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 4,601–4,700 of 14,752
Robust partitioning and indexing for iris biometric database based on local features
Khalaf, E. T., Mohammad, M. N., & Moorthy, K. (2018) · IET Biometrics · doi:10.1049/iet-bmt.2017.0130 · Cited by 12
Copy-move Forgery Detection Using GLCM-Based Rotation-Invariant Feature: A Preliminary Research
Teerakanok, S., & Uehara, T. (2018) · IEEE Annual Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac.2018.10259 · Cited by 12
“The figure shows the results of the key-point search using SURF.”
MethodInfluentialMarkiewicz, J. S., Pilarska, M., Łapiński, S., et al. (2018) · Measurement · doi:10.1016/j.measurement.2018.07.001 · Cited by 12
Khan, S. D. (2013) · Cited by 13
Real-Time 3D Reconstruction in Minimally Invasive Surgery with Quasi-Dense Matching
Zampokas, G., Tsiolis, K., Peleka, G., et al. (2018) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist.2018.8577106 · Cited by 12
“After experimentation, it is concluded that the most efficient approach is Good Features to track proposed by Shi-Tomasi [12].”
MethodGraph-Based Image Matching for Indoor Localization
Manzo, M. (2019) · Machine Learning and Knowledge Extraction · doi:10.3390/make1030046 · Cited by 12
“The method adopted the Speeded Up Robust Features (SURF) method [26] that is robust to recognize landmark.”
MethodCivera, J., & Lee, S. H. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-28603-3_6 · Cited by 12
Texture classification using block intensity and gradient difference (BIGD) descriptor
Hu, Y., Wang, Z., & AlRegib, G. (2020) · Signal Processing Image Communication · doi:10.1016/j.image.2019.115770 · Cited by 13
“Although DMD captures non-quantized patch-based features at multiple scales and orientations, the neglect of first-order gradients may deteriorate the discriminative ability [10][26].”
BackgroundAnomaly Detection of Trackside Equipment Based on GPS and Image Matching
Gao, L., Jiu, Y., Wei, X., Wang, Z., & Xing, W. (2020) · IEEE Access · doi:10.1109/access.2020.2966783 · Cited by 15
Haque, A. S. M. F. A., Rahman, M. R., Marouf, A. A., et al. (2019) · International Conference on Electrical Information and Communication Technology (EICT) · doi:10.1109/eict48899.2019.9068830 · Cited by 12
“Traditional feature descriptors such as local binary pattern (LBP) [8-9], scale invariant feature transform (SIFT) [10], speeded up robust features (SURF) [11], histogram of oriented gradients (HOG) [12] etc. are applied for better classifications.”
BackgroundA Novel Indoor Localization Method Based on Image Retrieval and Dead Reckoning
Qian, J., Cheng, Y., Ying, R., & Liu, P. (2020) · Applied Sciences · doi:10.3390/app10113803 · Cited by 12
High-quality Panorama Stitching based on Asymmetric Bidirectional Optical Flow
Meng, M., & Liu, S. (2020) · International Conference on Computational Intelligence and Applications (ICCIA) · doi:10.1109/iccia49625.2020.00030 · Cited by 16
Dual-View Oracle Bone Script Recognition System via Temporal-Spatial Psychovisual Modulation
Sun, W., Zhai, G., Gao, Z., Chen, T., Zhu, Y., & Wang, Z. (2020) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr49039.2020.00047 · Cited by 14
“Speeded-up robust feature algo-rithm (SURF) [1] is an improved algorithm based on SIFT algorithm.”
MethodExperiments on iris recognition using SURF descriptors, texture and a repetitive method
Ignat, A., & Păvăloi, I. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.08.019 · Cited by 12
Minimal Solvers for Single-View Lens-Distorted Camera Auto-Calibration
Lochman, Y., Dobosevych, O., Hryniv, R. O., & Pritts, J. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00293 · Cited by 12
Fernández, C. I., Haddadi, A., Leblon, B., Wang, J., & Wang, K. (2021) · Remote Sensing · doi:10.3390/rs13030396 · Cited by 12
Visual Features Assisted Robot Localization in Symmetrical Environment Using Laser SLAM
Ge, G., Zhang, Y., Jiang, Q., & Wang, W. (2021) · Sensors · doi:10.3390/s21051772 · Cited by 14
Wang, X., Zhang, K., Zhang, X., Li, S., & Yan, J. (2021) · Infrared Physics & Technology · doi:10.1016/j.infrared.2021.103790 · Cited by 13
The Isowarp: The Template-Based Visual Geometry of Isometric Surfaces
Casillas-Pérez, D., Pizarro, D., Fuentes-Jiménez, D., Mazo, M., & Bartoli, A. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01472-w · Cited by 12
“Theexperimentusesa3Dtemplateandthewarpsarecomputedusing100SURFpointcorrespondences(Bayetal.”
MethodResearch on the Application of Visual SLAM in Embedded GPU
Ma, T., Bai, N., Shi, W., Wu, X., Wang, L., Wu, T. T., & Zhao, C. (2021) · Wireless Communications and Mobile Computing · doi:10.1155/2021/6691262 · Cited by 12
A fast forgery frame detection method for video copy-move inter/intra-frame identification
Zhong, J., Gan, Y., & Yang, J. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03386-4 · Cited by 11
“Compared to SIFT and SURF, the relatively low dimension of the descriptor can also improve the matching efficiency.”
MethodInfluentialThe Functional Correspondence Problem
Lai, Z., Purushwalkam, S., & Gupta, A. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01548 · Cited by 13
Stitching Videos from a Fisheye Lens Camera and a Wide-Angle Lens Camera for Telepresence Robots
Dong, Y., Pei, M., Zhang, L., et al. (2021) · International Journal of Social Robotics · doi:10.1007/s12369-020-00744-8 · Cited by 12
“A keypoint detector and descriptor (e.g., SUFT [2]) is used to obtain feature points from the two video images.”
MethodZhang, W., Lin, S., Bijarbooneh, F. H., Cheng, H.-F., Braud, T., Zhou, P., Lee, L., & Hui, P. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3532202 · Cited by 16
Practical, Fast and Robust Point Cloud Registration for Scene Stitching and Object Localization
Sun, L. (2022) · IEEE Access · doi:10.1109/access.2021.3140105 · Cited by 12
MDN-VO: Estimating Visual Odometry with Confidence
Kaygusuz, N., Méndez, O., & Bowden, R. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636827 · Cited by 15
Foreign Object Detection of Sintering Transport Belt Based on CNN
Xiao, C., Sun, B., Wang, Y., & Qiu, L. (2021) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2021.12.005 · Cited by 12
Li, Z., Yue, J., & Fang, L. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3141101 · Cited by 12
“In summary, we want to to verify the feature robustness, accuracy and advantages of multiple feature combinations in adaptive region amplification, we have selected three remote sensing image configurations: SIFT [16], SURF [19], and RIFT [41].”
MethodContent-Based Image Retrieval Using Angles Across Scales
Sukhia, K. N., Ali, S. S., Riaz, M. M., et al. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3131340 · Cited by 12
Zhang, X., Liao, P., Chen, G., Zhu, K., Tan, X., Wang, T., Li, X., & Wu, H. (2022) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2022.102795 · Cited by 14
Ahmed, K., & Saini, M. (2022) · Signal Image and Video Processing · doi:10.1007/s11760-022-02217-z · Cited by 11
Large Scale Graph-based SLAM Using Aerial Images as Prior Information
Kümmerle, R., Steder, B., Dornhege, C., Kleiner, A., Grisetti, G., & Burgard, W. (2010) · The MIT Press eBooks · doi:10.7551/mitpress/8727.003.0039 · Cited by 10
Object Recognition in High-Resolution Indoor THz SAR Mapped Environment
Batra, A., Sheikh, F., Khaliel, M., Wiemeler, M., Göhringer, D., & Kaiser, T. (2022) · Sensors · doi:10.3390/s22103762 · Cited by 12
Pathmakumar, T., Muthugala, M. A. V. J., Samarakoon, S. M. B. P., et al. (2022) · Sensors · doi:10.3390/s22145317 · Cited by 12
BK tree indexing for active vision-based loop-closure detection in autonomous navigation
Tsintotas, K. A., Sevetlidis, V., Papapetros, I. T., Balaska, V. E., Psomoulis, A., & Gasteratos, A. C. (2022) · Mediterranean Conference on Control and Automation (MED) · doi:10.1109/med54222.2022.9837138 · Cited by 15
Semantic Pose Verification for Outdoor Visual Localization with Self-supervised Contrastive Learning
Orhan, S., Guerrero, J. J., & Baştanlar, Y. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00444 · Cited by 15
Occluded Text Detection and Recognition in the Wild
Raisi, Z., & Zelek, J. (2022) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv55824.2022.00026 · Cited by 15
“They first used SURF [13] to extract futures of the input number image and then compare the extracted future coordinates with the interest points of a database cluster.”
MethodCrime Scene Shoeprint Image Retrieval: A Review
Wu, Y., Dong, X., Shi, G., et al. (2022) · Electronics · doi:10.3390/electronics11162487 · Cited by 12
Varga, D. (2022) · Sensors · doi:10.3390/s22186775 · Cited by 15
Indoor–Outdoor Point Cloud Alignment Using Semantic–Geometric Descriptor
Yang, Y., Fang, G., Miao, Z., et al. (2022) · Remote Sensing · doi:10.3390/rs14205119 · Cited by 12
Huang, W., Li, W., Tang, L., Zhu, X., & Zou, B. (2022) · Sensors · doi:10.3390/s22208027 · Cited by 14
Image Registration Algorithm for Remote Sensing Images Based on Pixel Location Information
Zhang, X., Zhou, Y., Qiao, P., et al. (2023) · Remote Sensing · doi:10.3390/rs15020436 · Cited by 12
Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields
Zhang, M., Zheng, S., Bao, Z., Hebert, M., & Wang, Y.-X. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00086 · Cited by 22
A survey on digital video stabilization
Sarıgül, M. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14726-1 · Cited by 13
COLMAP-SLAM: A FRAMEWORK FOR VISUAL ODOMETRY
Morelli, L., Ioli, F., Beber, R., Menna, F., Remondino, F., & Vitti, A. (2023) · 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-1-w1-2023-317-2023 · Cited by 29
“Performance worsens if descriptors thought for lower computation resources instead of discriminative ones are used, such as ORB (Rublee et al., 2011) or SURF (Bay et al., 2006; Jin et al., 2021).”
Wu, Z., Li, D., Li, C., Chen, Y., & Li, S. (2023) · Applied Sciences · doi:10.3390/app13127027 · Cited by 13
Ensemble Deep Learning Object Detection Fusion for Cell Tracking, Mitosis, and Lineage
Toubal, I. E., Al-Shakarji, N., Cornelison, D., & Palaniappan, K. (2023) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2023.3288470 · Cited by 15
“Appearance features in the classical literature consisted of unsupervised hand-crafted features such as SIFT [37], SURF [5], ORB [60], DCT [20] or others.”
Read It, Don't Watch It: Captioning Bug Recordings Automatically
Feng, S., Xie, M., Xue, Y., & Chen, C. (2023) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse48619.2023.00197 · Cited by 28
“…metric to segment actions from GUI recordings, we compared it with 5 image-processing baselines, including pixel level (e.g, absolute differences ABS [45], color histogram HIST [46]), structural level (e.g., SIFT [47], SURF [48]), and motion-estimation level (e.g., edge detection EDGE [49]).”
Cira, C.-I., Díaz-Álvarez, A., Serradilla, F., & Callejo, M. Á. M. (2023) · Electronics · doi:10.3390/electronics12183980 · Cited by 14
Wang, Z., Zhang, L., Zhao, S., & Zhou, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3323498 · Cited by 13
“To achieve this goal, we extract the SURF (Speeded-Up Robust Features) [55] corners from the occupancy grids, and screen the matching pairs with high similarity according to Lowe’s criterion [56].”
Zero-Shot Traffic Sign Recognition Based on Midlevel Feature Matching
Gan, Y., Li, G., Togo, R., Maeda, K., Ogawa, T., & Haseyama, M. (2023) · Sensors · doi:10.3390/s23239607 · Cited by 12
IRGen: Generative Modeling for Image Retrieval
Zhang, Y., Zhang, T., Chen, D., Wang, Y., Chen, Q., Xie, X., Sun, H., Deng, W., Zhang, Q., Yang, F., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72633-0_2 · Cited by 40
Yang, J., & Gapar, Y. (2024) · ICCK Transactions on Emerging Topics in Artificial Intelligence · doi:10.62762/tetai.2024.115892 · Cited by 13
A Comparative Study of Correspondence-Search Algorithms in MIS Images
Puerto, G. A., & Mariottini, G.-L. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33418-4_77 · Cited by 12
“Note that ACC’s is faster than AMA and DBA for SIFT and SURF, while it becomes dramatically slower than AMA with ASIFT.”
InfluentialImprovement the Bag of Words Image Representation Using Spatial Information
Farhangi, M. M., Soryani, M., & Fathy, M. (2012) · Advances in intelligent systems and computing · doi:10.1007/978-3-642-31552-7_69 · Cited by 13
Towards Fast Image-Based Localization on a City-Scale
Sattler, T., Leibe, B., & Kobbelt, L. P. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34091-8_9 · Cited by 15
Affine transforms between image space and color space for invariant local descriptors
Song, X., Muselet, D., & Trémeau, A. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.01.025 · Cited by 12
Particle Filter Vehicle Tracking Based on SURF Feature Matching
Lu, X., Izumi, T., Teng, L., et al. (2014) · IEEJ Journal of Industry Applications · doi:10.1541/ieejjia.3.182 · Cited by 12
Äniruddha Acharya, K., & Babu, R. V. (2013) · National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) · doi:10.1109/ncvpripg.2013.6776198 · Cited by 12
Expressions invariant face recognition using SURF and Gabor features
Bairagi, B. K., Chatterjee, A., Das, S. C., et al. (2012) · International Conference on Emerging Applications of Information Technology · doi:10.1109/eait.2012.6407888 · Cited by 12
Automatic Weak Calibration of Master-Slave Surveillance System Based on Mosaic Image
Li, Y., Li, S., & Wang, J. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.450 · Cited by 12
Thakoor, K. A., Marat, S., Nasiatka, P. J., McIntosh, B. P., Sahin, F. E., Tanguay, A. R., Weiland, J. D., & Itti, L. (2013) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2013.6618345 · Cited by 12
Video based head detection and tracking surveillance system
Xie, D., Dang, L., & Tong, R. (2012) · International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) · doi:10.1109/fskd.2012.6234136 · Cited by 15
Vision-Aided Inertial Navigation Using Planar Terrain Features
Panahandeh, G., & Jansson, M. (2011) · International Conference on Robot, Vision and Signal Processing · doi:10.1109/rvsp.2011.64 · Cited by 12
“The Matlab OpenSURF Toolbox v0.”
MethodA survey on real-time motion estimation techniques for underwater robots
Ferreira, F., Veruggio, G., Caccia, M., & Bruzzone, G. (2014) · Journal of Real-Time Image Processing · doi:10.1007/s11554-014-0416-z · Cited by 14
A Novel Saliency Detection Method for Lunar Remote Sensing Images
Chen, H.-Z., Jing, N., Wang, J., Yong-guang, C., & Chen, L. (2013) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2013.2244845 · Cited by 12
“The method for extracting SURF points is based on a fast-Hessian detector, as detailed in [15].”
MethodOne-sided Radial-Fundamental Matrix Estimation
Brito, J. H., Zach, C., Koeser, K., et al. (2012) · British Machine Vision Conference (BMVC) · doi:10.5244/c.26.96 · Cited by 12
Global Context Descriptors for SURF and MSER Feature Descriptors
Carmichael, G., Laganière, R., & Bose, P. K. (2010) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2010.47 · Cited by 12
Keypoint descriptor fusion with Dempster–Shafer theory
Mondéjar-Guerra, V. M., Muñoz‐Salinas, R., Marín-Jiménez, M. J., Carmona-Poyato, A., & Medina-Carnicer, R. (2015) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2015.03.001 · Cited by 15
“For each keypoint detected, they compute SIFT and SURF descriptors and combine them by simple concatenation.”
BackgroundMethodInfluentialA Low Complexity Interest Point Detector
Chen, J., Duan, L., Gao, F., et al. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2354237 · Cited by 12
“Bay [14] used box filters and integral images to approximate the Determinant of Hessian of Gaussian scales, thereby saving the convolution operations and differential operations.”
Vehicle logo recognition based on interior structure using SIFT descriptor and neural network
Lipikorn, R., Cooharojananone, N., Kijsupapaisan, S., et al. (2014) · International Conference on Information Science, Electronics and Electrical Engineering · doi:10.1109/infoseee.2014.6946190 · Cited by 12
An Automatic Plant Growth Measurement System for Plant Factory
Chen, W.-T., Yeh, Y.-H. F., Liu, T., et al. (2013) · IFAC Proceedings Volumes · doi:10.3182/20130327-3-jp-3017.00073 · Cited by 12
Informative visual words construction to improve bag of words image representation
Farhangi, M. M., Soryani, M., & Fathy, M. (2014) · IET Image Processing · doi:10.1049/iet-ipr.2013.0449 · Cited by 12
“Furthermore, some may use blob detection algorithms such as difference of Gaussian [5], Harris detector [6] or Hessian matrix [7] to fi nd salient points, which are placed on the corners and edges of the objects [1, 8, 9].”
MethodAn empirical analysis of malicious internet banking software behavior
Gregio, A. R. A., Fernandes, D. S., Afonso, V. M., et al. (2013) · ACM Symposium on Applied Computing · doi:10.1145/2480362.2480704 · Cited by 12
Zhang, J., Tsoi, A. C., & Lo, S. (2014) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2014.6889596 · Cited by 14
Mobile robot localization using multiple observations based on place recognition and GPS
Saito, T., & KURODA, Y. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630776 · Cited by 12
Performance evaluation of a Pose Estimation method based on the SwissRanger SR4000
Hong, S., Ye, C., Bruch, M., et al. (2012) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2012.6283123 · Cited by 12
Exploiting Attitude Sensing in Vision-Based Navigation for an Airship
Mirisola, L. G. B., & Dias, J. M. M. (2009) · Journal of Robotics · doi:10.1155/2009/854102 · Cited by 12
Automatic trademark detection and recognition in sport videos
Ballan, L., Bertini, M., Bimbo, A. D., et al. (2008) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2008.4607581 · Cited by 12
“In this field the two main types of features used are related to shape [1] or are pixel-based [2, 3, 4].”
BackgroundSituation-based indoor wayfinding system for the visually impaired
Ko, E., Ju, J. S., & Kim, E. Y. (2011) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/2049536.2049545 · Cited by 14
Least squares image matching: A comparison of the performance of robust estimators
Li, Z., & Jinling Wang, A. (2014) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-ii-1-37-2014 · Cited by 12
“For example, in the following stereo images pair A and B taken from UAV (Figure 1), SURF and BRISK points are extracted and matched, then filtered by RANSAC.”
MethodCDIKP: A highly-compact local feature descriptor
Tsai, Y., Wang, Q., & You, S. O. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4761099 · Cited by 12
Designing simple indoor navigation system for UAVs
Kara-Mohamed, M., Patra, S., & Lanzon, A. (2011) · 2006 14th Mediterranean Conference on Control and Automation · doi:10.1109/med.2011.5983054 · Cited by 12
“Different algorithms and schemes are developed to excel the feature detection and speed up the matching process [7], [8].”
Real-time traffic sign detection and recognition for in-car driver assistance systems
Oruklu, E., Pesty, D., Neveux, J., et al. (2012) · Conference proceedings · doi:10.1109/mwscas.2012.6292185 · Cited by 12
On computing the average orientation of vectors and lines
Olson, E. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979562 · Cited by 12
“In feature descriptor algorithms like SIFT [2] and SURF [3], a histogram of directions is used to find a canonical orientation to describe a pixel patch.”
MethodRanking by K-Means Voting Algorithm for Similar Image Retrieval
Górecki, P., Sopyła, K., & Drozda, P. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-29347-4_59 · Cited by 12
A nonparametric learning approach to range sensing from omnidirectional vision
Plagemann, C., Stachniss, C., Hess, J., et al. (2010) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2010.02.008 · Cited by 12
Parallel Deep Learning with Suggestive Activation for Object Category Recognition
Varadarajan, K. M., & Vincze, M. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39402-7_36 · Cited by 12
“Primary among these methods include SIFT [1], G-RIF [2], SURF [3], GLOH [4] and MSER [5].”
MethodLiu, C., Fagen, Z., Sun, Y., et al. (2012) · Journal of Navigation · doi:10.1017/s0373463312000264 · Cited by 12
“For a feature-based method, Bay et al., (2006) proposed the Speeded Up Robust Feature (SURF) algorithm based on previous research results by considering the time assumption.”
MethodImage categorization through optimum path forest and visual words
Papa, J. P., & Rocha, A. D. R. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6116475 · Cited by 12
Vehicle bottom anomaly detection algorithm based on SIFT
Gao, X., Wu, Y., Yang, K., & Li, J. (2015) · Optik · doi:10.1016/j.ijleo.2015.08.268 · Cited by 12
On the completeness of feature-driven maximally stable extremal regions
Martins, P., Carvalho, P., & Gatta, C. (2016) · Pattern Recognition Letters · doi:10.1016/j.patrec.2016.01.003 · Cited by 12
“, SIFT (Lowe, 2004), SURF (Bay et al., 2008), or sGLOH (Bellavia et al.”
MethodFast Urban Aerial Image Matching Based on Rectangular Building Extraction
Yang, X., Wang, J., Qin, X., et al. (2015) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2015.2502280 · Cited by 12
Learning and Calibrating Per-Location Classifiers for Visual Place Recognition
Gronát, P., Šivic, J., Obozinski, G., & Pajdla, T. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-015-0878-x · Cited by 13
“First, SURF [1] descriptors are extracted.”
ResultYamazaki, K. (2016) · Autonomous Robots · doi:10.1007/s10514-016-9559-z · Cited by 12
“Although recently developed image features (Bay et al. 2008; Mikolajczyk and Schmid 2004; Lowe 2004) provide highly reliable results in object detection, these features cannot be used directly for clothing because the relevant transformations are assumed to be limited to solid objects.”
BackgroundObject class recognition using combination of color SIFT descriptors
Rassem, T. H., & Khoo, B. E. (2011) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist.2011.5962197 · Cited by 14
Robust visual tracking based on generative and discriminative model collaboration
Dou, J., Qin, Q., & Tu, Z. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3872-6 · Cited by 13
Local Pattern Collocations Using Regional Co-occurrence Factorization
Zou, Q., Ni, L., Wang, Q., Hu, Z., Li, Q., & Wang, S. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2619912 · Cited by 12
“[26] H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded up robust features,” in Proc.”
InfluentialAn efficient wood image retrieval using SURF descriptor
Huang, S., Cai, C., Zhao, F., He, D., & Zhang, Y. (2009) · doi:10.1109/ictm.2009.5413007 · Cited by 13
Integral-image based implementation of U-SURF algorithm for embedded super parallel processor
Sato, Y., Sugimura, T., 野田, 英., et al. (2009) · International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) · doi:10.1109/ispacs.2009.5383795 · Cited by 12
“While U-SURF[1] algorithm is robust and scalable to extract interest points and their features, it requires processes in many regions that are scattered in an image.”
Method
Metadata
- Authors
- Bay, H., Tuytelaars, T., & Van Gool, L.
- Affiliations
- ETH Zurich (CH)
- KU Leuven (BE)
- ORCID
- Tuytelaars, Tinne
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2006
- Pages
- 404-417
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1677409904
- Semantic Scholar
- 9ad3179098eb9ac7f0c81bf89b6bdcde91752880
- Cited by
- 14,955
- References
- 39
- Citations by year
- 2026: 210 · 2025: 519 · 2024: 727 · 2023: 757 · 2022: 878 · 2021: 975 · 2020: 978 · 2019: 1036 · 2018: 968 · 2017: 976 · 2016: 930 · 2015: 1079 · 2014: 1006 · 2013: 982 · 2012: 884
- FWCI
- 196.80
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Lecture notes in computer science (publishedVersion)
- Lirias (KU Leuven) (submittedVersion, other-oa)
- Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Object Detection Techniques
- Keywords
- SURF, keypoint detection, feature descriptors, scale invariance, rotation invariance, integral image, Hessian matrix, feature matching, object recognition, repeatability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.