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 13,301–13,400 of 14,752
Efficient Bitmap-based Indexing and Retrieval of Similarity Search Image Queries
Jafari, O., Nagarkar, P., & Montaño, J. (2020) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai49293.2020.9094616
“Often, multimedia, such as images, are represented and stored as a collection of high-dimensional features, which are extracted using feature-extraction algorithms such as SIFT [1], SURF [2], etc.”
MethodCucchiarelli, A., Diamantini, C., Dragoni, A. F., Francescangeli, F., Frontoni, E., Mancini, A., Marinelli, F., Christian Morbidoni, B., Pezzella, F., Pisacane, O., et al. (2019) · Springer eBooks · doi:10.1007/978-3-030-32762-0_6
Mai, A., Menke, J. T., & Yang, A. Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.04384
Spacecraft Attitude Determination using Terrestrial Illumination Matching
Shockley, L. M., & Bettinger, R. (2020) · AIAA SciTech Forum · doi:10.2514/6.2020-1097
AdaBoost with "keypoint presence features" for real-time vehivle visual detection
Bdiri, T., Moutarde, F., Bourdis, N., et al. (2009) · HAL (Le Centre pour la Communication Scientifique Directe)
de Felice, O., & de Felice, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.05006
Learning Transformation-Aware Embeddings for Image ForensicsPreprint
Bharati, A., Moreira, D., Flynn, P. J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.04547
A Rapid Road Image Mosaic Method Based on Monocular Camera
Li, W., & Cao, Y. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1437/1/012008
“In coarse matching stage, the SURF [9] feature points are extracted and described for each image, and then feature points are matched in the space of feature descriptor.”
MethodObject Detection by Monocular Camera and Laser Sensors for Small Unmanned Aerial Vehicle
Dzurovčin, P., Švadlenka, L., Džunda, M., et al. (2019) · Acta Avionica · doi:10.35116/aa.2019.0013
Improved Real-time Pedestrian Detection Method
Zhao, Z., & Lei, X. (2019) · IEEE International Conference on Computer Science and Network Technology (ICCSNT) · doi:10.1109/iccsnt47585.2019.8962471
“SURF[3] algorithm is also an improved algorithm based on SIFT, which obtains the key point location through the construction of Hessian matrix.”
MethodWilms’ Tumor in Childhood: Can Pattern Recognition Help for Classification?
Müller, S., Weickert, J., & Graf, N. M. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-39343-4_4
Baybuz, О. G., Sydorova, M. G., Polonska, A. Y., et al. (2019) · Actual problems of automation and information technology · doi:10.15421/431912
Zhang, J., Li, B., Sun, J., et al. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-2810-1_53
Salcedo, A. F. C., Marín-García, E. J., & Bejarano, J. B. P. (2019) · Scientia et technica · doi:10.22517/23447214.21631
Autonomous integrity monitoring of a vision based pedestrian dead reckoning system.
Wang, Y., Tang, B., Zheng, L., et al. (2019)
A hybrid approach to find cloned objects in copy move forged images
Chakraverti, A. K., & Dhir, V. K. (2019) · International Journal of Forensic Software Engineering · doi:10.1504/ijfse.2019.10026443
A New Semantic Descriptor for Data Association in Semantic SLAM
Lee, H.-U., Lee, K.-H., & Kuc, T. (2019) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas47443.2019.8971639
Enhancing Privacy in Photo Based Location Information Services using Encryption Free Framework
Chandraleka, M. (2020) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2020.1083
Automated salamander recognition using deep neural networks and feature extraction
Bakløkken, J., Schoeler, F., Nørholm, H., George, S., Pedersen, M., & Dervo, B. K. (2019) · NORA - Norwegian Open Research Archives
Detección efectiva de rostros en imágenes utilizando descriptores basados en HOG
Alcántara-Montiel, C. V., Pedraza‐Ortega, J. C., Ramos-Arreguín, J. M., et al. (2019) · Research in Computing Science · doi:10.13053/rcs-148-8-28
“- SURF (Speeded-up Robust Features): según lo escrito por Awad y Hassaballah [10], este detector-descriptor fue desarrollado por Bay et al. [11] y se considera como una alternativa al SIFT, siendo el SURF mucho más eficiente y robusto, aun cuando se basa en propiedades similares a las del SIFT.”
BackgroundA Deep learning based evaluation method for feature detectors using satellite images
Djerida, A., Zhao, Z., & Zhao, J. (2019) · Chinese Automation Congress · doi:10.1109/cac48633.2019.8996307
Representation learning of spatio-temporal features from video
da Costa, G. D. B. P. (2020) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.55.2020.tde-03022020-093918 · Cited by 1
PSI (ψ) Invariant Features for Face Recognition
Cholin, A. S., Vinay, A., Bhat, A. D., et al. (2020) · Springer proceedings in mathematics & statistics · doi:10.1007/978-981-15-1338-1_27
Defect detection in ID cards with accurately reconstructed reference image
Chen, X., Jian-wen, C., & Wang, Y. (2020) · International Conference on Multimedia and Image Processing (ICMIP) · doi:10.1145/3381271.3381298
“AKAZE is accelerated KAZE[7], which applies nonlinear scale space, and is more stable and faster than typical descriptor SURF[8] and SITF[9].”
MethodMatching of Weakly-Localized Features under Different Geometric Models
Farhan, E. (2020) · Image Processing On Line · doi:10.5201/ipol.2020.247
Estimating a Null Model of Scientific Image Reuse to Support Research Integrity InvestigationsPreprint
Acuna, D. E., & Xiang, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00878
Mane, V. M., & Shinde, S. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-1286-5_26
Wavelet Based Multi-Trend Structure Descriptor for Effective Image Retrieval
Natarajan, M., & Sathiamoorthy, S. (2019) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces45898.2019.9002388
The Comparison of Different Visual Features for Visual Odometry
Jiang, Y., Wang, Q., Dong, C., Zhou, M. Q., & Zhong, K. (2018) · IEEE CSAA Guidance, Navigation and Control Conference (CGNCC) · doi:10.1109/gncc42960.2018.9019195
“2 [4].”
MethodA Method for Content-Based Image Retrieval with a Two-Stage Feature Matching
Huang, J., Yang, S., & Wang, W. (2019) · International Conference on Intelligent Control and Information Processing · doi:10.1109/icicip47338.2019.9012213
“Later, some local descriptors [8], [9] are proposed for image retrieval, such as the scale invariant feature transform (SIFT) and speeded up robust features (SUR-F) [10].”
BackgroundChen, T.-T., Wang, D.-C., Liu, M.-X., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-41964-6_49
Weeping and Gnashing of Teeth: Teaching Deep Learning in Image and Video Processing ClassesPreprint
Bovik, A. C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.01870
“My prepared course materials covered the essential topics of image formation, sampling and Fourier theory, wavelets, linear and nonlinear filtering, image coding, and feature detection using LoG and DoG, SIFT and SURF, using them for picture quality prediction, texture analysis, edge, boundary, and line detection, vis…”
InfluentialImage Descriptors and Similarity Measures
Lepetit, V. (2021) · Springer eBooks · doi:10.1007/978-3-030-63416-2_797
Photonics-Enhanced Image-Detection Sensing of Multiphase Flows
Carrasco-Ortiz, S. L., Valero, E., Morant, M., et al. (2019) · Springer series in optical sciences/SPringer series in optical sciences · doi:10.1007/978-3-030-30113-2_9
A perception pipeline exploiting trademark databases for service robots
Song, J. (2020) · The University of Queensland · doi:10.14264/uql.2020.171
Long-term 3D Registration Method Based on LCT Tracking and Improved ORB Detection
Yong, J., Wang, Y., Lei, X., et al. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023068
“At present, SI FT (Scale Invariant Feature Transform) algorithm [12] , SURF (Speeded Up Robust Features) algorithm [13] and ORB (Oriented FAST and Rotated BRIEF) algorithm [14] are popular image feature detection methods. algorithm is one order of magnitude faster than SURF and two orders faster…”
MethodEvaluation and Review of Object Tracking Solutions for Video Sequences
Nasreen, A., Chethan, K. P., Patil, R. M., et al. (2018) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict43934.2018.9034300
“It makes the best use of integral images [5] [10].”
BackgroundA Local Image Feature Approach as a Step of a Top-Down RGBD Semantic Segmentation Method
Ibarra-Vázquez, G., Puente, C., & Nunez-Varela, J. I. (2019) · Research in Computing Science · doi:10.13053/rcs-148-11-3
“Speeded Up Robust Features (SURF) [4] has a detector and a descriptor part.”
BackgroundMethodA Novel Frame Similarity Based Pedestrian Counting Approach in Surveillance Videos
Srivastava, H., Mathew, A., & Mathew, J. (2018) · IEEE India Council International Conference (INDICON) · doi:10.1109/indicon45594.2018.8987189
“…e.g-for sparsely populated dataset threshold lies between between 0.6-0.7 and for densely populated dataset threshold holds between 0.4-0.6 i ← first frame, j ← second frame, n ← total frames 5: while ( i < n − 1) and ( j < n ) do 6: Calculate features of frame i and j using SURF descriptor [1].”
BackgroundMethodInfluentialChoi, Y., Khac, C. N., Park, J. H., et al. (2020) · International Conference on Consumer Electronics · doi:10.1109/icce46568.2020.9043175
“In [8], SURF [9] is used to match points between two frames, and then removes the false positive bounding boxes by epipolar constraint.”
MethodShen, J., Zhang, Z., Langlang, G., et al. (2018) · International Conference on Instrumentation and Measurement, Computer, Communication and Control (IMCCC) · doi:10.1109/imccc.2018.00023
Defect-Classification of Parts by BOW Algorithm Based on ZYNQ
Shi, S., Liu, B., Liu, G., & Yao, A. (2018) · International Conference on Instrumentation and Measurement, Computer, Communication and Control (IMCCC) · doi:10.1109/imccc.2018.00036
“SURF (Speed Up Robust Feature) is an algorithm to extract and describe key points, proposed by Herbert etc, to improve the inefficiency and poor real-time capability of the SIFT (Scale Invariant Feature Transform) algorithm [5].”
MethodHatefi, E., Karshenas, H., & Adibi, P. (2020) · International Computer Conference, Computer Society of Iran (CSICC) · doi:10.1109/csicc49403.2020.9050133
“Features of two datasets O31 and OC10 can be extracted from handcrafted features (SURF) [32] or VGG features.”
BackgroundRobust Feature Matching via Two Constraints Interaction
Liu, Y., Li, Y., Xu, Z., et al. (2019) · IEEE International Conference on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom) · doi:10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00168
“For the traditional feature detection and description, SIFT [14], SURF [15] and ORB [16] have been proven to be effective.”
MethodTwo-stage Discriminative Re-ranking for Large-scale Landmark RetrievalPreprint
Yokoo, S., Ozaki, K., Simo‐Serra, E., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.11211
Depth Estimation from a Single Holoscopic 3D Image and Image Up-sampling with Deep-learning
Aondoakaa, A. S. (2020) · Brunel University Research Archive (BURA) (Brunel University London)
Image Mosaic Algorithm Based on SURF
Sun, Q., Yang, H., Wang, L., et al. (2020) · Lecture notes in electrical engineering · doi:10.1007/978-981-13-9409-6_253
Towards visualization and searching :a dual-purpose video coding approach
da Silva, R. C. (2018)
Multi-modal Datasets for Super-resolutionPreprint
Li, H., Quan, W., Yan, M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.05804
“As to the feature extraction, we make a selection among the SUFT [20], ORB [21] and SIFT [22] algorithms.”
Depth Sensing Beyond LiDAR RangePreprint
Zhang, K., Xie, J., Snavely, N., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.03048
“We first detect sparse matches between the left and back images with SURF [4].”
InfluentialRemoving Mismatches Using Corresponding Circles
Taime, A., Khamjane, A., & Satori, K. (2019) · doi:10.1109/isacs48493.2019.9068918
“In despite the performance of some local descriptors[6], [7], [9]–[11], the putative correspondence set usually contains a large of false correspondences, because of the ambiguities that exist in some similar images.”
BackgroundIllumination Robust Loop Closure Detection with the Constraint of Pose
Yan, D., Tuo, W., Wang, W., & Li, S. (2020) · Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering) · doi:10.2174/2352096513999200422141150
A Study on 3D Reconstruction Method for Common View Field in Hybrid Vision System
Lin, C., Zhou, H., Chen, W., & Zhang, Y. (2020) · Smart innovation, systems and technologies · doi:10.1007/978-981-15-3867-4_5
Yanai, ., Harada, H., & Nga, D. H. (2014) · TRECVID
Causo, A., Kamal, S. O., Vidas, S., & Chen, I. (2020) · Springer eBooks · doi:10.1007/978-3-030-35679-8_4
Residual and Ensemble Learning on Locally Derived Features for Face Recognition
Vinay, A., Gupta, A., Bharadwaj, A., et al. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-3914-5_2
Attribute-Based MED System with Word Histograms.
Matsuo, T., & Nakajima, S. (2011)
Tao, K., Dong, Y., Bian, Y., et al. (2012)
Hardware Architecture Design for Template Matching
Roh, D. W., & Jeon, J. W. (2019) · International SoC Design Conference · doi:10.1109/isocc47750.2019.9078515
“BRIEF is much faster than SIFT (Scale Invariant Feature Transform) [2], more accurate than SURF (Speeded-Up Robust Features) [3], and uses less computing power [4, 5].”
MethodA Review of Computer Vision Methods in Network SecurityPreprint
Zhao, J., Masood, R., & Seneviratne, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.03318
Single-sample writers -- "Document Filter" and their impacts on writer identificationPreprint
Pinhelli, F., Britto, A. D. S., Oliveira, L. S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.08424
A Hybrid Framework for Matching Printing Design Files to Product Photos
Kaplan, A., & Akagündüz, E. (2020) · Balkan Journal of Electrical and Computer Engineering · doi:10.17694/bajece.677326
LEFT: LOCAL EDGE FEATURES TRANSFORM
Тихомирова, Т. А., Fedorenko, G. Т., Nazarenko, K. M., et al. (2020) · Vestnik komp iuternykh i informatsionnykh tekhnologii · doi:10.14489/vkit.2020.03.pp.011-018
Arbitrary-sized Image Training and Residual Kernel Learning: Towards Image Fraud IdentificationPreprint
Li, H., Huang, X., Fu, Z., & Li, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.11043
Near-Duplicate Keyframe Retrieval by Computing
Zhu, J., Hoi, C. H., Lyu, M. R.-T., et al. (2011)
Occluded Work-piece Localization via Adversarial Network and Template Matching
Jiang, Y., & Li, Y. (2019) · International Conference on Safety Produce Informatization (IICSPI) · doi:10.1109/iicspi48186.2019.9095941
“…on the idea of feature descriptor can defend the small change of light and a few occlusions, such as Scale Invariant Feature Transform (SIFT) [3], Principal Components Analysis SIFT (PCA-SIFT) [4], Histogram of Gradients (HOG) [5], Speeded Up Robust Features (SURF) [6], steerable filters [7] etc.”
BackgroundBuilt Infrastructure Monitoring and Inspection Using UAVs and Vision-based AlgorithmsPreprint
Ly, K. K., & Phung, M. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.09486 · Cited by 3
A Preliminary Study for Identification of Additive Manufactured Objects with Transmitted ImagesPreprint
Yamamoto, K., Kawamura, R., Takazawa, K., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.12027
“In this experiment, the SURF algorithm[34] was used to perform feature extraction.”
MethodPEMANFAATAN METODE WAVELET PADA ROBOT SEPAKBOLA BERBASIS MACHINE LEARNING GOOGLE TENSORFLOW
Aryanto, A., & Melvi, M. (2020) · Journal of Energy and Electrical Engineering · doi:10.37058/jeee.v1i2.1552
“Sedangkan analisis aproksimasi dilakukan melalui bagian frekuensi rendah dari induk wavelet[8-11].”
BackgroundFeature Voting for Object Localization via Density Ratio Estimation
Wang, L.-T., Deng, D., & Chen, C. (2019) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2019.12.012
“In order to formulate this intuition, we represent a region by a collection of local features such as SIFT [13] and SURF [14] for images, STIP [15] for videos, and deep pixel features [16, 17].”
MethodFeature Points Extraction Based on Line Fitting for Power Distribution Switch
Qin, C., Qin, X., Feng, L., et al. (2019) · International Conference on Information Science and Control Engineering · doi:10.1109/icisce48695.2019.00152
Semantics-Driven Unsupervised Learning for Monocular Depth and Ego-Motion EstimationPreprint
Wei, X., Feng, J., & Zhou, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.04371 · Cited by 2
Alternative Position Estimation Systems for Micro Air Vehicles
Mantelli, M. (2020) · IntechOpen eBooks · doi:10.5772/intechopen.92224
“When comparing the MAV images against the patches, each Monte Carlo-based work proposed a novel measurement model, in which one has a new image descriptor called abBRIEF to robustly compute an image signature to the comparison [31], and the other used SURF descriptors [32] and machine learning to compare MAV images an…”
MethodAzimpourkivi, M. (2019) · FIU - Digital Commons (Florida International University) · doi:10.25148/etd.fidc007073
Characterization of Shared Resource Contention in Multi-core Systems
Danielsson, J. (2019) · DiVA (Mälardalen University College)
A Hybrid Framework for Matching Printing Design Files to Product PhotosPreprint
Kaplan, A., & Akagündüz, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.05355
High-Resolution Document Image Reconstruction from Video
Motamednia, H., Minouei, M., Cheraaqee, P., et al. (2020) · doi:10.1109/mvip49855.2020.9116907
“To answer this question, we used SURF features [21] to locate the patches in the final mosaic.”
MethodWilliamson, A., Dickinson, P., Lambrou, T., & Murray, J. C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.13065 · Cited by 2
Distance Invariant RGB-D Object Recognition Using DSMS System
Patekar, R., & Nandedkar, A. V. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-6315-7_11
Self-Calibration Supported Robust Projective Structure-from-MotionPreprint
Gong, R., Paudel, D. P., Chhatkuli, A., & Gool, L. V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.02045
Self-citationSimplicial Complex Based Point Correspondence Between Images Warped onto Manifolds
Sharma, C., & Kaul, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58526-6_4 · Cited by 1
“Planar feature extractors like SIFT [24], SURF [4], ORB [28], BRISK [21], and FREAK [2] extract descriptors either on an unwrapped equirectangular version of an omnidirectional image or directly on the 2D (flat) representation of the spherical image.”
Utilization of Scale in Keypoint Detection and Feature Description
Rhodes, A. P. (2019) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.7437
Hash Retrieval Method for Recaptured Images Based on Convolutional Neural Network
Li, J., Wang, X., & Liu, S. (2020) · World Symposium on Artificial Intelligence (WSAI) · doi:10.1109/wsai49636.2020.9143281
“SIFT algorithm has greatly encouraged the research effort, such as SURF (Speeded Up Robust Features) [3], PCA-SIFT [4], and so on.”
MethodReal-time Dense Reconstruction of Tissue Surface from Stereo Optical VideoPreprint
Zhou, H., & Jayender, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.12623
Concept-Based Multimedia Processing Using Semantic and Contextual Knowledge
Spyrou, E., Mylonas, P., & Kollias, S. (2017) · doi:10.1201/b13016-17
Silhouette Vectorization by Affine Scale-spacePreprint
He, Y., Kang, S. H., & Morel, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.12117
“c Compared with the SURF detector [13].”
MethodZhou, F., Wu, W., & Luo, Y. (2020) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc49329.2020.9164530
“But compared with SIFT [2] and SURF [3] features, ORB features have lower correct matching rates.”
ResultProduction: Generating Photogrammetric Outcomes
Stylianidis, E. (2020) · Springer tracts in civil engineering · doi:10.1007/978-3-030-47310-5_7
Fast Matching for Consecutive Frames of UAV Video
Yin, X., Yang, D., Lin, D., et al. (2020) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc49329.2020.9164566
“At present, the research on image matching has achieved good results [5-7] such as correlation coefficient algorithm [8], the mutual information algorithm, SIFT [1], SURF [9] and ORB [10] operator, etc.”
MethodSpacecraft Attitude Determination Using Terrestrial Illumination Matching
Shockley, L. M., & Bettinger, R. A. (2020) · Proceedings - IEEE Aerospace Conference · doi:10.1109/aero47225.2020.9172618
Multi-sensor Image Stitching and Fusion Based Air Infrared Target Cooperative Detection
Nan, J., Zhao, B.-J., Cui, T., et al. (2019) · IEEE International Conference on Signal, Information and Data Processing (ICSIDP) · doi:10.1109/icsidp47821.2019.9173075
“Comparing with SURF [9] and FAST [10], the image registration precision (IRP) is utilized to evaluate the effectiveness of the proposed grid corner feature.”
MethodSSNet: Saliency-SelectNet for Vehicle Re-Identification
Li, X., Li, G., & Liang, J. (2020) · ASCE International Conference on Transportation and Development (ICTD) · doi:10.1061/9780784483138.024
An Approach to Cohort Selection in Cloud for Face Recognition
Garain, J., Maity, S., & Kumar, D. (2020) · Smart innovation, systems and technologies · doi:10.1007/978-981-15-6202-0_11
Баязітов, М. Р., Bayazitov, D. M., Бузиновський, А. Б., Liashenko, A., Novikov, D., & Семенович, Г. Л. (2020) · Medical Informatics and Engineering · doi:10.11603/mie.1996-1960.2020.2.11175
Retaining Image Feature Matching Performance Under Low Light ConditionsPreprint
Shyam, P., Bangunharcana, A., & Kim, K.-S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.00842
Statistical Descriptors-Based Image Classification of Textural Images
Bagavathi, C., & Saraniya, O. (2020) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-5558-9_78
A Novel Keypoints-Based Image Registration Method with Fully Convolutional Neural Network
Yang, X., Li, D., He, Q., et al. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-8083-3_9
Gwo, C. (2020) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1145/3408127.3408129
“INTRODUCTION Zernike moments (ZMs) are used in a wide variety of fields, such as breast density classification, tumor shape, benign and malignant differentiation [1, 2], brain MRI imaging tumor identification [3], and Alzheimer's disease recognition [4].”
BackgroundDeep learning for real-world object detection
Wu, X. (2020) · Singapore Management University Institutional Knowledge (InK) (Singapore Management University)
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.