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 9,101–9,200 of 14,752
Sarhan, S. S., Hamad, S., & Elmougy, S. (2016) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661816030184 · Cited by 3
Sachdev, K., Kaur, M., & Gupta, S. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-981-10-1708-7_91 · Cited by 3
Automatic control and digital correction of scale and rotation mismatch in stereo pairs
Chafonova, V., Варисовна, Г. И., & Tihomirova, G. V. (2016) · Computer Optics · doi:10.18287/2412-6179-2016-40-1-112-120 · Cited by 3
COMPARISON OF 3D REALITY CAPTURE TECHNOLOGIES FOR THE SURVEY OF STONE WALLS
Valero, E., Forster, A. M., Bosché, F., et al. (2016) · doi:10.4995/arqueologica8.2016.2582 · Cited by 3
Real Time Object Detection & Tracking over a Mobile Platform
Mekhtiche, M. A., Bencherif, M. A., Algabri, M., et al. (2016) · Indian Journal of Science and Technology · doi:10.17485/ijst/2015/v8i32/92131 · Cited by 3
Pose estimation of landscape images using DEM and orthophotos
Produit, T., Tuia, D., Golay, F., et al. (2012) · doi:10.1109/cvrs.2012.6421262 · Cited by 3
Point-cloud registration using 3D shape contexts
Price, M., Green, J., & Dickens, J. (2012) · doi:10.1109/robomech.2012.6558468 · Cited by 3
“In 2D, methods such as SIFT [10] and SURF [11] achieve this by generating a multi-resolution image pyramid and selecting keypoints that are consistent over a range of scales.”
MethodOriginal Image Tracing with Image Relational Graph for Near-Duplicate Image Elimination
Huang, F. L., Zhou, Z., Liu, T., et al. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48674-1_29 · Cited by 3
Mobile manipulation and visual servoing design of a configurable mobile manipulator
Song, K., Jiang, S.-Y., Wu, C.-J., et al. (2013) · doi:10.1109/cacs.2013.6734139 · Cited by 3
An empirical evaluation of local descriptors in object recognition
Rani, R., Kumar, R., & Singh, A. P. (2016) · International Conference on Advances in Computing, Communications and Informatics (ICACCI) · doi:10.1109/icacci.2016.7732263 · Cited by 3
“Ke and Sukthankar [19] presented the better version of SIFT's descriptor i.e; PCA-SIFT.”
MethodUsing semantic maps for room recognition to aid visually impaired people
Liu, Q., Li, R., Hu, H., & Gu, D. (2016) · International Conference on Automation and Computing (ICAC) · doi:10.1109/iconac.2016.7604900 · Cited by 3
“1) Feature Extraction: In our system, we adopt SURF (Speeded up Robust Features) [23] for both mapping and object recognition.”
MethodChifa, N., Badri, A., Ruichek, Y., et al. (2016) · Studies in computational intelligence · doi:10.1007/978-3-319-46245-5_5 · Cited by 3
Robustness of interest point detectors in near infrared, far infrared and visible spectral images
Molina, A., Ramirez, T., & Díaz, G. M. (2016) · Symposium on Image, Signal Processing and Artificial Vision (STSIVA) · doi:10.1109/stsiva.2016.7743321 · Cited by 3
“In order to accomplish scale–space analysis after previous process, SURF found interest points, by interpolating the maxima of the determinant of the Hessian matrix in scale and image space, due to the large difference in scale of firsts layers with every octave.”
MethodInfluentialBinary Data Comparison using Similarity Indices and Principal Components Analysis
Kane, N., Aznag, K., Oirrak, A. E., et al. (2016) · The International Arab Journal of Information Technology · Cited by 3
Real-time autonomous multi resolution visual surveys based on seafloor scene complexity
Otsuki, Y., Thornton, B., Maki, T., et al. (2016) · IEEE/OES Autonomous Underwater Vehicles · doi:10.1109/auv.2016.7778692 · Cited by 3
Performance Evaluation of an Accessory Category Recognition System Using Deep Neural Network
Sakai, Y., Oda, T., Ikeda, M., et al. (2016) · International Conference on Network-Based Information Systems · doi:10.1109/nbis.2016.51 · Cited by 3
“The system was based on local feature extraction methods, such as Scale Invariant Feature Transform (SIFT) [18]–[20] and Speed Up Robust Features (SURF) [21], [22] methods for extracting the feature points.”
MethodImproving the Discriminative Power of Bag of Visual Words Model
Ouni, A., Urruty, T., & Visani, M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-51814-5_21 · Cited by 3
Global motion compensated visual attention-based video watermarking
Oakes, M., Bhowmik, D., & Abhayaratne, C. (2016) · Journal of Electronic Imaging · doi:10.1117/1.jei.25.6.061624 · Cited by 3
“38 Speeded up robust features detection 39 could be used to directly align key feature points between consecutive frames, but this would be very computationally exhaustive.”
Fast-Gaussian SIFT and its hardware architecture for keypoint detection
Liu, K., Wang, J., Zhao, X., et al. (2016) · IEEE Asia Pacific Conference on Circuits and Systems (APCCAS) · doi:10.1109/apccas.2016.7803996 · Cited by 3
“4 shows the proposed hardware architecture with the design specification [octave, extrema-scale] = [2, 2].”
BackgroundMethodInfluentialFaraz, K., Blondel, W., Amouroux, M., & Daul, C. (2016) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2016.7821014 · Cited by 4
Autonomous Mobile Robot Navigation Using Scene Matching with Local Features
Shioya, T., Kogure, K., Iwata, T., et al. (2016) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2016.p0887 · Cited by 3
Seo, J. (2016) · Deep Blue (University of Michigan) · Cited by 6
Rapid, automated mosaicking of the human corneal subbasal nerve plexus
Vaishnav, Y. J., Rucker, S. A., Saharia, K., & McNamara, N. A. (2017) · Biomedizinische Technik/Biomedical Engineering · doi:10.1515/bmt-2016-0148 · Cited by 3
Real-time 3D work-piece tracking with monocular camera based on static and dynamic model libraries
Zhu, W., Wang, P., Li, R., & Nie, X. (2017) · Assembly Automation · doi:10.1108/aa-02-2017-018 · Cited by 3
“Point features including SIFT (Lowe, 2004), SURF (Bay et al., 2006), BRISK (Leutenegger et al., 2011) and ORB (Rublee et al., 2011) have good performance for those objects with rich texture, but tend to fail where there are few points that can be detected.”
MethodReconstruction of 3D Models Consisting of Line Segments
Ienaga, N., & Saitô, H. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54427-4_8 · Cited by 3
“To achieve the matching of feature points, techniques, such as scale-invariant feature transform [3] or speeded up robust features [4], are often used.”
MethodSolve Classification Tasks with Probabilities. Statistically-Modeled Outputs
Gritsenko, A., Eirola, E., Schupp, D., Ratner, E. R., & Lendasse, A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59650-1_25 · Cited by 3
Indoor visual localization of a wheelchair using Shi-Tomasi and KLT
Lima, M. V. P., Kurka, P. R. G., Silva, Y. M. L. R., et al. (2017) · IEEE Canadian Conference on Electrical and Computer Engineering (CCECE) · doi:10.1109/ccece.2017.7946816 · Cited by 3
“A variety of algorithms can perform reliable detection of features, such as the Shi-Tomasi[4] and Harris[5] corner detectors and the SIFT[6] and SURF[7] detectors of bubbles.”
MethodSoftware architecture for an exploration robot based on Urbi
Baillie, J.-C., Demaille, A., Duceux, G., et al. (2011) · Cited by 3
Amin, M., Tanveer, T. A., Shah, S., Abdullah, M., & Shafi, M. (2017) · Cluster Computing · doi:10.1007/s10586-017-1010-5 · Cited by 4
“3 due to the fact that feature detectors like SIFT, SURF, BoW uses handcrafted features.”
BackgroundInfluentialCoordinated robotic system for civil structural health monitoring
Qidwai, U. A., & Akbar, M. A. (2017) · MATEC Web of Conferences · doi:10.1051/matecconf/201712001003 · Cited by 3
Nakagawa, M., Akano, K., Kobayashi, T., et al. (2017) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-iv-2-w4-349-2017 · Cited by 3
“In our experiments, we used SURF to achieve both high-speed processing and high stability, because our algorithm may allow mismatching in feature matching.”
BackgroundMethodInfluentialImproved pose estimation by inlier refinement for visual odometry
More, R., Kottath, R., Jegadeeshwaran, R., Kumar, V., Karar, V., & Poddar, S. (2017) · International Conference on Sensing, Signal Processing and Security (ICSSS) · doi:10.1109/ssps.2017.8071595 · Cited by 4
Real-Time Color Object Recognition and Navigation for QUARC QBOT2
Obaid, W., Rabie, T. F., & Baziyad, M. (2017) · International Conference on Computer and Applications (ICCA) · doi:10.1109/comapp.2017.8079758 · Cited by 3
Ду, С., & Ikenaga, T. (2017) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.e100.a.2275 · Cited by 3
Implementation of an Image Stitching Algorithm to a Low-Cost Digital Microscope
Botan, R., Côco, K. F., & Komati, K. S. (2017) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2017.44 · Cited by 3
“One of the downsides of SURF is that it is not very robust against light variations and changes in points of view [14] when compared to the Scale-Invariant Feature Transform (SIFT) algorithm [15].”
MethodResultAl-Hussaini, I., Islam, Z., Mallick, A., & Hoque, M. E. (2017) · IEEE International Conference on Signal and Image Processing Applications (ICSIPA) · doi:10.1109/icsipa.2017.8120613 · Cited by 3
“SURF is also rotation invariant.”
MethodInfluentialLidiawaty, B. R., Ramadijanti, N., & Ningrum, E. S. (2017) · doi:10.1109/kcic.2017.8228577 · Cited by 3
“Equation (2) is the characteristic when the camera moves to the right.”
BackgroundAuthenticity inspection by image recognition using feature point matching
Inoue, R., Goto, T., & Hirano, S. (2017) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce.2017.8229296 · Cited by 3
“SIFT Features The Scale Invariant Feature Transform (SIFT) [2, 3] is a matching method for detecting features that are invariant to scale change and rotation of images.”
MethodVideoGIS data retrieval based on multi-feature fusion
Dai, H., Hu, B. X., Cui, Q., et al. (2017) · International Conference on Intelligent Systems and Knowledge Engineering (ISKE) · doi:10.1109/iske.2017.8258831 · Cited by 3
“[18] propose the famous SURF feature, the dimension of the feature point descriptor is reduced by improving the SIFT algorithm, which is significantly improved in feature extraction and matching speed compared with the SIFT algorithm.”
MethodFast integral image computing scheme for vision based applications
Kumar, S., Kumar, P., & Pandey, S. (2017) · IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics (UPCON) · doi:10.1109/upcon.2017.8251098 · Cited by 3
Cascading classifier with discriminative multi-features for a specific 3D object real-time detection
Wang, R., Liang, Y., Xu, J. W., & He, Z. H. (2018) · The Visual Computer · doi:10.1007/s00371-018-1472-3 · Cited by 3
“15 Precision–recall curves showing the performance of the proposed method and that of the method in [34]”
MethodInfluentialPortable 3-D modeling using visual pose tracking
Strobl, K. H., Mair, E., Bodenmüller, T., Kielhöfer, S., Wüsthoff, T., & Suppa, M. (2018) · Computers in Industry · doi:10.1016/j.compind.2018.03.009 · Cited by 3
Employing Kaze Features for the Purpose of Emotion Recognition
Vaish, A., & Gupta, S. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-10-7871-2_65 · Cited by 3
A study on near-real-time geometric correction system of drones image
Jin, C. M., Young, K. T., Seob, L. M., et al. (2018) · International Conference on Information Networking · doi:10.1109/icoin.2018.8343087 · Cited by 3
Recognizing Human Activities in Videos Using Improved Dense Trajectories over LSTM
Singh, K. K., & Mukherjee, S. (2018) · Communications in computer and information science · doi:10.1007/978-981-13-0020-2_8 · Cited by 3
Recurrent neural network based virtual detection line
Kadiķis, R. (2018) · International Conference on Machine Vision · doi:10.1117/12.2309772 · Cited by 3
“Versatile and widely used feature descriptors include SIFT [10], SURF [11] and ORB [12].”
MethodFull Representation Data Embedding via Nonoverlapping Historical Features
Shan, J., Hou, C., Tao, H., et al. (2018) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2837675 · Cited by 3
Feng, D., Xu, K., Mi, H., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-97289-3_9 · Cited by 3
Combining Multiple Features for Product Categorisation by Multiple Kernel Learning
Chavaltada, C., Pasupa, K., & Hardoon, D. R. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-93692-5_1 · Cited by 6
Pedersen, B., Bailey, D. G., Hodgson, R. M., Holt, K. A., & Marsland, S. (2017) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2017.8402498 · Cited by 6
“A peak accuracy of 86% when using a K nearest or voting classifier was achieved with the LBP + SURF set.”
MethodInfluentialA Novel Approach for Face Authentication Using Speeded Up Robust Features Algorithm
Mendoza-Martinez, C., Pedraza‐Ortega, J. C., & Ramos-Arreguín, J. M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13647-9_33 · Cited by 3
“The most common algorithms used in this field are LDA and PCA [4], SIFT [5] and SURF [6].”
BackgroundMethodResultInfluentialHsu, Y., Chang, S.-Y., & Guo, J.-I. (2018) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-china.2018.8448869 · Cited by 3
“(3), we define a weighted score between the detection and the trackers.”
BackgroundThe Information Fusion of the IR and UV Image for the Insulation Fault Diagnosis
Ai, J., Ma, L., Gao, K., et al. (2018) · International Conference on Information Fusion (FUSION) · doi:10.23919/icif.2018.8455224 · Cited by 3
“SURF is an improved algorithm of SIFT.”
MethodInfluentialA Novel Method of Object Identification and Tagging Using Speeded-Up Robust Feature
Roy, L. K., & Kv, R. (2018) · doi:10.1109/icicct.2018.8473150 · Cited by 3
“stages namely, Interest point detection, SURF descriptor [9][10] and Matching where the system is expected to extract the main key points from the particular input image.”
BackgroundZhou, W., Chen, Y., & Liang, S. (2018) · Applied Sciences · doi:10.3390/app8102006 · Cited by 3
An Optimization of Video Sequence Stitching Method
Yu, H., & Kong, L. (2018) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2018.8484309 · Cited by 3
“The full name of SURF is Speeded-Up Robust Features[14].”
BackgroundLearned Invariant Feature Transform and Extreme Learning Machines for Face Recognition
Vinay, A., Hegde, N. S., Tejas, S. K., et al. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-1595-4_23 · Cited by 3
Keyframe-based Local Normal Distribution Transform Occupancy Maps for Environment Mapping
Belter, D., Piaskowski, K., & Staszak, R. (2018) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2018.8502517 · Cited by 3
A Novel Kinect V2 Registration Method Using Color and Deep Geometry Descriptors
Gao, Y., Michels, T., & Koch, R. (2018) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2018.8553327 · Cited by 3
“4) Interest Point Detection: The Speeded Up Robust Features (SURF) have robust and stable performance in computer vision and robotics applications [27].”
BackgroundA New Retrieval System Based on Low Dynamic Range Expansion and SIFT Descriptor
Khwildi, R., & Zaid, A. O. (2018) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2018.8547089 · Cited by 3
“Among the well-known methods, used for describing the invariant interest points, we can mention SIFT [2], SURF [5], BRISK [6], FREAK [7] and ORB [8].”
MethodEdge-Based Loop Closure Detection in Visual SLAM
Mendieta, D. F., Capua, F. R., Tarrio, J., & Moreyra, M. L. (2018) · Argentine Conference on Automatic Control (AADECA) · doi:10.23919/aadeca.2018.8577273 · Cited by 3
“Los algoritmos como SIFT y SURF, ampliamente populares en la comunidad, permiten obtener descriptores robustos por su invariancia a la luz, escala y rotación.”
BackgroundInfluentialMatching Risk for Feature Selection in Visual SLAM
Kim, C.-H., Lee, T.-J., & Cho, D. (2018) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2018.11.532 · Cited by 3
Outlier Detection using Hierarchical Spatial Verification for Visual Place Recognition
Yuan, M., Li, Z. G., Wan, K.-W., & Yau, W. (2018) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2018.8581070 · Cited by 3
An Effective Dual-Fisheye Lens Stitching Method Based on Feature Points
Li, Y., Ya, L., Zhu, C., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-05710-7_55 · Cited by 3
Multilevel Interpolation for Feature-based Motion Correction in Neurosurgery
Chen, F., Müller, J., Müller, J., et al. (2018) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas.2018.8584666 · Cited by 3
“In this work, three different feature detectors and descriptors methods have been applied: SIFT [11], SURF [12] and FAST [13] in combination with BRIEF [14].”
MethodInfluentialGökçe, B., & Sonugür, G. (2018) · Afyon Kocatepe University Journal of Sciences and Engineering · doi:10.5578/fmbd.67513 · Cited by 3
Hierarchical Inspection System Using Visual and MFL Probe Robots
Qidwai, U. A., Akbar, M. A., Maqbool, M. M. H., et al. (2018) · IAES International Journal of Robotics and Automation (IJRA) · doi:10.11591/ijra.v7i4.pp283-296 · Cited by 3
Implementing Content Based Video Retrieval Using Speeded-Up Robust Features
Tarigan, J. T., Sihombing, P., & Marpaung, E. P. (2019) · International Journal of Simulation Systems Science & Technology · doi:10.5013/ijssst.a.19.03.07 · Cited by 3
“Introduced by Bay et al [1], SURF performance is capable to outperform other implementation of interest point detector proposed by Harris et al. [2] and Lindeberg et al. [3].”
BackgroundInfluentialA robust object verification algorithm using aligned chamfer history image
Shih, H.-C., & Wang, H.-Y. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7396-8 · Cited by 3
Evaluating the effect of MIPM on vehicle detection performance
Ershadi, N. Y., Menéndez, J. M., & Jiménez, D. (2019) · Transportation Letters · doi:10.1080/19427867.2019.1585682 · Cited by 3
“In the fi rst group, Scale-Invariant Feature Transform (SIFT) (Chen and Meng 2013), Speeded Up Robust Features (SURF) (Bay, Tuytelaars, and Van Gool 2006), Histogram of Oriented Gradient (HOG) (Khairdoost, Monadjemi, and Jamshidi 2013), and Haar-like features (Viola and Jones 2001) are mostly used…”
MethodVideo stabilization performance enhancement for low-texture videos
Unnikrishnan, S., & Sreelekha, G. (2019) · Journal of Real-Time Image Processing · doi:10.1007/s11554-019-00862-1 · Cited by 3
Digital Image Correlation Method Based on SURF in Airship Envelope Measurement
Zhao, L., Wang, Q., Zhou, P., et al. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-981-13-6061-9_7 · Cited by 3
Content-Based Image Retrieval : A Comprehensive Study
Aman, E., Rawat, A., Giri, A., & Gothwal, H. (2019) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit1952275 · Cited by 3
Catfish density estimation by aerial images analysis and deep learning
Conte, D., Gaucher, P., & Sansone, C. (2019) · ACM Symposium on Applied Computing · doi:10.1145/3297280.3297575 · Cited by 3
“Several approaches were tested, in particular, indirect estimation techniques based on descriptor points (e.g. SIFT [12], SURF [2]).”
MethodShape-based ATR for wide-area processing of satellite imagery
DelMarco, S. P., Tom, V. T., Webb, H. F., et al. (2019) · doi:10.1117/12.2518185 · Cited by 3
Handwritten Arabic Word Spotting Using Speeded Up Robust Features Algorithm
Makhfi, N. E. (2019) · International Conference on Optimization and Applications (ICOA) · doi:10.1109/icoa.2019.8727692 · Cited by 3
VISION-BASED INDOOR LOCALIZATION VIA A VISUAL SLAM APPROACH
Li, M., & Rottensteiner, F. (2019) · 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-w13-827-2019 · Cited by 3
“The first type of techniques is based on point features, such as the Hessian-affine detector (Lindeberg, 1998) combined with SIFT (Lowe, 2004) or SURF (Bay et al., 2008) descriptors.”
MethodFinn, A., Brinkworth, R. S. A., Griffiths, D., et al. (2019) · 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-w13-277-2019 · Cited by 3
“Such features are typically extracted using algorithms such as SIFT (scale invariant feature transformation) (Lowe, 1999) and SURF (speeded up robust features) (Bay et al., 2008).”
MethodSuperpixel-Based Feature Tracking for Structure from Motion
Cao, M., Jia, W., Lv, Z., et al. (2019) · Applied Sciences · doi:10.3390/app9152961 · Cited by 3
Gesture Recognition in Images Using Neural Networks
das Neves, A. R. N., Okada, H. K. R., & Shitsuka, R. (2019) · Research Society and Development · doi:10.33448/rsd-v8i11.1470 · Cited by 2
WSNs and on-Board Visual Fuzzy Servoing on Blimp Robot for Tracking Purposes
AL-Jarrah, R. A., Al-Jarrah, M. A., & Roth, H. (2015) · International Journal of Computer and Communication Engineering · doi:10.17706/ijcce.2016.5.3.215-221 · Cited by 3
“Invariant Feature Transform (SIFT) and Speeded UP Robust Feature algorithm (SURF) [26], [27].”
MethodRoad Lane Landmark Extraction: A State-of-the-art Review
Izquierdo, A., López-Guede, J. M., & Graña, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29859-3_53 · Cited by 3
An Image-based Recommender System Based on Image Annotation
Özkan, K., Kurt, Z., & Seke, E. (2019) · DergiPark (Istanbul University) · Cited by 3
An Efficient Binary Descriptor to Describe Retinal Bifurcation Point for Image Registration
Islam, S. T., Saha, S., Rahaman, G. M. A., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-31332-6_47 · Cited by 3
Srividhya, S., Prakash, S., & Elangovan, K. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-30465-2_16 · Cited by 4
Fast Loop Closure Detection via Binary Content
Wang, H., Li, J., Ran, M., & Xie, L. (2019) · International Conference on Control and Automation · doi:10.1109/icca.2019.8899937 · Cited by 3
“In recent years, there are also some binary descriptors used in loop closure detection such as Binary Robust Invariant Scalable Keypoints (BRISK) and Binary Robust Independent Elementary Features (BRIEF), [10], [11], [12], [13], [14].”
MethodLCD: Learned Cross-Domain Descriptors for 2D-3D Matching
Pham, Q.-H., Uy, M. A., Hua, B., Nguyen, D. T., Roig, G., & Yeung, S.-K. (2020) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v34i07.6859 · Cited by 93
“Image descriptors, both fully hand-crafted (Lowe 2004; Bay, Tuytelaars, and Van Gool 2006; Rublee et al. 2011) and partially learned (Brown, Hua, and Winder 2010; Tola, Lepetit, and Fua 2009), have been well studied in early days of computer vision.”
LVO: Line only stereo Visual Odometry
Lange, M., Raisch, C., & Schilling, A. (2019) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2019.8911808 · Cited by 4
“In a following step, those points are extracted and matched to points found in the other image, using a certain type of descriptor [2][3].”
Brands and Caps Labeling Recognition in Images Using Deep Learning
Golovko, V. A., Kroshchanka, A., & Mikhno, E. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-35430-5_4 · Cited by 3
Automated Diagnosis of Meniscus Tears from MRI of the Knee
Saygılı, A., & Albayrak, S. (2019) · DergiPark (Istanbul University) · Cited by 3
Image Matching Research Based on Improved SIFT Algorithm
Zhang, S., Li, X., & Yin, D. (2019) · International Conference on Video, Signal and Image Processing (VSIP) · doi:10.1145/3369318.3369340 · Cited by 3
Video Alignment Using Bi-Directional Attention Flow in a Multi-Stage Learning Model
Abobeah, R., Shoukry, A., & Katto, J. (2020) · IEEE Access · doi:10.1109/access.2020.2967750 · Cited by 3
Evaluation of Local Features for Near-Uniform Scene Images
Jong, T. K., & Bong, D. B. L. (2019) · IEEE International Conference on Signal and Image Processing Applications (ICSIPA) · doi:10.1109/icsipa45851.2019.8977755 · Cited by 3
“proposed the Speeded up Robust Feature (SURF) that has similar matching rates to SIFT with much faster performance [11].”
ResultAn Improved ORB Algorithm of Extracting Features Based on Local Region Adaptive Threshold
Yang, K., Yin, D., Zhang, J., et al. (2019) · International Conference on Systems and Informatics (ICSAI) · doi:10.1109/icsai48974.2019.9010209 · Cited by 3
“Bay, et al., proposed the Speeded Up Robust Features (SUR F) algorithm in 2006, which is an improved algorithm of SIFT and faster than the SIFT algorithm [8].”
MethodPerformance Evaluation of State-of-the-Art Filtering Criteria Applied to SIFT Features
Konlambigue, S., Pothin, J., Honeiné, P., et al. (2019) · IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) · doi:10.1109/isspit47144.2019.9001815 · Cited by 3
Hand gesture recognition by histogram based kernel using density measure
Gajalakshmi, P., & Sharmila, T. S. (2019) · International Conference on Power and Embedded Drive Control (ICPEDC) · doi:10.1109/icpedc47771.2019.9036590 · Cited by 3
“These limitations are avoid by SURF local features, in which H. Bay et al [20] calculated the interest points using Hessian function, involve second order of Gaussian derivative.”
MethodFourier Based Pre-Processing For Seeing Through Water
James, J. G., & Rajwade, A. V. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093496 · Cited by 3
Handwritten Text Segmentation Approach in Historical Arabic Documents
Makhfi, N. E. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-0947-6_61 · Cited by 3
A Novel approach for Hand Gesture Recognition using Kirsch edge with Bit Plane
Sharma, A., & Tazi, S. N. (2019) · International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iccs45141.2019.9065731 · Cited by 3
Yazdanshenas, A., Yazdanshenas, A., & Goh, C. (2020) · SN Computer Science · doi:10.1007/s42979-020-00130-1 · Cited by 4
“Using speeded up robust features (SURF) for point feature matching, additional control points are drawn to improve the accuracy of the transformation matrix [11, 12].”
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.