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 11,401–11,500 of 14,752
LK-ORB-SLAM3: An RGB-D Visual SLAM Algorithm Fusing Optical Flow Tracking and Feature Matching
Dai, J., Sun, S., Liu, J., et al. (2024) · International Conference on Robotics, Control and Automation Engineering (RCAE) · doi:10.1109/rcae62637.2024.10834228 · Cited by 1
Self-trainable and adaptive sensor intelligence for selective data generation
Rezvani, A., Huang, W., Chen, H., Ni, Y., & Imani, M. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1403187 · Cited by 2
MAR-VO: A Match-and-Refine Framework for UAV’s Monocular Visual Odometry in Planetary Environments
Liu, J., Zhou, B., Wan, X., Pan, Y., Li, Z., & Shao, Y. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3534581 · Cited by 1
“This strategy ensures invariance to transformations such as translation, rotation, and scale, as demonstrated by algorithms such as Harris [17], SIFT [9], SURF [18], FAST [19], and ORB [2].”
A Survey on Objective Quality Assessment of Omnidirectional Images
Sui, X., Wang, S., & Fang, Y. (2024) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc63619.2025.10849147 · Cited by 4
IMU-Assisted Gray Pixel Shift for Video White Balance Stabilization
Zhang, L., Chen, X., & Wang, Z. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3535396 · Cited by 1
“Restrictions apply. estimation in Section IV-B with SURF [25] and LK optical flow [36].”
An Automatically Annotated Spacecraft Intelligent Perception Dataset Based on Segment Anything Model
Chen, Z., Zhao, S., & Zhong, R. (2024) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta63115.2024.00061 · Cited by 1
“Early studies utilized traditional image processing methods to extract manually designed features from images, such as SURF [1] and Harris corner [2].”
Comparing MTCNN and Viola-Jones Algorithm in Face Recognition
Bahmeie, A., & Shakiba, M. (2024) · Iranian Conference on Intelligent Systems (ICIS) · doi:10.1109/icis64839.2024.10887519 · Cited by 1
Bare Printed Circuit Board Defects Localization and Detection Using YOLOv5 Models
Khan, W. A., Hamza, A., Akram, M. U., et al. (2024) · International Conference on Robotics and Automation in Industry (ICRAI) · doi:10.1109/icrai62391.2024.10894537 · Cited by 1
“Hassanin et al. [4] utilized the speeded up robust feature (SURF) [5] to for feature extraction in combination with image processing techniques for defects identification.”
Desmarescaux, M., Kaddah, W., Alfalou, A., & Deconninck, J.-C. (2025) · Neural Processing Letters · doi:10.1007/s11063-025-11742-0 · Cited by 5
“Unlike traditional pattern recognition methods [3, 52, 60, 61, 75], which focus on classifying individual instances, OD literature seeks to classify multiple instances within the same class.”
Markiewicz, J. S. (2025) · Reports on Geodesy and Geoinformatics · doi:10.2478/rgg-2025-0006 · Cited by 1
OFPoint: Real-Time Keypoint Detection for Optical Flow Tracking in Visual Odometry
Wang, Y., Sun, L., & Qin, W. (2025) · Mathematics · doi:10.3390/math13071087 · Cited by 2
Du, W., Wang, H., Lei, D., Hang, Z., Cui, C., & He, J. (2025) · Scientific Reports · doi:10.1038/s41598-025-93625-x · Cited by 3
Multimodal Image Matching Using Sharpened Side Phase Fusion Method
Wang, Y., Lan, C., Gao, T., et al. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3561806 · Cited by 1
Extreme Two-View Geometry From Object Poses with Diffusion Models
Sun, Y., Sun, C., Liu, Y., Ma, Y., & Yiu, S. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-5812-1_16 · Cited by 4
Detection and Matching of Similar Clothing Images Using Improved YOLO Network
Ye, S., Sorokina, V., & Ablameyko, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-87663-9_28 · Cited by 1
SCONet: Convolutional Occupancy Networks for Multi-Organ Segmentation
Jouvencel, M., Kéchichian, R., Digne, J., et al. (2025) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi60581.2025.10980745 · Cited by 1
“This descriptor is computed with the 3D implementation [15] of the original algorithm [16] and yields a 48-valued vector ( s 1 i , ..., s 48 i ) for each point i .”
A dual branch based stitching method for whole slide hyperspectral pathological imaging
Zhang, J., Zhang, Q., Wang, J., et al. (2025) · Displays · doi:10.1016/j.displa.2025.103090 · Cited by 1
Research on Image Stitching Based on an Improved LightGlue Algorithm
Feng, Y., Zhang, F., Li, X., et al. (2025) · Processes · doi:10.3390/pr13061687 · Cited by 1
Unified Image Similarity Detection Using Neural Networks and Feature Metrics
Prathima, C., Babu, G. M., Koushik, A., et al. (2025) · doi:10.1109/icdsaai65575.2025.11011644 · Cited by 1
“It is also to identify image features that are fast and can accurately represent a scene even when the image has undergone a lot of transformation or noise the important point-based methods used to perform this detection include the Speeded-up Robust Features (SURF) [9] and ORB [16].”
Hong, Z., Chen, J., Tong, X., et al. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3577755 · Cited by 1
“Traditional feature-based matching methods, such as scale-invariant feature transform (SIFT) [22], speed-up robust features (SURFs) [23], and KAZE [24], primarily rely on image gradients to characterize feature points.”
Fang, Q., Gao, C., Jiang, T., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3578719 · Cited by 1
Guo, Y., Jin, J., Zhao, H., Ni, Y., & Shen, Y. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128745 · Cited by 1
Ground Target Recognition Technology of UAV Based on YOLOv10
Wang, H., Zhu, L., Ma, T., Zhong, C., & Dai, R. (2025) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl65390.2025.11085523 · Cited by 1
“…employed traditional methods including template matching, feature extraction algorithms such as Scale - Invariant Feature Transform (SIFT)and Speeded-Up Robust Features (SURF)[3][4], as well as conventional machine learning algorithms like Support Vector Machines (SVM)and decision trees[5].”
Lu, B., Zhou, T., Li, Q., Chi, W., Wang, Y., Wang, Y., Liu, H., Gu, J., & Sun, L. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3594113 · Cited by 1
“To detect visual features at each sampling frame, the speeded-up robust features (SURF) [28] calculator is leveraged to generate a dense feature collection, in which the Hessian threshold is empirically adjusted as H t = 5 , aiming to prevent an insufficient quantity due to semantic variations, as…”
TOSD: A Hierarchical Object-Centric Descriptor Integrating Shape, Color, and Topology
Choi, J.-H., Pyo, J.-W., An, Y.-C., & Kuc, T. (2025) · Sensors · doi:10.3390/s25154614 · Cited by 1
“Traditional local feature descriptors such as SIFT [9] and SURF [10] have been widely used for keypoint-based feature matching [11].”
Weng, Z., Wu, X., Li, Y., & Zheng, Z. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70236 · Cited by 1
“Traditional image matching algorithms, such as SIFT [21], SURF [22], and ORB [23], have been widely applied in visual simultaneous localization and mapping (SLAM) [24, 25], visual tracking [26], 3D reconstruction [27], and image retrieval [28].”
Zhang, Z., Zheng, X., Wu, X., Peng, C., & Cao, X. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00120 · Cited by 6
A Multimodal Multi-Drone Cooperation System for Real-Time Human Searching
Peng, J., Li, Q., Tan, Y., Zhao, D., Chen, J., & Jiang, Y. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3619530 · Cited by 1
Improved UAV Image Matching Algorithm Based on SIFT
Fan, Z., Ji, Y., Yan, S., et al. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-981-96-7703-0_17 · Cited by 1
Elements of Visual Concept Analysis
Wu, L., & Hua, X. (2011) · Studies in computational intelligence · doi:10.1007/978-3-642-19551-8_25 · Cited by 1
Discovering multilingual concepts from unaligned web documents by exploring associated images
Zhang, X., Jin, X., Li, L., et al. (2013) · International World Wide Web Conference (WWW) · doi:10.1145/2487788.2487874 · Cited by 1
Visual Saccades for Object Recognition
Starzyk, J. A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19324-3_70 · Cited by 1
A topology-based approach to computing neighborhood-of-interest points using the Morse complex
da Silva, R. D., Schwartz, W. R., Pedrini, H., Pulido, J., & Hamann, B. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.05.001 · Cited by 1
Improved Action Recognition Using an Efficient Boosting Method
Abouelenien, M., & Yuan, X. (2012) · Communications in computer and information science · doi:10.1007/978-3-642-35326-0_20 · Cited by 1
“Speeded Up Robust Feature SURF [2] uses integral images for image convolutions and 2D Haar wavelet responses for an efficient feature description.”
MethodRen, R., Pang, C. K., Ma, L., et al. (2014) · Proceedings in adaptation, learning and optimization · doi:10.1007/978-3-319-13356-0_53 · Cited by 1
Action Recognition via an Improved Local Descriptor for Spatio-temporal Features
Yang, K., Du, J., & Zhai, C.-M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24728-6_31 · Cited by 1
Multimodal Fusion: Combining Visual and Textual Cues for Concept Detection in Video
Galanopoulos, D., Dojchinovski, M., Chandramouli, K., et al. (2015) · Springer eBooks · doi:10.1007/978-3-319-14998-1_13 · Cited by 1
Top-Down Tracking and Estimating 3D Pose of a Die
Torres, F., & Kropatsch, W. G. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34166-3_54 · Cited by 1
Towards Understanding Articulated Objects
Sturm, J., Stachniss, C., Pradeep, V., Plagemann, C., Konolige, K., & Burgard, W. (2009) · Cited by 2
Rozpoznawanie osób na podstawie kostek dłoni
Nowakowski, W. (2011) · Elektronika : konstrukcje, technologie, zastosowania · Cited by 1
Panorama Image Construction Using Multiple-Photos Stitching from Biological Data
Rosenkranz, J., Xu, Y. X., Zhang, X., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33191-6_24 · Cited by 1
Enhancing Point Clouds Accuracy of Small Baseline Images Based on Convex Optimization
Le, M.-H., Vavilin, A., Yang, S.-M., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-31087-4_23 · Cited by 1
Interactive Representations of Multimodal Databases
Marchand‐Maillet, S., Morrison, D., Székely, E., & Bruno, É. (2010) · Elsevier eBooks · doi:10.1016/b978-0-12-374825-6.00006-x · Cited by 1
Detailed Visual Recognition of Road Scenes for Guiding Autonomous Vehicles
Dickmanns, E. D. (2011) · Springer eBooks · doi:10.1007/978-3-642-24349-3_11 · Cited by 1
Phrases Visuelles pour l'annotation automatique d'images.
Albatal, R., Mulhem, P., & Chiaramella, Y. (2010) · Association en Recherche d’Information et Applications · doi:10.24348/coria.2010.3 · Cited by 1
Bio-inspired engineering for the exploration of remote worlds
Spells, C. F., Doucette, S., & Ketsdever, A. (2015) · Proceedings - IEEE Aerospace Conference · doi:10.1109/aero.2015.7118931 · Cited by 1
Разработка и исследование методики распознавания изображений для систем расширенной реальности
Finogeev, A., & Четвергова, М. В. (2012) · IZVESTIA VOLGOGRAD STATE TECHNICAL UNIVERSITY · Cited by 1
Real-Time Tracking with Selective DoP-RIEF Features for Augmented Reality
Zhang, Y., Lü, P., Chen, J., & Duan, L. (2015) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2015.30 · Cited by 1
“SIFT [13] and SURF [15] are widely used because of the matching stability, and they are invariant with respect to image transformation and illumination.”
MethodCrowdsourcing and mobile device for wide areas monitoring
Guerriero, A., Giuliani, F., & Nitti, D. O. (2015) · IEEE Workshop on Environmental, Energy, and Structural Monitoring Systems (EESMS) · doi:10.1109/eesms.2015.7175847 · Cited by 1
Detection of the Vanishing Line of the Ocean Surface from Pairs of Scale-Invariant Keypoints
Fefilatyev, S., Shreve, M., & Goldgof, D. B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41181-6_17 · Cited by 1
“Two algorithms, SURF [1] and SIFT have been tested on a number of images of ocean surface.”
MethodComparativa de detectores de características visuales y su aplicación al SLAM
Cortijo, A. M. R., & Cazorla, M. (2009) · Cited by 1
Virtual Reality Control Systems
Reichenbach, T., Vasiljević, G., & Kovačić, Z. (2010) · BiblioBoard Library Catalog (Open Research Library) · doi:10.5772/intechopen.84005 · Cited by 1
A low-cost stereoscopic µP-based vision system for industrial light objects grasping
Kanellakis, C., Kyritsis, G., Tsilomitrou, O., et al. (2015) · 2006 14th Mediterranean Conference on Control and Automation · doi:10.1109/med.2015.7158837 · Cited by 1
Fast Line-Segment Extraction for Semi-dense Stereo Matching
Mckinnon, B., & Baltes, J. (2008) · Springer eBooks · doi:10.1007/978-3-540-78157-8_5 · Cited by 1
Comparison of metric space browsing strategies for efficient image exploration
Čech, P., & Grošup, T. (2015) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2015.7153631 · Cited by 1
Localization inside Tunnels Using Machine Vision
Hsieh, Y., & Liao, Y. (2014) · Proceedings of the ... ISARC · doi:10.22260/isarc2014/0116 · Cited by 1
“This is an important factor contributing to the popularity of SIFT and SURF descriptors.”
MethodInfluentialImage registration using the shearlet transform
Easley, G. R., Barbu-McInnis, M., & Labate, D. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2188816 · Cited by 1
A Feature Point Matching Algorithm for Complex Background Image
Wang, X., Liu, D., & Wang, L. (2015) · IEEE International Conference on Big Data and Cloud Computing (BDCloud) · doi:10.1109/bdcloud.2015.26 · Cited by 1
Yao, Y., & Li, C. (2013) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2013.209 · Cited by 1
“There are in total 13 states in the HCRF model for our own database (Fig.3 shows 4 of the 13 states, which form the gesture of digit 4), and 15 states in the Palm Graffiti Digits database [3].”
BackgroundMethodInfluentialEvaluation of synthesized electrocardiogram on additional leads based on clinical data
Yoshida, Y., Zhu, X. Y., Chen, W., & Wei, D. (2012) · IEEE International Conference on Virtual Environments, Human-Computer Interfaces and Measurement Systems (VECIMS) · doi:10.1109/vecims.2012.6273186 · Cited by 3
[Paper] Aerial Image Matching using Adaptive Selection of Orientation Code Image Pyramids
Ishimaru, M., & Sato, M. (2013) · ITE Transactions on Media Technology and Applications · doi:10.3169/mta.1.148 · Cited by 1
Filtering out background features from BoF representation by generating fuzzy signatures
Qiu, Q., Cao, Q., & Adachi, M. (2014) · International conference on Fuzzy Theory and Its Applications · doi:10.1109/ifuzzy.2014.7091224 · Cited by 1
Sonar based mapping using PHD filter
Abdella, H. K., Lane, D. M., & Maurelli, F. (2014) · doi:10.1109/oceans.2014.7003083 · Cited by 1
“In terms of feature representation most visual SLAM techniques are based on point features which are abundantly extracted using feature extractors such as Scale-invariant feature transform (SIFT) [5] and Speeded Up Robust Features (SURF) [6].”
Real Time Non-rigid Surface Detection Based on Binary Robust Independent Elementary Features
Kuo, C.-T., Tsai, L. Y., Feng, M. Y., et al. (2014) · International Symposium on Computer, Consumer and Control · doi:10.1109/is3c.2014.98 · Cited by 1
“Bay put forth Speeded Up Robust Features (SURF) (Bay et al., 2006), and proposed to apply the Hessian matrix to locate changeable keypoints and consolidate integral images to achieve scale invariance, same as the steps to establish the pyramidal image.”
Pose graph for improved monocular visual odometry
Kicman, P., & Narkiewicz, J. P. (2014) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2014.6957413 · Cited by 1
“URF descriptor [12] (SU).”
BackgroundA novel object recognition system for cognitive robot
Luo, Y., Gao, Y., Liu, L., et al. (2012) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2012.6246763 · Cited by 1
The Research of Image Feature Matching Method Based on CH-SURF
Wang, Z., & Deng, J. (2013) · International Conference on Advanced Computer Science and Electronics Information (ICACSEI) · doi:10.2991/icaise.2013.4 · Cited by 1
A Feature Point Tracking Method By Using Template Matching and Buffer
Cho, J.-H., Ahn, C.-W., & Jun, J.-H. (2014) · 한국인터넷방송통신학회 논문지 · doi:10.7236/jiibc.2014.14.4.173 · Cited by 1
“SIFT(Scale Invariant Feature Transform) [2] , SURF (Speeded Up Robust Features) [3] , KLT (Kanade Lucas Tomasi Feaure Tracker) [4] 등 여 러 추적방법 [6] 이 있다.”
Local interest region description using multiple support regions
Huang, M., Mu, Z., & Zeng, H. (2015) · Journal of Optics · doi:10.1007/s12596-015-0257-6 · Cited by 1
“The SURF descriptor [10] also relies on local gradient histograms and speeds up the gradient computations using integral images, while almost preserving the quality of SIFT.”
BackgroundMethodUse pattern-recognition-based technology to explore a new interactive system on smart dining table
Wu, F., Wang, P.-C., Tseng, W.-T., Cheng, C.-M., Chou, Y., & Sung, Y.-H. (2013) · International Conference on Orange Technologies · doi:10.1109/icot.2013.6521205 · Cited by 1
“The Speed Up Robust Feature (SURF) as the scaleinvariant feature transform algorithm (SIFT) is a scaleinvariant and anti-rotation feature point detection and description method[14].”
MethodOverview of the major challenges in the wide baseline stereo vision
Roszkowski, M. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.905582 · Cited by 1
Volume Measurement of Deposits Based on Stereo Vision and SURF
Jia, Z., & Han, Y. (2015) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.743.533 · Cited by 1
An Efficient Cloud-Based Iris Recognition Solution for Mobile Devices
Santos, F. A., Faria, F. A., Boukerche, A., et al. (2015) · ACM International Symposium on Mobility Management and Wireless Access (MobiWac) · doi:10.1145/2810362.2810373 · Cited by 1
Real-time monitoring of television advertisement using BoW
Pan, D., Shi, P. A., & Li, M. (2014) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2014.7003759 · Cited by 1
A Improved Infrared and Visible Images Matching Based on SURF
Li, D. M., & Zhang, J. L. (2013) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.325-326.1637 · Cited by 1
An Examination of Feature Detection for Real-Time Visual Odometry in Untextured Natural Terrain
Otsu, K., Otsuki, M., Ishigami, G., & Kubota, T. (2013) · Advances in intelligent systems and computing · doi:10.1007/978-3-642-37374-9_39 · Cited by 1
Lu, Y.-Y., Stamatopoulos, C., & Fraser, C. S. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2021512 · Cited by 1
Affine estimation via region expansion
Farhan, E., & Hagege, R. R. (2014) · IEEE Workshop on Statistical Signal Processing (SSP) · doi:10.1109/ssp.2014.6884580 · Cited by 1
Range Image Registration Using a Photometric Metric under Unknown Lighting
Thomas, D., & Sugimoto, A. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.21 · Cited by 1
Asset identification using image descriptors
Friedel, R., Salas, Ó. F., Kalva, H., & Furht, B. (2013) · Multimedia Tools and Applications · doi:10.1007/s11042-013-1688-1 · Cited by 1
Hazardous sign detection for safety applications in traffic monitoring
Benešová, W., Kottman, M., & Sidla, O. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.905813 · Cited by 1
Comparing two methods of object detection in autonomous vehicle
Rosas-Miranda, D. I., Ponomaryov, V. I., & Palacios-Enriquez, A. (2014) · International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE) · doi:10.1109/iceee.2014.6978279 · Cited by 1
A Robust False Matching Points Detection Method for Remote Sensing Image Registration
Shan, X. J., & Tang, P. T. P. (2015) · 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/isprsarchives-xl-7-w3-699-2015 · Cited by 1
Fast Approximate Matching of Videos from Hand-Held Cameras for Robust Background Subtraction
Hamid, R., Sarma, A. D., Coste, D. D., et al. (2015) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2015.46 · Cited by 1
Common field-of-view of cameras in robotic swarms
Zhu, C., Bamann, C., Henkel, P., et al. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6697162 · Cited by 1
KAZE Feature Point with Modified-SIFT Descriptor
Meixi, C., Yule, Y., & Zhao, Y. J. (2013) · Advances in intelligent systems research/Advances in Intelligent Systems Research · doi:10.2991/icmt-13.2013.153 · Cited by 1
“Similar to SURF [3], we first calculate first order derivatives and in a circular neighbourhoodof radius with a sampling step of size .”
MethodCreación de un modelo visual del entorno basado en imágenes omnidireccionales
Gil, A., Valiente, D., Reinoso, Ó., & Marín, J. M. (2012) · Revista Iberoamericana de Automática e Informática Industrial RIAI · doi:10.1016/j.riai.2012.09.011 · Cited by 1
“A continuación, para cada uno de estos puntos se calcula un descriptor SURF.”
BackgroundInfluentialResearch on the feature set construction method for spherical stereo vision
Zhu, J., Wan, L., Röning, J., et al. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2083386 · Cited by 1
CWSURF: A novel coloured local invariant descriptor based on SURF
Jalilvand, A., Boroujeni, H. S., & Charkari, N. M. (2011) · doi:10.1109/iccke.2011.6413353 · Cited by 1
Local features and histogram based planar object recognition
Phan, D., Na, I. S., & Kim, S.-H. (2014) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1145/2557977.2558075 · Cited by 1
“Bay [11] in 2006 because it produces smaller descriptor as well as speeds up matching step.”
BackgroundKuzub, J., Mébarki, Y., & Whitehead, A. D. (2011) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2011.14 · Cited by 1
A Peak Detection Method for Understanding User States for Empathetic Intelligent Agents
Kim, H., & Choi, Y. S. (2013) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2013.118 · Cited by 1
Qualified matching feature collection for feature point-based copy-move forgery detection
Yu, L., Han, Q., & Niu, X. (2015) · Journal of Electronic Imaging · doi:10.1117/1.jei.24.2.023035 · Cited by 1
Random projections for feature matching
McCane, B. (2014) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1145/2683405.2683432 · Cited by 1
Fast Approximated SIFT Applied in Moving Objects Detection
Tang, W., & Wang, Z. (2008) · Chinese Conference on Pattern Recognition · doi:10.1109/ccpr.2008.47 · Cited by 1
“Lowe SIFT(Scale Invariant Feature Transform) [1] 128 Ke Sukthankar PCA-SIFT(Principal Components Analysis-SIFT) [2] PCA 36 SIFT Mikolajczyk GLOH(Gradient Location and Orientation Histogram) [3] SIFT SIFT PCA SIFT SURF(Speeded Up Robust Features) [4] SIFT”
MethodD-Note: Computer-Aided Digital Note Taking System on Physical Book
Xie, D., Zhou, Z., & Wu, J. (2011) · International Conference on Image and Graphics · doi:10.1109/icig.2011.44 · Cited by 1
In-building navigation system using a camera
Wangsiripitak, S. (2014) · International Conference on Knowledge and Smart Technology · doi:10.1109/kst.2014.6775390 · Cited by 1
“SURF features [13] are possible alternative, however the system still suffers from running in frame rate (here 30 fps) [9].”
BackgroundMonocular SLAM for a Small-Size Humanoid Robot
Wang, Y.-T., Hung, D.-Y., & Cheng, S.-H. (2011) · Tamkang University Institutional Repository (TKUIR) · doi:10.6180/jase.2011.14.2.05 · Cited by 2
Suivi d'objets par caractéristiques locales encodant la structure
Bouachir, W. (2014) · R-libre (Université Téluq) · Cited by 2
Image Pyramids, the Wavelet Transfm and Multiresolution Analysis
Beyerer, J., León, F. P., & Frese, C. (2015) · Springer eBooks · doi:10.1007/978-3-662-47794-6_15 · 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.