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 11,301–11,400 of 14,752
Robust OCR Pipeline for Automated Digitization of Mother and Child Protection Cards in India
Pant, D., Talukder, D., Seth, A., Pant, D., Singh, R. K., Dua, B., Pandey, R., Maruthi, S., Johri, M., & Arora, C. (2023) · ACM Journal on Computing and Sustainable Societies · doi:10.1145/3608114 · Cited by 2
Underwater Terrain Map Building Based on Depth Image Using Multi-Beam Sonar Sensor
Lim, Y., Lee, Y., Yeu, T., et al. (2023) · International Conference on Ubiquitous Robots (UR) · doi:10.1109/ur57808.2023.10202363 · Cited by 1
“A. Image Feature Extraction Method Representative image feature extraction methods include SIFT (Scale-Invariant-Feature Transform)[1], SURF (Speeded Up Robust Features)[2], ORB (Speeded Up Robust Features)[3].”
MethodPotapov, A., Kurenkov, M., Karpyshev, P., Yudin, E., Savinykh, A., Kruzhkov, E., & Tsetserukou, D. (2023) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2023-spring57618.2023.10200561 · Cited by 1
A REVIEW OF VISUAL ODOMETRY FOR UAV AUTONOMOUS NAVIGATION
Khachatryan, T. B. (2023) · doi:10.53297/18293336-2023.1-9 · Cited by 1
Surface Defect Detection for Die Castings Based on the Improved YOLOv5 Method
Zhang, H., Xu, X., Zhu, Z., You, T., Li, Q., & Li, D. (2023) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm58088.2023.10218864 · Cited by 1
Comprehensive Study of Indexing Techniques Used for Extracting CNN Features
Saini, M., Gupta, P., & Kaur, H. (2023) · International Conference on Inventive Research in Computing Applications (ICIRCA) · doi:10.1109/icirca57980.2023.10220679 · Cited by 1
“Some popular handcrafted feature extraction techniques include ScaleInvariant Feature Transform (SIFT)[2], Speeded Up Robust Feature (SURF)[3], and Local Binary Patterns (LBP)[4].”
MethodInfluentialSwin Transformer based Siamese Network for Thermal and Optical Image Registration
Elsaeidy, M., Yağmur, İ. C., Ateş, H. F., & Gunturk, B. K. (2023) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu59756.2023.10224035 · Cited by 2
Research on Matching Players Before and After Occlusion for Field Sports
JIANG, W., YAMAMOTO, Y., Nakamura, K. D., Tanaka, C., Tanaka, S., Naruo, T., & Zhiwei, X. I. A. O. (2022) · Journal of the Japan society of photogrammetry and remote sensing · doi:10.4287/jsprs.61.218 · Cited by 1
Fast and robust for texture-less feature registration via adaptive heterogeneous kernels
Ma, Y., Song, Q., Lin, H., Liu, C., Hu, M., & Zhu, X. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110945 · Cited by 1
Effective image registration model using optimized KAZE algorithm
Zhang, S., Shen, J., Zheng, S., & Tang, J. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16887-5 · Cited by 1
Self-supervised Lunar Surface Image Feature Point Detection and Matching
Qian, K., Wang, W., Ma, J., Han, L., Chen, M., & Qi, C. (2023) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar58764.2023.10250140 · Cited by 1
Automatic Helmet (Object) Detection and Tracking the Riders Using Kalman Filter Technique
Vairamani, A. D. (2023) · Contributions to environmental sciences & innovative business technology · doi:10.1007/978-981-99-3288-7_7 · Cited by 1
Yeh, S.-H., Xie, S., Yan, W., & Song, D. (2023) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case56687.2023.10260305 · Cited by 1
Pafitis, M., Savva, A. D., Kyrkou, C., et al. (2023) · Springer eBooks · doi:10.1007/978-3-031-40677-5_12 · Cited by 1
Research on Workpiece Corner Detection Method based on Combination Method Image Feature Points
Han, D., Li, T., Huang, M., et al. (2023) · IEEE International Conference on Electronic Measurement & Instruments · doi:10.1109/icemi59194.2023.10270113 · Cited by 1
An emotion recognition system: bridging the gap between humans-machines interaction
Nouman, A., Iqbal, H., & Saleem, M. K. (2023) · IAES International Journal of Robotics and Automation (IJRA) · doi:10.11591/ijra.v12i4.pp315-324 · Cited by 2
Heidari, M., & Mehrdad, V. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17174-z · Cited by 2
“This algorithm was introduced by Herbert Bay et al. [30, 31] which can be used for object recognition and classification.”
CAD system for epileptic seizure detection from EEG through image processing and SURF-BOF technique
Alshayeji, M. H. (2023) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad0572 · Cited by 1
Comparative study of feature extraction algorithms for panorama stitching
Ding, T. (2023) · Applied and Computational Engineering · doi:10.54254/2755-2721/16/20230900 · Cited by 1
Distance-Aware Vector-Field and Vector Screening Strategy for 6D Object Pose Estimation
Wang, L., Yang, C., Xin, J., & Yin, B. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-46308-2_31 · Cited by 1
Лаптев, Н. В., Gerget, O. M., Лаптев, В. В., et al. (2023) · Известия ТПУ Промышленная кибернетика · doi:10.18799/29495407/2023/1/13 · Cited by 1
Lin, C.-F., Su, C.-W., & Chen, C. (2023) · Optical Engineering · doi:10.1117/1.oe.62.11.113103 · Cited by 1
An efficient hybrid approach for vehicle detection and tracking
El-Alami, A., Nadir, Y., Amhaimar, L., & Mansouri, K. (2023) · International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom59760.2023.10322924 · Cited by 2
A New Visual Front-end Combining KLT with Descriptor Matching for Visual-inertial Odometry
Wu, Z., Yu, B., Li, R., Deng, Z., & Shi, Y. (2023) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-023-02008-9 · Cited by 1
“Other methods, such as SIFT [10], SURF [11], and AKAZE [12], are based on the Difference of Gaussian (DoG) and are more adaptable to scale but computationally expensive.”
Bianconi, F., Filippucci, M., Pelliccia, G., Rossi, G. L., Tocci, T., Tribbiani, G., & Correa, D. (2023) · Materials Evaluation · doi:10.32548/2023.me-04311 · Cited by 2
Boosting Facial Landmark Detection via Self-supervised and Semi-supervised Learning
Minh, C. N., Ngoc, T. N., Dinh, T. L., Sang, D. V., Wong, P.-M., Chng, C.-B., & Chui, C. (2023) · International Symposium on Information and Communication Technology · doi:10.1145/3628797.3629017 · Cited by 2
MATCHING FILTER-BASED VSLAM OPTIMIZATION IN INDOOR ENVIRONMENTS
Wei, S., & Wang, S. (2023) · 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-xlviii-1-w2-2023-679-2023 · Cited by 1
Remote sensing image registration based on multi-head self-attention mechanism
Jianxing, H., Chen, Y., Xiuhan, D., et al. (2023) · International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS) · doi:10.1109/iciibms60103.2023.10347825 · Cited by 1
Hybrid6D: A Dual-Stream Transformer-CNN Approach for 6D Object Pose Estimation from RGB-D Images *
Fu, S., Zhang, Q., Sun, X., Liu, M., & Fan, Z. (2023) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio58561.2023.10354630 · Cited by 2
A Hybrid Supervised Fusion Deep Learning Framework for Microscope Multi-Focus Images
Yang, Q., Chen, H., Jiang, M., Wang, M., Zhang, J., Sun, Y., & Tan, T. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-50078-7_17 · Cited by 1
Klasifikasi Tenun Timor Menggunakan Metode SVM Berdasarkan Speeded Up Robust Features
Kelen, Y. P. K., & Baso, B. (2023) · Jurnal Teknologi Informasi dan Ilmu Komputer · doi:10.25126/jtiik.1067625 · Cited by 1
Витальевич, Л. Н., Витальевич, Л. В., Gerget, O. M., Kolpashchikov, D. Y., & Кравченко, A. А. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-50423-5_4 · Cited by 1
Multi-scale pyramidal hash learning for traditional building facade image retrieval
Wang, C., Wang, Y., Deng, D., Cao, J., & Zhao, W. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-02057-4 · Cited by 1
“Afterward, the SIFT algorithm (Scale-invariant feature transform) [28] and accelerated robust features (SURF) [3] were introduced.”
Three-dimensional positioning on image point of interest via google geographic information
Jie, L., Yang, C., & Kao, Y.-F. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-023-02947-8 · Cited by 1
“…in addition to variations in ambient lighting and panorama distortion, and traditional image alignment techniques such as scale-invariant feature transform (SIFT) [13] and speeded-up robust features (SURF) [14] feature point matching algorithms can no longer meet the matching accuracy requirements.”
An elliptical sampling based fast and robust feature descriptor for image matching
Gupta, N., & Rohil, M. K. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17951-w · Cited by 1
“Speeded-Up Robust Features Descriptor (SURF) descriptor, proposed by Bay et al. [22], is designed as an efficient alternative to SIFT.”
Expanded photo-model-based stereo vision pose estimation using a shooting distance unknown photo
Tian, H., & Wang, J. (2024) · International Journal of Advanced Robotic Systems · doi:10.1177/17298806231218789 · Cited by 1
“19 However, mismatch is inevitable.”
Technique to Estimate Geometry Information from Gaze Detection Datasets Based on Multiple Cameras
Park, T. (2023) · Journal of Digital Contents Society · doi:10.9728/dcs.2023.24.12.3071 · Cited by 1
Local topology similarity guided probabilistic sampling for mismatch removal
He, Z., Shen, C., & Zhao, X. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110293 · Cited by 2
TEG: image theme recognition using text-embedding-guided few-shot adaptation
Wang, J., Lu, W., Wang, Y., Shi, K., Jiang, X., & Zhao, H. (2024) · Journal of Electronic Imaging · doi:10.1117/1.jei.33.1.013028 · Cited by 1
“Traditional shallow machine learning algorithms, such as support vector machines and NN, using handcrafted low-level or shallow visual features 8 – 12 have been extensively studied extensively for image recognition tasks.”
BackgroundRemote sensing image feature matching via graph classification with local motion consistency
Liu, Y., Gao, X., & Li, Z. (2024) · International Journal of Digital Earth · doi:10.1080/17538947.2024.2308713 · Cited by 1
“Speeded Up Robust Features (SURF) (Bay, Tuytelaars, and Van Gool 2006): Similar to SIFT, but uses integral images to accelerate computation, resulting in higher speed.”
Multi-View Consistency for Correspondence Pruning
Yang, P. L., Peng, F., Liu, Y., & Zhou, W. Z. (2023) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia60676.2023.10429445 · Cited by 1
Using a Robot for Indoor Navigation and Door Opening Control Based on Image Processing
Hsu, C.-H., & Juang, J. (2024) · Actuators · doi:10.3390/act13020078 · Cited by 1
Detection of Counterfeit Currency Through SURF and Haar Cascade Classifier
Kashyap, A., Suresh, B., & Tyagi, K. D. (2023) · doi:10.1109/icsc60394.2023.10441382 · Cited by 1
A New Image Stitching Method with Entropy and Template Matching
Wu, J., Lin, Y., Teng, K., et al. (2024) · International Conference on Consumer Electronics · doi:10.1109/icce59016.2024.10444502 · Cited by 1
“[7] proposed the speeded-up robust feature (SURF) algorithm based on SIFT.”
MethodMulti-View 3D Reconstruction for Construction Site Monitoring
Chen, G., Vlaminck, M., Philips, W. R., et al. (2024) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0012308300003660 · Cited by 1
“Traditional methods such as SIFT (Lowe, 2004) and SURF (Bay et al., 2006), based on handcrafted features, face challenges with viewpoint changes and repetitive patterns.”
MethodSilhouette-Based 6D Object Pose Estimation
Cui, X., Li, N., Zhang, C., Zhang, Q., Feng, W., & Wan, L. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2092-7_8 · Cited by 1
“However, these methods require the use of feature descriptors such as SIFT [17], SURF [1], or ORB [24], hence struggle to handle textureless objects.”
MethodA Real-time Positioning Model for UAV's Patrolling Images Based on Airborne LiDAR Point Cloud Fusion
Fan, W., Liu, H., Pei, H., et al. (2024) · KSCE Journal of Civil Engineering · doi:10.1007/s12205-024-2254-2 · Cited by 1
Fast keypoint filtering for feature-based identity documents classification on complex background
Valishina, N. Z., Gayer, A. V., Skoryukina, N. S., et al. (2024) · doi:10.1117/12.3023194 · Cited by 1
“The most popular algorithms for addressing this task include SIFT [4], SURF [5], BRISK [6] and ORB [7].”
MethodDurukan, G., Nar, M. T., Özcan, A., Çakıl, L., & Kara, H. (2024) · Engineering cyber-physical systems and critical infrastructures · doi:10.1007/978-3-031-56322-5_1 · Cited by 2
A Visual SLAM Based-Method for Vehicle Localization
Hsu, C.-Y., & Lin, N.-H. (2024) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2024-01-2845 · Cited by 1
A Review of RGB-D Image Classification Methods
Yadav, N. K., & Saraswat, M. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-9531-8_2 · Cited by 1
Bian, H., Fan, S., Zhang, H., Qin, L., Cui, H., & Wang, X. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03175-4 · Cited by 2
“For instance, normalization of descriptors is used in [6, 10, 11].”
Patch-Based Transformer for Low-Light Image Enhancement
Zhang, Y., Jiang, S. L., & Tang, X. (2023) · doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics60724.2023.00065 · Cited by 1
“For instance, feature extraction algorithms like SIFT [17] and SURF [18] employ image patches to detect keypoints across different scales and orientations.”
MethodLearning context-aware local feature descriptors for 3D reconstruction
Yang, J., Zhou, J., Fan, H., Dong, J., & Yu, H. L. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127793 · Cited by 2
Pose Estimation Method of Maintainability Test Components Based on PVNet
Wang, F., Ge, Z., qi, C., Yang, Y., & Luo, X. (2023) · International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) · doi:10.1109/cei60616.2023.10527854 · Cited by 1
“Commonly used feature point extraction algorithms include SIFT [5] and SURF [6].”
MethodImage retrieval using underlying importance feature histogram
He, Q., & Liu, G. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09735-6 · Cited by 2
“Some representative approaches use local descriptors; for instance, the scale-invariant feature transform [23], Speeded-Up Robust Features [24] and bag-of-words (BoW) models [25].”
UAV Cross-Modal Image Registration: Large-Scale Dataset and Transformer-Based Approach
Xiao, Y. H., Liu, F., Zhu, Y., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-1417-9_16 · Cited by 1
Automatic Detection and Extraction Framework of Ground Control Points for Remotely Sensed Data
Mezouar, O., Meskine, F., & Boukerch, I. (2024) · IEEE Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS) · doi:10.1109/m2garss57310.2024.10537306 · Cited by 1
“After selecting the best detector-descriptor features, we utilized the Lowe's ratio test, as mentioned in [16] and [17] to determine the validated matches.”
MethodTriangle Descriptor Loop Detection Method Based on Faster-LIO
Wang, S., Huang, H., Yang, J., et al. (2024) · 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-xlviii-4-w10-2024-183-2024 · Cited by 1
Hajebi, B., & Hajebi, P. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09932-3 · Cited by 1
“Studies have also used an ensemble of convolutional neural networks (CNNs) to improve identifying fabric colors [9].”
RetractedOutlier Robust Feature Correspondence by Learning Based Matching Process
Yang, X., Zeng, S., & Liu, Z. (2024) · Journal of Systems Science and Complexity · doi:10.1007/s11424-024-3141-0 · Cited by 1
“The proposed method is closely related to the shape context method [26] among the approaches relying on carefully crafted appearance descriptors like SIFT [1] and SURF [27] .”
SCENES: Subpixel Correspondence Estimation With Epipolar Supervision
Kloepfer, D. A., Henriques, J. F., & Campbell, D. (2024) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv62453.2024.00137 · Cited by 3
“Early efforts involved hand-crafted criteria for keypoint detection, description, and matching in well-established meth-ods such as the Harris corner detector [17], SIFT [26], SURF [3], and ORB [30].”
MethodPDE-Constrained Scale Optimization Selection for Feature Detection in Remote Sensing Image Matching
Peng, Y., Zhou, B., & Qi, F. (2024) · Mathematics · doi:10.3390/math12121882 · Cited by 1
Detection of human finger joints in ultrasound images: structure and optimization
Bąk, A., Wereszczyński, K., Segen, J., et al. (2024) · International Journal of Electronics and Telecommunications · doi:10.24425/ijet.2024.149541 · Cited by 1
Arslan, E., & Şekertekin, A. (2024) · Afyon Kocatepe University Journal of Sciences and Engineering · doi:10.35414/akufemubid.1389048 · Cited by 1
Li, H., Gao, B., He, X., et al. (2024) · The Photogrammetric Record · doi:10.1111/phor.12511 · Cited by 1
“…algorithm selection, SURF and SIFT have certain scale invariance, but compared with the two operators, the SURF operator has faster computing speed (Bay et al., 2006); the ASIFT operator itself corrects the affine deformation and (5) cannot obtain the scale value of the original image feature…”
Hidden Barcode in Sub-Images with Invisible Locating Marker
Jia, J., Gao, Z., Yang, Y., Sun, W., Zhu, D., Liu, X., Min, X., & Zhai, G. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3674976 · Cited by 2
“Key Points Detection : To match image pairs with the same contents, many methods of key points detection and matching have been proposed, such as Harris corner detection [15], SIFT [22], ORB [28], and SURF [1], and others [44].”
Dish Detection in Indian Food Platters: A Computational Framework for Diet Management
Goel, M., Dargar, S., Ghatak, S., Verma, N., Chauhan, P., Gupta, A., Vishnumolakala, N., Amuru, H., Gambhir, E., Chhajed, R., et al. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-58181-6_20 · Cited by 1
A Survey of Deep Learning Technology in Visual SLAM
Meng, H., & Lu, H. (2024) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc61514.2024.10592584 · Cited by 4
“Common handcraft features include point features and descriptors: SIFT [4], FAST [5], SURF [6], BRIEF [7], ORB [8], etc., as well as line features: MLSD [9], ELSED [10], and FSG [11] developed on the basis of LSD [12].”
BackgroundResearch on target recognition method of robotic arm based on improved ORB
Gao, Z., Lv, M. Y., & Zhang, J. (2024) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc62350.2024.10588335 · Cited by 1
Peng, Z., Song, R., Yang, H., Li, Y., Lin, J., Xiao, Z., & Yan, B. (2024) · Applied Sciences · doi:10.3390/app14146276 · Cited by 1
“Taking advantage of compact representation and computational efficiency, the methods implemented with global features can describe the image appearance using a single vector, e.g., BRIEF [7] and SURF [8].”
MethodCamera Pose Optimization with Genetic Algorithm in Digital Twin
Kim, K., & Jo, K. (2024) · International Symposium on Industrial Electronics · doi:10.1109/isie54533.2024.10595748 · Cited by 2
Content-Based Medical Image Retrieval for Medical Radiology Images
Barać, D., Manojlović, T., Napravnik, M., Hržić, F., Mamula, M., Miletić, D., & Štajduhar, I. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-66535-6_6 · Cited by 1
Han, Y., Long, Z., Zhang, Y., Wu, J., Fang, Z., & Fan, R. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611456 · Cited by 1
Research on Unsupervised Feature Point Prediction Algorithm for Multigrid Image Stitching
Li, J., Chen, Y., & Mu, A. (2024) · Symmetry · doi:10.3390/sym16081064 · Cited by 1
Research on Mobile Robot Localization Algorithm with Improved ORB Extraction Matching
Sun, H., Wei, L., Jiang, Y., et al. (2024) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma61710.2024.10633169 · Cited by 1
“There are mainly three methods used for feature point extraction: SURF (speed up robust features) [6], SIFF (scale invariant feature transform) [7], and ORB (Oriented Fast and Rotated Brief) [8].”
MethodMiura, H., & Kamata, H. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-7225-4_16 · Cited by 1
Yumeng, 李. L., Yifan, 张. Z., Guang, 杨. Y., & Hui, 李. L. (2024) · Laser & Optoelectronics Progress · doi:10.3788/lop241214 · Cited by 1
Wen, L., Mei, X., Tan, Y., et al. (2024) · Photonics · doi:10.3390/photonics11090844 · Cited by 1
SUGrasping: a semantic grasping framework based on multi-head 3D U-Net
Cao, H., Zhang, Y., Ge, Z., Chen, X., Liu, X., & Zhao, J. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20037-w · Cited by 1
“These descriptors should be resistant to changes in scale, illumination, rotation, and so on [14–16].”
Tan, L. V., Jadin, M. S., Osman, M. K., et al. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-3851-9_6 · Cited by 1
Combining Old School Autoencoder with Cotracker for Improved Skin Feature Tracking
Shi, W.-P., & Nordling, T. E. M. (2024) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea61579.2024.10664688 · Cited by 1
“On the other hand, DFE has demonstrated strong performance when compared to other tracking methods, such as SIFT [17], SURF [3], and Lucas-Kanade [18], as discussed by Chang and Nordling [5].”
MethodRemote Sensing Image Registration Using Fast Visual Saliency and Improved SIFT
Khalili, F., Razzazi, F., & Hosseini, S. A. (2024) · doi:10.1109/icee63041.2024.10667849 · Cited by 1
“SURF algorithm is faster than SIFT, but its accuracy is considerably lower [4].”
MethodPCB Large Color Variation Image Registration with Local Optimization LoFTR
Hou, Y., Zhang, Y., Liu, X., Wu, H., Jia, J., Li, X., Liu, S., Wang, L., & Zhao, X. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-71716-1_4 · Cited by 1
Cao, Z., Zhao, W., Zhao, H., & Pang, L. (2024) · Journal of Information and Intelligence · doi:10.1016/j.jiixd.2024.09.002 · Cited by 2
A Multi-Source Remote Sensing Image Matching Approach Based on Texture-Enhanced Region Features
Zhao, Z., Wang, F., You, H., et al. (2024) · doi:10.1109/icsip61881.2024.10671417 · Cited by 1
“For example, common methods such as the speeded up robust features (SURF) [3], [4], SAR-SIFT [5], OS-SIFT [6], the uniform robust SIFT (UR-SIFT) [7], and others are based on improvements to SIFT, providing more possibilities for multi-source remote sensing image matching.”
MethodTriple-Camera Rectification for Depth Estimation Sensor
Jeon, M., Park, J., Kim, J.-W., et al. (2024) · Sensors · doi:10.3390/s24186100 · Cited by 1
“…except the approximate chart area considering the margin is Various feature detection methods such as Harris corner detection [22], SIFT [23], SURF [24], ORB [25], FAST [26], BRIEF [27], HOG [28], and MSER [29] often show poor performance near the out-of-focus area (in our case, it mostly happens…”
MethodGMVO: graph-CNN-based trajectories’ instance-level segmentation for multi-motion visual odometry
Wan, F., Zhao, Q., Sun, H., et al. (2024) · Systems Science & Control Engineering · doi:10.1080/21642583.2024.2409119 · Cited by 1
“In this paper, we selected three feature points, namely ORB (Rublee et al., 2011), SIFT (Lowe, 2004), and SURF (Bay et al., 2006), to construct the required trajectory data set for training and testing the GMVO algorithm.”
Li, H., Wan, G., Li, X., Wang, C., Zhang, H., & Liu, B. (2024) · Sensors · doi:10.3390/s24206643 · Cited by 1
“Established algorithms include ICP [8], SIFT [9], SURF [10], ORB [11], EPnP [12], and PPF [13].”
MethodSkin feature point tracking using deep feature encodings
Chang, J. R., & Nordling, T. E. M. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02405-y · Cited by 3
“SIFT [32] and SURF [63], though not the latest advancements, serve as essential benchmarks in our research, shaping our approach to feature matching.”
Zhang, W., Wang, Q., Huang, K., Huang, X., Guo, F., & Gu, X. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681548 · Cited by 4
“As a fundamental task in image processing, dense image registration has been widely investigated [3, 32], which is also known as image matching or correspondence [33].”
Exploring Matching Rates: From Keypoint Selection to Camera Relocalization
Lin, H., Long, C., Fei, Y., Xia, Q., Yin, E., Yin, B., & Yang, X. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681628 · Cited by 6
“Typical hand-crafted methods for keypoint description include SIFT [27], SURF [2], and ORB [30].”
MethodTwo-View Correspondence Learning With Local Consensus Transformer
Wang, G., & Chen, Y. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3488197 · Cited by 2
“…such as features from accelerated segment test (FAST) [18], scale-invariant feature transform (SIFT) [11], speeded-up robust feature (SURFs) [19], Con-textDesc [20], and SP [12] have played pivotal roles in this process, offering distinctive features capable of withstanding various…”
IMAGE MATCHING BASED HAZARDOUS MATERIAL DETECTION AND WARNING SYSTEM
Okur, F. B., & Eyüpoğlu, C. (2024) · İstanbul Ticaret Üniversitesi Fen Bilimleri Dergisi · doi:10.55071/ticaretfbd.1469991 · Cited by 1
TMBuD-v2: A Multi-Purpose Urban Landmark Detection Dataset
Orhei, C., Mocofan, M., Vert, S., & Vasiu, R. (2024) · International Symposium on Electronics and Telecommunications (ISETC) · doi:10.1109/isetc63109.2024.10797342 · Cited by 1
“A popular approach to this problem involved combining features like SIFT [8], SURF [9], or other variants which are clustered in a KD-Trees Visual Vocabulary using approximate k-means [10] or Scalable Vocabulary Trees [11].”
Identifying Traffic Congestion Through Vehicle Counting and Motion Estimation
Duong, M.-T., Phan, T.-D., Nguyen, V.-B., & Le, M.-H. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-76197-3_11 · Cited by 1
Analysis of the effectiveness of object recognition algorithms using a thermal imaging camera
Kozik, J., Nawrat, A., & Daniec, K. (2024) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme62383.2024.10797047 · Cited by 1
Dai, D., Quan, Q., & Cai, K.-Y. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801926 · Cited by 1
“SURF [3], SIFT [4]) to extract key points and establish the correspondence to recover the pose.”
SURF and Texture Classification on Occluded Hand Images
Ignat, A., Păvăloi, I., & Niţă, C. D. (2024) · E-Health and Bioengineering Conference (EHB) · doi:10.1109/ehb64556.2024.10805588 · Cited by 1
Classification of Melanoma Cancer Using Deep Convolutional Neural Networks
Güneş, A., & Dönmez, E. (2024) · Journal of Advanced Research in Natural and Applied Sciences · doi:10.28979/jarnas.1505804 · 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.