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 4,901–5,000 of 14,752
Quality Assurance for Document Image Collections in Digital Preservation
Huber-Mörk, R., & Schindler, A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33140-4_10 · Cited by 12
“Faster keypoint detection and description method include Features from Accelerated Segment Test (FAST) [19], Speeded up Robust features (SURF) [1], and the recently developed Oriented Brief (ORB) based on Binary Robust Independent Elementary Features (BRIEF) [20].”
MethodRotation and translation covariant match kernels for image retrieval
Tolias, G., Bursuc, A., Furon, T., & Jeǵou, H. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.06.007 · Cited by 12
“The optimal performance is achieved with κ in the range [2 , 8] .”
Describing, Navigating and Recognising Urban Spaces - Building an End-to-End SLAM System
Newman, P. M., Chandran-Ramesh, M., Cole, D., Cummins, M., Harrison, A., Posner, I., & Schroeter, D. (2010) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-14743-2_21 · Cited by 11
Feature-based matching of underwater images
Kudzinava, M., Campos, R. G., & Martı́, J. (2008) · Instrumentation viewpoint · doi:10.5821/iwp.2007.6.15826 · Cited by 11
Detecting Regions from Single Scale Edges
Rapantzikos, K., Avrithis, Y., & Kollias, S. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35749-7_23 · Cited by 11
Towards a robust visual SLAM approach: Addressing the challenge of life-long operation
Hochdorfer, S., & Schlegel, C. (2009) · Cited by 11
A framework for robust cognitive spatial mapping
Pronobis, A., Sjöö, K., Aydemir, A., Bishop, A. N., & Jensfelt, P. (2009) · Cited by 11
Face pose estimation with automatic 3D model creation in challenging scenarios
Gil-Jiménez, P., Bergasa, L. M., Nuevo, J., et al. (2012) · Image and Vision Computing · doi:10.1016/j.imavis.2012.06.013 · Cited by 11
Video summarization based on shot boundary detection with penalized contrasts
Medentzidou, P., & Kotropoulos, C. L. (2015) · International symposium on image and signal processing and analysis/ISPA ... · doi:10.1109/ispa.2015.7306058 · Cited by 11
“If two candidate keyframes have more than τSURF = 4 matching points, they are considered similar and they are also deleted [17].”
BackgroundExploiting eye–hand coordination to detect grasping movements
Carrasco, M., & Clady, X. (2012) · Image and Vision Computing · doi:10.1016/j.imavis.2012.07.001 · Cited by 12
3D plane detection for robot perception applying particle swarm optimization
Masuta, H., Makino, S., & Lim, H. (2014) · World Automation Congress (WAC) · doi:10.1109/wac.2014.6936041 · Cited by 11
Epipolar Geometry Estimation, Metric Reconstruction and Error Analysis from Two Images
Takimoto, R. Y., Martins, T. D. C., Takase, F. K., et al. (2012) · IFAC Proceedings Volumes · doi:10.3182/20120523-3-ro-2023.00098 · Cited by 11
Automatic construction of an action video shot database using web videos
Nga, D. H., & Yanai, . (2011) · International Conference on Computer Vision · doi:10.1109/iccv.2011.6126284 · Cited by 11
Robust object tracking with occlusion handle
Yu, G., Hu, Z., Lu, H., et al. (2010) · Neural Computing and Applications · doi:10.1007/s00521-010-0400-x · Cited by 11
“Local image features, like SIFT [1], SURF [2] and MSER [3], extract information based on part of image locally rather than the whole one.”
MethodImprovement of speeded-up robust features for robot visual simultaneous localization and mapping
Wang, Y.-T., & Lin, G. (2013) · Robotica · doi:10.1017/s0263574713000830 · Cited by 11
“2 applied the concepts of box filter and integral image 13 in their speeded-up robust features (SURF) approach for detecting local invariant features.”
MethodInfluentialIdentification of vehicle tracks and association to wireless endpoints by multiple sensor modalities
Becker, D., Einsiedler, J., Schäufele, B., Binder, A., & Radusch, I. (2013) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2013.6817878 · Cited by 12
Score level fusion of SIFT and SURF for iris
Bakshi, S., Das, S., Mehrotra, H., et al. (2012) · International Conference on Devices, Circuits and Systems (ICDCS) · doi:10.1109/icdcsyst.2012.6188740 · Cited by 11
Feulner, J., Zhou, S. K., Angelopoulou, E., et al. (2010) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2010.11.004 · Cited by 11
“The “Speeded Up Robust Features” (SURF) [6, 7] have gained popularity for computer vision applications because they have good discriminative power, are robust and can be made invariant to rotation.”
Fast Orthogonal Haar Transform PatternMatching via Image Square Sum
Li, Y., Li, H., & Cai, Z. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2303082 · Cited by 11
Robust descriptors for 3D point clouds using Geometric and Photometric Local Feature
Hwang, H., Hyung, S., Yoon, S., et al. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385920 · Cited by 11
Learning bag of visual words for motorbike detection
Thai, N. D., Le, T. S., Thoai, N., et al. (2014) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2014.7064450 · Cited by 11
Feature-based recognition approaches for infrared anti-ship missile seekers
Gray, G., Aouf, N., Richardson, M. A., et al. (2012) · The Imaging Science Journal · doi:10.1179/1743131x12y.0000000012 · Cited by 11
An UAV navigation aided with computer vision
Zhang, C., Chen, J., Song, C., et al. (2014) · doi:10.1109/ccdc.2014.6852209 · Cited by 11
“Scale invariant feature transform (SIFT)[3] was systematically proposed in the 2004 by Lowe et al, which marked the mature of feature based stitching algorithm, after that in 2006, speeded up robust features(SURF)[1] proposed by Herbert Bay is an enhancement to SIFT.”
MethodA hull census transform for scene change detection and recognition towards topological map building
Wang, M.-L., & Lin, H. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5652817 · Cited by 11
“The SURF feature extraction technique [6] is used in this work and the proposed HCT is compiled based on the extracted image features.”
BackgroundMethodReal-Time Hand Gesture Recognition Based on the Depth Map for Human Robot Interaction
Hamissi, M., & Faez, K. (2013) · International Journal of Electrical and Computer Engineering (IJECE) · doi:10.11591/ijece.v3i6.3954 · Cited by 11
Robot Localisation Using Natural Landmarks
Anderson, P., Yusmanthia, Y., Hengst, B., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39250-4_12 · Cited by 11
“Both SIFT [9] and SURF [2], [1] are feature representations that are designed to be stable under scale and viewpoint changes.”
BackgroundMethodComputing OpenSURF on OpenCL and General Purpose GPU
Yan, W., Shi, X., Yan, X., et al. (2013) · International Journal of Advanced Robotic Systems · doi:10.5772/57057 · Cited by 11
Active guidance for laser retinal surgery with a handheld instrument
Becker, B. C., Valdivieso, C. R., Biswas, J., et al. (2009) · doi:10.1109/iembs.2009.5333489 · Cited by 11
“Using interest points detected by the Speeded Up Robust Features (SURF) algorithm of Bay et al. [11], a homography is computed with the standard RANSAC algorithm [12] and applied to align the planned pattern to new video frames.”
A novel Genetic Algorithms and SURF-Based approach for image retargeting
Oliveira, S. A. F., Neto, A. R. R., & Bezerra, F. N. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.09.015 · Cited by 11
Autonomous Underwater Vehicle to Inspect Hydroelectric Dams
CavalcantiNeto, E., Cavalcante, R., Varela, A. T., et al. (2014) · International Journal of Computer Applications · doi:10.5120/17728-8801 · Cited by 11
Nest: Networked smartphones for target localization
Shang, Y., Zeng, W., Ho, K. C., et al. (2012) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc.2012.6181154 · Cited by 11
A hierarchical classification method for finger knuckle print recognition
Kong, T., Yang, G., & Yang, L. (2014) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/1687-6180-2014-44 · Cited by 11
“In this paper, we separately use Gabor [22] and SURF [23] to extract the basic and minor features.”
MethodFULLY AUTOMATED IMAGE ORIENTATION IN THE ABSENCE OF TARGETS
Stamatopoulos, C., Chuang, T., Fraser, C. S., et al. (2012) · 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/isprsarchives-xxxix-b5-303-2012 · Cited by 11
Camera handoff and placement for automated tracking systems with multiple omnidirectional cameras
Chen, C., Yao, Y., Page, D. L., Abidi, B. R., Koschan, A. F., & Abidi, M. A. (2009) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2009.04.004 · Cited by 10
Food Texture Descriptors Based On Fractal And Local Gradient Information
Bosch, M., Boushey, C. J., Delp, E. J., Khanna, N., & Zhu, F. M. (2011) · PubMed · doi:10.5281/zenodo.42607 · Cited by 10
Geometric Expansion for Local Feature Analysis and Matching
Farhan, E., & Hagege, R. R. (2015) · SIAM Journal on Imaging Sciences · doi:10.1137/140997671 · Cited by 11
“As shown, for example in [8, 2], for many applications it is sufficient to consider the effect of the change of plane translation, the scale (zoom) and the rotation around the optical axis (which are a subset of the full affine model).”
BackgroundMethodA Top-Down Approach for a Synthetic Autobiographical Memory System
Damianou, A., Ek, C. H., Boorman, L. W., Lawrence, N. D., & Prescott, T. J. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-22979-9_28 · Cited by 11
Mobile Indoor Positioning Using Wi-fi Localization and Image Processing
Ching, J. C., Domingo, C., Iglesia, K., et al. (2013) · Proceedings in information and communications technology · doi:10.1007/978-4-431-54436-4_19 · Cited by 11
Space-variant blur deconvolution and denoising in the dual exposure problem
Tallón, M., Mateos, J., Babacan, S. D., et al. (2012) · Information Fusion · doi:10.1016/j.inffus.2012.08.003 · Cited by 11
Bag‐of‐features for image memorability evaluation
Lahrache, S., Ouazzani, R. E., & Qadi, A. E. (2016) · IET Computer Vision · doi:10.1049/iet-cvi.2015.0383 · Cited by 11
“As well, when we use Gist instead of SURF we reach a result of 50.87%.”
MethodInfluentialOn Different Colour Spaces for Medical Colour Image Classification
Ruberto, C. D., Fodde, G., & Putzu, L. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23192-1_40 · Cited by 11
Parallelizing image feature extraction algorithms on multi-core platforms
Lu, Y., Li, Y., Song, B., Zhang, W., Chen, H., & Peng, L. (2016) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2016.03.001 · Cited by 11
Bohi, A., Prandi, D., Guis, V. H., et al. (2016) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-016-0669-1 · Cited by 11
A sonar image mosaicing algorithm based on improved SIFT for USV
Li, H., Yi, D., He, X., et al. (2014) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2014.6885981 · Cited by 11
Automatic tracking of intraoperative brain surface displacements in brain tumor surgery
Kumar, A. N., Miga, M. I., Pheiffer, T. S., et al. (2014) · doi:10.1109/embc.2014.6943888 · Cited by 11
CCTV Scene Perspective Distortion Estimation From Low-Level Motion Features
Arandjelović, O., Pham, D.-S., & Venkatesh, S. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2424055 · Cited by 11
New image descriptor from edge detector and blob extractor
Grycuk, R., Scherer, R., & Gabryel, M. (2015) · Journal of Applied Mathematics and Computational Mechanics · doi:10.17512/jamcm.2015.4.04 · Cited by 12
Zhao, C., & Zhao, H. (2016) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2016.07.002 · Cited by 11
A Feature Learning Framework for Histology Images Classification
Ruberto, C. D., & Putzu, L. (2016) · Elsevier eBooks · doi:10.1016/b978-0-12-804203-8.00003-1 · Cited by 11
Chionna, F., Argese, F., Palmieri, V., et al. (2016) · Conservation Science in Cultural Heritage · doi:10.6092/issn.1973-9494/6174 · Cited by 11
MARVIN: Mobile Autonomous Robot for Video Surveillance Networks
Claudi, A., Benedetto, F. D., Dolcini, G., et al. (2012) · doi:10.1109/ems.2012.37 · Cited by 11
“SIFT and SURF performances are greatly above the upper bound for the control period, and are clearly unsuitable in the proposed reference scenario.”
MethodInfluentialLCO: A robust and efficient local descriptor for image matching
Duo, J., Chen, P., & Zhao, L. (2016) · AEU - International Journal of Electronics and Communications · doi:10.1016/j.aeue.2016.12.018 · Cited by 11
Technologies for under-ice AUV navigation
Bandara, D., Leong, Z. Q., Nguyen, H. D., et al. (2016) · IEEE/OES Autonomous Underwater Vehicles · doi:10.1109/auv.2016.7778657 · Cited by 11
“Aiming to address this issue, there are number of feature detectors and descriptors that have been proposed in literature including: Harris Corner [15], Smallest Univalue Segment Assimilating Nucleus (SUSAN) [16], Scale-Invariant Feature transform (SIFT) [17], Speeded up Robust Features (SURF) [18], Binary Robust Inde…”
MethodA comparative study of control architectures in UAV/UGV-based surveillance system
Khaleghi, A. M., Xu, D., Minaeian, S., Li, M., Yuan, Y., Liu, J., Son, Y., Vo, C., Mousavian, A., & Lien, J. (2014) · Cited by 10
Saito, M., Kiuchi, K., Shimizu, S., Yokota, T., Fujino, Y., Saito, T., & KURODA, Y. (2014) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2014.p0185 · Cited by 11
Improving feature matching strategies for efficient image retrieval
Wang, L., & Wang, H. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.02.006 · Cited by 12
“These patches are often described by local invariant feature descriptors like Scale Invariant Feature Transform (SIFT) [8] and SURF [10] to obtain robust and powerful discrimination.”
Semi-Automatic Semantic Video Annotation Tool
Aydınlılar, M., & Yazıcı, A. (2012) · Springer eBooks · doi:10.1007/978-1-4471-4594-3_31 · Cited by 11
Tracking Objects using Artificial Neural Networks and Wireless Connection for Robotics
Oñate, J. M. B., Chipantasi, D. J. M., & Velasco, N. (2017) · Journal of Telecommunication Electronic and Computer Engineering (JTEC) · Cited by 11
Elliptical Higher-Order-Spectra Periocular Code
Algashaam, F. M. A., Nguyen, K., Chandran, V., & Banks, J. (2017) · IEEE Access · doi:10.1109/access.2017.2697898 · Cited by 14
Design of a Convolutional Two-Dimensional Filter in FPGA for Image Processing Applications
Licciardo, G. D., Cappetta, C., & Benedetto, L. D. (2017) · Computers · doi:10.3390/computers6020019 · Cited by 11
Matching by Monotonic Tone Mapping
Kovacs, G. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2711613 · Cited by 11
Automation of product packaging for industrial applications
Perez-Vidal, C., Gracia, L., de Paco, J. M., Wirkus, M., Azorín, J. M., & de Gea, J. (2017) · International Journal of Computer Integrated Manufacturing · doi:10.1080/0951192x.2017.1369165 · Cited by 14
Combination of Face and Posture Features for Tracking of Moving Human Visual Characteristics
Andriana, D., Prihatmanto, A. S., Hidayat, E., et al. (2017) · International Journal on Electrical Engineering and Informatics · doi:10.15676/ijeei.2017.9.3.14 · Cited by 11
“Combination of Face and Body Posture Features Generally, visual object detection can utilize existing popular methods such as HOG, SVM, LBP, or SURF [1, 4, 15].”
MethodInfluentialVietnamese food recognition using convolutional neural networks
Phat, T. V., Dang, T., Pham, Q., et al. (2017) · International Conference on Knowledge and Systems Engineering/Proceedings · doi:10.1109/kse.2017.8119446 · Cited by 11
“For local features, we resize all images into the size 200 × 200 pixels and compare the performance of using SIFT, SURF, and HOG.”
BackgroundMethodInfluentialVisual inertial odometry using coupled nonlinear optimization
Hong, E., & Lim, J. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206610 · Cited by 16
“Our proposed method used KLT [11] feature tracker instead of using descriptor approaches like SIFT [12], SURF [13], BRIEF [14] and ORB [15] to get robust observation in dynamic environments.”
MethodInferring Fine-Grained PM2.5 with Bayesian Based Kernel Method for Crowdsourcing System
Li, S., Xi, T., Tian, Y., et al. (2017) · Globecom · doi:10.1109/glocom.2017.8254421 · Cited by 11
“To do image registration, we will first extract surf descriptor of the images, which is translation invariant, scale invariant and rotation invariant [11].”
3D Orientation Estimation of Industrial Parts from 2D Images using Neural Networks
Langlois, J., Mouchère, H., Normand, N., et al. (2018) · International Conference on Pattern Recognition Applications and Methods · doi:10.5220/0006597604090416 · Cited by 11
“More recently, the well known SIFT local descriptor was employed to get a pose description of an object (Lowe, 2004).”
BackgroundInfluentialZhao, X., Zhang, J., Yang, C., et al. (2018) · Remote Sensing · doi:10.3390/rs10050663 · Cited by 11
Texture description using multi-scale morphological GLCM
Rafi, M., & Mukhopadhyay, S. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5989-2 · Cited by 13
“The widely used techniques for texture characterization includes scale invariant feature transform (SIFT) [27], speeded up robust feature(SURF) [2], histogram of oriented gradients (HOG) [10], gradient location and orientation histogram (GLOH) [30], region covariance matrix (RCM) [42], edgelet [46], gray level co-occu…”
MethodBenchmark for the robustness of image features in rainy conditions
Duthon, P., Bernardin, F., Chausse, F., & Colomb, M. (2018) · Machine Vision and Applications · doi:10.1007/s00138-018-0945-8 · Cited by 11
X-Vision: An Augmented Vision Tool with Real-Time Sensing Ability in Tagged Environments
Sun, Y., Kantareddy, S. N. R., Bhattacharyya, R., & Sarma, S. E. (2018) · IEEE International Conference on RFID Technology and Applications (RFID-TA) · doi:10.1109/rfid-ta.2018.8552778 · Cited by 11
Classification Methods in Image Analysis with a Special Focus on Medical Analytics
Amelio, L., & Amelio, A. (2018) · Intelligent systems reference library · doi:10.1007/978-3-319-94030-4_3 · Cited by 16
Matching Multi-Sensor Remote Sensing Images via an Affinity Tensor
Chen, S., Xiuxiao Yuan, A., Yuan, W., Niu, J., Xu, F., & Zhang, Y. (2018) · Remote Sensing · doi:10.3390/rs10071104 · Cited by 13
Unsupervised Maximum Margin Incomplete Multi-view Clustering
Tao, H., Hou, C., Yi, D., & Zhu, J. (2018) · Communications in computer and information science · doi:10.1007/978-981-13-2122-1_2 · Cited by 12
Assessing the Impact of Corneal Refraction and Iris Tissue Non-Planarity on Iris Recognition
Thompson, J., Flynn, P. J., Boehnen, C. B., et al. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2869342 · Cited by 11
“Using a method similar to SURF [18], the most significant feature point is marked.”
MethodAn Integrated Deep Neural Network for Defect Detection in Dynamic Textile Textures
Siegmund, D., Prajapati, A., Kirchbuchner, F., & Kuijper, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01132-1_9 · Cited by 11
UGC: Real-Time, Ultra-Robust Feature Correspondence via Unilateral Grid-Based Clustering
Zheng, Z., Ma, Y., Zheng, H. Y., et al. (2018) · IEEE Access · doi:10.1109/access.2018.2871729 · Cited by 11
Multi-frame Super Resolution for Ocular Biometrics
Reddy, N., Noor, D. F., Li, Z., & Derakhshani, R. R. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00086 · Cited by 11
Tracking multiple extended targets with multi‐Bernoulli filter
Hu, Q., Ji, H., & Zhang, Y. (2019) · IET Signal Processing · doi:10.1049/iet-spr.2018.5125 · Cited by 11
“The ⋅ , ⋅ , ∥ ⋅ , ⋅ ∥p and ∥ ⋅ , ⋅ ∥F denote the absolute value, p−norm and Frobenius-norm operations [39], respectively.”
Clustering based one-to-one hypergraph matching with a large number of feature points
Nawaz, M., Khan, S., Qureshi, R., et al. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.01.001 · Cited by 11
Automatic Dewarping of Retina Images in Adaptive Optics Confocal Scanning Laser Ophthalmoscope
Chen, H., He, Y., Wei, L., Li, X., & Zhang, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2914463 · Cited by 11
Performance Evaluation of Feature Descriptors for Aerial Imagery Mosaicking
Aktar, R., Aliakbarpour, H., Bunyak, F., et al. (2018) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2018.8707402 · Cited by 11
“Figure 4 showcases the performance of different feature descriptors (ST+NCC [28], SURF [30], ASIFT [31]) in VMZ for two images selected from dataset 09152008flight2tape1 6 (top row: Frame 000000, bottom row: Frame 001329).”
BackgroundUAV AND LIDAR IMAGE REGISTRATION: A SURF-BASED APPROACH FOR GROUND CONTROL POINTS SELECTION
Kalantar, B., Ueda, N., Al-Najjar, H. A. H., Moayedi, H., Halin, A. B. A., & Mansor, S. B. (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-w13-413-2019 · Cited by 12
Stream-Based ORB Feature Extractor with Dynamic Power Optimization
Tran, P. D., Pham, T. H., Lam, S.-K., et al. (2018) · International Conference on Field-Programmable Technology (FPT) · doi:10.1109/fpt.2018.00024 · Cited by 11
“Many feature descriptors such as Scale-Invariant Feature Transform (SIFT) [1], Speeded Up Robust Features (SURF) [2], Oriented Fast and Rotated BRIEF (ORB) [3], etc. have been previously explored.”
BackgroundAyhan, B., & Kwan, C. (2019) · Sensors · doi:10.3390/s19163526 · Cited by 11
Comparison of Descriptors for SAR ATR
Belloni, C., Aouf, N., Caillec, J. L., et al. (2019) · Proceedings of the IEEE National Radar Conference · doi:10.1109/radar.2019.8835804 · Cited by 11
Investigation of Fusion Features for Apple Classification in Smart Manufacturing
Ismail, A., Idris, M. Y. I., Ayub, M. N. B., & Por, L. Y. (2019) · Symmetry · doi:10.3390/sym11101194 · Cited by 12
Segmentation Guided Registration for 3D Spectral-Domain Optical Coherence Tomography Images
Pan, L., Guan, L., & Chen, X. (2019) · IEEE Access · doi:10.1109/access.2019.2943172 · Cited by 11
Deep Domain Adaptation for Regression
Singh, A., & Chakraborty, S. (2019) · Studies in computational intelligence · doi:10.1007/978-3-030-31764-5_4 · Cited by 14
Lecrosnier, L., Boutteau, R., Vasseur, P., Savatier, X., & Fraundorfer, F. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8916886 · Cited by 11
“This matching process can be either performed by comparing image descriptors, such as SURF [1] or SIFT [2], or by comparing image intensity value directly.”
MethodAccumulative Errors Optimization for Visual Odometry of ORB-SLAM2 Based on RGB-D Cameras
Qin, J., Li, M., Liao, X., & Zhong, J. (2019) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi8120581 · Cited by 11
A Triangle Feature Based Map-to-map Matching and Loop Closure for 2D Graph SLAM
Jiang, B., Zhu, Y., & Liu, M. (2019) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio49542.2019.8961777 · Cited by 11
“Blob image feature descriptors (SIFT, SURF) have better performance with ”softened” images [9] but are outperformed by corner features in ”hard” images.”
MethodA Robotic Charging Scheme for Electric Vehicles Based on Monocular Vision and Force Perception
Lv, X., Chen, G., Hu, H., et al. (2019) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio49542.2019.8961689 · Cited by 11
Ground Texture Based Localization Using Compact Binary Descriptors
Schmid, J. F., Simon, S. F., & Mester, R. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197221 · Cited by 11
BOLD3D: A 3D BOLD descriptor for 6Dof pose estimation
Zhou, J., Liu, Y., Liu, J., Xie, Q., Zhang, Y., Zhu, X., & Ding, X. H. (2020) · Computers & Graphics · doi:10.1016/j.cag.2020.05.008 · Cited by 11
“One cannot directly apply traditional region-based 2D descriptors, such as SIFT [6] or SURF [7] to distinguish these texture-less mechanical parts.”
MethodDEEP-AD: A Multimodal Temporal Video Segmentation Framework for Online Video Advertising
Țapu, R., Mocanu, B., & Zaharia, T. B. (2020) · IEEE Access · doi:10.1109/access.2020.2997949 · Cited by 13
“points [16], globalized with a Bag of Visual Words [17] representation for video scene segmentation.”
BackgroundFPGA implementation of HOOFR bucketing extractor-based real-time embedded SLAM applications
Nguyen, D. D., Elouardi, A., Rodríguez, S., & Bouaziz, S. (2020) · Journal of Real-Time Image Processing · doi:10.1007/s11554-020-00986-9 · Cited by 13
“There are many different extractors used in various SLAM systems such as: SIFT [3], SURF [4] or ORB [5, 6].”
MethodAKUImg: A database of cartilage images of Alkaptonuria patients
Rossi, A., Giacomini, G., Cicaloni, V., et al. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103863 · Cited by 11
Constructing big panorama from video sequence based on deep local feature
Cao, M., Zheng, L., Jia, W., et al. (2020) · Image and Vision Computing · doi:10.1016/j.imavis.2020.103972 · Cited by 11
On improving the accuracy of self-calibrated stereo digital image correlation system
Thiruselvam, N. I., & Subramanian, S. J. (2020) · Measurement Science and Technology · doi:10.1088/1361-6501/abae3b · Cited by 11
“the other hand, in self calibration, features on the specimen itself are tracked across images collected from multiple viewpoints using robust algorithms such as SIFT [23] and SURF [24] to calibrate moving cameras [12, 13, 16].”
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.