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 5,801–5,900 of 14,752
Local Histogram Based Descriptor for Tracking in Wide Area Imagery
Mathew, A., & Asari, V. K. (2012) · Communications in computer and information science · doi:10.1007/978-3-642-31686-9_14 · Cited by 8
Online unsupervised cumulative learning for life-long robot operation
Gatsoulis, Y., Burbridge, C., & McGinnity, T. M. (2011) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2011.6181678 · Cited by 7
“The sum of the ownership vectors of the best matching nodes of the network produces a histogram of votes, an example is shown in Figure 2, which together with the number of unknowns features determines the classification of the perception.”
BackgroundVision-based mobile robot localization and mapping using the PLOT features
Lin, R., Wang, Z., Sun, R., & Sun, L. (2012) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2012.6285115 · Cited by 9
Visual tracking using compensated motion model for mobile cameras
Lu, J.-Y., Wei, Y.-C., & Tang, A. C.-W. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6116558 · Cited by 8
A system for supporting paper-based augmented reality
Ryu, H., & Park, H. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2439-7 · Cited by 8
A unified visual graph-based approach to navigation for wheeled mobile robots
Hartmann, J., Klüssendorff, J. H., & Maehle, E. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696610 · Cited by 8
A bio-inspired kinematic controller for obstacle avoidance during reaching tasks with real robots
Srinivasa, N., Bhattacharyya, R., Sundareswara, R., Lee, C., & Grossberg, S. (2012) · Neural Networks · doi:10.1016/j.neunet.2012.07.010 · Cited by 9
Indoor localization and mapping using camera and inertial measurement unit (IMU)
Mostofi, N., Elhabiby, M., & El‐Sheimy, N. (2014) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans.2014.6851507 · Cited by 12
Enhancement of Underwater Videomosaics for Post-processing
Rzhanov, Y., & Gu, F. (2007) · doi:10.1109/oceans.2007.4449276 · Cited by 8
Towards Better Land Cover Classification Using Geo-tagged Photographs
Oba, H., Hirota, M., Chbeir, R., et al. (2014) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2014.78 · Cited by 8
“It includes the following steps (1) extracting Speeded Up Robust Features (SURF) [19] from each photograph, (2) applying k-means clustering to all image features extracted from each photograph, and using k centroids of clustering result as visual words, (3) constructing a histogram using visual words as histogram bins…”
MethodAn image-based indoor positioning for digital museum applications
Kawaji, H., Hatada, K., Yamasaki, T., et al. (2010) · International Conference on Virtual Systems and Multimedia (VSMM) · doi:10.1109/vsmm.2010.5665958 · Cited by 8
A multi-sensor-based mobile robot localization framework
Duan, P., Tian, G., & Wu, H. (2014) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2014.7090403 · Cited by 8
User assisted stereo image segmentation
Tasli, H. E., & Alatan, A. A. (2012) · 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video · doi:10.1109/3dtv.2012.6365447 · Cited by 8
“It is observed that the popular methods such as SIFT [14] or SURF [15] rely on costly descriptors for detection and matching.”
MethodPart-based methods for handwritten digit recognition
Wang, S., Uchida, S., Liwicki, M., & Feng, Y. (2013) · Frontiers of Computer Science · doi:10.1007/s11704-013-2297-x · Cited by 8
Integrated vision-based system for efficient, semi-automated control of a robotic manipulator
Jiang, H., Wachs, J. P., & Duerstock, B. S. (2014) · International Journal of Intelligent Computing and Cybernetics · doi:10.1108/ijicc-09-2013-0042 · Cited by 9
“A Speeded Up Robust Features (SURF) algorithm was employed to recognize these daily living test objects (Bay et al., 2006).”
MethodFinding and reusing learning materials with multimedia similarity search and social networks
Little, S., Ferguson, R., & Rüger, S. (2012) · Technology Pedagogy and Education · doi:10.1080/1475939x.2012.698378 · Cited by 10
Improving Semantic Search in Digital Libraries Using Multimedia Analysis
Kollia, I., Kalantidis, Y., Rapantzikos, K., et al. (2012) · Journal of Multimedia · doi:10.4304/jmm.7.2.193-204 · Cited by 8
Parsimonious loop-closure detection based on global image-descriptors of panoramic images
Gerstmayr-Hillen, L., Schluter, O., Krzykawski, M., et al. (2011) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2011.6088548 · Cited by 8
Spatio-temporal Good Features to Track
Feichtenhofer, C., & Pinz, A. J. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.40 · Cited by 8
Analysis of Local Features for Handwritten Character Recognition
Uchida, S., & Liwicki, M. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.479 · Cited by 8
Imura, J., Kasada, K., Narumi, T., et al. (2014) · ITE Transactions on Media Technology and Applications · doi:10.3169/mta.2.225 · Cited by 8
Multi-feature hierarchical topic models for human behavior recognition
Li, H., Zhang, F., & Zhang, S. (2014) · Science China Information Sciences · doi:10.1007/s11432-013-4794-9 · Cited by 8
A mediator-based approach for integrating heterogeneous multimedia sources
Beneventano, D., Gennaro, C., Bergamaschi, S., et al. (2011) · Multimedia Tools and Applications · doi:10.1007/s11042-011-0904-0 · Cited by 8
A Unified Geolocation Framework for Web Videos
Song, Y., Zhang, Y., Cao, J., et al. (2014) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2533989 · Cited by 8
Evaluation of thermal imaging for people detection in outdoor scenarios
Königs, A., & Schulz, D. (2012) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr.2012.6523883 · Cited by 8
Object Recognition: Performance evaluation using SIFT and SURF
Rani, R., Grewal, S. K., & Panwar, K. (2013) · International Journal of Computer Applications · doi:10.5120/13094-0375 · Cited by 8
“SURF [15] is also popularly known as approximate SIFT.”
MethodRotation invariant feature lines transform for image matching
Ye, Z., & Qu, H. (2014) · Journal of Electronic Imaging · doi:10.1117/1.jei.23.5.053002 · Cited by 8
Tracking Color marker using projective transformation for augmented reality application
Belghit, H., Zenati-Henda, N., Bellabi, A., et al. (2012) · doi:10.1109/icmcs.2012.6320245 · Cited by 8
An adaptive uniform distribution surf for image stitching
Wang, Z.-L., Yan, F.-H., & Zheng, Y. (2013) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2013.6745290 · Cited by 8
Automatic License Plate Recognition System using SURF Features and RBF Neural Network
Chaturvedi, A., & Sethi, N. (2013) · International Journal of Computer Applications · doi:10.5120/12243-8524 · Cited by 9
A Primer on Autonomous Aerial Vehicle Design
Coppejans, H., & Myburgh, H. C. (2015) · Sensors · doi:10.3390/s151229785 · Cited by 9
The Impact of the Image Feature Detector and Descriptor Choice on Visual SLAM Accuracy
Schmidt, A., & Kraft, M. (2014) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-10662-5_25 · Cited by 8
A novel local derivative quantized binary pattern for object recognition
Shang, J., Chen, C., Pei, X., Hu, L., Tang, H. Q., & Sarem, M. (2015) · The Visual Computer · doi:10.1007/s00371-015-1179-7 · Cited by 8
“[2] introduced the speeded up robust feature (SURF) and performed nearly the same effect with three to sevenfold speed-ups.”
MethodHeinrich, S., Folleher, P., Springstübe, P., et al. (2013) · Advances in intelligent systems and computing · doi:10.1007/978-3-642-37835-5_70 · Cited by 8
Do We Need Binary Features for 3D Reconstruction?
Fan, B., Kong, Q., Sui, W., et al. (2016) · IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.144 · Cited by 8
Rotation invariant similarity measure for non-local self-similarity based image denoising
Zuo, C., Jovanov, L., Luong, H. Q., et al. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351074 · Cited by 8
Secure Encrypted Image Search in Mobile Cloud Computing
Zou, Q., Wang, J., & Chen, X. (2015) · International Conference on Broadband and Wireless Computing, Communication and Applications (BWCCA) · doi:10.1109/bwcca.2015.41 · Cited by 7
SEIP: System for Efficient Image Processing on Distributed Platform
Liu, T., Liu, Y., Li, Q., Wang, X., Gao, F., Zhu, Y., & Qian, D. (2015) · Journal of Computer Science and Technology · doi:10.1007/s11390-015-1595-1 · Cited by 9
Sheta, B. I. (2012) · International Journal of Computer Science & Engineering Survey · doi:10.5121/ijcses.2012.3502 · Cited by 8
“Then, the SURF descriptor is extracted from a square region generated and aligned to the selected orientation [25].”
BackgroundMethodA Survey on Marker-less Augmented Reality
Kote, S., & Borkar, B. (2014) · International Journal of Engineering Trends and Technology · doi:10.14445/22315381/ijett-v10p328 · Cited by 8
Vision-Based Intraoperative Cone-Beam CT Stitching for Non-overlapping Volumes
Fuerst, B., Fotouhi, J., & Navab, N. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24553-9_48 · Cited by 8
Identifying a Joint in Medical Ultrasound Images Using Trained Classifiers
Wereszczyński, K., Segen, J., Kulbacki, M., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11331-9_75 · Cited by 8
“Multiple image feature descriptors and their mixtures are evaluated as the basis for the classifier’s feature vector, including SURF [1, 2], FAST [3], ORB [4], BRISK [5], FREAK [6], and three classification methods: Nearest neighbor classifier, Support Vector Machines or SVM [12], and Decision trees [13].”
MethodInfluentialComparative study of SURF and FREAK descriptor on Indian Rupee Currency notes
Mulmule-Shirkhedkar, D., & Dani, A. R. (2015) · doi:10.1109/infop.2015.7489488 · Cited by 8
An Improvement of Positional Accuracy for View-Based Navigation Using SURF
Hagiwara, Y., Imamura, H., Choi, Y., et al. (2010) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.130.1395 · Cited by 8
Face Classification by Local Texture Analisys through CBIR and SURF Points
Benavides, C., Villegas-Cortéz, J., Roman, G., et al. (2016) · IEEE Latin America Transactions · doi:10.1109/tla.2016.7530440 · Cited by 8
Object classification using a local texture descriptor and a support vector machine
Ferraz, C. T., & Gonzaga, A. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-4003-0 · Cited by 8
A wheel-based side-view car detection using snake algorithm
Vinoharan, V., Ramanan, A., & Kodituwakku, S. R. (2012) · IEEE International Conference on Information and Automation for Sustainability (ICIAfS) · doi:10.1109/iciafs.2012.6419902 · Cited by 8
Object tracking based on ORB and temporal-spacial constraint
Wu, S., Fan, Y., Zheng, S., et al. (2012) · IEEE International Conference on Advanced Computational Intelligence · doi:10.1109/icaci.2012.6463235 · Cited by 8
Map-Reduce based framework for instrument detection in large-scale surgical videos
Sunny, B. C., Ramesh, R., Varghese, A., et al. (2015) · doi:10.1109/iccc.2015.7432968 · Cited by 8
Robust scene matching method based on sparse representation and iterative correction
Yang, S., Xiao, B. J., Yan, L., et al. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.11.009 · Cited by 8
“Some feature detection and feature matching algorithms are proposed: point feature detection methods such as Harris operator [1], SURF operator [2], SUSAN operator [3]; Line feature detection methods such as: Canny operator [4], Ridgelet transformation [5]; Improved feature detection methods such as [6], [7]; Feature…”
MethodMinwalla, C., Tulpan, D., Belacel, N., et al. (2016) · Unmanned Systems · doi:10.1142/s2301385016500102 · Cited by 8
Tian, T., Zhang, Y., Dou, H., & Tong, H. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-4167-7 · Cited by 8
“These features are designed with robustness to rotation, scaling, occlusion, illumination changes and other advantages, and efforts on developing better local description methods have never been stopped during the past decade [3, 4, 19, 48].”
BackgroundMethodInterpretation-driven Visual Association.
Grace, K. S., Saunders, R., & Gero, J. S. (2011) · Cited by 8
An efficient similar image search framework for large-scale data on cloud
Nguyen, T. D. T., & Huh, E. (2017) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1145/3022227.3022291 · Cited by 8
“The main contributions of this research is summarized as following: • We employed a fast and robust image representation method, namely SURF (Speeded-Up Robust Features) [1] to extract image features and form it into list of descriptor vectors.”
BackgroundMethodInfluentialRobust online 3D reconstruction combining a depth sensor and sparse feature points
Bylow, E., Olsson, C., & Kahl, F. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7900211 · Cited by 8
Towards edge-caching for image recognition
Drolia, U., Guo, K., Tan, J., Gandhi, R., & Narasimhan, P. (2017) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2017.7917629 · Cited by 10
A stereo line matching technique for aerial images based on a pair-wise relation approach
Ok, A. Ö., Wegner, J. D., Heipke, C., Rottensteiner, F., Sörgel, U., & Toprak, V. (2010) · Institutional Repository of Leibniz Universität Hannover (Leibniz Universität Hannover) · doi:10.15488/848 · Cited by 9
An Automatic Robust Point Cloud Registration on Construction Sites
Kim, P., & Cho, Y. K. (2017) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784480823.049 · Cited by 8
Uncertainty Quantification of Lucas Kanade Feature Track and Application to Visual Odometry
Wong, X. I., & Majji, M. (2017) · IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.131 · Cited by 8
Optimized 3D mapping of a large area with structures using multiple multirotors
Darrah, M., Trujillo, M. M., Speransky, K., et al. (2017) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2017.7991414 · Cited by 8
“This group uses SIFT or SURF methods [19, 20] of feature extraction to identify significant features on the map.”
MethodMultiple RGB-D sensor-based 3-D reconstruction and localization of indoor environment for mini MAV
Li, Y., Wang, Y., & Wang, D. (2017) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2017.08.011 · Cited by 9
Time series classification with feature covariance matrices
Ergezer, H., & Leblebicioğlu, K. (2017) · Knowledge and Information Systems · doi:10.1007/s10115-017-1098-1 · Cited by 13
Towards Edge-Aware Spatio-Temporal Filtering in Real-Time
Schaffner, M., Scheidegger, F., Cavigelli, L., Kaeslin, H., Benini, L., & Smolić, A. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2757259 · Cited by 10
“Well performing descriptors (binary and non-binary) such as BinBoost [39], SIFT [10], DAISY [15] or SURF [11] therefore employ Histograms of Oriented Gradients (HOG) [38] or variations thereof as basic building blocks.”
MethodOrdered minimum distance bag-of-words approach for aerial object identification
Unlu, E., Zenou, E., & Rivière, N. (2017) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2017.8078559 · Cited by 8
“SURF is known for its robustness counter illumination variations and rotational invariance [3].”
BackgroundExploiting textures for better action recognition in low-quality videos
Rahman, S., See, J., & Ho, C. C. (2017) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-017-0221-2 · Cited by 8
Local Region Expansion: a Method for Analyzing and Refining Image Matches
Farhan, E., Meir, E., & Hagege, R. R. (2017) · Image Processing On Line · doi:10.5201/ipol.2017.154 · Cited by 8
Light-weight visual place recognition using convolutional neural network for mobile robots
Park, C., Jang, J., Zhang, L., & Jung, J.-I. (2018) · International Conference on Consumer Electronics · doi:10.1109/icce.2018.8326274 · Cited by 8
“These methods are robust to both appearance and viewpoint change because they benefit by local descriptors such as Speed Up Robust Feature (SURF) and oriented FAST/rotated BRIEF (ORB) [9, 10].”
MethodKoh, V., Swamidoss, I. N., Aquino, M. C., et al. (2018) · Journal of Medical Systems · doi:10.1007/s10916-018-0960-3 · Cited by 8
HartSift: A High-Accuracy and Real-Time SIFT Based on GPU
Li, Z., Jia, H., & Zhang, Y. (2017) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads.2017.00029 · Cited by 8
Optimization of a HMM-Based Hand Gesture Recognition System Using a Hybrid Cuckoo Search Algorithm
Sagayam, K. M., Hemanth, D. J., Vasanth, X. A., et al. (2018) · Springer eBooks · doi:10.1007/978-3-319-77625-5_4 · Cited by 8
Image Complexity Guided Network Compression for Biomedical Image Segmentation
Mishra, S., Chen, D. Z., & Hu, X. S. (2021) · ACM Journal on Emerging Technologies in Computing Systems · doi:10.1145/3471190 · Cited by 11
A New Invariant to Illumination Feature Descriptor for Pattern Recognition
Diaz-Escobar, J., Kober, V. I., Карнаухов, В. Н., & Gonzalez-Fraga, J. A. (2018) · Journal of Communications Technology and Electronics · doi:10.1134/s1064226918120045 · Cited by 8
“The proposed descriptor construction algorithm (MHOG) was compared to the most known algorithms SIFT [21] and SURF [22].”
MethodHeterogeneous Implementation of a Novel Indirect Visual Odometry System
Lin, C.-H., Wang, W., Liu, S.-H., Hsu, C.-C. J., & Chien, C.-H. (2019) · IEEE Access · doi:10.1109/access.2019.2904142 · Cited by 7
Hou, R., Jeong, S., Law, K. H., et al. (2019) · Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems · doi:10.1117/12.2515617 · Cited by 8
Efficient Planar Surface-Based 3D Mapping Method for Mobile Robots Using Stereo Vision
Guo, B., Dai, H., Li, Z., et al. (2019) · IEEE Access · doi:10.1109/access.2019.2920511 · Cited by 8
A Sample-Free Bayesian-Like Model for Indoor Environment Recognition
Oyebode, K. O., Du, S., van Wyk, B. J., & Djouani, K. (2019) · IEEE Access · doi:10.1109/access.2019.2920686 · Cited by 7
Wan, X., Wang, C., & Li, S. (2019) · Sensors · doi:10.3390/s19143117 · Cited by 8
Hardware-Software Co-Design of an Image Feature Extraction and Matching Algorithm
Chien, C.-H., Chien, C., & Hsu, C.-C. J. (2019) · doi:10.1109/icoias.2019.00013 · Cited by 8
“To tackle such problem, several approaches such as Speed Up Robust Features (SURF) [2], Principal Components Analysis SIFT (PCA-SIFT) [3], and so on, are proposed.”
MethodLiu, T., Zhang, X., Li, Q., Fang, Z., & Tahir, N. (2019) · Remote Sensing · doi:10.3390/rs11161912 · Cited by 8
Fan, Z., Liu, Z., Qu, Z., et al. (2019) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2019.2936818 · Cited by 8
“Refined algorithms were proposed, such as principal component analysis (PCA)-SIFT [7] and SURF [8].”
BackgroundMethodEfficient Properties-Based Learning for Mismatch Removal
Li, Y., Huang, Q., Liu, Y., Huang, Y., & Sun, X. (2019) · IEEE Access · doi:10.1109/access.2019.2947178 · Cited by 8
“[11] E. Rublee, V. Rabaud, K. Konolige, and G. R. Bradski, ‘‘ORB: An efficient alternative to SIFT or SURF,’’ in Proc.”
MethodInfluentialCopy-Move Forgery Detection using SIFT and GLCM-based Texture Analysis
Chowdhury, M., Shah, H., Kotian, T., Subbalakshmi, N., & David, S. S. (2019) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2019.8929276 · Cited by 8
“In [11], the technique works based on the analysis of Delaunay triangles of local keypoints found using SIFT, SURF etc. Recently, Roy et al. [12] delved into the challenging but rarely attended problem of Similar but Genuine Objects (SGO) in Copy-Move Forgery Detection.”
MethodResearch on Image Registration Algorithm and Its Application in Photovoltaic Images
Zhao, E., Li, L., Song, M., et al. (2019) · IEEE Journal of Photovoltaics · doi:10.1109/jphotov.2019.2958149 · Cited by 8
Zhang, W., Yan, Z., Wang, Q., Wu, X., & Zuo, W. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.02.001 · Cited by 10
A Review of Hybrid Indoor Positioning Systems Employing WLAN Fingerprinting and Image Processing
Firdaus, F., Ahmad, N. A., & Sahibuddin, S. (2020) · International journal of electrical and computer engineering systems · doi:10.32985/ijeces.10.2.2 · Cited by 9
“Speeded Up Robust Features (SURF) is a new invariant interest point detector and descriptor that is scalable and rotatable [53].”
BackgroundMachine Learning Approach to Improve Flower Classification Using Multiple Feature Set
Kishotha, S., & Mayurathan, B. (2019) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciis47346.2019.9063349 · Cited by 8
“2) Speeded-Up robust features (SURF): SURF descriptor [14] is a scale and rotation-invariant descriptor.”
MethodSpatio-temporal deep learning methods for motion estimation using 4D OCT image data
Bengs, M., Gessert, N., Schlüter, M., et al. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02178-z · Cited by 8
“Also, Laves et al. used conventional features such as SIFT [18] and SURF [1] with 2D maximum intensity projects for motion estimation in the context of volume of interests stabilization with OCT [17].”
MethodMulti-UAV collaborative system with a feature fast matching algorithm
Wang, T., Zhang, Y., Liang, J., Chen, Y., & Wang, C.-L. (2020) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2000047 · Cited by 9
“The speeded up robust feature (SURF) algorithm (Bay et al., 2006) is an improvement on the SIFT algorithm.”
MethodGirth Measurement Based on Multi-View Stereo Images for Garment Design
Yang, L., Huang, Q., Song, X., Li, M., Hou, C., & Xiong, Z. (2020) · IEEE Access · doi:10.1109/access.2020.3021019 · Cited by 10
3D Object Localization Using 2D Estimates for Computer Vision Applications
Siddique, T. H. M., Rehman, Y., Rafiq, T., et al. (2021) · doi:10.1109/majicc53071.2021.9526270 · Cited by 8
MultiLevel Feature Pooling Network for Uncalibrated Stereo Rectification in Autonomous Vehicles
Nguyen, T. P., Tran, T. H.-P., & Jeon, J. W. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.3026307 · Cited by 8
Li, Y., Pei, W., & He, Z. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413870 · Cited by 8
“In particular, key-points are typically detected in two input images using a hand-crafted feature detector, such as SIFT [18], SURF [2], BRISK [15] or ORB [26].”
MethodLi, D., Miao, J., Shi, X., Tian, Y., Long, Q., Cai, T., Guo, P. Y., Yu, H., Yang, W., Yue, H., et al. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636248 · Cited by 7
Automated Object Detection for Visual Inspection of Nuclear Reactor Cores
Devereux, M., Murray, P., & West, G. M. (2021) · Nuclear Technology · doi:10.1080/00295450.2020.1863067 · Cited by 8
OnionNet: Single-View Depth Prediction and Camera Pose Estimation for Unlabeled Video
Gu, T., Wang, Z., Li, D., Yang, H., Du, W., & Zhou, Y. (2020) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2020.3042521 · Cited by 8
Automated Malaria Parasite Detection Using Artificial Neural Network
Özbılge, E., Güler, E., Güvenir, M., et al. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-64058-3_78 · Cited by 8
Dynamic tree branch tracking for aerial canopy sampling using stereo vision
Busch, C. A. M., Stol, K., & van der Mark, W. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106007 · Cited by 8
Ground Texture Based Localization: Do We Need to Detect Keypoints?
Schmid, J. F., Simon, S. F., & Mester, R. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340996 · Cited by 8
“Besides random and uniform keypoint sampling, we examine SIFT and SURF, as well as the three detectors, which we found to be the fastest [6] among the implemented methods in OpenCV 4.0 [17]: FAST, GFTT, and CenSurE.”
MethodInfluentialREBOR: A new sketch-based 3d object retrieval framework using retina inspired features
Shi, X., Chen, H., & Zhao, X. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10618-4 · Cited by 7
“SIFT [18] and SURF [9] are two of the most known methods which enable the detection of blobs while Leutenegger et al. proposed BRISK [23] to detect corners on multi-scale.”
BackgroundMethodInfluentialCounterfeit Detection and Avoidance with Physical Inspection
Asadizanjani, N., Rahman, M. T., & Tehranipoor, M. M. (2020) · Springer eBooks · doi:10.1007/978-3-030-62609-9_2 · Cited by 13
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.