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 10,201–10,300 of 14,752
Depth map building based on pixel number variation and SURF
Hsu, C.-C., Huang, P.-T., Cai, Z.-H., Lu, M.-C., & Lu, Y.-Y. (2014) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2014.6974593 · Cited by 2
Potluck: Cross-Application Approximate Deduplication for Computation-Intensive Mobile Applications
Guo, P., & Hu, W. (2018) · ACM SIGPLAN Notices · doi:10.1145/3296957.3173185 · Cited by 10
RAFT-SLAM: Deep Optical-Flow Assisted Simultaneous Localization and Mapping
Zhao, C., Meng, S., Dai, Y., et al. (2021) · China Automation Congress (CAC) · doi:10.1109/cac53003.2021.9727736 · Cited by 2
“Researcher have proposed many kinds of feature point detectors such as Scale-Invariant Feature Transform (SIFT) [1], SURF [2], Features from Accelerated Segment Test (FAST) [3], etc. Feature points is able to offer reliable correspondences between two images under a certain degree of illumination…”
Applying FAST & FREAK Algorithms in Selected Object Tracking
S.Khachikian, M. E. (2016) · International Journal of Advanced Research in Electrical Electronics and Instrumentation Engineering · doi:10.15662/ijareeie.2016.0507003 · Cited by 3
Wu, Y., Bai, Z., Gong, M., BoYiTing, Q. U., Li, H., Zhang, M., Ma, W., & Miao, Q. (2021) · Scientia Sinica Technologica · doi:10.1360/sst-2021-0193 · Cited by 3
Chen, Q., Yang, H., Mars, J., et al. (2016) · ACM SIGOPS Operating Systems Review · doi:10.1145/2954680.2872368 · Cited by 2
Automatic Visual Reading of Meters Using Deep Learning
Koščević, K., & Subašić, M. (2019) · Proceedings of the Croatian Computer Vision Workshop · doi:10.20532/ccwv.2018.0002 · Cited by 2
“To extract features SURF [5] method is used.”
MethodImage Matching Techniques: A Review
Kaur, R., & Devendran, V. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-0098-3_74 · Cited by 2
Automatic detection of scintillation light splashes using conventional and deep learning methods
Jiang, Y., Bugby, S. L., & Cosma, G. (2022) · Journal of Instrumentation · doi:10.1088/1748-0221/17/06/p06021 · Cited by 2
Image Registration Between Real Image and Virtual Image Based on Self-supervised Keypoint Learning
Kim, S., Jang, I., & Ko, B. C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-02444-3_30 · Cited by 2
Automatic Detection of Safety Helmet Based on Improved YOLO Deep Model
Nan, N., & Hu, C. (2022) · Smart innovation, systems and technologies · doi:10.1007/978-981-16-9735-7_20 · Cited by 2
Plant Classification Using Firefly Algorithm and Support Vector Machine
Milovanović, M., Petrović, A., Jassim, H. S., et al. (2022) · International Scientific Conference Sinteza · doi:10.15308/sinteza-2022-443-448 · Cited by 2
An Acoustic-Inertial Pose Estimation Method with Robust Feature Match and Graph Optimization
Li, B., Yan, W., Li, H., & Zhang, L. (2022) · Asian Control Conference (ASCC) · doi:10.23919/ascc56756.2022.9828281 · Cited by 2
A New CBIR Model Using Semantic Segmentation and Fast Spatial Binary Encoding
Ouni, A., Château, T., Royer, E., Chevaldonné, M., & Dhome, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16014-1_35 · Cited by 3
An Intelligent Tracking System for Moving Objects in Dynamic Environments
Hakami, N. A., Mahmoud, H. A. H., & AlArfaj, A. A. (2022) · Actuators · doi:10.3390/act11100274 · Cited by 2
Comparison Between the Traditional and Deep Learning Algorithms on Image Matching
Zeng, S., Zhao, Y., & Li, S. (2022) · IEEE/ACIS International Conference on Computer and Information Science (ICIS) · doi:10.1109/icis54925.2022.9882428 · Cited by 2
Li, J., Kuang, Z., Lu, G., Peng, Y., Shang, W., Li, J., & Wei, W. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/5249449 · Cited by 3
Gopalapillai, R. (2022) · Asian Conference on Innovation in Technology (ASIANCON) · doi:10.1109/asiancon55314.2022.9908897 · Cited by 2
Deep Reinforcement Learning Based Loop Closure Detection
Iqbal, A., Thapa, R., & Gans, N. (2022) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-022-01720-2 · Cited by 2
“Prevalent local visual feature descriptors include SIFT [15], ORB [16] and SURF [17].”
MethodKim, H., Yamakawa, Y., & Ishikawa, M. (2022) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2022.p1043 · Cited by 2
Global Mean Square Error Separation Loss
Hou, Y. (2022) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2363/1/012007 · Cited by 3
“Traditional object detectors consist of three cascaded steps of proposal generation, feature extraction and region classification [1-4].”
BackgroundMethodReal-Time Stereo Visual Odometry Based on an Improved KLT Method
Guo, G., Dai, Z., & Dai, Y. (2022) · Applied Sciences · doi:10.3390/app122312124 · Cited by 2
Content-Based Image Retrieval for Painting Style with Convolutional Neural Network
Tan, W. S., Chin, W. Y., & Lim, K. Y. (2022) · IEM Journal · doi:10.54552/v82i3.122 · Cited by 2
Robust Self-supervised Correspondence Learning for SAR-optical Image Matching
An, C., Cao, F., Wang, P., & Shi, T. (2022) · International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) · doi:10.1109/cei57409.2022.9950181 · Cited by 2
Learning to Detect Good Keypoints to Match Non-Rigid Objects in RGB Images
Melo, W., Potje, G., Cadar, F., Martins, R., & Nascimento, E. R. (2022) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi55357.2022.9991805 · Cited by 3
Image Retrieval and Pattern Spotting on Historical Documents with Binary Descriptors
Curi, Z., Nicolas, S., Tranouez, P., Britto, A. D. S., & Heutte, L. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956416 · Cited by 2
Domain Adaption Based on MSE Criterion and Progressive RKHS Subspace Learning (MSEpRKHS_DA)
Qiu, Y., Liu, S., Ma, Z., & He, H. (2022) · IEEE Access · doi:10.1109/access.2022.3216884 · Cited by 2
“1 The related instructions of this experiment are as follows : 1) We use the RBF kernel [25], k ( x 1 , x 2 ) = e According to IGLDA [14], the Speed Up Robust Features (SURF) [26] of this dataset are first extracted; then the SURF of each domain are normalized.”
MethodMohtaram, N., & Achakir, F. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20716-7_6 · Cited by 2
Jung, C.-H., & Seo, S. (2022) · Journal of Next-generation Convergence Information Services Technology · doi:10.29056/jncist.2022.12.01 · Cited by 2
Semantic SuperPoint: A Deep Semantic Descriptor
Gama, G. S., Rosa, N. D. S., & Grassi, V. (2022) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars/sbr/wre56824.2022.9996027 · Cited by 2
Digit Recognition Using Composite Features With Decision Tree Strategy.
Chen, C., & Huang, K.-W. (2023) · International Journal of Interactive Multimedia and Artificial Intelligence · doi:10.9781/ijimai.2022.12.001 · Cited by 3
Two-View Structure-from-Motion with Multiple Feature Detector Operators
Dippold, E. J., & Tsai, F. (2023) · Remote Sensing · doi:10.3390/rs15030605 · Cited by 2
Differentiable Rendering for Pose Estimation in Proximity Operations
Bhaskara, R. R., Eapen, R. T., & Majji, M. (2023) · AIAA SciTech Forum · doi:10.2514/6.2023-2317 · Cited by 3
BEBLID-SLAM: An Efficient Feature-Based Monocular SLAM System
Yang, F., Song, H., Li, H., & Jie, B. (2022) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac57282.2022.10023629 · Cited by 2
Li, K., Wang, X., Shi, L., & Geng, N. (2023) · IEEE Access · doi:10.1109/access.2023.3246803 · Cited by 3
“Early handcrafted local descriptor methods for place recognition are generally based on gradient histograms such as Scale-Invariant Feature Transform (SIFT) [22] and Speeded Up Robust Features (SURF) [23].”
MethodGPU-based Real-time Image Mosaicing for UAVs
Tian, F., Zhou, Y., Cheng, J., et al. (2022) · International Conference on Network and Information Systems for Computers (ICNISC) · doi:10.1109/icnisc57059.2022.00039 · Cited by 2
SSD PCB Component Detection Using YOLOv5 Model
Kim, P., Huang, X., & Fang, Z. (2023) · Journal of information and communication convergence engineering · doi:10.56977/jicce.2023.21.1.24 · Cited by 2
A Down-to-Earth Approach for Camera to World Map Georeferencing Using SfM
Krock, T. J., Collins, J., Fraser, J., et al. (2022) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr57179.2022.10092204 · Cited by 2
“3D point cloud model was reconstructed at ∼ 20cm 3 voxel resolution (using VB3D2). including SIFT [20], SURF [21], AKAZE [22], and ORB [23] available in OpenCV [24], but none of them were able to find coherent matches between satellite, raw, or ground projected images which had significant 3D…”
MethodDetection and classification of vehicles using audio visual cues
Anuja Prasad, S., Mary, L., & Koshy, B. I. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14868-2 · Cited by 3
Towards image processing of reentry event
Kyselica, D., Šilha, J., Ďurikovič, R., Bartková, D., & Tóth, J. (2023) · Journal of Applied Mathematics Statistics and Informatics · doi:10.2478/jamsi-2023-0003 · Cited by 2
Progressive refinement imaging with depth-assisted disparity correction
Kluge, M., Weyrich, T., & Kolb, A. (2023) · Computers & Graphics · doi:10.1016/j.cag.2023.07.036 · Cited by 2
“First, a set of photometric SURF features with 2D keypoint locations K curr ∈ R 2 are detected in the current color image I curr , using the Hessian feature threshold ε h = 1000 and four SURF octaves with four scales in each octave.”
InfluentialFusion of Appearance and Motion Features for Daily Activity Recognition from Egocentric Perspective
Abdullah, M. H. L., AlDahoul, N., & Karim, H. B. A. (2023) · Sensors · doi:10.3390/s23156804 · Cited by 2
“Object-centric representation was obtained based on the local SURF [16] features aggregated using a Bag of Word method.”
MethodImproved Boundary Identification of Stacked Objects with Sparse LiDAR Augmentation Scanning
You, H., Xu, F., & Du, J. (2023) · Journal of Construction Engineering and Management · doi:10.1061/jcemd4.coeng-13626 · Cited by 2
Localization for self-driving vehicles based on deep learning networks and RGB cameras
(2023) · International Journal of Advanced Technology and Engineering Exploration · doi:10.19101/ijatee.2023.10101118 · Cited by 4
Image Tampering Recognition Algorithm Based on Improved YOLOv5s
Liu, Z. (2023) · IEEE Access · doi:10.1109/access.2023.3311474 · Cited by 2
Deep Dense Projection Estimator for Images With Multi-Geometric Structures
Yan, H., & Zhou, R. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3313250 · Cited by 2
DualRC: A Dual-Resolution Learning Framework With Neighbourhood Consensus for Visual Correspondences
Li, X., Han, K., Li, S., & Prisacariu, V. A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3316770 · Cited by 4
Homography augmented particle filter SLAM
Słowak, P., & Kaniewski, P. (2023) · Metrology and Measurement Systems · doi:10.24425/mms.2023.146420 · Cited by 3
Localize the Copy-Move Forged Region of an Image Using Improved SIFT
Dhanaraj, R. S., & Srıdevı, M. (2023) · SN Computer Science · doi:10.1007/s42979-023-02388-7 · Cited by 2
An Infrared and Visible Image Registration Network Based on Modal Transformation
Cheng, L., Fang, J., Ruan, J., et al. (2023) · doi:10.1109/mlccim60412.2023.00020 · Cited by 2
Visional grasping control of robot based on QR code
Juang, L. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18279-9 · Cited by 2
“Scale-invariant feature transform (SIFT) [7], Speed up Robust Features (SURF) [8], Harris Corner Detector and Features from Accelerated Segment Test (FAST) [9] are popular algorithms in recent years.”
A Multi-Modal Attention-Based Approach for Points of Interest Detection on 3D Shapes
Shu, Z., Yu, J., Chao, K., Xin, S., & Liu, L. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3368767 · Cited by 2
“In the 2D domain, techniques like SIFT [20], Harris [21], ORB [22], and SURF [23] offer scale and rotational invariance by extracting localfeaturestogeneratekeypointdescriptors.”
From Clay to Code: The Evolution of 3D Sculpting and Its Impact on Virtual Realms
Sahu, J. P. (2024) · International Journal of Research Publication and Reviews · doi:10.55248/gengpi.5.0424.0921 · Cited by 2
FishIR: Identifying Pufferfish Individual Based on Deep Learning and Face Recognition
Lin, Y., Xie, S., Ghose, D., Liu, X., You, J., Korhonen, J., Liu, J., & Dash, S. P. (2024) · IEEE Access · doi:10.1109/access.2024.3390412 · Cited by 2
“…distinct regions and subsequently applying conventional feature extraction techniques, such as Histogram of Oriented Gradients (HOG) [30], Local Binary Patterns (LBP) [31], Scale-Invariant Feature Transform (SIFT) [32], and Speeded Up Robust Features (SURF) [33], among others, to derive features.”
MethodSADGFeat: Learning local features with layer spatial attention and domain generalization
Bai, W., Zhang, Y., Wang, L., Liu, W., da Hu, J., & Huang, G. S. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105033 · Cited by 2
Detecting change in graffiti using a hybrid framework
Wild, B., Verhoeven, G., Muszyński, R., et al. (2024) · The Photogrammetric Record · doi:10.1111/phor.12496 · Cited by 2
“For this study, four well-established feature detectors and descriptors were used: SIFT (Lowe, 1999), SURF (Bay et al., 2006), AKAZE (Alcantarilla, 2013) and BRISK (Leutenegger et al., 2011).”
Color consistency method for cameras with unknown model
Bibikov, S. A., RAS, I. R. –. B. O. T. F. ". A. P., Petrov, M. V., et al. (2023) · Computer Optics · doi:10.18287/2412-6179-co-1205 · Cited by 2
Classifier Boosting for Human Activity Recognition
Hamid, R. (2012) · Springer eBooks · doi:10.1007/978-1-4419-9326-7_9 · Cited by 3
SaddleSURF: A Saddle Based Interest Point Detector
Sajith Kecheril, S., Issac, A., & Velayutham, C. S. (2012) · Communications in computer and information science · doi:10.1007/978-3-642-28926-2_45 · Cited by 2
A Performance Analysis of Vision-Based Robot Localization System
Qi, Y. (2013) · Cited by 2
Efficient Media Retrieval from Non-Cooperative Queries
Shih, K. J., Di, W., Jagadeesh, V., & Piramuthu, R. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-20904-3_35 · Cited by 2
A VISION-BASED HYBRID SYSTEM FOR REAL-TIME ACCURATE LOCALIZATION IN AN INDOOR ENVIRONMENT
Gay‐Bellile, V., Tamaazousti, M., Dupont, R., et al. (2010) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0002825602160222 · Cited by 2
A study into annotation ranking metrics in geo-tagged image corpora
Hughes, M. M., Jones, G. J. F., & O'Connor, N. E. (2012) · Arrow@dit (Dublin Institute of Technology) · Cited by 2
Real-Time Text Tracking for Text-to-Speech Translation Camera for the Blind
Goto, H., & Hoda, T. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-08596-8_101 · Cited by 2
A Natural Interface for the Training of Medical Personnel in an Immersive and Virtual Reality System
Bimbo, A. D., Ferracani, A., Pezzatini, D., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41181-6_77 · Cited by 2
“The vision module represents a hand, segmented with a skeletal tracker, with a regular grid of 5 SURF[15] descriptors.”
MethodA Vision-Based Navigation Facility for Planetary Entry Descent Landing
Lanza, P., Noceti, N., Maddaleno, C., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33868-7_54 · Cited by 2
“All feature based methods make use of an optimized implementation of SURF features [9] chosen as a trade-off between efficiency and accuracy, although other features (such as, SIFT and Harris corners) are available.”
MethodMulti-Table Reinforcement Learning for Visual Object Recognition
Piñol, M., Sappa, A. D., & Toledo, R. (2013) · Lecture notes in electrical engineering · doi:10.1007/978-81-322-0997-3_42 · Cited by 2
Video Retrieval Based on Uncertain Concept Detection Using Dempster–Shafer Theory
Shirahama, K., Kumabuchi, K., Grzegorzek, M., & Uehara, K. (2015) · Springer eBooks · doi:10.1007/978-3-319-14998-1_12 · Cited by 2
“Many descriptors, like Scale-Invariant Feature Transform (SIFT) [19], Speeded Up Robust Features (SURF) [20] and RGB SIFT [21], are currently available.”
BackgroundLearning-Based Local Visual Representation and Indexing
(2015) · Elsevier eBooks · doi:10.1016/c2014-0-01997-1 · Cited by 2
Research of Object Recognition and Tracking Based on Feature Matching
Ahn, H., & Rhee, S.-B. (2014) · Lecture notes in electrical engineering · doi:10.1007/978-3-662-45402-2_152 · Cited by 2
Video Retrieval Based on Words-of-Interest Selection
Wang, L., Song, D., & Elyan, E. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-20161-5_71 · Cited by 2
Silva, R., Aires, K. R. T., Veras, R. D. M. S., Santos, T., Lima, K. A. B., & Soares, A. C. B. (2012) · Latin American Computer Conference (CLEI) · doi:10.1109/clei.2012.6427165 · Cited by 2
Digital image watermarking with partial embedding on blue color component
Thongkor, K., & Amornraksa, T. (2014) · doi:10.1109/apsipa.2014.7041667 · Cited by 2
Robust Real-Time Facial Expressions Tracking and Recognition
Zraqou, J. S., Alkhadour, W., & Al-Nuaimi, A. (2014) · International Journal of Technology and Educational Marketing · doi:10.4018/ijtem.2014010108 · Cited by 2
Feature Extraction and Representation for HumanAction Recognition
Zhen, X. (2013) · Cited by 2
Improving Hessian Matrix Detector for SURF
Chi, Y., Xiong, Z., Chang, Q., Li, C., & Sheng, H. (2011) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e94.d.921 · Cited by 2
“The box filter is employed for Hessian matrix, which has gone further from the Lowe’s LoG approximation [3].”
BackgroundMethodCombining two point clouds generated from depth camera
Li, X., Guo, W. P., Li, M., & Sun, L. (2013) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2013.6739868 · Cited by 2
Secure image databases through distributed source coding of SIFT descriptors
Nambiar, A., Tagliasacchi, M., & Magli, E. (2012) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2012.6343428 · Cited by 2
Feature Extraction and Recognition for Human Action Recognition
Luo, J. (2014) · Cited by 2
Towards an Optimal Interest Point Detector for Measurements in Ultrasound Images
Zukal, M., Beneš, R., Číka, P., et al. (2013) · Measurement Science Review · doi:10.2478/msr-2013-0049 · Cited by 2
“The Fast Hessian detector [30] differs from the Harris detector in the matrix used to detect the interest points.”
BackgroundMethod3D-based monocular SLAM for mobile agents navigating in indoor environments
Pangercic, D., Rusu, R. B., & Beetz, M. (2008) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2008.4638495 · Cited by 2
“The first point is amendable by implementing a better feature operator, like SURF [1] or tuples of straight 3D lines.”
MethodO'Map: An assistive solution for identifying and localizing objects in a semi-structured environment
Alam, S., Anam, I., & Yeasin, M. (2015) · John Spoor Broome Library Institutional Repository (California State University) · Cited by 2
Harris Correlation Descriptor (HCD): A Novel Descriptor for Point Matching
Wang, X. G., Wu, F. C., & Wang, Z. H. (2008) · doi:10.1109/csse.2008.1313 · Cited by 2
Prakash, C. D., Li, J., Akhbari, F., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14249-4_71 · Cited by 2
Mobile Image Search: Challenges and Methods
Yang, X. Y., & Cheng, K.-T. T. (2015) · Springer eBooks · doi:10.1007/978-3-319-24702-1_10 · Cited by 2
“[12, 13], is one of the most popular high-quality point detectors in the literature.”
BackgroundMethodApplication of SIFT and SURF Detectors for Medical X-Ray Images
Bhende, P. G. (2016) · Journal of Medical Science And clinical Research · doi:10.18535/jmscr/v4i3.09 · Cited by 2
“In 2006, Bay et al. introduced speeded up robust features technique (SURF), in which use of integral images for image convolutions and Fast-Hessian detector is applied [2] .”
BackgroundMethodResultInfluentialContent based Video Retrieval using Enhance Feature Extraction
HPatel, D. (2015) · International Journal of Computer Applications · doi:10.5120/21173-4052 · Cited by 2
Tracking and Identifying a Changing Appearance Target
Phon-Amnuaisuk, S., & Ahmad, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-26181-2_23 · Cited by 2
Abnormal Appearance Detection of Substation Based on Image Comparison
Zhang, X., Li, L., Li, J., et al. (2016) · MATEC Web of Conferences · doi:10.1051/matecconf/20165908001 · Cited by 2
“ORB is proposed as a very fast binary invariant descriptor based on BRIEF, it greatly speeds up processing procedure for feature extraction and matching compared to traditional key point descriptor, such as SIFT and speeded up robust features (SURF) [10].”
MethodVisual Odometry based on improved feature matching and Unscented Kalman Filter
Yu, H., Xie, L., Chen, J., Song, C., & Guo, F. (2016) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2016.7554203 · Cited by 2
Integrating performance of web search engine with Machine Learning approach
Jadhav, P. A., Chatur, P. N., & Wagh, K. (2016) · International Conference on Advances in Electrical, Electronics, Information, Communication and Bio-Informatics · doi:10.1109/aeeicb.2016.7538344 · Cited by 2
Akyol, K., Bayır, Ş., Şen, B., et al. (2016) · Journal of Computer Sciences and Applications · doi:10.12691/jcsa-4-3-2 · Cited by 2
“We built our study by making use of key point detector and descriptor algorithms called SURF (Speeded-Up Robust Features) and ORB (Oriented FAST and Rotated BRIEF) were introduced in [13,14] respectively with the insights gained from these previous work.”
MethodGaze-contingent interactive visualization of high-dynamic-range imagery
Kalash, M., Singh, K., Eskicioglu, R., et al. (2016) · doi:10.1109/etvis.2016.7851159 · Cited by 2
“This matching is achieved using feature detection and matching algorithms (SURF [12], ORB [13] and BRISK [14] were tested).”
MethodPose Tracking in Augmented Reality of Cultural Heritage
Asmar, D. (2017) · International Journal of Computational Methods in Heritage Science · doi:10.4018/ijcmhs.2017010108 · Cited by 2
An overview of image matching algorithms from two radically points of view
Dhouha, B., Kaâniche, K., & Mekki, H. (2016) · doi:10.1109/ipas.2016.7880125 · Cited by 2
An improved TLD algorithm based on Kalman filter and SURF feature matching
Zhao, L., Chen, Y., & Ye, Q. (2017) · AIP conference proceedings · doi:10.1063/1.4982579 · Cited by 2
Robotic arm control by fine-tuned convolutional neural network model
Bayraktar, E., Yiğit, C. B., & Boyraz, P. (2017) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2017.7960444 · Cited by 2
“Bunlardan en çok kullanılan SIFT [10], SURF [11], BRISK [12] ve ORB [13] yöntemleri içerik itibariyle benzer adımlardan oluşmaktadır; ölçek-uzayı gösterimi, anahtar nokta konumlandırma, yönelim atama ve anahtar nokta tanımlama.”
Recent Advances in Feature Extraction and Description Algorithms
Salahat, E. N., & Qasaimeh, M. (2017) · Advances in multimedia and interactive technologies book series · doi:10.4018/978-1-5225-2848-7.ch016 · Cited by 2
Car Make and Model Recognition using Sparse Coding and Bag of Features
Kamal, I., Housni, K., & Hadi, Y. (2017) · International Conference on Big Data, Cloud and Applications (BDCA) · doi:10.1145/3090354.3090435 · Cited by 2
An application of panoramic mosaic in UAV aerial image
Hu, J., Zhou, Y., Zhao, C., et al. (2017) · International Conference on Control and Automation · doi:10.1109/icca.2017.8003206 · Cited by 2
“Interest points, as SIFT feature [6], Surf feature [7], Orb feature [8], are robust to changes in lighting, rotation, viewpoint, translation and scale.”
Background
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.