2025) · Acta Optica Sinica · doi:10.3788/aos241761 · Cited by 1
Training-free Adapter for Multi-Modal Image Matching for All-Day Visual Place Recognition
Uggi, A., & Channappayya, S. S. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889993 · Cited by 2
“The classical approaches [20], [21] use a two-stage hand-designed pipeline to detect and describe keypoints, with descriptors used for matching.”
EFormer-VPR: Fusing Events and Frames with Transformer for Visual Place Recognition
Zhang, Y., Shen, Y., Zhu, Z., Hai, R., Chen, S., & Zheng, N. (2024) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc58415.2024.10919907 · Cited by 1
“Learning-based algorithms are usually used to extract basic features, which have shown better performance than handcrafted algorithms [29], [30] in large-scale image retrieval tasks.”
Ajewole, O. K., Anjuwon, O., Ezugwu, C. A. K., Adetiba, G., Adewuyi, I. A., & Abiola, J. O. (2024) · IEEE Nigeria International Conference on Disruptive Technologies for Sustainable Development (NIGERCON) · doi:10.1109/nigercon62786.2024.10927138 · Cited by 1
Gaussian Splatting for Rapid and Precise 3D Modeling in Mapping Application: Literature Review
Wijaya, H. M., Handayani, H. H., & Hariyanto, T. (2024) · IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS) · doi:10.1109/agers65212.2024.10932937 · Cited by 3
“However, these techniques are often slow and computationally demanding, making them unsuitable for real-time applications where speed is as crucial as accuracy [1][6].”
Clothing Image Retrieval Algorithm Using YOLOv8 and Attention Model
Ye, S., Sorokina, V. V., & Ablameyko, S. (2024) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661824701153 · Cited by 1
“Traditional methods for feature extraction include SIFT (scale-invariant feature transform) [10], SURF (speeded-up robust features) [2], HOG (histogram of oriented gradients) [4], and others.”
Research on Rapid and Accurate 3D Reconstruction Algorithms Based on Multi-View Images
Yang, L., Ge, H., Yang, Z., et al. (2025) · Applied Sciences · doi:10.3390/app15084088 · Cited by 1
Litvinov, P. A., & Bessmertny, I. (2025) · Scientific and technical journal of information technologies mechanics and optics · doi:10.17586/2226-1494-2025-25-2-303-310 · Cited by 1
Cao, Z., Hui, F., Xu, X., et al. (2025) · Transactions in GIS · doi:10.1111/tgis.70052 · Cited by 1
Robust Vision-Based Target Outline Reconstruction and In-Plane Trajectory Measurement
Hong, S., Xiong, Y., Gou, Y., He, Q., & Peng, Z. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3565061 · Cited by 1
“By utilizing the Hessian matrix and Haar wavelets, the SURF method extracts feature points as descriptors and matches them across frames to track motion [26].”
Regional Type II multivariate Laplace descriptor based on Lie group
Liao, D., Liu, G., & Wang, H. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111776 · Cited by 1
Ou, D., & Xiao, Y. (2025) · Journal of Nondestructive Evaluation · doi:10.1007/s10921-025-01191-z · Cited by 2
“Another approach avoids the need for 3DmarkerspriorsbyemployingfeaturedescriptorslikeSIFT [21], SURF [22], ORB [23], and BRISK [24] to search and match 2D-2D point pairs across multi-view images.”
Multiview Landmark-Assisted UAV Swarm 6-DoF Pose Estimation Using Resonant Beam and VIO
Du, S., Xu, M., Li, Y., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3573755 · Cited by 1
“Feature point-based methods provide accurate estimation in feature-rich environments [17], with common feature extractors, including SIFT [18], SURF [19], and ORB [20], which also serve as the foundation for multiview landmark-based methods.”
MPA-Det: multi-path aggregation-based object detection framework for aerial visual computing
Lei, Y., Jin, K., Qiu, Z., Sun, Y., Bai, H., & He, W. (2025) · The Visual Computer · doi:10.1007/s00371-025-03933-6 · Cited by 2
“Classic feature extraction methods, such as SIFT (Scale-Invariant Feature Transform) [9] and SURF (Speeded-Up Robust Features) [10], have been widely used for their robustness to scale, rotation, and illumination changes.”
6-DoF object pose estimation based on deep learning and iterative optimization techniques
Liu, Y., Ma, L., Ren, Y., & Qi, S. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04218-0 · Cited by 1
WinMRSI: Feature Matching With Window Attention for Multimodal Remote Sensing Image
Di, Y., Liao, Y., Liu, Y., Zhou, H., Zhu, K., Lu, M., Duan, Q., & Liu, J. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3576233 · Cited by 3
Gao, T., Lan, C., Lyu, L., Shi, Q., Huang, W., Wang, Y., & Mu, Z. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3576741 · Cited by 5
HTMP: Triple-Scale Multilevel Network With Hessian Spatial Loss for Pansharpening
Zhang, B., Zhang, D., Shi, S., & Guo, Z. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3580088 · Cited by 1
An Optimal Viewpoint-Guided Visual Indexing Method for UAV Autonomous Localization
Ye, Z., Zheng, Y., Ji, Z., et al. (2025) · Remote Sensing · doi:10.3390/rs17132194 · Cited by 1
A Survey of Visual SLAM Based on RGB-D Images Using Deep Learning and Comparative Study for VOE
Le, V.-H., & Nguyen, T.-H.-P. (2025) · Algorithms · doi:10.3390/a18070394 · Cited by 2
Detection and localization of copy-move tampering along with adversarial attack in a digital image
Diwan, A., & Roy, A. (2025) · Discover Computing · doi:10.1007/s10791-025-09658-3 · Cited by 2
“Based on the above result, it was decided to use SURF (Speeded-Up Robust Features) [42] as the detector for the proposed keypoint-based approach.”
Liu, Y., Huang, K., Qi, X., Hao, S., Li, J., Huang, Z., Yang, M., Zhao, N., Li, Y., Mao, R., et al. (2025) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2025.3580227 · Cited by 1
“The frontend computes the initial pose state of camera, primarily through feature point extraction and matching [14], [15], [16].”
MultS-ORB: Multistage Oriented FAST and Rotated BRIEF
Zhang, S., Wang, Y., Ma, J., Yang, J., Huang, L., & Ning, X. (2025) · Mathematics · doi:10.3390/math13132189 · Cited by 2
Pan, K., Guo, W. J., Liu, Y., et al. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3586317 · Cited by 1
“Traditional methods rely on handcrafted features [9], [10] for image matching, which, despite their robustness to rotation and scale variations, only capture low-level geometric and texture information, lacking understanding of high-level semantics such as terrain categories and building…”
Real Time Purpose Identification and Trace Using Deep-Learning and Computer Vision
Chauhan, S., & Mehra, R. (2024) · doi:10.1109/sustained63638.2024.11074164 · Cited by 1
“The real-time identification rate can be enhanced by integrating object tracking and performing categorization on a subset of frames captured at fixed intervals [18].”
Wang, Y., Chao, H., Zhang, Y., et al. (2025) · PLoS ONE · doi:10.1371/journal.pone.0328052 · Cited by 1
“Traditional methods such as SIFT [15], SURF [16], FAST [17], and ORB [18] have long been used to detect initial features.”
Key-Points Based Visual Servo For Accurate Cross-Task Robot Manipulations
Zhang, C., Xie, Z., & Chen, G. (2024) · doi:10.1145/3735014.3735890 · Cited by 1
“Traditional VS frameworks rely on handcrafted visual features (e.g., SIFT [2], SURF [3], and ORB [4]) to extract and match feature points, which are then used to estimate pose deviations and generate control signals.”
An improved similarity matching model for the content-based image retrieval model
Asokaraj, M., Kumar, J. P., & Ashwin, N. (2025) · International Journal on Smart Sensing and Intelligent Systems · doi:10.2478/ijssis-2025-0031 · 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.