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 5,001–5,100 of 14,752
González‐Aguilera, D., de Oña, E. R., López-Fernández, L., Farella, E. M., Stathopoulou, E. K., Toschi, I., Fabio Remondino, A., Rodríguez‐Gonzálvez, P., Hernández‐López, D., Fusiello, A., et al. (2020) · 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/isprs-archives-xliii-b5-2020-213-2020 · Cited by 13
An automatic electronic instrument for accurate measurements of food volume and density
Yuan, D., Hu, X., Zhang, H., Jia, W., Mao, Z., & Sun, M. (2020) · Public Health Nutrition · doi:10.1017/s136898002000275x · Cited by 10
Affine Template Matching Based on Multi-Scale Dense Structure Principal Direction
Dong, J., Hu, M., Lu, J., et al. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3020970 · Cited by 11
“This algorithm can be computed and compared much faster by relying on integral images for image convolutions [21].”
MethodStereo Visual Inertial Mapping Algorithm for Autonomous Mobile Robot
Zhang, M., Han, S., Wang, S., Liu, X., Hu, M., & Zhao, J. (2020) · International Conference on Intelligent Robotics and Control Engineering (IRCE) · doi:10.1109/irce50905.2020.9199252 · Cited by 13
“Numerous feature extraction algorithms have been proposed: Harris corner [13], Fast corner [14], SIFT [15], SURF [16] and ORB [17].”
MethodChien, J.-C., Lee, J.-D., Su, E., et al. (2020) · Sensors · doi:10.3390/s20236997 · Cited by 11
Singh, N., & Singh, V. P. (2020) · Traitement du signal · doi:10.18280/ts.370519 · Cited by 11
“The main disadvantage of SIFT features are its scale invariance strategy, which is not able to provide sufficient control points in case of high order transformation [27].”
BackgroundCorNet: Unsupervised Deep Homography Estimation for Agricultural Aerial Imagery
Kharismawati, D. E., Aliakbarpour, H., Aktar, R., Bunyak, F., Palaniappan, K., & Kazic, T. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-65414-6_28 · Cited by 11
Improved bag-of-features using grey relational analysis for classification of histology images
Pal, R., Saraswat, M., & Mittal, H. (2021) · Complex & Intelligent Systems · doi:10.1007/s40747-021-00275-3 · Cited by 16
“Out of many feature extraction methods, SURF is the fastest method because it uses box filters for the convolution of images and converts each image as the integral image.”
BackgroundMethodInfluentialWang, H., Qi, J., Lei, Y.-F., et al. (2021) · Remote Sensing · doi:10.3390/rs13081507 · Cited by 11
Hazgui, M., Ghazouani, H., & Barhoumi, W. (2021) · Evolving Systems · doi:10.1007/s12530-021-09386-1 · Cited by 13
“Methods like SURF (Bay et al. 2006) have inspired from SIFT while detecting local invariant keypoints differently using integral images in order to reduce the computational time.”
BackgroundMethodInfluentialCombating Ambiguity for Hash-Code Learning in Medical Instance Retrieval
Fang, J., Fu, H., Zeng, D., Xiao, Y., Yan, Y., & Liu, J. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3082531 · Cited by 14
Modified Bag of Visual Words Model for Image Classification
Sultani, Z. N., & Dhannoon, B. N. (2021) · Journal of Al-Nahrain University-Science · doi:10.22401/anjs.24.2.11 · Cited by 11
Monocular Object SLAM using Quadrics and Landmark Reference Map for Outdoor UAV Applications
Shao, P., Mo, F., Chen, Y., Ding, N., & Huang, R. (2021) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar52367.2021.9517328 · Cited by 9
CapsNet meets SIFT: A robust framework for distorted target categorization
Lin, Z., Gao, W., Jia, J., & Huang, F. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.08.087 · Cited by 11
An End-to-End Traffic Light Detection Algorithm Based on Deep Learning
Yan, S., Liu, X., Wu, Q., & Chen, Q. (2021) · International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) · doi:10.1109/spac53836.2021.9539934 · Cited by 15
Sensing Crop Geometry and Structure
Gregorio, E., & Llorens, J. (2021) · Progress in precision agriculture · doi:10.1007/978-3-030-78431-7_3 · Cited by 12
A Robust Rigid Registration Framework of 3D Indoor Scene Point Clouds Based on RGB-D Information
Zhong, S.-S., Guo, M.-Q., Lv, R., Chen, J.-G., Xie, Z., & Liu, Z. (2021) · Remote Sensing · doi:10.3390/rs13234755 · Cited by 10
Sim2Real Object-Centric Keypoint Detection and Description
Zhong, C., Yang, C., Sun, F., Qi, J., Mu, X., Liu, H., & Huang, W. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i5.20482 · Cited by 14
Li, Y., Li, L., Fang, Y., Peng, H., & Ling, N. (2022) · Electronics · doi:10.3390/electronics11081264 · Cited by 13
Rock Fracture Centerline Extraction based on Hessian Matrix and Steger Algorithm
Mansourian, L., Abdullah, M. T., Abdullah, L. N., et al. (2016) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2016.02.018 · Cited by 11
“Later, Bay et al. [26] proposed SURF, which is a quicker SIFT.”
BackgroundA New Dataset and Performance Evaluation of a Region-based CNN for Urban Object Detection
Dominguez-Sanchez, A., Orts‐Escolano, S., García‐Rodríguez, J., & Cazorla, M. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489478 · Cited by 12
“Another popular algorithm is SURF (Speeded Up Robust Features) presented in [7], which reduced the computation cost of SIFT by approximating Laplacian of Gaussian with filter kernels.”
MethodNo-Reference Quality Assessment of Authentically Distorted Images Based on Local and Global Features
Varga, D. (2022) · Journal of Imaging · doi:10.3390/jimaging8060173 · Cited by 12
Fast Graph Refinement and Implicit Neural Representation for Tissue Tracking
Schmidt, A., Mohareri, O., DiMaio, S., & Salcudean, S. E. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811742 · Cited by 13
Lu, M., Liu, J., Wang, F., & Xiang, Y. (2022) · Remote Sensing · doi:10.3390/rs14143450 · Cited by 17
Dimensionality reduction through visual data resampling for low-storage loop-closure detection
Tsintotas, K. A., An, S., Papapetros, I. T., Konstantinidis, F. K., Sirakoulis, G. C., & Gasteratos, A. C. (2022) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist55454.2022.9827748 · Cited by 16
A new multi‐object tracking pipeline based on computer vision techniques for mussel farms
Zeng, D., Liu, I., Bi, Y., Vennell, R., Briscoe, D. K., Xue, B., & Zhang, M. (2023) · Journal of the Royal Society of New Zealand · doi:10.1080/03036758.2023.2240466 · Cited by 11
Assessment of the accuracy of 3D models obtained with DSLR camera and Kinect v2
Lachat, E., Macher, H., Landes, T., et al. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2184866 · Cited by 11
A novel method for analysing lighting variance
Ross, P., English, A., Ball, D., Upcroft, B., Wyeth, G. F., & Corke, P. (2013) · QUT ePrints (Queensland University of Technology) · Cited by 11
Eyesight Sharing in Blind Grocery Shopping: Remote P2P Caregiving through Cloud Computing
Kulyukin, V., Zaman, T., Andhavarapu, A., & Kutiyanawala, A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-31534-3_12 · Cited by 11
Towards a Multimodal Silent Speech Interface for European Portuguese
Freitas, J., Teixeira, A. J. S., Dias, M. S., & Bastos, C. A. C. (2011) · InTech eBooks · doi:10.5772/16935 · Cited by 12
Joint Random Sample Consensus and Multiple Motion Models for Robust Video Tracking
Strandmark, P., & Gu, I. Y. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02230-2_46 · Cited by 11
Vision tracking system for mobile robots using two Kalman filters and a slip detector
Hwang, W., Park, J., Kwon, H.-I., et al. (2010) · doi:10.1109/iccas.2010.5670110 · Cited by 11
“The image processing block recognizes the target in camera image using Speeded-up Robust Feature (SURF) [5], and decides the position of the target in the camera image.”
MethodSLAM solution based on particle filter with outliers filtering in dynamic environments
Vidal, F. S., Barcelos, A. D. O. P., & Rosa, P. F. F. (2015) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie.2015.7281544 · Cited by 11
Gammeter, S., Quack, T., Tingdahl, D., et al. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15549-9_53 · Cited by 11
“Match photos pair-wise using local image features (we use SURF [19]).”
MethodSelf-citationReal-time side scan image generation and registration framework for AUV route following
King, P., Vardy, A., Vandrish, P., et al. (2012) · IEEE/OES Autonomous Underwater Vehicles · doi:10.1109/auv.2012.6380758 · Cited by 11
Remote sensing image matching via Harris detector and sift discriptor
Dai, J., Wei-dong, S., Liang, P., & Zhang, J. (2010) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2010.5647782 · Cited by 11
“However, the scale-space analysis required for the calculation of the SIFT feature point positions is too slow for visual servicing applications [16]-[17].”
MethodCV-SLAM using ceiling boundary
Choi, H., Kim, D. Y., Hwang, J. P., Kim, E., & Kim, Y.-O. (2010) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2010.5516788 · Cited by 11
Joint image representation and classification in random semantic spaces
Zhang, C., Zhu, X., Li, L., Zhang, Y., Liu, J., Huang, Q., & Tian, Q. (2015) · Neurocomputing · doi:10.1016/j.neucom.2014.12.083 · Cited by 12
Analysis and comparison of feature detection and matching algorithms for rovers vision navigation
Bai, X., Ning, X., & Wang, L. (2012) · Fifth International Symposium on Instrumentation and Control Technology · doi:10.1109/isict.2012.6291628 · Cited by 12
“Representative feature extraction and matching algorithms include Moravec operator[5], Harris algorithm[6], Förstner algorithm[7], SIFT algorithm[8] and SURF algorithm[9].”
BackgroundMethodAdvanced 3D localization by fusing measurements from GPS, inertial and vision sensors
Ababsa, F. (2009) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2009.5346784 · Cited by 11
Detecting image spam using local invariant features and pyramid match kernel
Zuo, H., Hu, W., Wu, O., Chen, Y., & Luo, G. (2009) · International World Wide Web Conference (WWW) · doi:10.1145/1526709.1526921 · Cited by 12
“Among them, the MSER[5] and SURF [6] detector showed good accuracy and stability on our image spam detection application.”
Fast SIFT algorithm based on Sobel edge detector
Li, Y., Liu, L., Wang, L., et al. (2012) · International Conference on Consumer Electronics, Communications and Networks (CECNet) · doi:10.1109/cecnet.2012.6201824 · Cited by 11
Efficient planar features matching for robot localization using GPU
Charmette, B., Royer, E., & Chausse, F. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543757 · Cited by 15
Online video advertising based on user’s attention relavancy computing
Wang, J., Fang, Y., & Lu, H. (2008) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2008.4607646 · Cited by 11
Multisensory embedded pose estimation
Eyjólfsdóttir, E., & Turk, M. (2011) · Proceedings · doi:10.1109/wacv.2011.5711479 · Cited by 11
Khan, Z. H., Gu, I. Y., Wang, T., et al. (2009) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2009.5202733 · Cited by 11
HALF-SIFT: High-Accurate Localized Features for SIFT
Cordes, K., Muller, O., Rosenhahn, B., et al. (2009) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2009.5204283 · Cited by 11
Two camera system for robot applications; navigation
Lidholm, J., Ekstrand, F., & Asplund, L. (2008) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2008.4638417 · Cited by 11
“The current feature detectors with the highest repeatability, such as SIFT [8] and SURF [2], create descriptors for each feature in order to simplify the matching task.”
MethodGirdhar, Y., & Dudek, G. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509464 · Cited by 13
“To build the vocabulary, we extract SURF [14] features from a subsampling of all the images in the observation set, and then cluster them using k means algorithm to get 1000 words.”
MethodAn Evaluation of Local Features for Face Detection and Localization
Asbach, M., Hosten, P., & Unger, M. (2008) · International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) · doi:10.1109/wiamis.2008.58 · Cited by 11
“However, in Figure 4 we show the performance of all four detectors combined with SIFT and SURF descriptors.”
MethodInfluentialObject Recognition and Selection Method by Gaze Tracking and SURF Algorithm
Heo, H., Lee, W. O., Lee, J. W., et al. (2011) · doi:10.1109/cmsp.2011.60 · Cited by 11
Adaptive appearance based loop-closing in heterogeneous environments
Majdik, A. L., Galvez-Lopez, D., Lazea, G., & Castellanos, J. A. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094537 · Cited by 12
Ranking the local invariant features for the robust visual saliencies
Xia, S., Ren, P., & Hancock, E. R. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4761170 · Cited by 11
Acoustic Stereo Imaging (ASI) system
Assalih, H., Pétillot, Y., & Bell, J. M. (2009) · doi:10.1109/oceanse.2009.5278275 · Cited by 11
“More advanced feature descriptors could be applied like SIFT [10] and SURF [11].”
MethodSelf-contained image mapping of placental vasculature in 3D ultrasound-guided fetoscopy
Yang, L., Wang, J., Ando, T., et al. (2015) · Surgical Endoscopy · doi:10.1007/s00464-015-4690-z · Cited by 11
Image based view localization system retrieving from a panorama database by surf
Naoyuki, Y., Uchiyama, H., Saitô, H., et al. (2009) · Cited by 11
Feature matching based positioning algorithm for swarm robotics
Seçkin, A. Ç., Karpuz, C., & Özek, A. (2016) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2016.06.006 · Cited by 11
McAllister, P., Zheng, H., Bond, R., & Moorhead, A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48746-5_18 · Cited by 14
“This process only requires three operations to compute the value of the region [14].”
BackgroundHuman activity recognition using standard descriptors of MPEG CDVS
Kamiński, Ł., Maćkowiak, S., & Domański, M. (2017) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew.2017.8026248 · Cited by 12
“descriptor from static images to video sequences, SURF (Speeded-Up Robust Features) descriptor [6] provides comparable or even better results than SIFT, while it can be calculated in a relatively efficient way.”
ResultNotice of Removal: A new algorithm for training sparse autoencoders
Shamsabadi, A. S., Babaie‐Zadeh, M., Seyyedsalehi, S. Z., Rabiee, H. R., & Jutten, C. (2017) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2017.8081588 · Cited by 11
“For example, algorithms such as SIFT [6], RIFT [7], HOG [8], GHOG [9], and SURF [10] have been proposed to extract features from images.”
MethodJacobson, A., Chen, Z., & Milford, M. J. (2018) · Biological Cybernetics · doi:10.1007/s00422-017-0745-7 · Cited by 13
“Camera based place recognition techniques use whole-image [Olivia, 2005, Milford and Wyeth, 2012] or feature-based techniques [Lowe, 1999, Bay et al., 2006] to represent locations.”
MethodFast and Robust Estimation for Unit-Norm Constrained Linear Fitting Problems
Ikami, D., Yamasaki, T., & Aizawa, K. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00850 · Cited by 11
A Multi-frame Stereo Vision-Based Road Profiling Technique for Distress Analysis
Dhiman, A., Chien, H.-J., & Klette, R. (2018) · International Symposium on Pervasive Systems, Algorithms and Networks (ISPAN) · doi:10.1109/i-span.2018.00012 · Cited by 13
“[18] proposed a methodology of detecting mean depth values of potholes by matching speeded-up robust features (SURF) [19] in an uncalibrated stereo pair of images, without employing disparity images.”
MethodExtract Features from Periocular Region to Identify the Age Using Machine Learning Algorithms
Kamarajugadda, K. K., & Polipalli, T. R. (2019) · Journal of Medical Systems · doi:10.1007/s10916-019-1335-0 · Cited by 11
A new axiomatic methodology for the image similarity
Amelio, A. (2019) · Applied Soft Computing · doi:10.1016/j.asoc.2019.04.043 · Cited by 12
Wu, H., Mu, J., Da, T., Xu, M., Taylor, R. H., Iordachita, I. I., & Chirikjian, G. S. (2019) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2019.8842953 · Cited by 10
A Genetic Programming Method for Scale-Invariant Texture Classification
Ghazouani, H., Barhoumi, W., & Antit, Y. (2020) · Proceedings of the international neural networks society · doi:10.1007/978-3-030-48791-1_47 · Cited by 11
Steder, B., Ruhnke, M., Grzonka, S., et al. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6048325 · Cited by 11
Ghuffar, S. (2016) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-iii-1-63-2016 · Cited by 11
Liang, Y., Liu, X., Wang, Z., et al. (2008) · Cited by 11
Object recognition using the OpenCV Haar cascade-classifier on the iOS platform
Reinius, S. (2013) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 11
Modeling and Optimizing the Coverage of Multi- Camera Systems
Mavrinac, A. (2012) · Scholarship at UWindsor (University of Windsor) · Cited by 13
Cardiac View Classification Using Speed Up Robust Features
Balaji, N., Subashini, T. S., & Chidambaram, N. (2015) · Indian Journal of Science and Technology · doi:10.17485/ijst/2015/v8is7/62245 · Cited by 11
Vision based localization: from humanoid robots to visually impaired people
Alcantarilla, P. F. (2011) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 11
cltorch: a Hardware-Agnostic Backend for the Torch Deep Neural Network Library, Based on OpenCLPreprint
Perkins, H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.04884 · Cited by 17
RFVTM: A Recovery and Filtering Vertex Trichotomy Matching for Remote Sensing Image RegistrationPreprint
Zhao, M., An, B., Wu, Y., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2204.00818 · Cited by 11
“histograms as SIFT-like descriptors, speeded-up robust feature [27] utilizes the sums of Haar wavelet responses and estimates”
MethodAn empirical study of non-rigid surface feature matching
Doshi, A., Hilton, A., & Starck, J. (2008) · doi:10.1049/cp:20081082 · Cited by 11
A Fast HOG Descriptor Using Lookup Table and Integral ImagePreprint
Huang, C., & Huang, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.06256 · Cited by 12
Aurora Guard: Reliable Face Anti-Spoofing via Mobile Lighting SystemPreprint
Zhang, J., Tai, Y. Y., Yao, T., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.00713 · Cited by 11
“(Boulkenafet, Komulainen, and Ha-did 2017) converted the face image from RGB space to HSV-YCbCr space and extracted channel-wise SURF features (Bay, Tuytelaars, and Van Gool 2006) 2 D images, they suffer from poor generalization to unseen attacks and complex lighting conditions, especially when RGB…”
MethodGenetic Programming for Automatic Global and Local Feature Extraction to Image Classification
Bi, Y., Zhang, M., & Xue, B. (2021) · doi:10.26686/wgtn.13884998 · Cited by 11
A Scalable Staining Strategy for Whole-Brain ConnectomicsPreprint
Lu, X., Wu, Y., Schalek, R. L., Meirovitch, Y., Berger, D. R., & Lichtman, J. W. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.09.26.558265 · Cited by 10
YOLO-DFW: An improved detection method for printed circuit board surface defects based on YOLOv8
Zhou, Y., Xu, X., Fan, W., & Jiang, Z. (2025) · Displays · doi:10.1016/j.displa.2025.103201 · Cited by 15
Towards Utilizing Deep Uncertainty In Traditional SLAM
Esfahani, M. A., Wu, K., Yuan, S., & Wang, H. (2019) · International Conference on Control and Automation · doi:10.1109/icca.2019.8899572 · Cited by 13
Robust Visual Teach and Repeat for UGVs Using 3D Semantic Maps
Mahdavian, M., Yin, K., & Chen, M. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3189165 · Cited by 10
“The two common ways to process and abstract raw images for VTR are 1) creating 2D or 3D SLAM maps and 2) extracting and memorizing local features such as SIFT [1], SURF [2], BRIEF [3] or ORB [4] for each frame.”
Miniscule Object Detection in Aerial Images Using YOLOR: A Review
Pawar, N., Waghmare, A., Pratap, A., et al. (2022) · Algorithms for intelligent systems · doi:10.1007/978-981-19-3951-8_52 · Cited by 11
Suguna, M. R., Kalaivani, A., & Anusuya, S. (2022) · Symmetry · doi:10.3390/sym14102041 · Cited by 10
Automation of flow analysis in scleral vessels based on descriptive-associative algorithms
Kerimkhan, B., Nedzved, A., Zhumadillayeva, А., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-31866-4 · Cited by 10
“We compare the performance of three different image matching techniques as SIFT 20 , SURF 21 , and Shi-Tomasi Corner Detector 22 for different image with vessels.”
MethodZhao, S., Gong, M., Zhao, H., Zhang, J., & Tao, D. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01837-3 · Cited by 16
Multilevel Attention Siamese Network for Keypoint Detection in Optical and SAR Images
Zhang, S., Fu, Z., Liu, J., et al. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3293143 · Cited by 10
“However, they are computationally time-consuming, and to improve the computational speed of keypoint detection, speeded up robust features (SURF) [15] uses Harr filters and integral images to reduce the computational requirements.”
BackgroundMethodGeneral cross-modality registration framework for visible and infrared UAV target image registration
Luo, Y., Cha, H., Zuo, L., Cheng, P., & Zhao, Q. (2023) · Scientific Reports · doi:10.1038/s41598-023-39863-3 · Cited by 10
Benkley, T., Li, C., & Kolinski, J. M. (2023) · Experimental Mechanics · doi:10.1007/s11340-023-00981-8 · Cited by 10
Vision-based Runway Detection and Landing for Unmanned Aerial Vehicle Enhanced Autonomy
Tsapparellas, K., Jelev, N., Waters, J., Brunswicker, S., & Mihaylova, L. S. (2023) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma57826.2023.10215523 · Cited by 13
“Speeded-up robust features (SURF) were presented in Bay’s paper [40].”
MethodContent-based medical image retrieval using fractional Hartley transform with hybrid features
Rani, K. V., Prince, M. E., Therese, P. S., Shermila, P. J., & Devi, E. A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16462-y · Cited by 10
“As shown by [6, 7], this characteristic ensures the crucial feature of scale-invariance.”
Kannapiran, S., Bendapudi, N., Yu, M.-Y., Parikh, D., Berman, S., Vora, A., & Pandey, G. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341872 · Cited by 11
Learnable Graph Matching: A Practical Paradigm for Data Association
He, J., Huang, Z., Wang, N., & Zhang, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3362401 · Cited by 13
Zhou, Y., Han, T., Nie, Q., et al. (2024) · Sensors · doi:10.3390/s24041127 · Cited by 10
“The feature point method utilizes a set of specific feature points, such as ORB [38], SURF [39], or SIFT [40], to represent the environment.”
MethodViolent Video Recognition by Using Sequential Image Collage
Tu, Y.-S., Shen, Y.-S., Chan, Y. Y., Wang, L., & Chen, J. (2024) · Sensors · doi:10.3390/s24061844 · Cited by 9
“…of the DT methodology, the enhanced dense trajectories (iDTs) method [23] emerges as a refined iteration. iDT incorporates the speeded up robust features (SURF) [41]—a computationally expedited variant of the scale-invariant feature Transform (SIFT) [42]—to fortify its feature extraction prowess.”
MethodLocal feature matching from detector-based to detector-free: a survey
Liao, Y., Di, Y., Zhu, K., Zhou, H., Lu, M., Zhang, Y., Duan, Q., & Liu, J. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05330-3 · Cited by 15
“On the other hand, SURF [293, 294] used the detector metric of the Hessian matrix and the distribution-based descriptor to achieve feature matching by image convolution.”
3D Reconstruction of Buildings Based on 3D Gaussian Splatting
Cai, Z., Yang, J., Wang, T., Huang, H., & Guo, Y. (2024) · 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/isprs-archives-xlviii-4-w10-2024-37-2024 · Cited by 15
Chen, M., Shi, Y., Wu, L., et al. (2024) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2024.108526 · Cited by 10
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.