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 6,001–6,100 of 14,752
Exploiting Monge structures in optimum subwindow search
An, S., Peursum, P., Liu, W., et al. (2010) · 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.2010.5540119 · Cited by 8
People and clothes recognition based on topic model
Sakurai, R., Lee, J., & Kawagoe, K. (2011) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2011.6147618 · Cited by 8
Ha, J.-W., Kim, B.-H., Lee, B., et al. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15246-7_10 · Cited by 8
Hochdorfer, S., Lutz, M., & Schlegel, C. (2009) · IEEE International Conference on Technologies for Practical Robot Applications · doi:10.1109/tepra.2009.5339626 · Cited by 8
Learning multiple codebooks for low bit rate mobile visual search
Lin, J., Duan, L., Chen, J., et al. (2012) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2012.6288038 · Cited by 8
“SIFT [2], SURF [3], PCA-SIFT [4]), recent works put more emphasis on the compactness of descriptors.”
MethodSimeone, L., & Iaconesi, S. (2011) · IEEE International Conference on Advanced Learning Technologies (ICALT) · doi:10.1109/icalt.2011.43 · Cited by 10
Automated highlight generation from cricket broadcasts using ORB
Ringis, D. J., & Pooransingh, A. (2015) · IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM) · doi:10.1109/pacrim.2015.7334809 · Cited by 8
“In terms of computation time, [21] was able to compare to SIFT and SURF methods to the ORB on the same dataset.”
BackgroundInfluentialA new sparse representation-based object segmentation framework
Yao, J., Yu, H., & Hu, R. (2015) · The Visual Computer · doi:10.1007/s00371-015-1171-2 · Cited by 8
ActiveAd: A novel framework of linking ad videos to online products
Wang, J., Xu, M. G., Lu, H., et al. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.12.038 · Cited by 8
“A 4 4 region is used to extract 64 d SURF features for 100 selected key points.”
BackgroundRobotic bodily aware interaction within human environments
Jerbić, B., Stipanĉić, T., & Tomašić, T. (2015) · SAI Intelligent Systems Conference · doi:10.1109/intellisys.2015.7361160 · Cited by 8
Survey of Feature Points Detection and Matching using SURF, SIFT and PCA-SIFT
Shah, U., Mistry, D., & Patel, Y. (2014) · Journal of Emerging Technologies and Innovative Research · Cited by 8
Fast image search with deep convolutional neural networks and efficient hashing codes
Li, J., & Li, J. (2015) · International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) · doi:10.1109/fskd.2015.7382128 · Cited by 8
“Although several manual features have been proposed to represent the images [19, 2, 22], performance of these visual descriptors is still not very good before the recent breakthrough in deep learning.”
BackgroundSpatio-temporal SURF for Human Action Recognition
Megrhi, S., Mseddi, W. S., & Beghdadi, A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-319-03731-8_47 · Cited by 8
Accelerating the construction of BRIEF descriptors using an FPGA-based architecture
de Lima, R., Martínez-Carranza, J., Morales-Reyes, A., et al. (2015) · International Conference on ReConFigurable Computing and FPGAs (ReConFig) · doi:10.1109/reconfig.2015.7393285 · Cited by 8
“Alternatives to SIFT have been proposed such as SURF (Speeded Up Robust Features) [2] and HOG (Histogram of Oriented Gradients) [22], among others, aiming at reducing processing time, whilst maintaining similar discrimination capabilities.”
MethodBag-of-Visual Words Codebook Development for the Semantic Content Based Annotation of Images
Olaode, A. A., Naghdy, G. A., & Todd, C. (2015) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis.2015.64 · Cited by 8
“Robust Features (SURF) [33] gives Emax of 2884.”
BackgroundInfluentialIMAGE-BASED LOCALIZATION FOR INDOOR ENVIRONMENT USING MOBILE PHONE
Huang, Y., Wang, H., Zhan, K., et al. (2015) · 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-4-w5-211-2015 · Cited by 8
“This contribution has been peer-reviewed. doi:10.5194/isprsarchives-XL-4-W5-211-2015 213 SIFT and SURF we deployed is based on OpenCV [13], while ASIFT is provide by the author1.”
MethodInfluentialHuman Collaborative Localization and Mapping in Indoor Environments with Non-Continuous Stereo
Guerra, E., Munguía, R., Bolea, Y., & Grau, A. (2016) · Sensors · doi:10.3390/s16030275 · Cited by 8
Improved 3D sparse maps for high-performance SFM with low-cost omnidirectional robots
Cavestany, P., Rodríguez, A. L., Barberá, H. M., et al. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351744 · Cited by 8
P-SURF: A Robust Local Image Descriptor
Liu, C., Yang, J., & Huang, H. (2011) · Journal of information science and engineering · doi:10.6688/jise.2011.27.6.13 · Cited by 8
Performance Analysis of Multimedia Retrieval Workloads Running on Multicores
Lu, Y., Wang, X., Zhang, W., et al. (2016) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2016.2533606 · Cited by 8
Holistic Privacy Impact Assessment Framework for Video Privacy Filtering Technologies
Badii, A., Al-Obaidi, A. A., Einig, M., & Ducournau, A. (2013) · Signal & Image Processing An International Journal · doi:10.5121/sipij.2013.4602 · Cited by 12
Masataka, S., & Hashimoto, M. (2013) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.133.1010 · Cited by 8
Side-scan sonar image registration based on modified phase correlation for AUV navigation
Song, Y., He, B., Zhang, L., & Yan, T. (2016) · OCEANS 2016 - Shanghai · doi:10.1109/oceansap.2016.7485521 · Cited by 9
“Feature-based registration methods (SIFT [21], SURF [22], Harris Comer Detector [23] and etc.) have difficulties in matching sonar images when there are few keypoints or the percentage of inliers are less than 8%.”
MethodLearning-based quality assessment of retargeted stereoscopic images
Liu, Y., Sun, L., & Yang, S. (2016) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2016.7552873 · Cited by 8
Mixed prototyping environment with different video tracking techniques
Bruno, F., Angilica, A., Cosco, F., et al. (2011) · Lirias · Cited by 8
Chermak, L., & Aouf, N. (2012) · IEEE International Conference on Cybernetic Intelligent Systems (CIS) · doi:10.1109/cis.2013.6782161 · Cited by 9
An object tracking in particle filtering and data association framework, using SIFT features
Souded, M., Giulieri, L., & Brémond, F. (2011) · International Conference on Imaging for Crime Detection and Prevention (ICDP) · doi:10.1049/ic.2011.0104 · Cited by 8
Performance Assessment of Feature Detector-Descriptor Combination
Madbouly, A. M. M., & Mostafa, M.-S. M. (2015) · Cited by 8
Automatic camera self-calibration for immersive navigation of free viewpoint sports video
Yao, Q., Sankoh, H., Nonaka, K., et al. (2016) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2016.7813399 · Cited by 8
Building semantic maps for blind people to navigate at home
Liu, Q., Li, R., Hu, H., & Gu, D. (2016) · Computer Science and Electronic Engineering Conference · doi:10.1109/ceec.2016.7835881 · Cited by 9
“In our system, we adopt SURF (Speeded up Robust Features) [18] for both mapping and object recognition.”
MethodMultiple lab ware manipulation in life science laboratories using mobile robots
Ali, M. M., Liu, H., Stoll, N., et al. (2016) · International Conference on Mechatronics - Mechatronika · Cited by 8
Tree-based indexing for real-time ConvNet landmark-based visual place recognition
Hou, Y., Zhang, H., & Zhou, S. (2017) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881416686951 · Cited by 8
Combining SURF descriptor and complex networks for face recognition
Piotto, J. G. D. S., & Lopes, F. M. (2016) · International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) · doi:10.1109/cisp-bmei.2016.7852721 · Cited by 8
“Moreover, the method adopt the picture integral convolution technique, which makes the whole process less computationally expensive [4].”
BackgroundMethodVideo stabilization for an aerial surveillance system using sift and surf
Kaur, J., & Bathla, A. K. (2016) · International Conference on Next Generation Computing Technologies · doi:10.1109/ngct.2016.7877509 · Cited by 8
A fully pipelined and parallel hardware architecture for real-time BRISK salient point extraction
Azimi, E., Behrad, A., Ghaznavi‐Ghoushchi, M. B., et al. (2017) · Journal of Real-Time Image Processing · doi:10.1007/s11554-017-0693-4 · Cited by 8
A web service-based approach for developing self-adaptive systems
Kafaf, D. A., & Kim, D. (2017) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2017.06.030 · Cited by 8
VISION-BASED VERIFICATION OF AUTHENTIC JAKIM HALAL LOGO
Razali, S. M., Isa, N. F., Htike, Z. Z., et al. (2015) · Cited by 8
Repeating average filter for noisy texture classification
Shakoor, M. H., & Tajeripour, F. (2017) · Scientia Iranica · doi:10.24200/sci.2017.4124 · Cited by 8
Effect of Spatial Filtering on Object Detection with the SURF Algorithm
Tomaszewski, M., Osuchowski, J., & Debita, Ł. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-75025-5_12 · Cited by 8
Unsupervised Change Detection of Remote Sensing Images Based on SURF and SVM
Wu, L., Liu, B., & Zhao, B. (2017) · doi:10.1109/ciis.2017.39 · Cited by 8
“SURF is a local descriptor extraction method having valuable properties such as invariance to illumination and viewpoint [13].”
MethodGuidi, G., Malik, U. S., Frischer, B., et al. (2017) · doi:10.1109/vsmm.2017.8346268 · Cited by 8
“In the last 20 years, the developments in digital photography and the introduction of robust algorithms for the automatization of feature extraction from images [5]–[8] have led to a whole new role of image-based 3D imaging in several areas, including cultural heritage documentation [9].”
BackgroundMeasurement-Based Evaluation of Data-Parallelism for OpenCV Feature-Detection Algorithms
Danielsson, J., Jägemar, M., Behnam, M., et al. (2018) · IEEE Annual Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac.2018.00105 · Cited by 8
“The knowledge of how feature detection algorithms such as FAST, HARRIS or SURF affect the shared resources is an important part when incorporating them into a multicore system, since it can give an indication on how well the algorithm scales with parallelism opportunities offered by multi-cores.”
MethodInfluentialCopy-Move Forgery Localization Using Convolutional Neural Networks and CFA Features
Liu, L., Zhao, Y., Ni, R., & Tian, Q. (2018) · International Journal of Digital Crime and Forensics · doi:10.4018/ijdcf.2018100110 · Cited by 11
Depth compression via planar segmentation
Kumar, S. H., & Ramakrishnan, K. R. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6327-4 · Cited by 8
“SURF feature-point detection and matching algorithm [2] is used to find point-correspondences between frames I k and I k+1.”
MethodLocally Low-Rank Regularized Video Stabilization With Motion Diversity Constraints
Wu, H., Xiao, L., Lian, Z., & Shim, H. J. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2875671 · Cited by 9
Fuzzy theoretic model based analysis of image features
Kumar, M., Chatterjee, S., Zhang, W., et al. (2018) · Information Sciences · doi:10.1016/j.ins.2018.12.024 · Cited by 8
Landmark Recognition: From Small-Scale to Large-Scale Retrieval
Magliani, F., Fontanini, T., & Prati, A. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-03000-1_10 · Cited by 8
Object Detection by Point Feature Matching using Matlab
Bulbul, M. F., Badsha, F., & Islam, M. R. (2018) · Advances In Image and Video Processing · doi:10.14738/aivp.66.5619 · Cited by 8
Tian, X., Li, H., & Deng, H. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-018-7025-y · Cited by 8
Bibars, A., & Mahroos, M. (2019) · IET Computer Vision · doi:10.1049/iet-cvi.2018.5203 · Cited by 8
“Scale-invariant feature transform (SIFT) [15] and Speeded Up Robust Features (SURF) [16] are the most used descriptors due to their invariance to image scale and rotation changes.”
MethodResultInfluentialAutomatic data labeling by neural networks for the counting of objects in videos
Namatēvs, I., Sudars, K., & Poļaka, I. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.01.118 · Cited by 12
Kinect Sensor based Object Feature Estimation in Depth Images
Sharma, K. (2015) · International Journal of Signal Processing Image Processing and Pattern Recognition · doi:10.14257/ijsip.2015.8.12.23 · Cited by 8
Yang, Y.-S., & Yeh, S. (2019) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-019-00997-0 · Cited by 8
“This study uses SURF [15, 16] to define the target feature point of the target object, and uses RANSAC [17] to estimate homography matrix [18, 19] to obtain the center position of the target feature, and executes ILC calculation based on this center position.”
MethodPerformance analysis of single-query 6-DoF camera pose estimation in self-driving setups
Fu, J., Pertuz, S. D., Matas, J., & Kämäräinen, J. (2019) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2019.04.009 · Cited by 9
Lim, G. H., Lau, N., Pedrosa, E., Amaral, F., Pereira, A., Azevedo, J. L., & Cunha, B. (2019) · Advanced Robotics · doi:10.1080/01691864.2019.1617780 · Cited by 8
“Therefore, pose estimation cannot rely on approaches such as color segmentation or local feature matching such as SIFT [14], SURF [15] and feature learning [16].”
MethodYang, T., Ma, J., Miao, Y., Liu, X., Wang, X., & Meng, Q. (2019) · Information Sciences · doi:10.1016/j.ins.2019.07.078 · Cited by 9
Liu, W., Wang, C., Bian, X., Chen, S., Li, W., Lin, X., Li, Y., Weng, D., Lai, S., & Li, J. (2019) · Remote Sensing · doi:10.3390/rs11192243 · Cited by 10
Relative Pose Estimation of Visual SLAM Based on Convolutional Neural Networks
Ruan, X., Wang, F., & Huang, J. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8870974 · Cited by 9
Vehicle Attribute Recognition Algorithm Based on Multi-task Learning
Sun, J., Jia, C., & Shi, Z. (2019) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot.2019.00029 · Cited by 9
“The traditional vehicle attribute recognition method mainly extracts manual image features (such as SURF[2], LBP, HOG[3], etc.), using texture, edge, contour and other features, through the classification algorithm (such as SVM, Adaboost, random forest, etc.) training model to achieve vehicle attribute recognition, Zh…”
MethodVirtual Reality and Convolutional Neural Networks for Railway Catenary Support Components Monitoring
Liu, W., Liu, Z., & Núñez, A. A. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917061 · Cited by 9
“In the literature, there are many excellent feature extraction algorithms [18-21].”
BackgroundUnsupervised Content-Based Image Retrieval Technique Using Global and Local Features
Sadique, M. F., Biswas, B. K., & Haque, S. (2019) · International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT) · doi:10.1109/icasert.2019.8934595 · Cited by 8
Li, J., Long, X., Hu, S., Hu, Y., Gu, Q., & Xu, D. (2019) · Journal of Real-Time Image Processing · doi:10.1007/s11554-019-00931-5 · Cited by 8
“Speeded Up Robust Features (SURF) [9] proposed by Bat et al.”
Ebadi, K., & Agha–mohammadi, A. (2020) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-33950-0_7 · Cited by 8
3D Documentation of Cultural Heritage
Agosto, E., Ardissone, P., Bornaz, L., et al. (2020) · Advances in religious and cultural studies (ARCS) book series · doi:10.4018/978-1-7998-2871-6.ch001 · Cited by 8
Transfer Learning from Synthetic Data in the Camera Pose Estimation Problem
Charco, J. L., Sappa, A. D., Vintimilla, B. X., et al. (2020) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0009167604980505 · Cited by 8
“Classical approaches estimate the extrinsic camera parameters from feature points (e.g., SIFT (Lowe, 1999), SURF (Bay et al., 2006), BRIEF (Calonder et al., 2012)), which are detected and described in the pair of images used to estimate the pose (relative translation and rotation) between the cameras.”
BackgroundHistogram-Based Descriptor Subset Selection for Visual Recognition of Industrial Parts
Merino, I., Azpiazu, J., Remazeilles, A., & Sierra, B. (2020) · Applied Sciences · doi:10.3390/app10113701 · Cited by 8
Monocular Visual Odometry with Unmanned Underwater Vehicle Using Low Cost Sensors
Dabove, P., Pietra, V. D., & Piras, M. (2020) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans46316.2020.9109841 · Cited by 11
Feature Point Registration Model of Farmland Surface and Its Application Based on a Monocular Camera
Li, Y., Huang, D., Qi, J., Chen, S., Sun, H., Liu, H., & Jia, H. (2020) · Sensors · doi:10.3390/s20133799 · Cited by 9
Word-Spotting approach using transfer deep learning of a CNN network
Benabdelaziz, R., Gaceb, D., & Haddad, M. (2020) · International Conference on Communications, Control Systems and Signal Processing (CCSSP) · doi:10.1109/ccssp49278.2020.9151583 · Cited by 10
Gathering Effective Information for Real-Time Material Recognition
Zhang, H., Jiang, Z., Xiong, Q., Wu, J., Yuan, T., Li, G., Huang, Y., & Ji, D. (2020) · IEEE Access · doi:10.1109/access.2020.3020382 · Cited by 6
Online calibration of exterior orientations of a vehicle-mounted surround-view camera system
Ouyang, Z., Hu, L., Lu, Y., Wang, Z., Peng, X., & Kneip, L. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197127 · Cited by 11
“On real images, we extract SURF features [27] to obtain and match point correspondences, and we use the LSD detector [28] and the method presented in [29] to detect and classify vertical lines.”
MethodDeep Relationship Analysis in Video with Multimodal Feature Fusion
Yu, F., Wang, D., Zhang, B., & Ren, T. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3416303 · Cited by 11
“Feature matching methods use scale invariant features like speed up robust features (SURF) [1] to detect local feature of an image.”
MethodLatent Space Metric Learning For Sidescan Sonar Place Recognition
Larsson, M., Bore, N., & Folkesson, J. (2020) · IEEE/OES Autonomous Underwater Vehicles Symposium (AUV) · doi:10.1109/auv50043.2020.9267885 · Cited by 8
Stable image matching for 3D reconstruction in outdoor
Cao, M., Gao, H., & Jia, W. (2021) · International Journal of Circuit Theory and Applications · doi:10.1002/cta.2997 · Cited by 10
Multiple Copy-Move Forgery Detection Based on Density Clustering
Zhou, X. H., & Shi, Q. J. (2021) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661821010181 · Cited by 8
AirCode: A Robust Object Encoding Method
Xu, K., Wang, C., Chen, C., Wu, W., & Scherer, S. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3141221 · Cited by 9
Xie, Y., Liu, M., Zhou, S., & Wang, Y. (2021) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2021.3113129 · Cited by 8
Which Parts Determine the Impression of the Font?
Ueda, M., Kimura, A., & Uchida, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86334-0_47 · Cited by 8
“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.”
MethodInfluentialImage Ranking via Attribute Boosted Hypergraph
Zhou, Y., Tang, S., Zhang⋆, Y., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34778-8_73 · Cited by 8
“For each images, 6 kinds of visual features are extracted: 2,688-D Color Histogram, 252-D HOG [4], 2,000-D LSS [18], 2,000-D SIFT [16], 2,000-D RGSIFT [19], 2000-D SURF [3] descriptors.”
MethodZhang, L., Xie, B., Li, W., Zhou, G., & Zhao, X. (2022) · Optics & Laser Technology · doi:10.1016/j.optlastec.2022.107858 · Cited by 9
Search Space Reduction in Biometric Databases
Kavati, I., Prasad, M. V. N. K., & Bhagvati, C. (2018) · IGI Global eBooks · doi:10.4018/978-1-5225-5204-8.ch066 · Cited by 8
Smart Voting System through Facial Recognition
Choudhary, N., Agarwal, S., & Lavania, G. (2019) · International Journal of Scientific Research in Computer Sciences and Engineering · doi:10.26438/ijsrcse/v7i2.710 · Cited by 8
“The amount of distortion and attenuation plays a big role in generating a clear and transparent image in a localized area of the image frequency as it would be important aspect while capturing the image and processing of it to accurately match it with one that is present in the database [3].”
BackgroundAdvanced Map Matching Technologies and Techniques for Pedestrian/Wheelchair Navigation
Ren, M. (2012) · D-Scholarship@Pitt (University of Pittsburgh) · Cited by 15
Speeded-Up Robust Features Based Moving Object Detection on Shaky Video
Zhou, M., & Asari, V. K. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-22786-8_86 · Cited by 8
3D map reconstruction with sensor kinect: Searching for solution applicable to small mobile robots
Beňo, P., Duchoň, F., Tölgyessy, M., et al. (2014) · doi:10.1109/raad.2014.7002252 · Cited by 8
Image Classification Using PSO‐SVM and an RGB‐D Sensor
López-Franco, C., Villavicencio, L., Arana‐Daniel, N., & Alanís, A. Y. (2014) · Mathematical Problems in Engineering · doi:10.1155/2014/695910 · Cited by 9
Li, Y., & Davis, C. H. (2008) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2008.4779174 · Cited by 8
The eye says it all: Periocular region methodologies
Ambika, D. R., Radhika, K. R., & Seshachalam, D. (2012) · doi:10.1109/icmcs.2012.6320240 · Cited by 8
Intra-operative adjustment of standard planes in C-arm CT image data
Brehler, M., Görres, J., Franke, J., et al. (2015) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-015-1281-3 · Cited by 8
Introducing locally affine-invariance constraints into lunar surface image correspondence
Zhang, Y.-R., Yang, X., Qiao, H., Liu, Z., & Liu, C. (2016) · Neurocomputing · doi:10.1016/j.neucom.2015.12.082 · Cited by 8
A New Shape Feature for Vehicle Classification in Thermal Video Sequences
Yang, D., & Park, H. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2452780 · Cited by 8
“The first category is a local feature extraction method that includes a scale-invariant feature transform [1], speeded up robust features [2], histograms of oriented gradients (HOG) [3], and a pyramid HOG (PHOG) [4].”
MethodCedillo-Hernández, M., Garcia-Ugalde, F. J., Cedillo-Hernández, A., et al. (2014) · International Conference on Mechatronics, Electronics and Automotive Engineering (ICMEAE) · doi:10.1109/icmeae.2014.16 · Cited by 8
“In this paper we propose a fast CBVR technique which involves the combination of a local descriptor obtained from Speeded Up Robust Feature (SURF) algorithm [9] together with an effective and fast object matching operation.”
BackgroundMethodInfluentialA multi-camera system for damage and tampering detection in a postal security framework
Noceti, N., Zini, L., & Odone, F. (2018) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-017-0242-x · Cited by 8
Tangent-V: Math Formula Image Search Using Line-of-Sight Graphs
Davila, K., Joshi, R., Setlur, S., Govindaraju, V., & Zanibbi, R. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-15712-8_44 · Cited by 13
Unsupervised Domain Adaptation using Graph Transduction Games
Vascon, S., Aslan, S., Torcinovich, A., et al. (2019) · doi:10.1109/ijcnn.2019.8852075 · Cited by 8
Enhancement of RGB-D Image Alignment Using Fiducial Markers
Madeira, T., de Oliveira, M. A. R., & Dias, P. (2020) · Sensors · doi:10.3390/s20051497 · Cited by 13
Dual Embedding Expansion for Vehicle Re-identification
Sebastian, C., Imbriaco, R., Bondarev, E., & de With, P. H. N. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00298 · Cited by 11
“SIFT [25], SURF [3] or HoG [6].”
A single-camera feature-based vision system for helicopter autonomous landing
Cesetti, A., Frontoni, E., Mancini, A., Zingaretti, P., & Longhi, S. (2009) · Università Politecnica delle Marche (Università Politecnica delle Marche) · Cited by 9
Spatial Statistics of Visual Keypoints for Texture Recognition
Nguyen, H.-G., Fablet, R., & Boucher, J. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15561-1_55 · Cited by 12
Probabilistic Vehicular Trace Reconstruction Based on RF-Visual Data Fusion
Al-Kuwari, S. M., & Wolthusen, S. D. B. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-13241-4_3 · Cited by 8
“Methods like SURF [6], perform such image-based detection by identifying interest points in the images.”
Method
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.