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 13,401–13,500 of 14,752
Deep Learning-based Self Organizing Map for Content-based Image Retrieval Applications
Awny, E. (2020) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2020/217942020
Le, D. C., & Youn, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09255
Wang, Y., Chen, Q., Wang, P., Lü, Y., & Jia, G. (2020) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc49165.2020.00050 · Cited by 1
“Typical local features include Harris[2], SIFT[3], SURF[4], etc.”
Real-time image registration method based on improved ORB algorithm for microscope
Chen, Q., Jiang, N., Zhou, H., et al. (2020) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc49165.2020.00069
“The most common of these algorithms include scale-invariant feature transform (SIFT) [5], [6], speed up robust features (SURF) [7], KAZE features [8], Accelerated KAZE (AKAZE) [9], Features From Accelerated Segment Test (FAST) and Rotated Binary Robust Independent Elementary Features (BRIEF)…”
MethodGUI-focused overviews of mobile development videos
Alahmadi, M. D., Malkadi, A., & Haiduc, S. (2020) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3377812.3390900
“Then, we filtered out duplicate frames, identified based on their distinctive features, determined using the Speeded Up Robust Features (SURF) algorithm [2] from the field of computer vision.”
MethodDirectly Obtaining Matching Points without Keypoints for Image Stitching
Huang, Y., Jing, M., Fan, Y., et al. (2020) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas45731.2020.9180818
A Stream Hardware Architecture for Keypoint Matching Based on a Speculative Approach
Lepecq, M., & Darouich, M. (2020) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas45731.2020.9180928
KLT Bin Detection and Pose Estimation in an Industrial Environment
Beloshapko, A., Knoll, C. J., Boughattas, B., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58817-5_9
An Efficient Binary Feature Based on Hierarchical Structure Histogram
Yu, W., Qin, X., & Wang, P. (2020) · International Conference on Computers, Information Processing and Advanced Education (CIPAE) · doi:10.1145/3419635.3419713
“Among these descriptors, SIFT [3] and SURF [4] are two influential works.”
BackgroundАЛГОРИТМ ВИЗНАЧЕННЯ ШЛЯХУ ДЛЯ АВТОНОМНОГО РУХУ БЕЗПІЛОТНОГО ТРАНСПОРТУ ПО ЛІНІЇ
Valko, N., БОЛГАРІН, Т. О., & Валько, К. (2020) · Applied Questions of Mathematical Modeling · doi:10.32782/kntu2618-0340/2020.3.2-1.3
Improved SURF Feature Matching Algorithm Based on FAST Scale Area
Sun, H., Liu, L., Wang, R., et al. (2020) · IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) · doi:10.1109/aeeca49918.2020.9213620
“For example: DoG (Difference of Gaussians) box algorithm [1], FAST algorithm [2], harris algorithm, SUSAN operator, Forstner algorithm, Moravec algorithm, BRISK algorithm [3] (Binary Robust Invariant Scalable Keypoints) and so on.”
MethodSegmenting Epipolar LinePreprint
Li, S., Cai, Q., & Wu, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.05131
“For two images without a priori information we usually use feature detection methods like SIFT [1] or SURF [2] to find the correspondence between images.”
Ullah, T., Khan, A., & Waleed, M. (2020) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai50035.2020.9223199
“SURF descriptor has powerful invariant attributes like rotation invariance, contrast invariance, scale invariance, illumination invariance and translation invariance for recognition in image or video [22, 23].”
BackgroundEffective Non-Cooperative Surveillance for UAS Situational Awareness
Keller, J. M., Deng, B., Gore, D., et al. (2020) · Integrated Communications, Navigation and Surveillance Conference (ICNS) · doi:10.1109/icns50378.2020.9222908
Research on Unstructured Electronic Archives Query Based on Visual Retrieval Technology
Hui, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60799-9_52
Robustness evaluation of remote-sensing image feature detectors with TH priori-information data set
Duan, Y., Tao, X., Liu, X., et al. (2020) · China Communications · doi:10.23919/jcc.2020.10.016
Extreme Value Preserving NetworksPreprint
Sun, M., Li, J., & Zhang, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.08367
Bionic Vision Descriptor for Image Retrieval
Li, G., Liu, S., Wang, F., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63830-6_14
Кривоножко, А. М., Явтушенко, В., Самокиш, А. В., et al. (2020) · Системи озброєння і військова техніка · doi:10.30748/soivt.2020.63.03
Altukhov, A. I., Bilan, V. I., Григорьев, А. Н., et al. (2020) · Scientific and technical journal of information technologies mechanics and optics · doi:10.17586/2226-1494-2020-20-5-649-660
Robust Target Detection in Optical Scene Based on Multiple Reference Images
Kamel, M. M., Hussein, S., Salama, G. I., et al. (2020) · Novel Intelligent and Leading Emerging Sciences Conference (NILES) · doi:10.1109/niles50944.2020.9257980
“[4] improved SIFT's efficiency by introducing SURF (Speeded Up Robust Features) which is built on the on the basis of SIFT.”
MethodVisual and lidar-based SLAM by variational bayesian methods
Jiang, X. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/139813 · Cited by 1
Collective Learning Ambiance of Human Pursuance with Intelligent Revival and Prediction Analysis
Tharageswari, K., Raja, L., Selvapandian, D., & Dhanapal, R. (2020) · International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) · doi:10.1109/i-smac49090.2020.9243396
CS-ONPP: Class Similarity Based ONPP for the Modular Facial Expression Recognition
Sujata, Koringa, P. A., & Mitra, S. K. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-8697-2_39
A tracker selection model for augmented reality applications
Teixeira, J. M., & Teichneb, V. (2020) · Symposium on Virtual and Augmented Reality (SVR) · doi:10.1109/svr51698.2020.00073
Kwon, H. T., Koh, J.-W., Kim, S., et al. (2018) · Journal of the Korea Institute of Military Science and Technology · doi:10.9766/kimst.2018.21.3.315
SURF ve RANSAC Tabanlı Homografi Tahmini Kullanarak Otomatik İmaj Birleştirme
Bas, A. (2022) · Journal of Polytechnic · doi:10.2339/politeknik.768444 · Cited by 1
Infrared small target detection based on isotropic constraint under complex backgroundPreprint
Wang, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.12059
“ssian matrix is a square matrix composed of the second partial derivatives of multivariate functions and has been widely used in image processing. Herbert Bay proposed Speed Up Robust Features (SURF) [22], extracting the points of interest in the images using Hessian matrix. Benefitting from the acceleration of integr…”
Optimized Local Image Watermarking Combining Feature Point and Texture
Huang, Y., Guan, H., Zhang, S., et al. (2020) · International Conference on Culture-oriented Science & Technology (ICCST) · doi:10.1109/iccst50977.2020.00072
A Low-Complexity and Hardware-Oriented Image Stitching Algorithm
Wen, F.-J., Lin, J.-Y., Chiou, Y., et al. (2020) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan49838.2020.9258038
“There are several main methods for feature detection, such as Scale Invariant Feature Transform (SIFT) [2], Speeded-Up Robust Features (SURF) [3] and Feature from Accelerated Segment Test (FAST) [4], as well as various improved algorithms.”
MethodOnline Descriptor Enhancement via Self-Labelling Triplets for Visual Data AssociationPreprint
Shaoul, Y., Liu, K., Ok, K., & Roy, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.10471
“Although supervised learning methods [3], [4] have recently outperformed hand-engineered descriptors when at-tempting to adapt robustly to new data-association problems [5], [6], they can be difficult to train, and perform inconsistently.”
MethodFeature Engineering for Structural Health Monitoring (SHM)
Elhariri, E., El-Bendary, N., & Taie, S. A. (2020) · Advances in data mining and database management book series · doi:10.4018/978-1-7998-6659-6.ch008
A Monocular Visual-Inertial Odometry Based on Hybrid Residuals
Lai, Z., Gui, J.-J., Xu, D., Dong, H., & Deng, B.-S. (2020) · IEEE International Conference on Systems, Man and Cybernetics · doi:10.1109/smc42975.2020.9283418
“The feature points used in SLAM framework usually refer to robust local image feature points like SIFT [9], SURF [10], ORB [11], etc., and feature points matching is usually based on the comparison of the distance between feature point’s descriptor, i.e.”
MethodPaul, S. K., Hoseini, P., Nicolescu, M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.04135
“Although a few other variants of SIFT and SURF were proposed to address these limitations, they were not efficient enough for devices with limited computational resources.”
MethodInfluentialEnabling Tangible Interaction through Detection and Augmentation of Everyday ObjectsPreprint
Kosch, T., & Schmidt, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.10904 · Cited by 3
“Thereby, the algorithm has been used for object detection by comparing points of interest in a captured image relative to a reference image [2].”
Camera Based Presentation Support System for Multiscreen Venue Using Laser Pointer
Shibata, D., & Funahashi, K. (2020) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce50665.2020.9291753
“There are algorithms such as Scale Invariant Feature Transform (SIFT) [6], Speeded Up Robust Features (SURF) [7], KAZE [8], and Accelerated-KAZE (AKAZE) [9] as types of feature matching.”
MethodHigh-Throughput Image Alignment for Connectomics using Frugal Snap Judgments
Kaler, T., Wheatman, B., & Wooders, S. (2020) · IEEE High Performance Extreme Computing Conference · doi:10.1109/hpec43674.2020.9286243
“Other algorithms such as SURF [12] and ORB [13] are sometimes used in place of SIFT, but their use is not as common.”
MethodRegistration for Infrared Image Sequence via Distance Transform of Binary Features
Hui, B., Yang, C., He, M., & Yi, M. (2020) · International Conference on Aviation Safety and Information Technology (ICASIT) · doi:10.1145/3434581.3434638
Feng, X. (2018) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.5589
CNN-based Visual Ego-Motion Estimation for Fast MAV Maneuvers.Preprint
Xu, Y., & de Croon, G. (2021) · arXiv (Cornell University)
Target Tracking Algorithm Combining Improved GMS and Correlation Filtering
Dang, D., Liu, Q., Li, W., et al. (2020) · International Conference on Control, Robotics and Intelligent System (CCRIS) · doi:10.1145/3437802.3437807
Methods for large-scale image-based localization using structure-from-motion point clouds
Cheng, W. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/137803
Parameter Optimization of Feature Matching-Based Object Recognition Algorithm by using CMA-ES
Hagihara, D., Yano, T., & Kimura, N. (2020) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv50220.2020.9305448
Analysis of Vehicle Collision Prediction Algorithms Using CNN
Jain, T., Aggarwal, G., & Gupta, S. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-15-8335-3_62
Research on Fabric Image Mosaics Based on SURF
Xuan, S., Wenwen, X., Zhang, M., et al. (2020) · doi:10.1145/3436286.3436411
“Because the SURF [1] algorithm has superior registration accuracy and high real-time characteristics , this paper uses the SURF algorithm in the process of extracting feature points from the fabric image.”
MethodLee, S. (2020) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2020.10.010
“Typical examples include Scale Invariant Feature Transform (SIFT) [2] and Speeded Up Robust Features [4], and these are called keypoint descriptors.”
MethodComparation of several mapping methods for humanoid robot
Xu, X. (2020) · doi:10.1145/3444370.3444562
“A feature point method with rotation invariance is proposed in literature [16] and an improvement on SIFT method is proposed in reference [17].”
MethodAn Effective Rotational Invariant Key-point Detector for Image Matching
Hong-Phuoc, T., & Guan, L. (2020) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2020.00043
“In this paper, the average repeatability values of the RI-SCK detector on Webcam, VGG and EF datasets are compared with many popular hand-crafted detectors such as SIFT [2], SURF [3], SFOP [4], KAZE [17], AKAZE [18], Hessian Laplace [15], Harris Laplace [15], Hessian Affine [15], Harris Affine [15].”
MethodLi, M., Huang, X., & Zhang, Z. (2020) · arXiv (Cornell University)
Remote Space- and Time-Resolved Skin Perfusion Detection Using Photoplethysmography Imaging
Blanik, N. (2021) · Biological and medical physics, biomedical engineering · doi:10.1007/978-981-15-5449-0_11 · Cited by 1
A Two Fold Approach for Object Recognition with Bag of Visual Words using Artificial Neural Network
Raza, M. A., Hussain, Q., Mustafa, S., Bhatti, M. A., & Ahmad, M. (2020) · IEEE International Multitopic Conference (INMIC) · doi:10.1109/inmic50486.2020.9318197
3D Image Stitching of Train Bottom based on SURF and Cross Gauss Laplace Descriptor
Liu, W., Su, Z.-Y., Chen, J., et al. (2020) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac51587.2020.9337607
Development of augmented reality mobile application on android OS
Galeeva, А. М., & Medvedeva, О. А. (2021) · doi:10.36906/ap-2020/17
Large Scale Microscopic Image Mosaic Based on SURF Algorithm
王, 世. (2021) · Computer Science and Application · doi:10.12677/csa.2021.112030
Hand Gesture Recognition with Gaussian Scaling and Kirsch Edge Rotation
Narayan, S., Vipparthi, S. K., & Mazumdar, A. P. (2020) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciis51140.2020.9342716
A Novel SLAM Algorithm based on Region Focusing Image Segmentation
Tan, C., Ruan, X., & Zhu, X. (2020) · Chinese Automation Congress · doi:10.1109/cac51589.2020.9326761 · Cited by 1
Poly Scale Space Technique for Feature Extraction in Lip Reading: A New Strategy
Nandini, M. S., Bhajantri, N. U., & Nagavi, T. C. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-6353-9_6
Background Modeling with Freely Moving Camera
Hu, H. (2020) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc51575.2020.9345077
ESTIMATING RAINFALL IN THE PHILIPPINES USING AN AUTOMATED INTERPRETATION OF FORECAST IMAGES
Basa, T., Regonia, P. R., Racho, S. M., et al. (2012) · ASEAN Engineering Journal · doi:10.11113/aej.v2.15378
“Pmin =γ−α, Pmin ≥0 (2) Pmax =γ+α, Pmax ≤δmax (3)”
Monitoring Cracks on Concrete Surfaces using Multi-temporal Images
Santos, B. O., Valença, J., & Júlio, E. (2018) · Report · doi:10.2749/nantes.2018.s24-95
Картографіче забезпечення кореляційно-екстремальної навігаційної системи
Babeniuk, G. (2020) · Proceedings of National Aviation University · doi:10.18372/2306-1472.85.15135
Detecting Small Moving Targets in Infrared Imagery
Cuellar, A. (2020) · Journal of International Crisis and Risk Communication Research
Vers un apprentissage sans exemple plus réaliste
Cacheux, Y. L. (2020) · theses.fr (ABES) · doi:10.70675/a628e266zf8bdz4c57zb7b3z91477cfbf198
Hole Concealment Algorithm Using Camera Parameters in Stereo 360 Virtual Reality System
Cha, S., Nam, D.-Y., & Han, J.-K. (2021) · Applied Sciences · doi:10.3390/app11052033
Visual inertial odometry and lidar inertial odometry for mobile robot
Henawy, J. (2021) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/146364
Cellcounter: a deep learning framework for high-fidelity spatial localization of neuronsPreprint
Batabyal, T., Naik, A. A., Weller, D. S., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.10462
“There are several, popular discriminatory features, such as scale-invariant feature transform (SIFT) [11], histogram of oriented gradients (HOG) [12], speeded up robust features (SURF) [13], PCA-SIFT [14], non-redundant local binary pattern (LBP) [15] and Gabor filter bank [16].”
Signal Processing for Contactless Monitoring
Billah, M. S., Ahad, M. A. R., & Mahbub, U. (2021) · Intelligent systems reference library · doi:10.1007/978-3-030-68590-4_4
Influence of Membership Function Type on the Accuracy of Video Tracking Algorithm
Bozhenyuk, A. V., & Morev, K. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-1480-4_40
Фам, Т. А. (2021) · Естественные и Технические Науки · doi:10.37882/2223-2966.2021.02.31
“♦ Дескрипторы функций: в компьютерном зре-нии существуют некоторые алгоритмы, такие как SIFT (Scalar Invariant Feature Transform) [11], SURF (Speeded-Up Robust Features) [12], для описания локальных особенностей изображений, инва-риантных к масштабированию, ориентации, ис-кажению и освещению.”
SD-6DoF-ICLK: Sparse and Deep Inverse Compositional Lucas-Kanade Algorithm on SE(3)Preprint
Hinzmann, T., & Siegwart, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.16528
“Feature-based methods have come a long way from computationally expensive hand-crafted feature detectors and descriptors (SIFT [11], SURF [2]) to faster binary variants (BRISK [10]) and recently trainable approaches (SuperPoint [4], D2-Net [6]).”
MethodWhich Parts Determine the Impression of the Font?Preprint
Ueda, M., Kimura, A., & Uchida, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.14216
“Parts of an image sample have been utilized via local descriptors, such as SIFT [13] and SURF [2], to realize generic object recognition, image retrieval, and image matching.”
MethodInfluentialELMAS, B. (2021) · Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi · doi:10.19113/sdufenbed.818716
Vision-based 3D information modeling and applications
Ni, Y. (2021) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/145895
Convolutional Hough Matching NetworksPreprint
Min, J., & Cho, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.16831
IMPROVING GEOLOCATION BY COMBINING GPS WITH IMAGE ANALYSIS
Fabio, F., Pinho, ALEXANDRE, A., et al. (2014)
Deep Features for training Support Vector MachinePreprint
Nanni, L., Ghidoni, S., & Brahnam, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.03488
Motion correction of PET/CT images
Chie, J. A. K. C. (2017) · Purdue e-Pubs (Purdue University System) · doi:10.7912/c2bs9w
Xu, L. (2019) · Deep Blue (University of Michigan)
Khalaf, E. T. (2019) · UMP Institutional Repository (Universiti Malaysia Pahang)
Decimation and Analysis: An Internal Bleeding Detection Framework for 3D Ultrasound
Vukovich, M. (2018) · TSpace (University of Toronto)
Extreme Rotation Estimation using Dense Correlation VolumesPreprint
Cai, R., Hariharan, B., Snavely, N., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.13530
Yang, J., Yang, X., Zhou, Z., et al. (2021) · doi:10.1109/icicse52190.2021.9404132
“Traditional methods such as the scale invariant feature transform (SIFT) [1] and speeded-up robust features (SURF) [4], mainly focus to constructing robust appearance descriptor which can be used to find the point correspondence.”
MethodThe Realtime Indoor Localization Unmanned Aerial Vehicle
Zhou, Y., Yu, Z., & Ma, Z. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-2336-3_5
Implementasi Content Based Video Retrieval Menggunakan Speeded-up Robus Features (Surf)
Feldi, M., Solahuddin, S., & Yuswanita, L. (2021) · Sintaksis
Automatic License Plate Detection And Character Recognition
Swetha, D., Naik, R. R., Bhargav, P. R., et al. (2016) · Journal of Emerging Technologies and Innovative Research
Development of an Algorithm for Determining the Railway Tracks on Video Image
Deylid, I. A., Molodyakov, S. A., & Tyutin, B. (2021) · Smart innovation, systems and technologies · doi:10.1007/978-981-33-6632-9_3
Identificação automática de motociclistas através de processamento de imagens de vídeo de tráfego
Felicio, A. B. (2020) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.18.2020.tde-12052020-170835 · Cited by 1
Fusing CAMs-weighted features and temporal information for robust loop closure detection
Li, Y., Zhong, S.-H., Ren, T., & Liu, Y. (2021) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3444685.3446309
“These hand-crafted features mainly fall into two categories: local features such as SIFT [16] and SURF [2], and global features such as GIST [21] and HOG [19].”
MethodPREPRINT: Comparison of deep learning and hand crafted features for mining simulation dataPreprint
Georgiou, T., Schmitt, S., Bäck, T., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.06552
Alyosef, A. A., Elias, C., & Nürnberger, A. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412354
“Since keypoints features are the most popular in NDR research, we evaluate our approach utilizing: scale invariant feature transformation (SIFT) [11], speed-up robust feature (SURF) [12] and binary robust invariant scalable keypoints (BRISK) [13].”
MethodA Vehicular Electronic Image Stabilization System Based on A Gasoline Model Car PlatformPreprint
Zhang, N., Yang, Y., Wu, J.-H., et al. (2020) · Research Square · doi:10.21203/rs.3.rs-88810/v1
Learning to Predict Repeatability of Interest PointsPreprint
Doan, A.-D., Turmukhambetov, D., Latif, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.03578
A Report on the Cost of Data PrivacyPreprint
Balamurugan, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.06263
SHIMIZU, M., Kawanishi, Y., Deguchi, D., Ide, I., & Murase, H. (2021) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.87.447
Sistema computacional para identificar níveis de degradação em barras de aço
dos Santos, A. I. P., Gavião, E. S., Chapla, K., et al. (2021) · Congresso Internacional sobre Patologia e Reabilitação das Construções · doi:10.4322/cinpar.2021.079
Interactive Global Mosaic Stitching from Mesentery Video Sequences
Aktar, R., Huxley, V. H., Guidoboni, G., et al. (2020) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr50011.2020.9425109
Localization and Tracking of User-Defined Points on Deformable Objects for Robotic ManipulationPreprint
Dittus, S., Alt, B., Hermann, A., Katić, D., Jäkel, R., & Fleischer, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.09067 · Cited by 3
“To reach the precision required for sophisticated manipulation tasks, prior work requires external markers [10], [11] or elaborate physics models [3], [12]–[15].”
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.