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 5,301–5,400 of 14,752
Mobile Visual Aid Tools for Users with Visual Impairments
Liu, X., Doermann, D., & Li, H. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-12349-8_2 · Cited by 10
Probabilistic Appearance-Based Mapping and Localization Using Visual Features
Garcia‐Fidalgo, E., & Ortiz, A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-38628-2_33 · Cited by 11
“In our map, each node corresponds to a keyframe, and each keyframe is described by its SURF [16] features.”
MethodDominant SIFT: A novel compact descriptor
Tra, A. T., Lin, W., & Kot, A. C. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178189 · Cited by 10
Robust Arm and Hand Tracking by Unsupervised Context Learning
Spruyt, V., Ledda, A., & Philips, W. R. (2014) · Sensors · doi:10.3390/s140712023 · Cited by 12
Image-based localization using prior map database and Monte Carlo Localization
Kim, H., Oh, T., Lee, D., & Myung, H. (2014) · International Conference on Ubiquitous Robots and Ambient Intelligence · doi:10.1109/urai.2014.7057440 · Cited by 10
Embedded platform for local image descriptor based object detection
Kapela, R., Gugała, K., Śniatała, P., et al. (2015) · Applied Mathematics and Computation · doi:10.1016/j.amc.2015.02.029 · Cited by 10
Object recognition on mobile devices
Jung, K. (2012) · IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin) · doi:10.1109/icce-berlin.2012.6336488 · Cited by 10
“For the detection of interest points we use the SURF algorithm presented in [6].”
MethodInfluentialAtlas-based segmentation of brain magnetic resonance imaging using random walks
Morin, J.-P., Desrosiers, C., & Duong, L. (2012) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2012.6239246 · Cited by 10
“Likewise, in the second technique, we used the OpenSurf implementation of the Speeded Up Robust Feature (SURF) algorithm [2] to find the matches (xi, xq), and kept the match strengths returned by the algorithm as values k(xi, xq).”
MethodColor balancing for change detection in multitemporal images
Thomas, J., Bowyer, K. W., & Kareem, A. (2012) · doi:10.1109/wacv.2012.6163047 · Cited by 10
Girdhar, Y. A., & Dudek, G. (2011) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2011.32 · Cited by 10
c-Velocity: A Flow-Cumulating Uncalibrated Approach for 3D Plane Detection
Bouchafa, S., & Zavidovique, B. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-011-0475-6 · Cited by 10
Detection of moving objects in image plane for robot navigation using monocular vision
Wang, Y.-T., Sun, C.-H., & Chiou, M.-J. (2012) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/1687-6180-2012-29 · Cited by 10
A line matching method based on local and global appearance
Zhang, Y., Yang, H., & Liu, X. (2011) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2011.6100414 · Cited by 10
“By designing highly distinctive point feature descriptors robust to illumination change, affine transformation, scale change , as well as some extent of viewpoint change, matching methods based on point feature have made great progress, such as SIFT [1], SURF [2], DAISY [3].”
MethodDou, J., Li, J., Qin, Q., & Tu, Z. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.03.076 · Cited by 10
Uchiyama, H., Saitô, H., Servieres, M. C. J., et al. (2010) · Virtual Reality · doi:10.1007/s10055-010-0173-7 · Cited by 10
“Recently, the focus of research has been shifting towards the use of natural features from actual environments such as edges and feature points, because fiducial markers may not be available (for instance, because of installation permission in outdoor environments, size-based issues, and application…”
InfluentialObject Detection and Localization Using Random Forest
Liu, Z., & Xiong, H. (2012) · International Conference on Intelligent System Design and Engineering Application (ISDEA) · doi:10.1109/isdea.2012.669 · Cited by 10
Recognize objects with three kinds of information in landmarks
Han, Y. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.04.010 · Cited by 10
Feature Conjugation for Intensity-Coded LIDAR Point Clouds
Han, J.-Y., Perng, N.-H., & Lin, Y.-T. (2013) · Journal of Surveying Engineering · doi:10.1061/(asce)su.1943-5428.0000106 · Cited by 10
Detailed analysis and evaluation of keypoint extraction methods
Wu, X., Shi, Z., & Zhong, Y. (2010) · International Conference on Computer Application and System Modeling · doi:10.1109/iccasm.2010.5620674 · Cited by 11
An Improved Methodology for Image Feature Matching
Neto, V. F. D. C., & Campos, M. F. M. (2009) · doi:10.1109/sibgrapi.2009.24 · Cited by 10
ARTOT: Autonomous real-time object detection and tracking by a moving camera
Angelov, P. P., Gude, C., Sadeghi‐Tehran, P., et al. (2012) · IEEE International Conference on Intelligent Systems · doi:10.1109/is.2012.6335175 · Cited by 10
Se, S., & Pears, N. E. (2012) · Springer eBooks · doi:10.1007/978-1-4471-4063-4_2 · Cited by 15
Localization for indoor service robot by using local-features of image
Muramatsu, S., Chugo, D., Jia, S., et al. (2009) · 2009 ICCAS-SICE · Cited by 10
Learning indoor robot navigation using visual and sensorimotor map information
Yan, W., Weber, C., & Wermter, S. (2013) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2013.00015 · Cited by 14
“For details of computation of SURF features as well as feature matching please read the original paper (Bay et al., 2006).”
MethodA Latent Model for Visual Disambiguation of Keyword-based Image Search
Wan, K.-W., Tan, A., Lim, J., et al. (2009) · British Machine Vision Conference (BMVC) · doi:10.5244/c.23.67 · Cited by 10
A probabilistic Self-Organizing Map for facial recognition
Lefebvre, G., & García, C. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4760955 · Cited by 10
Maier, W., Mair, E., Burschka, D., & Steinbach, E. G. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152547 · Cited by 13
Accelerating vision and navigation applications on a customizable platform
Cong, J., Grigorian, B., Reinman, G., et al. (2011) · IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) · doi:10.1109/asap.2011.6043233 · Cited by 10
Autonomous mobile robot system concept based On PSO path planner and vSLAM
Mohamed, A. Z., Lee, S., & Hsu, H.-Y. (2011) · IEEE International Conference on Computer Science and Automation Engineering · doi:10.1109/csae.2011.5952810 · Cited by 10
Fuzzy Membership Descriptors for Images
Kumar, M., Stoll, N., Thurow, K., et al. (2015) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2015.2451706 · Cited by 10
“For a fair comparison, the key point matching criterion of SIFT and SURF methods remained the same as that of the fuzzy-membership-based method stated in (19) of Section II-C.”
MethodInfluentialAdaptive Navigation for Mobile Robots with Object Recognition and Ontologies
Reinaldo, J. O., Maia, R. S., & Souza, A. (2015) · Brazilian Conference on Intelligent Systems · doi:10.1109/bracis.2015.50 · Cited by 10
Urban, S., Weinmann, M., & Hinz, S. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.08.011 · Cited by 14
Davila, K., Agarwal, A. K., Gaborski, R. S., Zanibbi, R., & Ludi, S. A. (2013) · IEEE Western New York Image and Signal Processing Workshop (WNYISPW) · doi:10.1109/wnyipw.2013.6890981 · Cited by 11
Object Reidentification in Multiple Cameras System
de Oliveira, Í. O., & Pio, J. L. D. S. (2009) · doi:10.1109/em-com.2009.5402974 · Cited by 10
Visual Aesthetic Analysis for Handwritten Document Images
Majumdar, A., Krishnan, P., & Jawahar, C. V. (2016) · International Conference on Frontiers in Handwriting Recognition · doi:10.1109/icfhr.2016.0085 · Cited by 10
Vision based object grasping of industrial manipulator
Lin, C.-C., Gonzalez, P., Cheng, M.-Y., et al. (2016) · International Conference on Advanced Robotics and Intelligent Systems (ARIS) · doi:10.1109/aris.2016.7886613 · Cited by 10
System Considerations of an Image Assisted Total Station - Evaluation and Assessment
Reiterer, A., & Wagner, A. (2012) · Cited by 10
Adaptive human tracking for smart wheelchair
Utaminingrum, F., Kumiawan, T. A., Fauzi, M. A., et al. (2017) · International Symposium on Computational and Business Intelligence (ISCBI) · doi:10.1109/iscbi.2017.8053535 · Cited by 10
“A total of six keypoint-based methods are used in the proposed framework: ORB [3], KAZE [4], AKAZE [5], BRISK [6], SIFT [7], and SURF [8].”
MethodFeature Extraction and Template Matching Algorithms Classification for PCB Fiducial Verification
Fonseka, S., & Jayasinghe, J. A. K. S. (2018) · Journal of Achievements of Materials and Manufacturing Engineering · doi:10.5604/01.3001.0011.6015 · Cited by 10
An improved GMS-PROSAC algorithm for image mismatch elimination
Zhao, P., Ding, D., Wang, Y., & Liu, H. (2018) · Systems Science & Control Engineering · doi:10.1080/21642583.2018.1477635 · Cited by 10
“In summary, the above experimental results show that the real-time of the improved algorithm is obviously better than the traditional ORB algorithm, even an order of magnitude faster than the classical SIFT and SURF image matching algorithms.”
MethodInfluentialSafe Avoidance Path Detection Using Multi Sensor Integration for Small Unmanned Aerial Vehicle
Ramli, M. F., Shamsudin, S. S., & Legowo, A. (2018) · IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace) · doi:10.1109/metroaerospace.2018.8453521 · Cited by 10
“The SURF algorithm will generate feature points that are detected on each image frames.”
MethodInfluentialPixel-wise depth based intelligent station for inferring fine-grained PM2.5
Xi, T., Tian, Y., Li, X., et al. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2018.08.051 · Cited by 10
A Rapid UAV Image Georeference Algorithm Developed for Emergency Response
Wang, S., Ding, L., Chen, Z., et al. (2018) · Journal of Sensors · doi:10.1155/2018/8617843 · Cited by 10
Unsupervised domain adaptation with target reconstruction and label confusion in the common subspace
Jiang, B., Chen, C., & Jin, X. (2018) · Neural Computing and Applications · doi:10.1007/s00521-018-3846-x · Cited by 10
“However, most of these methods are designed for small datasets such as Office dataset [49] and work on low dimensions surf features [5] rather than high dimensions raw image pixels.”
MethodIntoxicated Person Identification Using Thermal Infrared Images and Gait
Bhuyan, M. K., Dhawle, S., Sasmal, P., & Κούκιου, Γ. (2018) · International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET) · doi:10.1109/wispnet.2018.8538761 · Cited by 11
“After the extraction of SURF features from the images, K-means clustering is performed on all the 64-dimensional features.”
MethodInfluentialComparison and extension of three methods for automated registration of multimodal plant images
Michael, H., Junker, A., Neumann, K., Altmann, T., & Gladilin, E. (2019) · Plant Methods · doi:10.1186/s13007-019-0426-8 · Cited by 10
“Common approaches for the detection of feature-points are based on edges and corners (e.g., FAST [7], Shi and Tomasi [8], Harris operators [9], SUSAN [10]), blob detection (e.g., MSER [11], DoG, DoH), structure tensors, and generalized feature descriptions (e.g., SURF [12], HOG, SIFT [13]).”
BackgroundBotev, J., Mayer, J., & Rothkugel, S. (2019) · doi:10.1145/3304113.3326117 · Cited by 12
“Common feature point extraction algorithms such as SIFT [12], the accelerated FAST [2], or ORB [14], all return a large set of key points.”
MethodAugmented robust PCA for foreground-background separation on noisy, moving camera video
Gao, C., Moore, B. E., & Nadakuditi, R. R. (2017) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2017.8309159 · Cited by 10
Weakly Supported Plane Surface Reconstruction via Plane Segmentation Guided Point Cloud Enhancement
Yan, S., Yang, P. L., Wang, G., Lai, S., & Zhang, M. (2019) · IEEE Access · doi:10.1109/access.2019.2946456 · Cited by 10
Jiang, M., Feng, X., Song, S., Herrmann, J. M., Li, J., Li, Y., Hu, Z., Li, Z., Liu, J., & Li, S. (2019) · IEEE Access · doi:10.1109/access.2019.2952445 · Cited by 11
“It is difficult to calculate the transformation parameters 9 by the traditional feature point projection [27], [28], because discriminative feature points are hardly extractable from the MSIS scans.”
BackgroundSwathi, R., & Srinivas, A. (2019) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-019-01063-w · Cited by 10
“The results achieved by the proposed scheme with SS-CSA algorithm are compared with some of the existing techniques, such as speeded up robust features (SURF) (Bay et al. 2006), binary robust invariant scalable keypoints (BRISK) (Leutenegger et al. 2011), SURF ?”
MethodInstance search based on weakly supervised feature learning
Lin, J., Yu, Z., & Zhao, W. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.11.029 · Cited by 9
A Line Matching Method Based on Multiple Intensity Ordering with Uniformly Spaced Sampling
Xing, J., Wei, Z., & Zhang, G. (2020) · Sensors · doi:10.3390/s20061639 · Cited by 10
Gong, H., Chen, L., Li, C., Zeng, J., Tao, X., & Wang, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2994440 · Cited by 12
“Generalized descriptors such as LBP [6], SIFT [7], SURF [8], ORB [9], mean projection transform, dual-tree complex wavelets, and Haar-like descriptor [10] are common feature extraction methods.”
MethodA Framework for Inter-camera Association of Multi-target Trajectories by Invariant Target Models
Daliyot, S., & Netanyahu, N. S. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37484-5_31 · Cited by 9
Vietnamese Food Recognition System Using Convolutional Neural Networks Based Features
Ung, H. T., Dang, T., Thai, V.-P., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63007-2_37 · Cited by 10
An improved ORB feature extraction and matching algorithm based on affine transformation
Wang, Z., Ли, Ж., Cheng, L., et al. (2020) · Chinese Automation Congress · doi:10.1109/cac51589.2020.9327165 · Cited by 10
“To this end, SURF algorithm is proposed, which is an improved version of SIFT[5].”
MethodTracking Keypoints from Consecutive Video Frames Using CNN Features for Space Applications
Borse, J. H., Patil, D. D., & Kumar, V. (2021) · Tehnički glasnik · doi:10.31803/tg-20210204161210 · Cited by 10
An Image-Based Framework for Ocean Feature Detection and Analysis
Banesh, D., Petersen, M., Ahrens, J. P., Turton, T. L., Samsel, F., Schoonover, J., & Hamann, B. (2021) · Journal of Geovisualization and Spatial Analysis · doi:10.1007/s41651-021-00085-8 · Cited by 12
Guiding the focus of attention of blind people with visual saliency
Deville, B., Bologna, G., Vinckenbosch, M., & Pun, T. (2008) · Archive ouverte UNIGE (University of Geneva) · Cited by 10
The Intelligent Techniques in Robot KeJia – The Champion of RoboCup@Home 2014
Chen, K., Lu, D., Chen, Y., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-18615-3_11 · Cited by 10
“After this, all the regions are projected into the high quality RGB image, from where SURF [2] features are extracted and computed.”
MethodAUTONOMOUS 3D OBJECT MODELING BY A HUMANOID USING AN OPTIMIZATION-DRIVEN NEXT-BEST-VIEW FORMULATION
Foissotte, T., Stasse, O., Wieber, P.-B., et al. (2010) · International Journal of Humanoid Robotics · doi:10.1142/s0219843610002246 · Cited by 10
Online learning for automatic segmentation of 3D data
Tombari, F., Stefano, L. D., & Giardino, S. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094649 · Cited by 13
3D Human Action Recognition using Hu Moment Invariants and Euclidean Distance Classifier
Al-Azzo, F., Mohammed, A., & Milanova, M. G. (2017) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2017.080403 · Cited by 10
“SURF algorithm (Speeded Up Robust Features) has been presented in [16].”
BackgroundMethodTranslucent Image Recoloring through Homography Estimation
Huang, Y., Wang, C., & Li, C. (2018) · Computer Graphics Forum · doi:10.1111/cgf.13579 · Cited by 10
Schaumberg, A. J., Sirintrapun, S. J., Al‐Ahmadie, H. A., Schüffler, P. J., & Fuchs, T. J. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67834-4_4 · Cited by 13
Toward Massive Scalability in Image Matching
Moraleda, J., & Hull, J. J. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.836 · Cited by 10
“A number of techniques such as SIFT [7] and SURF [1] have been published for the problem of image matching using local descriptors extracted from 2010 International Conference on Pattern Recognition”
LOCAL FEATURE BASED IMAGE SIMILARITY FUNCTIONS FOR KNN CLASSIFICATION
Amato, G. M., & Falchi, F. (2011) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0003185401570166 · Cited by 10
Cooperative anchoring : sharing information about objects in multi-robot systems
LeBlanc, K. A. (2010) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 10
Accurate Vision-based Vehicle Localization using Satellite ImageryPreprint
Chu, H., Mei, H., Bansal, M., & Walter, M. R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1510.09171 · Cited by 15
Content-Based Image Retrieval Based on Late Fusion of Binary and Local DescriptorsPreprint
Ali, N., Mazhar, D. A., Iqbal, Z., Ashraf, R., Ahmed, J., & Khan, F. Z. (2017) · Preprints.org · doi:10.20944/preprints201703.0156.v1 · Cited by 11
Learning Spread-out Local Feature DescriptorsPreprint
Zhang, X., Yu, F. X., Kumar, S., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.06320 · Cited by 10
Deep Online Video StabilizationPreprint
Wang, M., Yang, G.-Y., Lin, J.-K., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.08091 · Cited by 10
Phon-Amnuaisuk, S., Murata, K. T., Pavarangkoon, P., Yamamoto, K., & Mizuhara, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.08675 · Cited by 11
DeepMeshFlow: Content Adaptive Mesh Deformation for Robust Image RegistrationPreprint
Ye, N., Wang, C., Liu, S., Jia, L., Wang, J., & Cui, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.05131 · Cited by 18
Blind Omnidirectional Image Quality Assessment with Viewport Oriented Graph Convolutional NetworksPreprint
Xu, J., Zhou, W., & Chen, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09140 · Cited by 10
P$^{2}$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth EstimationPreprint
Yu, Z., Jin, L., & Gao, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.07696 · Cited by 10
Automatic Targetless LiDAR-Camera Calibration: A SurveyPreprint
Li, X., Xiao, Y., Wang, B., et al. (2022) · Research Square · doi:10.21203/rs.3.rs-2018540/v1 · Cited by 10
OAMatcher: An Overlapping Areas-based Network for Accurate Local Feature MatchingPreprint
Dai, K., Xie, T., Wang, K., Jiang, Z., Li, R., & Zhao, L. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.05846 · Cited by 12
“The conventional detector-based approaches [6]–[19] first extract a set of keypoints, utilize handcrafted [8], [9], [20] or learning-based high-dimension vectors [6], [10]–[13] to describe them, and then implements matching algorithm [21]–[24] to generate This work was in part by National Natural…”
MethodWen, Y., Shah, A. B., Cao, R., Zhang, C., Chen, J., Wu, X., Xie, C., & Fu, X. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3549629 · Cited by 11
“In the past decades, the feature extraction technique has been growing rapidly and the popular methods include SIFT [44], SURF [45], and many others.”
Monocular 3D structure estimation for urban scenes
Nawaf, M. M., & Trémeau, A. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025764 · Cited by 9
“We are motivated by the experimental results indicated in Table 1, which shows a comparison between some selected feature matching methods as, SIFT [12], SURF [13], ORB [14], Lucas-Kanade (LK (Q denotes feature quality)), low level features detection (blobs and corners) with block matching (LF/BM) [3], and dense optic…”
MethodVideo key frame detection based on the restricted Boltzmann machine
Knop, M., Kapuściński, T., & Mleczko, W. K. (2015) · Journal of Applied Mathematics and Computational Mechanics · doi:10.17512/jamcm.2015.3.05 · Cited by 9
“The SURF algorithm is based on SIFT and works much faster because it uses Integral Images rather than Difference of Gaussians [11-14].”
MethodTOWARDS GUIDED UNDERWATER SURVEY USING LIGHT VISUAL ODOMETRY
Nawaf, M. M., Drap, P., Royer, J., Merad, D., & Saccone, M. (2017) · 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-xlii-2-w3-527-2017 · Cited by 9
CONSTRAINED BUNDLE ADJUSTMENT FOR STRUCTURE FROM MOTION USING UNCALIBRATED MULTI-CAMERA SYSTEMS
Huang, D., Elhashash, M., & Qin, R. (2022) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-2-2022-17-2022 · Cited by 9
LPOT: Locality-Preserving Gromov–Wasserstein Discrepancy for Nonrigid Point Set Registration
Wang, G. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3231652 · Cited by 9
“Generally, local features are well studied to match point sets in image feature matching, such as scale-invariant feature transform (SIFT) [10], speeded up robust features (SURF) [11], and learned SuperPoint [12].”
BackgroundAmprimo, G., Rechichi, I., Ferraris, C., & Olmo, G. (2023) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms58004.2023.00293 · Cited by 15
“Feature selection was performed by means of the the Speeded Up Robust Features (SURF) algorithm [25], by selecting only those features with a positive score.”
MethodOn Visual SLAM Algorithm Based on Point-Line Features in Weak Texture Environment
Jiang, X., Yu, F., Song, S., Wang, H., Cheng, W., & Weiyao, Z. (2023) · International Conference on Intelligent Computing and Signal Processing (ICSP) · doi:10.1109/icsp58490.2023.10248681 · Cited by 11
Encrypted Video Search with Single/Multiple Writers
Zheng, Y., Zhang, W., Song, W., Wang, X., & Fu, C. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3643887 · Cited by 11
“Feature extractors, such as SIFT [46], SURF [6], can capture informative and non-redundant features of inputting data, while BoVW [16] clusters similar features to an identical “bag.”
Shi, Z., Shi, H., Yang, K., Yin, Z., Lin, Y., & Wang, K. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10421857 · Cited by 10
IML-Net: A Framework for Cross-View Geo-Localization with Multi-Domain Remote Sensing Data
Yan, Y., Wang, M., Su, N., Hou, W., Zhao, C., & Wang, W. (2024) · Remote Sensing · doi:10.3390/rs16071249 · Cited by 10
EHIR: Energy-based Hierarchical Iterative Image Registration for Accurate PCB Defect Detection
Deng, S., Deng, L., Meng, X., Sun, T., Chen, B., Chen, Z., Hu, H., Xie, Y., Yin, H., & Yu, S. (2024) · Pattern Recognition Letters · doi:10.1016/j.patrec.2024.06.027 · Cited by 12
A Fusion Positioning System Based on Camera and LiDAR for Unmanned Rollers in Tunnel Construction
Huang, H. M., Hu, Y., & Wang, X. (2024) · Sensors · doi:10.3390/s24134408 · Cited by 11
Camera Pose Estimation and Relocalization Algorithm Based on Ground Texture
Sheng, C., Pan, Z., Ye, C., et al. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3428648 · Cited by 9
“It employs speeded-up robust feature (SURF) [16] features and optical flow methods on the visual front end.”
MethodSegIC: Unleashing the Emergent Correspondence for In-Context Segmentation
Meng, L., Lan, S., Li, H., Álvarez, J. M., Wu, Z., & Jiang, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72920-1_12 · Cited by 31
A Deep Learning Approach to Gun Detection in Surveillance System using YOLOv9
Sumi, L., & Dey, S. (2024) · Control Instrumentation System Conference (CISCON) · doi:10.1109/ciscon62171.2024.10696152 · Cited by 9
“Traditional methods of firearm detection often rely on handcrafted features such as Canny edge detectors, Histogram of Oriented Gradients (HOG), Speed-Up Robust Features (SURF), etc. [2], which may struggle to adapt to complex real-world scenarios and variations in firearm appearance.”
MethodNCMNet: Neighbor Consistency Mining Network for Two-View Correspondence Pruning
Liu, X., Qin, R., Yan, J., & Yang, J. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3462453 · Cited by 22
“Given a pair of images, feature key-points and their corresponding descriptors can be obtained by employing existing feature extraction methods, including hand-crafted [7], [8], [9] and learning-based works [10], [11], [12].”
MethodCombination Pattern Method Using Deep Learning for Pill Classification
Kim, S., Park, E.-Y., Kim, J., & Ihm, S.-Y. (2024) · Applied Sciences · doi:10.3390/app14199065 · Cited by 12
“The KAZE algorithm [36] was developed to improve the shortcomings of the conventional Scale-Invariant Feature Transform (SIFT) and Speeded-Up Robust Features (SURF) algorithms [37].”
Tong, X., Feng, Y., Ye, Z., et al. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3498351 · Cited by 9
“Traditional methods, such as SIFT, oriented FAST and rotated BRIEF (ORB) [27], and speeded up robust features (SURF) [28], cannot achieve accurate matching between the descent image and the reference map under the illumination variations [16], [29].”
EC-WAMI: Event Camera-Based Pose Optimization in Remote Sensing and Wide-Area Motion Imagery
Nkrumah, I., Moshrefizadeh, M., Tahri, O., Blasch, E., Palaniappan, K., & Aliakbarpour, H. (2024) · Sensors · doi:10.3390/s24237493 · Cited by 9
Differentiable Product Quantization for Memory Efficient Camera Relocalization
Laskar, Z., Melekhov, I., Benbihi, A., Wang, S., & Kannala, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73013-9_27 · Cited by 13
Metadata
- Authors
- Bay, H., Tuytelaars, T., & Van Gool, L.
- Affiliations
- ETH Zurich (CH)
- KU Leuven (BE)
- ORCID
- Tuytelaars, Tinne
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2006
- Pages
- 404-417
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1677409904
- Semantic Scholar
- 9ad3179098eb9ac7f0c81bf89b6bdcde91752880
- Cited by
- 14,955
- References
- 39
- Citations by year
- 2026: 210 · 2025: 519 · 2024: 727 · 2023: 757 · 2022: 878 · 2021: 975 · 2020: 978 · 2019: 1036 · 2018: 968 · 2017: 976 · 2016: 930 · 2015: 1079 · 2014: 1006 · 2013: 982 · 2012: 884
- FWCI
- 196.80
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Lecture notes in computer science (publishedVersion)
- Lirias (KU Leuven) (submittedVersion, other-oa)
- Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Object Detection Techniques
- Keywords
- SURF, keypoint detection, feature descriptors, scale invariance, rotation invariance, integral image, Hessian matrix, feature matching, object recognition, repeatability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.