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 5,201–5,300 of 14,752
Iwamoto, K., Mase, R., & Nomura, T. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738600 · Cited by 10
Full-reference and reduced-reference quality metrics based on SIFT
Farah, J., Hojeij, M.-R., Chrabieh, J., et al. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6853578 · Cited by 11
“For instance, the objective quality measures developed here with the SIFT descriptors could also be tested with other detectors such as SURF [17].”
MethodCompressive Sensing of Time Series for Human Action Recognition
Perez‐Concha, O., Xu, R. Y. D., & Piccardi, M. (2010) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2010.83 · Cited by 12
A Real Time Augmented Reality System Using GPU Acceleration
Tam, D. K., & Fiala, M. A. (2012) · Conference on Computer and Robot Vision (CRV) · doi:10.1109/crv.2012.21 · Cited by 10
Hand posture recognition and tracking based on Bag-of-Words for human robot interaction
Chuang, Y., Chen, L., Zhao, G., et al. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979767 · Cited by 10
Vision aided navigation for unmanned helicopters
Katzourakis, D., Vitzilaios, N. I., & Tsourveloudis, N. C. (2009) · Mediterranean Conference on Control and Automation (MED) · doi:10.1109/med.2009.5164717 · Cited by 10
“Another scheme for feature extractions is the Speeded Up Robust Features (SURF), a high performance algorithm which provides interest point detector and descriptor invariant in scale and rotation [9].”
MethodJiang, G., Liu, L., Zhu, W., Yin, S., & Wei, S. (2015) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/2744769.2744772 · Cited by 13
An iris retrieval technique based on color and texture
Jayaraman, U., Prakash, S., & Gupta, P. (2010) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/1924559.1924572 · Cited by 10
“Following are the two major steps which are followed to compute SURF features of an image.”
MethodInfluentialA hybrid pose tracking approach for handheld augmented reality
Li, J., Slembrouck, M., Deboeverie, F., et al. (2015) · International Conference on Distributed Smart Cameras · doi:10.1145/2789116.2789128 · Cited by 10
Consensus of multiple correspondences between sets of elements
Moreno‐García, C. F., & Serratosa, F. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.08.008 · Cited by 10
Contour model based homography estimation of texture-less planar objects in uncalibrated images
Zhang, Y., Zhou, L., Shang, Y., et al. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.10.023 · Cited by 10
Supervised Machine Learning and Bag of Words applied to Polen Grains Classification
Rodrigues, C. N. M., Gonçalves, A. B., Pistori, H., et al. (2015) · IEEE Latin America Transactions · doi:10.1109/tla.2015.7387260 · Cited by 10
“São usadas técnicas auxiliares denominadas SIFT e SURF [9].”
BackgroundEvaluation of Vision-Based Human Activity Recognition in Dense Trajectory Framework
Kataoka, H., Aoki, Y., Iwata, K., & Satoh, Y. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27857-5_57 · Cited by 10
Vision Based Hand Gesture Recognition: A Review
Simion, G., Gui, V., & Oteşteanu, M. (2013) · Cited by 12
A hardware design of optimized ORB algorithm with reduced hardware cost
Lee, K.-Y., Byun, K., & ETRI (2013) · Advanced Science and Technology Letters · doi:10.14257/astl.2013.43.11 · Cited by 10
SURF based matching for SAR image registration
Durgam, U. K., Paul, S., & Pati, U. C. (2016) · IEEE Students Conference on Electrical, Electronics and Computer Science · doi:10.1109/sceecs.2016.7509292 · Cited by 10
“SURF [8] is a scale and rotation invariant interest point detector and descriptor of images inspired from SIFT.”
BackgroundSample selection for visual domain adaptation via sparse coding
Li, X., Fang, M., Zhang, J.-J., & Wu, J. (2016) · Signal Processing Image Communication · doi:10.1016/j.image.2016.03.009 · Cited by 10
Zadeh, H. G., Haddadnia, J., & Montazeri, A. (2016) · PubMed Central · Cited by 12
Human Action Recognition Based on Multifeature Fusion
Zhang, S., Zhang, W., & Li, Y. (2016) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-2335-4_18 · Cited by 10
[Paper] Image Retrieval with Fisher Vectors of Binary Features
Uchida, Y., Sakazawa, S., & Satoh, S. (2016) · ITE Transactions on Media Technology and Applications · doi:10.3169/mta.4.326 · Cited by 13
A machine vision based autonomous navigation system for Lunar rover: the model and key technique
Li, H., & Zhong, C. (2016) · Sensor Review · doi:10.1108/sr-01-2016-0001 · Cited by 10
Exploiting distinctive topological constraint of local feature matching for logo image recognition
Tang, P., & Peng, Y. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.08.110 · Cited by 10
A Mosaicking Approach for Visual Mapping of Large-Scale Environments
Pinto, A. M., Pinto, H., & Matos, A. C. (2016) · doi:10.1109/icarsc.2016.18 · Cited by 10
“1The SURF [1] feature description was used in this research since it is invariant to scale and rotation, which are relevant characteristics for underwater mosaicking.”
MethodCOnfusion REduction (CORE) algorithm for local descriptors, floating-point and binary cases
Royer, E., Lelore, T., & Bouchara, F. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.01.005 · Cited by 10
Depth image super-resolution via multi-frame registration and deep learning
Tseng, C. W., Su, H., Lai, S., & JenChi, L. (2016) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2016.7820834 · Cited by 10
“SURF feature detector [20] is used to extract features from every color images, and then we match features from other color images to reference using Euclidean distance as matching metric with searching range of 60% of image size.”
MethodRWBD: Learning Robust Weighted Binary Descriptor for Image Matching
Huang, Z., Wei, Z., & Zhang, G. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2656471 · Cited by 12
“Starting from the original SIFT [7], SURF [8] to the recently proposed MROGH [9], Manuscript received June 21, 2016; revised October 6, 2016 and December 14, 2016; accepted January 15, 2017.”
BackgroundMethodLearning-based adaptive tone mapping for keypoint detection
Rana, A., Valenzise, G., & Dufaux, F. (2017) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2017.8019394 · Cited by 10
“Moreover, we use the Matlab’s Computer Vision toolbox for Harris, Shi-Tom, FAST, BRISK and SURF, and Vlfeat for SIFT.”
MethodThree-dimensional hyperspectral imaging technique
Ahlberg, J., Renhorn, I. G. E., Chevalier, T. R., et al. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2262456 · Cited by 10
A NOVEL AND FAST CORNER DETECTION METHOD FOR SAR IMAGERY
Jiao, N., Kang, W., Xiang, Y., et al. (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-w7-605-2017 · Cited by 10
“Lots of research efforts have been devoted to this topic, such as Harris detector (Harris and Stephens, 1988), Hessian detector (Bay et al., 2006), SUSAN detector (MA et al., 2007), FAST detector (Rosten and Drummond, 2006).”
BackgroundFeature-based efficient vehicle tracking for a traffic surveillance system
Sharma, K. (2017) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2017.10.002 · Cited by 10
An object detection and tracking system for unmanned surface vehicles
Li, T., Wang, L., Yang, J. J., et al. (2017) · doi:10.1117/12.2278220 · Cited by 10
Towards Visual Teach and Repeat for GPS-Denied Flight of a Fixed-Wing UAV
Warren, M., Paton, M., MacTavish, K., Schoellig, A. P., & Barfoot, T. D. (2017) · Springer proceedings in advanced robotics · doi:10.1007/978-3-319-67361-5_31 · Cited by 17
“We use oriented Speeded-Up Robust Features (SURF) [4] to detect and describe keypoints and calculate Y based on the octave and Hessian of the response.”
MethodHomography-Based Navigation System for Unmanned Aerial Vehicles
Al-Kaff, A., de la Escalera, A., & Armingol, J. M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70353-4_25 · Cited by 10
SkiMap++: Real-Time Mapping and Object Recognition for Robotics
Gregorio, D. D., Cavallari, T., & Stefano, L. D. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.84 · Cited by 10
Analytically derived fuzzy membership functions
Zhang, W., Kumar, M., Zhou, Y., et al. (2017) · Cluster Computing · doi:10.1007/s10586-017-1503-2 · Cited by 10
“Figure 9 shown an example of image matching by the methods of SURF (implemented in Matlab’s Computer Vision System Toolbox), SIFT (implemented in VL Feat library [32]), fuzzy membership functions based image descriptors [20], and the optimal fuzzy membership functions based image descriptors.”
MethodInfluentialHuang, Z., Gu, N., Hao, J., et al. (2018) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3161409 · Cited by 10
“The widely used approach is to leverage the image matching algorithms (e.g., SIFT [25] or SURF [5]) to recognize the target in the image [11, 36].”
MethodTowards real-time surface tracking and motion compensation integration for robotic surgery
Lindgren, K., Huang, K. J., & Hannaford, B. (2017) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2017.8279262 · Cited by 10
Comparative analysis of SIFT and SURF on KLT tracker for UAV applications
Micheal, A. A., & Vani, K. (2017) · International Conference on Communications and Signal Processing (ICCSP) · doi:10.1109/iccsp.2017.8286523 · Cited by 10
UAS Navigation with SqueezePoseNet—Accuracy Boosting for Pose Regression by Data Augmentation
Mueller, M., & Jutzi, B. (2018) · Drones · doi:10.3390/drones2010007 · Cited by 10
“CNNs solve image matching tasks, where Hand-made Features such as Scale Invariant Feature Transform (SIFT) [7], Oriented FAST and rotated BRIEF (ORB) [8] or Speeded Up Robust Features (SURFs) [9] might fail due to less descriptive features.”
Robust fingerprint verification for enhancing security in healthcare system
Jahan, S., Chowdhury, M., & Islam, R. (2017) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2017.8402502 · Cited by 11
“in 2006 [16].”
Face Recognition: Novel Comparison of Various Feature Extraction Techniques
Makhija, Y., & Sharma, R. S. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-0761-4_110 · Cited by 10
Multiple Subspace Alignment Improves Domain Adaptation
Thopalli, K., Anirudh, R., Thiagarajan, J. J., & Turaga, P. K. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682420 · Cited by 10
“For both SURF and Decaf representations, we repeated the adaptation experiments for all the 12 cases.”
MethodInfluentialChen, Z., Sheng, W., Yang, G., Su, Z., & Bao-juan, L. (2018) · World Congress on Intelligent Control and Automation · doi:10.1109/wcica.2018.8630714 · Cited by 14
Relative Altitude Estimation Using Omnidirectional Imaging and Holistic Descriptors
Berenguer, Y., Payá, L., Valiente, D., Peidró, A., & Reinoso, Ó. (2019) · Remote Sensing · doi:10.3390/rs11030323 · Cited by 10
An Improved ORB Feature Point Matching Algorithm
Zhang, Y., Li, C., Cao, C., & Gao, Y. (2018) · doi:10.1145/3297156.3297184 · Cited by 14
Cloud-Based Image Retrieval Using GPU Platforms
Mahmoudi, S. A., Belarbi, M. A., Dadi, E. W., et al. (2019) · Computers · doi:10.3390/computers8020048 · Cited by 10
“In the literature, several methods and algorithms can be applied for content-based image retrieval systems such as invariant features (SIFT [2] and SURF [3]), points of interest, contours and mean projection transform.”
InfluentialMethods of Mobile Robot Visual Navigation and Environment Mapping
Pershina, J. S., Kazdorf, S. Y., & Лопота, А. В. (2019) · Optoelectronics Instrumentation and Data Processing · doi:10.3103/s8756699019020109 · Cited by 11
“To describe local neighborhoods of point features in an image, one often uses descriptors such as SURF [16], SIFT [17], BRIEF [18], ORB [19], et al. One of the fastest and most reliable algorithms for matching point features is the nearest neighbor search (NNS) algorithm, which has higher…”
MethodComparative Study of Various Feature Extraction Techniques for Pedestrian Detection
Hiranmai, M., Niranjana Krupa, B., & Nagaraj, H. K. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.06.098 · Cited by 10
Beyond SIFT using binary features in Loop Closure Detection
Han, L., Zhou, G., Xu, L., & Fang, L. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206261 · Cited by 11
Object detection algorithm based AdaBoost residual correction Fast R-CNN on network
Lin, M., Chen, C., & Lai, C. (2019) · International Conference on Deep Learning Technologies (ICDLT) · doi:10.1145/3342999.3343013 · Cited by 10
Jointly Aligning Millions of Images With Deep Penalised Reconstruction Congealing
Annunziata, R., Sagonas, C., & Calì, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00017 · Cited by 11
“, SIFT [29], HOG [11], SURF [5], SCIRD [2, 4]),”
Feature‐assisted stereo correlation
Thiruselvam, N. I., & Subramanian, S. J. (2019) · Strain · doi:10.1111/str.12315 · Cited by 10
Improving CNN-based Planar Object Detection with Geometric Prior Knowledge
Cai, J., Hou, J., Lu, Y., Chen, H., Kneip, L., & Schwertfeger, S. (2020) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr50563.2020.9292601 · Cited by 15
Li, Z., Dong, Z., Yu, A., et al. (2019) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2019.8899848 · Cited by 10
“Aiming at computation speed, a novel method, coined Speeded Up Robust Feature (SURF) is presented in [6].”
MethodPreserving Spatial Information to Enhance Performance of Image Forgery Classification
Phan-Xuan, H., Le-Tien, T., Nguyen-Chinh, T., Do-Tieu, T., Nguyen-Van, Q., & Nguyen-Thanh, T. (2019) · International Conference on Advanced Technologies for Communications · doi:10.1109/atc.2019.8924504 · Cited by 11
Video stitching based on multi-view spatiotemporal feature points and grid-based matching
Krishnakumar, K., & Gandhi, S. I. (2019) · The Visual Computer · doi:10.1007/s00371-019-01780-w · Cited by 11
“In the method proposed by Greet Williams et al. [28], features are localized in the spatiotemporal domain using the determinant of the Hessian et al. [2].”
MethodEdge-Preserving Stereo Matching Using Minimum Spanning Tree
Zhang, C., He, C., Chen, Z., Liu, W., Li, M., & Wu, J. (2019) · IEEE Access · doi:10.1109/access.2019.2958527 · Cited by 11
Deep Learning for Biometric Face Recognition: Experimental Study on Benchmark Data Sets
Selitskaya, N., Sielicki, S., Jakaite, L., Schetinin, V., Evans, F., Conrad, M., & Sant, P. (2020) · Unsupervised and semi-supervised learning · doi:10.1007/978-3-030-32583-1_5 · Cited by 14
Loop Closure Detection Based on Improved Hybrid Deep Learning Architecture
Liu, Y., Xiang, R., Zhang, Q., Ren, Z., & Cheng, J. T. (2019) · International Conference on Ubiquitous Computing and Communications (IUCC) · doi:10.1109/iucc/dsci/smartcns.2019.00079 · Cited by 10
Mobile Robot Self-LocalizationUsing Visual Odometry Based on Ceiling Vision
Lin, Q., Liu, X., & Zhang, Z. (2019) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci44817.2019.9003092 · Cited by 10
Improved covariant local feature detector
Huo, Z., Zhang, Y., Liu, H., Wang, J., Liu, X., & Zhang, J. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.03.027 · Cited by 11
Survey on Scene Classification techniques
Patel, T., Dabhi, V. K., & Prajapati, H. B. (2020) · International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs48705.2020.9074460 · Cited by 11
An automatic image matching algorithm based on thin plate splines
Atik, M. E., Öztürk, O., Duran, Z., et al. (2020) · Earth Science Informatics · doi:10.1007/s12145-020-00476-3 · Cited by 10
“Thus, Bay et al. (2006) call it the ‘ Fast Hessian ’ detector.”
BackgroundShoitan, R., Moussa, M. M., & Elshoura, S. M. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09258-x · Cited by 10
“SURF [4] is a scale and rotation independent feature detector and descriptor, which is used to find feature points in an image and describe them.”
BackgroundImage Feature Learning with Genetic Programming
Ruberto, S., Terragni, V., & Moore, J. H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58115-2_5 · Cited by 12
UI Screens Identification and Extraction from Mobile Programming Screencasts
Alahmadi, M. D., Malkadi, A., & Haiduc, S. (2020) · International Conference on Program Comprehension · doi:10.1145/3387904.3389265 · Cited by 11
“We apply the feature descriptor SURF (see Section 2.1) on all n frames in the video to extract keypoints in each frame and the feature vectors that describe them.”
BackgroundInfluentialReliability Validation of Learning Enabled Vehicle Tracking
Sun, Y., Zhou, Y., Maskell, S. R., Sharp, J. J., & Huang, X. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196932 · Cited by 11
WA VIS: A Web-Based Augmented Reality Text Data Visual Analysis Tool
Pei, Y., Wu, Y., Wang, S., et al. (2019) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv47840.2019.00011 · Cited by 10
Salo, R. A., Belevich, I. N., Jokitalo, E., Gröhn, O. H. J., & Sierra, A. (2020) · NeuroImage · doi:10.1016/j.neuroimage.2020.117529 · Cited by 15
Liu, W., Lai, B., Wang, C., Cai, G., Su, Y., Bian, X., Li, Y., Chen, S., & Li, J. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3035359 · Cited by 12
Automatic Matching of Multispectral Images Based on Nonlinear Diffusion of Image Structures
Li, R., Zhao, H., Zhang, X., et al. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3043379 · Cited by 10
An, J., Meng, F., & Yan, Z.-J. (2021) · BioData Mining · doi:10.1186/s13040-021-00242-1 · Cited by 8
Learning to Distill Convolutional Features into Compact Local Descriptors
Lee, J., Jeong, Y., Kim, S., Min, J., & Cho, M. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00094 · Cited by 14
“The most well-known traditional local descriptor extraction approaches include SIFT [37], SURF [3], HOG [8, 37] and BRIEF [31].”
MethodLocalization Using Single Camera and Lidar in GPS-Denied Environments
Lezki, H., & Yetik, İ. Ş. (2020) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu49456.2020.9302512 · Cited by 10
Retinal image registration using log-polar transform and robust description of bifurcation points
Saha, S., Rahaman, G. M. A., Islam, T., et al. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102424 · Cited by 10
An Efficient Algorithm for Generating Harmonized Stereoscopic 360° VR Images
Nam, D.-Y., & Han, J.-K. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3056065 · Cited by 10
Soleimani, P., Capson, D. W., & Li, K. F. (2021) · Journal of Real-Time Image Processing · doi:10.1007/s11554-021-01089-9 · Cited by 10
“Scale invariant feature transform (SIFT) [1] and speeded up robust features (SURF) [2] are two popular multi-scale feature detector and descriptor algorithms.”
MethodAn efficient robust method for accurate and real-time vehicle plate recognition
Pirgazi, J., Sorkhi, A. G., & Kallehbasti, M. M. P. (2021) · Journal of Real-Time Image Processing · doi:10.1007/s11554-021-01118-7 · Cited by 13
“Some other algorithms employ keypoint localization like SIFT [34] and SUF [35].”
MethodRobust LIDAR-Based Localization in Underground Mines
Nielsen, K. (2021) · Linköping studies in science and technology. Thesis · doi:10.3384/lic.diva-175001 · Cited by 15
The DEVIL is in the Details: A Diagnostic Evaluation Benchmark for Video Inpainting
Szeto, R. B., & Corso, J. J. (2022) · 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/cvpr52688.2022.02038 · Cited by 10
Matching as Color Images: Thermal Image Local Feature Detection and Description
Deshpande, B., Hanamsheth, S., Lu, Y., & Lu, G. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414341 · Cited by 11
“BRIEF [7], SIFT [1], SURF [2], ORB [3], FAST [8] and WADE [9] algorithms are able to detect some features in thermal images but the quality of detection is rather unsatisfactory.”
MethodEnhancing two-view correspondence learning by local-global self-attention
Dai, L., Liu, X., Liu, Y., Yang, C., Wei, L., Lin, Y., & Chen, R. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.06.084 · Cited by 12
Gunshot Sound Measurement and Analysis
Tardif, B., Lo, D., & Goubran, R. A. (2021) · IEEE Sensors Applications Symposium (SAS) · doi:10.1109/sas51076.2021.9530145 · Cited by 10
Li, X., Zhu, J., Shi, H., et al. (2021) · Scientific Programming · doi:10.1155/2021/3965247 · Cited by 10
Zhou, X., Yu, C., Yuan, X., & Luo, C. (2021) · Sensors · doi:10.3390/s21217043 · Cited by 15
Towards Ontology-based Autonomous Intralogistics for Agile Remanufacturing Production Systems
Klein, J.-F., Wurster, M., Stricker, N., Lanza, G., & Furmans, K. (2021) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa45728.2021.9613486 · Cited by 19
TCL: Tightly Coupled Learning Strategy for Weakly Supervised Hierarchical Place Recognition
Shen, Y., Wang, R., Zuo, W., & Zheng, N. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3141663 · Cited by 10
Automobile Instrument Detection Using Prior Information and Fuzzy Sets
Zhang, J., Liu, Y., Yu, J., et al. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3135523 · Cited by 10
A Unified B-Spline Framework for Scale-Invariant Keypoint Detection
Zheng, Q., Gong, M., You, X., & Tao, D. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-021-01568-3 · Cited by 10
“The analysis of eigenvalues of the Hessian has been applied to detect blob (Bay et al. 2006) and line structures (Lorenz et al. 1997).”
BackgroundMethodInfluentialFiltering Deep Convolutional Features for Image Retrieval
Zhang, B.-J., Liu, G., & Hu, J.-K. (2022) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001422520036 · Cited by 10
Region-based adaptive association learning for robust image scene recognition
Lv, G., Dong, L., Zhang, W., & Xu, W. (2022) · The Visual Computer · doi:10.1007/s00371-022-02433-1 · Cited by 9
Air-Ground Multi-Source Image Matching Based on High-Precision Reference Image
Zhang, Y., Ma, G., & Wu, J. (2022) · Remote Sensing · doi:10.3390/rs14030588 · Cited by 11
HD Ground - A Database for Ground Texture Based Localization
Schmid, J. F., Simon, S. F., Radhakrishnan, R., et al. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811977 · Cited by 10
“Chen et al. [3] developed StreetMap, which is based on SURF [12] features and treats global and local localization separately.”
MethodPerformance Comparison of Feature Detectors on Various Layers of Underwater Acoustic Imagery
Zhou, X., Yuan, S., Yu, C., et al. (2022) · Journal of Marine Science and Engineering · doi:10.3390/jmse10111601 · Cited by 10
Corn Plant Disease Identification Using SURF-based Bag of Visual Words Feature
Dijaya, R., Suciati, N., & Saikhu, A. (2022) · doi:10.1109/icitee56407.2022.9954084 · Cited by 10
“The image features and descriptors were retrieved using the SURF detector and descriptor approach established by Bay et al [15].”
MethodClassification of multi-spectral data with fine-tuning variants of representative models
Lakshmi, T. R. V., Reddy, C. V. K., Kora, P., Swaraja, K., Meenakshi, K., Kumari, C. U., & Reddy, L. P. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16291-z · Cited by 16
A method for image-based shadow interaction with virtual objects
Ha, H., & Ko, K. H. (2014) · Journal of Computational Design and Engineering · doi:10.1016/j.jcde.2014.11.003 · Cited by 10
Comparison of Statistical Features for Medical Colour Image Classification
Ruberto, C. D., Fodde, G., & Putzu, L. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-20904-3_1 · Cited by 10
Image Abstraction in Crossmedia Retrieval for Text Illustration
Coelho, F., & Ribeiro, C. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-28997-2_28 · Cited by 8
Bag-of-Features Codebook Generation by Self-Organisation
Kinnunen, T., Kämäräinen, J., Lensu, L. T., & Kalviainen, H. A. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02397-2_15 · 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.