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 12,401–12,500 of 14,752
Flexible Edge Arrangement Templates for Object Detection
Li, Y., Tsin, Y., Genç, Y., et al. (2008) · Proceedings · doi:10.1109/wacv.2008.4544002
Efficient Surf Tracking by Nearest Neighbor Classifier
Tong, M., & Chen, S. (2014) · Journal of Computers · doi:10.4304/jcp.9.10.2449-2454 · Cited by 2
“and in the original surf paper [11] the author claims 0.”
BackgroundMethodInteractive segmentation method on stereo images
Tasli, H. E., & Alatan, A. A. (2012) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2012.6204552
A Mechanism to Improve Stereo Vision Systems in Automated Heterogeneous Platoons
Alfraheed, M., Dröge, A., Klingender, M., et al. (2014) · Springer eBooks · doi:10.1007/978-3-319-08816-7_41
A low-power VGA full-frame feature extraction processor
Jeon, D., Kim, Y., Lee, I., et al. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6638152
“Authors in [3] propose an object recognition SoC (System on a Chip) based on the SIFT (Scale-Invariant Feature Transform) algorithm and UVAM (Unified Visual Attention Model), which selects attentive points from input video.”
ResultInfluentialParallelized 45 degrees rotated image integration
Schweitzer, M., Jaspers, H., Kubertschak, T., et al. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738167
Submap joining smoothing and mapping for camera-based indoor localization and mapping
Bjärkefur, J., Karlsson, A., Grönwall, C., et al. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.883945
Propagation for feature matching using triangular constraints
Shao, Q., Liu, S., & Chen, S. (2013) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2013.6739709
Stereo Image Matching Based on SURF Descriptor
Zeng, L., & Zhai, Y. (2015) · Advanced materials research · doi:10.4028/www.scientific.net/amr.1083.142
Virtual feature point extraction from polyhedral structure
Uenishi, K., & Iwakiri, M. (2013) · International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) · doi:10.1109/ispacs.2013.6704606
“In contrast, Bundler[2] is an estimation software without preprocessing, estimates correspondences by extracting keypoints as SIFT(Scale Invariant Feature Transform)[3] or SURF(Speed Up Robust Features)[4] with brute force feature point matching.”
MethodImproved View-Based Navigation for Obstacle Avoidance using Ego-Motion
Hagiwara, Y., Suzuki, A., Kim, Y. B., et al. (2013) · Journal of Power System Engineering · doi:10.9726/kspse.2013.17.5.112
Irregular Regions Automatic Matching Based on Cobweb Partition Strategy
Wang, Z., & Liu, H. (2010) · Chinese Conference on Pattern Recognition · doi:10.1109/ccpr.2010.5659316
“Kadir 等[6]将尺度不变的显著区域[7]扩展 为仿射不变区域,首先在椭圆窗口中计算灰度概率密度 函数的信息熵,然后搜寻熵达到局部极值时的尺度和椭 圆参数来确定仿射不变区域显著区域。Matas[8]提出了 一种基于局部灰度极值的区域特征检测算法,称为最大 稳定极值区域(MSER 区域),该方法首先采用了一种 类似于分水岭的方法来检测灰度区域,然后用椭圆拟合 不规则区域的边缘,在众多的方法中该方法具有真正的 摄影不变性。Mikolajczyk 在文献[9]中对上述区域特征的 检测方法进行系统比较后指出,它们在不同的图像上各 有优势,不存在一种方法在总体性能方面显著优于其它 方法。 在区域描述子的构造及匹配方面,Lowe[10]提…”
InfluentialTracking with scattering descriptor
Tian, X., Jiao, L., & Shang, X. (2014) · IET Computer Vision · doi:10.1049/iet-cvi.2013.0124
Outliers handling in the structure-from-motion algorithm
Zhou, H., & Zhang, T. (2014) · IEEE International Conference on Information Science and Technology (ICIST) · doi:10.1109/icist.2014.6920356
“Until now, most of the SfM methods are based on feature points which are extract by the feature points extraction methods, such as SURF [5] and Harris [6].”
MethodResearch on Method of Items Recognition Based on SURF Algorithm
Chen, W. Y., Xie, W. Z., Zhao, Y. L., et al. (2011) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.121-126.4630
Groupwise registration of aerial imagesPreprint
Arandjelović, O., Pham, D.-S., & Venkatesh, S. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.05299
A new image matching algorithm based on scale adapted interest point detection
Liang, P., Shao-fa, L., & Wang, C. (2009) · International Conference on Information and Automation · doi:10.1109/icinfa.2009.5204944
Human Pose Tracking For Video Using SURF features
Yi, O. Y. (2010) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.39.203
Robust feature matching for aerial visual odometry
Mouats, T., & Aouf, N. (2014) · International Symposium ELMAR (ELMAR) · doi:10.1109/elmar.2014.6923324
“To alleviate this, interesting regions extractors are utilized where SIFT [6] and SURF [7] are the most established examples used in many computer vision applications.”
MethodExtending Filter-based Structure from Motion to Large Baselines
Fakih, A. H., & Zelek, J. (2011) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2011.51
Feature Points Extraction for Camera Tracking in Augmented Reality System
Kim, B.-G., Choi, J.-S., & Kim, J.-T. (2014) · International Journal of Multimedia and Ubiquitous Engineering · doi:10.14257/ijmue.2014.9.9.29
Large-scale 3D scene modeling by registration of laser range data with Google Maps images
Agrawal, A., Matsumura, M., Nakazawa, A., et al. (2009) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2009.5413885
Robust motion estimation using covariance intersection
Boulekchour, M., & Aouf, N. (2014) · 2006 14th Mediterranean Conference on Control and Automation · doi:10.1109/med.2014.6961507
“Similarly, SIFT [12] and SURF [23] features present also feature localisation errors.”
AN IMPROVED ALGORITHM USED IN AUTOMATIC MATCHING FOR LOW-ALTITUDE AERIAL IMAGE
Wan, X., Zhang, Z., & Wan, Y. (2012) · 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-xxxix-b6-183-2012
Interest Curves: Concept, Evaluation, Implementation and Applications
Li, B. (2015) · DiVA at Umeå University (Umeå University)
Nemoto, M., Nomura, Y., Hanaoka, S., et al. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15948-0_22
Evaluation of a Dialogue System for Children based on an Interaction-Oriented Cognitive Architecture
Venegas-Briones, E., Meza, I., & Pineda, L. A. (2011)
Robust feature matching for robot visual learning
Gao, C., Song, Y., & Jia, P. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6095137
“And some Fast descriptor, such as SURF[12], has been proposed too.”
MethodInfluentialSemantic concept detection in imbalanced datasets based on different under-sampling strategies
Guo, J., Foley, C., Gurrin, C. G., et al. (2011) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2011.6011923
Biologically Inspired Keypoints
Alahi, A., Goetz, G., & d'Angelo, E. (2015) · Wiley eBooks · doi:10.1002/9783527680863.ch15
Rae, A. (2008)
On Applications of Pyramid Doubly Joint Bilateral Filtering in Dense Disparity Propagation
Abadpour, A. (2014) · 3D Research · doi:10.1007/s13319-014-0008-5
“A generic descriptor–based stere-opsis technique utilizes a local image descriptor such as SIFT [57,58], SURF [13], DAISY [95], FAST [80], or GLOH [69], among others.”
MethodSélection de singularités locales par stimulation de carte GHSOM
Lefebvre, G., García, C., Salotti, J., et al. (2007) · HAL (Le Centre pour la Communication Scientifique Directe)
Masataka, S., & Hashimoto, M. (2012) · International Symposium on Optomechatronic Technologies · doi:10.1109/isot.2012.6403270
“As for keypoint matching methods, for example, SIFT[8] and SURF [9] are regarded as good examples of reduction method of matching data.”
BackgroundMethodRegional features with adaptable global mappings for recognition systems
Estabridis, K. (2012) · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/acssc.2012.6489317
“Transform (SIFT), Lowe, [1], Affine Scale Invariant Feature Transform (ASIFT), Yu/Morel, [2], and Speeded Up Robust Feature(SURF), [3].”
MethodSeo, H.-Y., Lee, H.-H., & Lee, J.-J. (2010) · doi:10.1109/iccas.2010.5669764
An indoor adaptive global motion estimation method
Zhang, H., & Gao, L. (2014) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2014.6896342
Medical Image Thresholding Using Online Trained Neural Networks
Othman, A. A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34500-5_79
“For every point, a feature vector consisting of the scale, the orientation and 64 SURF descriptors [16].”
MethodDiscriminant Splitting For Feature Extraction Applicable To View-Independent Object Recognition
Marras, I., Nikolaidis, N., & Pitas, I. (2011) · INFM-OAR (INFN Catania) · doi:10.5281/zenodo.42288
Jiang, Y., & Wei, H. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21090-7_26
“This kind of representation is fundamentally different to some local descriptors such as SIFT [9], SURF [10] or HoG [11] etc.”
MethodVisual control of multi-rotor UAVs
Duncan, S. J. M. (2014) · UC Research Repository (University of Canterbury) · doi:10.26021/3536
Comparing Effectiveness of Feature Detectors in Obstacles Detection from a Video
Qian, S., Tan, J. K., Kim, H., et al. (2014) · Journal of Robotics Networking and Artificial Life · doi:10.2991/jrnal.2014.1.3.3
“SURF or Speeded Up Robust Features [5] has been developed to speed up the feature detecting process using SIFT as a basic algorithm.”
MethodEl‐Sana, J., & Kedem, K. (2015) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2015.7333915
Haptic interaction with objects in a picture based on surface normal estimation
Kim, S.-C., & Kwon, D. (2013) · World Haptics Conference · doi:10.1109/whc.2013.6548383
Detection of Emergency Telephone Indicators in a Tunnel Environment
Wang, Z., Kagesawa, M., Ono, S., et al. (2014) · International Journal of Intelligent Transportation Systems Research · doi:10.1007/s13177-013-0071-y
“In data collected using ordinary cameras, keypoints [2, 18] invariant to rotations, affine changes, and illumination changes are preferable.”
MethodRapid discriminative detection for smart camera applications
Taylor, G., Wang, P., Rasheed, Z., et al. (2011) · ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC) · doi:10.1109/icdsc.2011.6042912
“Similar to the methods in [12] [13], the generative focus of attention stage uses detected SURF features [2] to vote for the location, size and orientation of the vehicle.”
Robust and Fast Keypoint Recognition Based on SE-FAST
Tan, X., Yang, X., & Xiao, S. (2009) · IEEE International Conference on Dependable, Autonomic and Secure Computing · doi:10.1109/dasc.2009.32
CDCF-based iris feature extraction and matching
Wang, J., & Xie, M. (2010) · doi:10.1109/icacia.2010.5709914
USE OF PROCESSING OF RAW IMAGE TO ANALYZE MECHANICAL WORK OF THE STONE IN VAULTING WEBS
González, M. C. (2016)
Notebook paper: TNO instance search submission 2011
Schavemaker, J. G. M., Versloot, C., de Wit, J. J., et al. (2011) · TNO Repository
Semantic supported object and context recognition
Sekiyama, K., Rachmadi, M. F., & Fukuda, T. (2013) · Society of Instrument and Control Engineers of Japan
Hyper-graph Matching with Bundled Feature
Li, D., & Zhou, Y. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-42057-3_85
“Object matching problem is mainly related to two aspects: (i) feature extraction and description [4–6].”
BackgroundNearly rigid descriptor-based matching for volume reconstruction from histological sections
Sun, S., Magalhães, N. D., & Cahill, N. D. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.911665
Integral correlograms and probabilistic diffusion for image tagging
Bauckhage, C. (2008) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2008.4711922
“Successful applications of this idea consider integral images [3, 9] or integral histograms [4, 6].”
BackgroundMethodA General Framework for a Robust Human Detection in Images Sequences
Benezeth, Y., Emile, B., Laurent, H., et al. (2009) · International Conference on Image and Graphics · doi:10.1109/icig.2009.172
Anomalous cases of astronaut helmet detection
Dolph, C. V., Moore, A., Schubert, M., et al. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2176743
PTZ camera calibration for Augmented Virtual Environments
Wang, L., You, S. O., & Neumann, U. (2009) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2009.5202757
“However, instead of using Harris corners we use SURF features [6] to match neighboring images because they are more robust and can be computed very fast.”
MethodInfluentialA Fast Video Mosaic Algorithm Based on Optimal Homography Matrix
Wang, W., Zhang, C., Sang, L., et al. (2012) · doi:10.1061/9780784412442.244
Investigation of Image Models for Landmark Classification
Hughes, M. M., Jones, G. J. F., & O'Connor, N. E. (2009) · International Workshop on Semantic Media Adaptation and Personalization · doi:10.1109/smap.2009.21
“Two of the most commonly used today are the Scale Invariant Feature Transform (SIFT) [9] and the Speeded Up Robust Features (SURF) [3] algorithms.”
MethodInfluentialTumor Diagnosis of the Human Brain using Symmetrical Characteristics in PET/CT Image
Zhang, R., 張, 瑞., & チョウ, ズ. (2014) · Yokohama National University Repository (Yokohama National University)
Image matching using feature set transformations
Razzaq, S., & Khalid, S. (2011) · International Conference on Emerging Technologies · doi:10.1109/icet.2011.6048473
“Both SIFT and SURF look at a square neighborhood region around the key point and factor in gradient direction and intensity of the neighborhood sub regions.”
BackgroundNavigation and Automatic Ground Mapping by Rover Robot
Zhao, L., & Wang, X. (2010)
Multiple partial solutions for the point-to-point correspondence problem in three views
Carrasco, M. (2012) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp.2012.6356179
Design of constrained Digital Signal Processing Systems
Ghibaudi, M. (2014) · CERN Document Server (European Organization for Nuclear Research)
Toward a distributed benchmarking tool for biometrics
Mahier, J., El-Abed, M., Hemery, B., et al. (2011) · International Conference on High Performance Computing & Simulation (HPCS) · doi:10.1109/hpcsim.2011.5999891
Rotation Invariant Tracking Algorithm Based on Circular HOGs
Miramontes-Jaramillo, D., Kober, V. I., & Diaz-Ramirez, V. H. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19264-2_12
Performance Evaluation of Scale Invariant Feature Transform
Mittal, A., & Kaur, N. (2014)
Discriminable Points That Stick Out of Their Environment
Klein, D. A., & Cremers, A. B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40602-7_41
“We compare results against a number of state-of-the-art keypoint detector/descriptor pairs provided by OpenCV-library(1), namely SIFT [8], SURF [1], FAST+ORB [11, 12] and BRISK [7].”
BackgroundResultOverlapping local image descriptor
Chen, M., Men, A., Fan, P., et al. (2009) · doi:10.1109/peits.2009.5406753
A Novel Extracting Blob-like Object Method Based on Scale-Space
Chen, W., Wang, X., Li, Q., et al. (2011) · doi:10.1109/icic.2011.25
Research of Vehicle Recognition Algorithm Based on Virtual Coil and Image Features
Tang, Z., Xian, Y., & Li, B. (2014) · Lecture notes in electrical engineering · doi:10.1007/978-3-642-55038-6_56
Automated Image Alignment and Monitoring Method for Efficient Stereoscopic 3D Contents Production
Kim, J., & Kim, T. (2014) · Journal of Broadcast Engineering · doi:10.5909/jbe.2014.19.2.205
“이를 위해 빠른 처리속도가 장점인 SURF (Speed Up Robust Feature) 알고리즘[12]을 이용하였으며, 보 다 가속화를 위해 GPU 기반병렬 컴퓨팅기법을 적용하였 다. 또한 이러한 방식으로 추출된 대응점에는 작은 위치오차 뿐만 아니라 오정합으로 인해 발생된 과대오차까지도포함 될 수 있으므로 이들을 걸러내기 위한 방법으로 RANSAC (RANdom Sample Consensus) 알고리즘[13]을 적용하였다.”
Classifying bags of keypoints using HMMs
Zaklouta, F., & Stanciulescu, B. (2010) · ACS/IEEE International Conference on Computer Systems and Applications · doi:10.1109/aiccsa.2010.5587039
“SURF (Speeded Up Robust Features) [9] uses the FastHessian Detector to extract keypoints.”
MethodA novel framework for fast scene matching in consumer image collections
Chen, X., Das, M., & Loui, A. C. P. (2010) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2010.5582565
“There has been recent work on matching feature-rich complex scenes using scale-invariant features (SIFT) [3] and faster feature extractions such as PCA-SIFT and SURF [4][5].”
ResultInfluentialDetecting non-transient anomalies in visual information using neural networks
Kounavis, M. E., Morrissette, J., Srinivasan, S., et al. (2011) · Proceedings - IEEE Symposium on Computers and Communications/IEEE Symposium on Computers and Communications · doi:10.1109/iscc.2011.5983853
Security of Forensic Techniques for Digital Images
Nguyen, H. C. (2013) · Technischen Universität Darmstadt · doi:10.26083/tuprints-00003587
Venkatasubramanian, G. (2011)
Image Retrieval Method Using Top-surf DescriptorPreprint
Ji, Y. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1104.0579
Design of multimedia matching service using manycores and GPGPU
Kim, D. J., Kim, C. M., Choi, J. H., et al. (2012) · International Conference on Information Science and Digital Content Technology
A Wavelet Model of Ganglion Cells Array and Its Application in Image Representation
Weng, D., Wang, Y., Wei, H., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-319-03731-8_77
Similar video detection using multiple direct-mapped cache
Murabayashi, N., & Yoshida, K. (2013) · International Journal of Intelligent Systems Technologies and Applications · doi:10.1504/ijista.2013.056522
Robust automated registration in the spatial domain
Van der Walt, S., & Bm, H. (2006) · SUNScholar (Stellenbosch University)
Khalique, M. S. M., Ullah, K. R., Gaip, W. E. N., et al. (2011) · Unimas Institutional Repository (Universiti Malaysia Sarawak)
Descriptor-Free Smooth Feature-Point Matching for Images Separated by Small/Mid Baselines
Li, P., Farin, D., Gunnewiek, R. K., et al. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74607-2_39
“proposed a new rotation- and scale-invariant interest point detector and descriptor, called SURF (Speeded Up Robust Features) [8].”
Background3D reconstruction of indoor scenes by casting visual rays in an occupancy grid
Shaker, S., Asmar, D., & Elhajj, I. H. (2010) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2010.5723495
“We use Scale Invariant Feature Transform (SIFT) [18] features but the method would work equally well with other features such as Speeded Up Robust Features (SURF) [19].”
BackgroundMethodLOCAL DESCRIPTORS BASED ON COLOR IMAGES
CHENG, D., Xie, S. Q., & Hämmerle, E. (2009) · International Journal of Information Acquisition · doi:10.1142/s0219878909002004
Image Color Registration for Illumination-Robust Pattern Recognition
Yang, U., Kang, M.-S., Son, J., et al. (2014) · Circuits Systems and Signal Processing · doi:10.1007/s00034-014-9819-0
Socket connector recognition based on SVM with speeded up robust feature (SURF)
Zhao, M. H., & Qin, S. (2009) · IEEE International Conference on Electronic Measurement & Instruments · doi:10.1109/icemi.2009.5274714
Integration of semantic vision techniques for an autonomous robot platform
Felps, C. M., Fick, M. H., Kinkade, K. R., et al. (2010) · Proceedings · doi:10.1109/ssst.2010.5442826
“In future work, we intend to research faster key point recognition software such as Speeded Up Robust Features (SURF) algorithm [12].”
MethodVisual Signature for Place Recognition in Indoor Scenarios
dos Santos, F. N., Costa, P., & Moreira, A. P. (2014) · Lecture notes in electrical engineering · doi:10.1007/978-3-319-10380-8_62
Spherical Mapping Based Motion Recovery for Panoramic Cameras
Li, Y., Zhou, Z., & Wu, W. (2009) · International Conference on Multimedia and Ubiquitous Engineering (MUE) · doi:10.1109/mue.2009.23
“The popular feature algorithms include Harris [3], KLT [4], SIFT [5] and SURF [6].”
MethodCompressing Sparse Feature Vectors Using Random Ortho-Projections
Rahtu, E., Salo, M., & Heikkilä, J. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.345
Dai, F., Rashidi, A., Brilakis, I., et al. (2011) · doi:10.5555/2431518.2431945
Efficient outlier removal in vision based navigation
Ma, Y., & Rao, S. U. (2012) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans.2012.6236920
Recognition of Amazigh Characters using Visual Rotation Invariant Features
Raoui, Y., & Bouyakhf, E. H. (2013) · International Journal of Computer Applications · doi:10.5120/11692-3395
Structure from Motion Methods for 3D Modeling of the Ear Canal
Telcean, F. S. (2007)
A Novel BA Complex Network Model on Color Template Matching
Han, R., Shen, S., Yue, G., et al. (2014) · The Scientific World JOURNAL · doi:10.1155/2014/918453
“Research Article”
Covariant support region and detection algorithm based on LoG corners
Liu, Y., & Li, J. (2009) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2009.5420847
Extraction of Object Position Information Using the Natural Image Marker
Park, K.-J., Moon, M.-S., & Lee, K. (2014) · Lecture notes in electrical engineering · doi:10.1007/978-3-662-45402-2_98
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.