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 1,201–1,300 of 14,752
A Dataset for Benchmarking Image-Based Localization
Sun, X., Xie, Y., Luo, P., & Wang, L. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.598 · Cited by 76
“First are image retrieval based methods using state-of-the-art visual features [3, 5, 18, 23] and geometry verification [26].”
MethodFace Feature Extraction: A Complete Review
Wang, H., Hu, J., & Deng, W. (2017) · IEEE Access · doi:10.1109/access.2017.2784842 · Cited by 63
Zhang, Z., Wang, M., Huang, Y., & Nehorai, A. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00362 · Cited by 59
“We consider two types of features: the SURF features [2] and the DeCAF6 features [9].”
MethodDeep Learning for Visual SLAM in Transportation Robotics: A review
Duan, C., Junginger, S., Huang, J., Jin, K., & Thurow, K. (2019) · Transportation Safety and Environment · doi:10.1093/tse/tdz019 · Cited by 63
A comprehensive investigation into sclera biometrics: a novel dataset and performance study
Vitek, M., Rot, P., Štruc, V., & Peer, P. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-04782-1 · Cited by 70
“• SURF [3]: A SIFT alternative from the literature adds several features to speed up every step of the algorithm, while keeping performance close to SIFT’s.”
MethodStructural health monitoring of railway tracks using IoT-based multi-robot system
Iyer, S., Velmurugan, T., Gandomi, A. H., Mohammed, V. N., Saravanan, K., & Nandakumar, S. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05366-9 · Cited by 67
“5 Ultrasonic sensor placement crack from the image are extracted using the Speeded-up robust features (SURF) algorithm [25].”
MethodThe Stereoscopic Analyzer — An image-based assistance tool for stereo shooting and 3D production
Zilly, F., Muller, M. G., Eisert, P., et al. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5649828 · Cited by 58
Content-Based Image Retrieval using SURF and Colour Moments
Velmurugan, K., & Baboo, L. D. S. S. (2011) · Global Journal of Computer Science and Technology · Cited by 59
Unsupervised t-Distributed Video Hashing and Its Deep Hashing Extension
Hao, Y., Mu, T., Goulermas, J. Y., Jiang, J., Hong, R., & Wang, M. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2737329 · Cited by 57
“Popular local feature descriptors include SIFT [53], SURF [54], and LBP [55].”
MethodAn overview of thermal face recognition methods
Krišto, M., & Ivašić-Kos, M. (2018) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.23919/mipro.2018.8400200 · Cited by 58
“6 Face grayscale thermal image (a), blood perfusion obtained transforming a medial axis on bit-plane (b); morphological gray level erosion and medical axis transform (c); result of Sobel operator (d) [9] (a) (b) (c) (d) Linear Descriptor) [12], the GJD (Gabor Jet Descriptor) [13], SIFT (Scale-Invariant Feature Transfo…”
ResultIn object detection deep learning methods, YOLO shows supremum to Mask R-CNN
Sumit, S. S., Watada, J., Roy, A., & Rambli, D. R. A. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1529/4/042086 · Cited by 68
“There are some other popular object detectors: SIFT (Scale-invariant feature transform), this technique identifies and explains the local characteristics in pictures [18], SURF (Speeded up robust features), it is a static Hessian scale and rotation based descriptor which extracts interested attributes in the images [1…”
MethodFixing Defect of Photometric Loss for Self-Supervised Monocular Depth Estimation
Chen, S., Pu, Z., Fan, X., & Zou, B. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3068834 · Cited by 62
Video stabilization: A comprehensive survey
Wang, Y., Huang, Q., Jiang, C., Liu, J., Shang, M., & Miao, Z. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.10.008 · Cited by 75
A Brief, In-Depth Survey of Deep Learning-Based Image Watermarking
Zhong, X. R., Das, A., Alrasheedi, F., & Tanvir, A. A. (2023) · Applied Sciences · doi:10.3390/app132111852 · Cited by 121
Eerola, T., Batrakhanov, D., Barazandeh, N. V., Kraft, K., Haraguchi, L., Lensu, L. T., Suikkanen, S., Seppälä, J., Tamminen, T., & Kalviainen, H. A. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10745-y · Cited by 88
“, 2007), Speeded Up Robust Features (SURF) (Bay et al., 2006; Chang et al., 2016), Inner-Distance shape context (IDSC) (Ling and Jacobs, 2007; Zheng et al.”
BackgroundInfluentialIndoor mapping using planes extracted from noisy RGB-D sensors
Lee, T.-K., Lim, S., Lee, S., An, S., & Oh, S. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385909 · Cited by 57
Location coding for mobile image retrieval
Tsai, S. S., Chen, D. M., Takacs, G., Chandrasekhar, V., Singh, J., & Girod, B. (2009) · EAI International Conference on Mobile Multimedia Communications (MobiMedia) · doi:10.4108/icst.mobimedia2009.7406 · Cited by 58
Graph-based approach for human action recognition using spatio-temporal features
Aoun, N. B., Mejdoub, M., & Amar, C. B. (2013) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2013.11.003 · Cited by 58
Ramírez-Alonso, G. M. D. J., & Chacon-Murguia, M. I. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.04.118 · Cited by 58
Sparse Spatial Coding: A novel approach for efficient and accurate object recognition
Oliveira, G. L., Nascimento, E. R., Vieira, A. W., & Campos, M. F. M. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6224785 · Cited by 60
Active machine learning-driven experimentation to determine compound effects on protein patterns
Naik, A. W., Kangas, J. D., Sullivan, D. P., & Murphy, R. F. (2016) · eLife · doi:10.7554/elife.10047 · Cited by 69
“Posthoc image quality control SURF ( Bay et al., 2006 ) features were calculated for each image using just the GFP channel, restricting the interest points to be within ~ 10 m m (150 pixels) of a segmented nucleus.”
MethodVideo Stabilization for Strict Real-Time Applications
Dong, J., & Liu, H. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2589860 · Cited by 58
DeepCAD: A Computer-Aided Diagnosis System for Mammographic Masses Using Deep Invariant Features
Abbas, Q. (2016) · Computers · doi:10.3390/computers5040028 · Cited by 60
Long-Term 3D Localization and Pose from Semantic Labellings
Toft, C., Olsson, C., & Kahl, F. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.83 · Cited by 61
“The main problem that makes long-term localization difficult is the fact that the feature descriptors used to describe the image and the 3D scene are not invariant to the changes in environment seen during different seasons, weather and time of day (such as SIFT [22], ORB [29] and SURF [5]).”
BackgroundInfluentialPotluck: Cross-Application Approximate Deduplication for Computation-Intensive Mobile Applications
Guo, P., & Hu, W. (2018) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3173162.3173185 · Cited by 78
“For example, the feature vector might be a 768-bit vector to represent the color histogram, a vector of N ⇥ 64 bytes to describe SURF features from the input image, or a vector of m ⇥ n bytes to represent the down-sampled version of the raw input image into m ⇥ n pixels.”
MethodInfluentialA Survey on Data‐Driven 3D Shape Descriptors
Rostami, R., Bashiri, F. S., Rostami, B., & Yu, Z. (2018) · Computer Graphics Forum · doi:10.1111/cgf.13536 · Cited by 63
“In this work, at first, salient feature points are detected in RGB-D images using the SURF algorithm [BTVG06].”
MethodFrom words to pixels: text and image mining methods for service research
Ordenes, F. J. V., & Zhang, S. (2019) · Journal of service management · doi:10.1108/josm-08-2019-0254 · Cited by 69
“The methods for image mining appear to be shifting, from traditional object recognition (e.g. SIFT, Lowe, 1999; SURF, Bay et al ., 2006) and machine learning (e.g. supervised learning with SVM and unsupervised learning with principal component 604 ,5 analysis (PCA)) to deep learning (CNN).”
MethodLearning spatial-temporal features for video copy detection by the combination of CNN and RNN
Hu, Y., & Lu, X. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.05.013 · Cited by 57
Sensor fusion for flexible human-portable building-scale mapping
Fallon, M. F., Johannsson, H., Brookshire, J., Teller, S. J., & Leonard, J. J. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385882 · Cited by 63
View-Wise Versus Cluster-Wise Weight: Which Is Better for Multi-View Clustering?
Hu, S., Lou, Z., & Ye, Y. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3128323 · Cited by 59
Nighthawk: Fully Automated Localizing UI Display Issues via Visual Understanding
Liu, Z., Chen, C., Wang, J., Huang, Y., Hu, J., & Wang, Q. (2023) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2022.3150876 · Cited by 58
Multimodal image registration techniques: a comprehensive survey
Velesaca, H. O., Guacho, G. K. B., Rouhani, M., & Sappa, A. D. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17991-2 · Cited by 72
“During last decades different hand-made feature descriptors have been proposed in the literature (e.g., [17–20]) to tackle the multimodal problem, most of them are adaptations of the well known EOH, SIFT, SURF, etc. (e.g., [21–23]).”
BackgroundRecognizing Ancient Coins Based on Local Features
Kampel, M., & Zaharieva, M. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-89639-5_2 · Cited by 63
“[23] introduced recently a further detector based on the Hessian matrix – the Fast-Hessian detector.”
BackgroundMethodFeature integration of EODH and Color-SIFT: Application to image retrieval based on codebook
Tian, X., Jiao, L., Liu, X., & Zhang, X. (2014) · Signal Processing Image Communication · doi:10.1016/j.image.2014.01.010 · Cited by 61
Rotation and Illumination Invariant Interleaved Intensity Order-Based Local Descriptor
Dubey, S. R., Singh, S. K., & Singh, R. K. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2358879 · Cited by 59
Automatic knowledge-based recognition of low-level tasks in ophthalmological procedures
Lalys, F., Bouget, D., Riffaud, L., & Jannin, P. (2012) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-012-0685-6 · Cited by 59
A Local Structural Descriptor for Image Matching via Normalized Graph Laplacian Embedding
Tang, J., Shao, L., Li, X., & Lü, K. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2402751 · Cited by 56
“We have observed that most of the available local descriptors such as shape context [16], SIFT [17], and SURF [18] use the distribution of some properties extracted from images to describe a feature point.”
MethodFarag, A. A., Ali, A., Graham, J. A., Farag, A. A., Elshazly, S., & Falk, R. L. (2011) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2011.5872380 · Cited by 53
Face Components Detection Using SURF Descriptors and SVMs
Kim, D., & Dahyot, R. (2008) · International Machine Vision and Image Processing Conference (IMVIP) · doi:10.1109/imvip.2008.15 · Cited by 63
Stereo wave imaging from moving vessels: Practical use and applications
Benetazzo, A., Barbariol, F., Bergamasco, F., et al. (2016) · Coastal Engineering · doi:10.1016/j.coastaleng.2015.12.008 · Cited by 57
Analysis of various image feature extraction methods against noisy image: SIFT, SURF and HOG
Routray, S., Ray, A. K., & Mishra, C. (2017) · International Conference on Electrical, Computer and Communication Technologies (ICECCT) · doi:10.1109/icecct.2017.8117846 · Cited by 67
“But, current research on image matching is typically based on SIFT [9], SURF [10] and HOG [11] descriptors due to good performance and wide range of applications.”
MethodInter-frame passive-blind forgery detection for video shot based on similarity analysis
Zhao, D., Wang, R.-K., & Lu, Z. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5791-1 · Cited by 65
“According to the algorithm proposed by Bay in [4] for easy application, the approximation of the second order derivatives in Eq.”
MethodRe-weighting and 1-Point RANSAC-Based PnP Solution to Handle Outliers
Zhou, H., Zhang, T., & Jayender, J. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2871832 · Cited by 61
Copy-move forgery detection using binary discriminant features
Raju, P. M., & Nair, M. S. (2018) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2018.11.004 · Cited by 66
“SIFT and SURF are floating point descriptors that have higher accuracy of keypoint detection and matching, but require huge memory and are relatively slower due to the large descriptor size.”
Revisiting Monocular Satellite Pose Estimation With Transformer
Wang, Z., Zhang, Z., Sun, X., Li, Z., & Yu, Q. (2022) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2022.3161605 · Cited by 59
Range and Motion Estimation of a Monocular Camera Using Static and Moving Objects
Chwa, D., Dani, A. P., & Dixon, W. E. (2015) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2015.2508001 · Cited by 57
“The point correspondences between consecutive images of a monocular camera needs to be described through the measurement model in both Euclidean and image spaces, which can be computed using the feature tracking techniques [32]–[34].”
Trends in Vehicle Re-Identification Past, Present, and Future: A Comprehensive Review
Zakria, Z., Deng, J., Yang, H. F., Khokhar, M. S., Kumar, R., Cai, J., Kumar, J., & Aftab, M. U. (2021) · Mathematics · doi:10.3390/math9243162 · Cited by 65
Ye, T., Zhao, Z., Zhang, J., Chai, X., & Zhou, F. (2021) · Journal of Systems Engineering and Electronics · doi:10.23919/jsee.2021.000073 · Cited by 61
Depth-Wise Separable Convolution Attention Module for Garbage Image Classification
Liu, F., Xu, H. F., Qi, M., Liu, D., Wang, J., & Kong, J. (2022) · Sustainability · doi:10.3390/su14053099 · Cited by 56
D-LIOM: Tightly-Coupled Direct LiDAR-Inertial Odometry and Mapping
Wang, Z., Zhang, L., Shen, Y., & Zhou, Y. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3168423 · Cited by 75
A Practical Survey on Visual Odometry for Autonomous Driving in Challenging Scenarios and Conditions
Agostinho, L. R., Ricardo, N. M., Pereira, M. I., Hiolle, A., & Pinto, A. M. (2022) · IEEE Access · doi:10.1109/access.2022.3188990 · Cited by 77
Multi-Ellipsoidal Extended Target Tracking With Variational Bayes Inference
Tuncer, B., Orguner, U., & Özkan, E. (2022) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2022.3192617 · Cited by 57
Image Classification Using Multiple Convolutional Neural Networks on the Fashion-MNIST Dataset
Nocentini, O., Kim, J., Bashir, M. Z., & Cavallo, F. (2022) · Sensors · doi:10.3390/s22239544 · Cited by 79
A Fast and Accurate Feature-Matching Algorithm for Minimally-Invasive Endoscopic Images
Puerto-Souza, G. A., & Mariottini, G.-L. (2013) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2013.2239306 · Cited by 62
Combining image descriptors to effectively retrieve events from visual lifelogs
Doherty, A., Conaire, C. Ó., Blighe, M., Smeaton, A. F., & O'Connor, N. E. (2008) · Multimedia Information Retrieval · doi:10.1145/1460096.1460100 · Cited by 55
An automated growth measurement system for leafy vegetables
Yeh, Y.-H. F., Lai, T.-C., Liu, T., Liu, C.-C., Chung, W.-C., & Lin, T. (2013) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2013.08.011 · Cited by 64
Image search—from thousands to billions in 20 years
Zhang, L., & Rui, Y. (2013) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/2490823 · Cited by 70
Albarelli, A., Rodolà, E., & Torsello, A. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-011-0432-4 · Cited by 57
Robust Feature Set Matching for Partial Face Recognition
Weng, R., Lu, J., Hu, J., Yang, G., & Tan, Y. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.80 · Cited by 57
“All these three baselines were used to match textural features of concatenated SIFT and SURF feature sets (SIFTSURF).”
MethodInfluentialDirect Visual Localisation and Calibration for Road Vehicles in Changing City Environments
Pascoe, G., Maddern, W., & Newman, P. M. (2015) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2015.23 · Cited by 60
“Successful methods for performing outdoor visual odometry, localisation and SLAM have typically made use of robust point feature detectors and descriptors, such as the well-known SIFT [17] and SURF [5].”
MethodA Model of Visual Attention for Natural Image Retrieval
Liu, G., & Fan, D.-P. (2013) · International Conference on Information Science and Cloud Computing Companion (ISCC-C) · doi:10.1109/iscc-c.2013.21 · Cited by 60
Open-source feature-tracking algorithm for sea ice drift retrieval from Sentinel-1 SAR imagery
Muckenhuber, S., Korosov, A. A., & Sandven, S. (2016) · The Cryosphere · doi:10.5194/tc-10-913-2016 · Cited by 69
Two-Stream Dictionary Learning Architecture for Action Recognition
Xu, K., Jiang, X., & Sun, T. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2665359 · Cited by 55
“[2] proposed SURF detector and descriptor which perform well while being calculated in a relatively efficient way.”
BackgroundMethodComplex Document Classification and Localization Application on Identity Document Images
Awal, A. M., Ghanmi, N., Sicre, R., & Furon, T. (2017) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2017.77 · Cited by 65
Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences
Fathy, M. E., Tran, Q.-H., Zia, M. Z., Vernaza, P., & Chandraker, M. K. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01267-0_49 · Cited by 54
Cao, G., Ruan, S., Peng, Y., Huang, S., & Kwok, N. M. (2018) · IEEE Access · doi:10.1109/access.2018.2842028 · Cited by 62
“Traditional feature-based image registration algorithms mainly integrate the speed-up robust features (SURF) algorithm and the scale-invariant feature transform (SIFT) algorithm for rapid feature extraction [27], [28].”
Scalable Logo Recognition Using Proxies
Fehérvári, I., & Appalaraju, S. (2019) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2019.00081 · Cited by 62
Ros‐NET: A deep convolutional neural network for automatic identification of rosacea lesions
Binol, H., Plotner, A., Sopkovich, J., Kaffenberger, B., Niazi, M. K. K., & Gurcan, M. N. (2020) · Skin Research and Technology · doi:10.1111/srt.12817 · Cited by 56
Dense Segmentation-Aware Descriptors
Trulls, E., Kokkinos, I., Sanfeliu, A., & Moreno-Noguer, F. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.372 · Cited by 53
Prior Guided Dropout for Robust Visual Localization in Dynamic Environments
Huang, Z., Xu, Y., Shi, J., Zhou, X., Bao, H., & Zhang, G. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00288 · Cited by 66
Wang, Y., Zhang, J., Cavichini, M., Bartsch, D., Freeman, W. R., Nguyen, T. Q., & An, C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3058570 · Cited by 60
“…feature detection and description meth-ods in computer vision can also be utilized in the retinal registration task, including Harris corner detection [18], histogram of oriented gradients (HOG) [19], scale invariant feature transformation (SIFT) [20], and speeded up robust features (SURF) [21].”
MethodDeep Homography for Efficient Stereo Image Compression
Deng, X., Yang, W., Yang, R., et al. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00154 · Cited by 55
“To calculate the homography matrix, the traditional methods firstly use feature matching algorithms such as SIFT [33] and SURF [6], to get feature points, and then use RANdom SAmple Consensus (RANSAC) algo-rithm [13] to calculate the transformation matrix.”
MethodChannel Split Convolutional Neural Network (ChaSNet) for Thermal Image Super-Resolution
Prajapati, K., Chudasama, V. M., Patel, H., Sarvaiya, A., Upla, K. P., Raja, K. B., Ramachandra, R., & Busch, C. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00493 · Cited by 76
“Hence, for Track-2, we perform image registration using SURF features [2] which results in semi-matched image pairs and later, those images are used for training the proposed methods.”
MethodSun, X., Guo, L., Zhang, W., et al. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3115637 · Cited by 55
“The registration between successive frames is built via SURF [46] feature point extraction and matching.”
MethodYang, X., Chen, D., Sun, Q., Wang, Y., Xia, Y., Yang, J., Lin, C., Dang, X., Cen, Z., Liang, D., et al. (2023) · Cell Discovery · doi:10.1038/s41421-023-00543-1 · Cited by 70
“Since SIFT, SURF, ORB feature descriptors could not distinguish the bright-fi eld images in the low-ef fi ciency and high-ef fi ciency groups at stage I (Supplementary Fig.”
MethodInfluentialAn Evaluation of Image Feature Detectors and Descriptors for Robot Navigation
Schmidt, A., Kraft, M., & Kasiński, A. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15907-7_31 · Cited by 54
Face recognition for newborns: A preliminary study
Bharadwaj, S., Bhatt, H. S., Singh, R., et al. (2010) · IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2010.5634500 · Cited by 55
An integrated technique for splicing and copy-move forgery image detection
Lin, S. D., & Wu, T. (2011) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2011.6100366 · Cited by 55
A survey on visual adult image recognition
Ries, C. X., & Lienhart, R. W. (2012) · Multimedia Tools and Applications · doi:10.1007/s11042-012-1132-y · Cited by 55
On the Accuracy, Efficiency, and Reusability of Automated Test Oracles for Android Devices
Lin, Y., Rojas, J. F., Chu, E. T.-H., et al. (2014) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2014.2331982 · Cited by 55
Duplication forgery detection using improved DAISY descriptor
Guo, J.-M., Liu, Y.-F., & Wu, Z.-J. (2012) · Expert Systems with Applications · doi:10.1016/j.eswa.2012.08.002 · Cited by 56
A smart atlas for endomicroscopy using automated video retrieval
André, B., Vercauteren, T. K., Buchner, A. M., Wallace, M. B., & Ayache, N. (2011) · Medical Image Analysis · doi:10.1016/j.media.2011.02.003 · Cited by 61
“In particular, the Speeded Up Robust Features (SURF) descriptor of Bay et al. (Bay et al., 2006) is more efficient than SIFT in terms of runtime, but was not considered in this study.”
MethodPassive copy-move forgery detection in videos
Pandey, R. C., Singh, S. K., & Shukla, K. K. (2014) · International Conference on Computer and Communication Technology · doi:10.1109/iccct.2014.7001509 · Cited by 61
Fast segmentation and adaptive SURF descriptor for iris recognition
Mehrotra, H., Sa, P. K., & Majhi, B. (2012) · Mathematical and Computer Modelling · doi:10.1016/j.mcm.2012.06.034 · Cited by 55
Evaluation of feature-based methods for automated network orientation
Apollonio, F. I., Ballabeni, A., Gaiani, M., & Remondino, F. (2014) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsarchives-xl-5-47-2014 · Cited by 66
Fast Almost-Gaussian Filtering
Kovesi, P. D. (2010) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2010.30 · Cited by 60
Spatiotemporal Localization and Categorization of Human Actions in Unsegmented Image Sequences
Oikonomopoulos, A., Patras, I., & Pantić, M. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2076821 · Cited by 55
Compact signatures for high-speed interest point description and matching
Calonder, M., Lepetit, V., Fua, P., Konolige, K., Bowman, J., & Mihelich, P. (2009) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2009.5459272 · Cited by 61
Ye, M., Giannarou, S., Meining, A. G., & Yang, G. (2015) · Medical Image Analysis · doi:10.1016/j.media.2015.10.003 · Cited by 70
Binary Coherent Edge Descriptors
Zitnick, C. L. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15552-9_13 · Cited by 56
UAV-based 3D modelling of disaster scenes for Urban Search and Rescue
Verykokou, S., Doulamis, A. D., Athanasiou, G., et al. (2016) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist.2016.7738206 · Cited by 55
A Superpixel-Based Variational Model for Image Colorization
Fang, F., Wang, T., Zeng, T., & Zhang, G. (2019) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2019.2908363 · Cited by 57
“Compared with the extended SURF [29] descriptor used in [11], DAISY descriptor can be calculated much faster, yet has similar properties such as rotation, illumination and scale invariant.”
MethodMoitra, D., & Mandal, R. K. (2019) · Health Information Science and Systems · doi:10.1007/s13755-019-0077-1 · Cited by 67
“The Maximally stable extremal regions (MSER) [36] was used to detect blob features and then the speeded up robust features (SURF) [37] was used to extract the scale independent features suitable for classification.”
MethodShin, J., Chang, Y. K., Heung, B., Nguyen-Quang, T., Price, G. W., & Al-Mallahi, A. A. (2020) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2020.03.016 · Cited by 62
Automated classification of diabetic retinopathy through reliable feature selection
Gayathri, S. G., Gopi, V. P., & Palanisamy, P. (2020) · Physical and Engineering Sciences in Medicine · doi:10.1007/s13246-020-00890-3 · Cited by 60
Video diver: generic video indexing with diverse features
Wang, D., Liu, X., Luo, L., Li, J., & Zhang, B. (2007) · Multimedia Information Retrieval · doi:10.1145/1290082.1290094 · Cited by 54
Mobile visual search on printed documents using text and low bit-rate features
Tsai, S. S., Chen, H., Chen, D. M., Schroth, G., Grzeszczuk, R., & Girod, B. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6116198 · Cited by 55
Incorporating prior knowledge in medical image segmentation: a survey
Nosrati, M. S., & Hamarneh, G. (2016) · arXiv · doi:10.48550/arxiv.1607.01092 · Cited by 55
“Other features such as frequency, bag of visual words, gradient location and orientation histogram (GLOH) (Mikolajczyk and Schmid, 2005), DAISY (Tola et al., 2008), GIST (spatial envelop) (Oliva and Torralba, 2001), local binary pttern (LBP) (Heikkil¨a et al., 2009), SURF (Bay et al., 2006), histogram of oriented grad…”
BackgroundRise of the Indoor Crowd: Reconstruction of Building Interior View via Mobile Crowdsourcing
Chen, S., Li, M., Ren, K., Fu, X., & Qiao, C. (2015) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/2809695.2809702 · Cited by 60
Performance evaluation of feature detection and matching in stereo visual odometry
Jiang, Y., Yun-xi, X., & Liu, Y. (2013) · Neurocomputing · doi:10.1016/j.neucom.2012.06.055 · Cited by 52
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.