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 801–900 of 14,752
Condition-CNN: A hierarchical multi-label fashion image classification model
Kolisnik, B., Hogan, I., & Zulkernine, F. H. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115195 · Cited by 85
AdaFusion: Visual-LiDAR Fusion With Adaptive Weights for Place Recognition
Lai, H., Yin, P., & Scherer, S. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3210880 · Cited by 110
Hameed, Z., García-Zapirain, B., Aguirre, J. J., & Isaza-Ruget, M. A. (2022) · Scientific Reports · doi:10.1038/s41598-022-19278-2 · Cited by 102
OmniGlue: Generalizable Feature Matching with Foundation Model Guidance
Jiang, H., Karpur, A., Cao, B., Huang, Q., & Araújo, A. D. M. (2024) · 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/cvpr52733.2024.01878 · Cited by 170
“The past decade has witnessed the evolution from hand-crafted [3, 29] to learning-based image features [10, 36, 38, 51, 55].”
BackgroundMethodGA-SIFT: A new scale invariant feature transform for multispectral image using geometric algebra
Li, Y., Liu, W., Xiao-tang, L., Huang, Q., & Li, X. (2014) · Information Sciences · doi:10.1016/j.ins.2013.12.022 · Cited by 83
Rey-Otero, I., & Delbracio, M. (2014) · Image Processing On Line · doi:10.5201/ipol.2014.82 · Cited by 121
“SURF [2], Harris and Hessian based detectors [19], MOPS [3], ASIFT [28] and SFOP [8], with methods using binary descriptors such as BRISK [13] and ORB [24], are just a few of the successful variants.”
BOLD Features to Detect Texture-less Objects
Tombari, F., Franchi, A., & Di, L. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.160 · Cited by 108
“Indeed, the former requires the algorithm to be trained carefully from nearly all the possible vantage points that may occur in the actual scene, which 4vision.caltech.edu/malaa/datasets/caltech-games 0 0,1 0,2 0,3 0,4 0,5 0,6 0,7 0,8 0,9 1 0 0,1 0,2 0,3 0,4 0,5 0,6 0,7 0,8 0,9 1 TP R FPR SIFT SURF ORB BOLD Line2D Hal…”
BackgroundMethodInfluentialA Multimodal LDA Model integrating Textual, Cognitive and Visual Modalities
Roller, S., & Walde, S. S. I. (2013) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d13-1115 · Cited by 101
“First, we compute a simple Bag of Visual Words (BoVW) model for our images using SURF key-points (Bay et al., 2008).”
MethodINSTRE: A New Benchmark for Instance-Level Object Retrieval and Recognition
Wang, S., & Jiang, S. (2015) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/2700292 · Cited by 98
“The category-level recognition, boosted by available large-scale datasets (e.g., ImageNet [Deng et al. 2009] and LabelMe [Russell et al. 2008]), has drawn many attentions in recent literatures [Deng et al. 2010; Gao and Koller 2011 .”
BackgroundFPGA based Speeded Up Robust Features
Šváb, J., Krajník, T., Faigl, J., & Přeučil, L. (2009) · IEEE International Conference on Technologies for Practical Robot Applications · doi:10.1109/tepra.2009.5339646 · Cited by 86
Mehmood, Z., Mahmood, T., & Javid, M. A. (2017) · Applied Intelligence · doi:10.1007/s10489-017-0957-5 · Cited by 89
“The interest point detectors like scale-invariant feature transform (SIFT) [19], speeded-up robust features (SURF) [20], histograms of oriented gradients (HOG) [21], maximally stable extremal regions (MSER) [22], and binary robust invariant scalable keypoints (BRISK) [23] were applied in various content-based image ma…”
BackgroundModeling and classification of defects in CFRP laminates by thermal non-destructive testing
Marani, R., Palumbo, D., Renò, V., et al. (2017) · Composites Part B Engineering · doi:10.1016/j.compositesb.2017.10.010 · Cited by 81
Dynamic Feature Matching for Partial Face Recognition
He, L., Li, H., Zhang, Q., & Sun, Z. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2870946 · Cited by 85
“[41] proposed a Robust Point Set Matching (RPSM) method based on SIFT descriptor, SURF descriptor [4] and LBP [2] histogram for partial face matching.”
MethodSantra, B., & Mukherjee, D. P. (2019) · Image and Vision Computing · doi:10.1016/j.imavis.2019.03.005 · Cited by 102
Abbas, Q., & Celebi, M. E. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7652-y · Cited by 86
Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task
Bhowmik, A., Gumhold, S., Rother, C., & Brachmann, E. (2020) · 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/cvpr42600.2020.00500 · Cited by 109
Review of vision-based occupant information sensing systems for occupant-centric control
Choi, H., Um, C. Y., Kang, K., Kim, H., & Kim, T. (2021) · Building and Environment · doi:10.1016/j.buildenv.2021.108064 · Cited by 97
Improved SIFT-Features Matching for Object Recognition
Alhwarin, F., Wang, C., Ristić–Durrant, D., & Gräser, A. (2008) · Electronic workshops in computing · doi:10.14236/ewic/vocs2008.16 · Cited by 93
“SIFT improving techniques developed recently targeted minimization of the computational time [16, 17, 18], while limited research aiming at improving the accuracy has been done.”
MethodPerformance Comparisons of Contour-Based Corner Detectors
Awrangjeb, M., Lu, G., & Fraser, C. S. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2200493 · Cited by 86
Tracking by an Optimal Sequence of Linear Predictors
Zimmermann, K., Matas, J., & Svoboda, T. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.119 · Cited by 84
“While some approaches [3], [4], [5], [9] exhaustively scan a subset of object poses S with a classifier approximating f ð t ; I ; t 0 Þ , other approaches [1], [2], [10], [11] use a gradient optimization of a criterion approximating f ð t Þ .”
MethodRecognizing Partial Biometric PatternsPreprint
He, L., Sun, Z., Zhu, Y., & Wang, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.07399 · Cited by 109
Recognizing architecture styles by hierarchical sparse coding of blocklets
Zhang, L., Song, M., Liu, X., Sun, L., Chen, C., & Bu, J. (2013) · Information Sciences · doi:10.1016/j.ins.2013.08.020 · Cited by 88
“, we extract SURF [2] descriptors from the building area and quantized them into a 100,000 dimensional feature vector to represent each building for architecture style recognition.”
MethodSTAP: Spatial-Temporal Attention-Aware Pooling for Action Recognition
Nguyen, T., Zheng, S., & Yan, S. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2333151 · Cited by 83
“Wang and Schmid [53] adopted the improved trajectory features using the advanced optical flow from SURF [55] matching and human detection.”
MethodDAISY Filter Flow: A Generalized Discrete Approach to Dense Correspondences
Yang, H., Lin, W.-Y., & Lu, J. (2014) · 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/cvpr.2014.435 · Cited by 92
Biologically Inspired Features for Scene Classification in Video Surveillance
Huang, K., Tao, D., Yuan, Y., Li, X., & Tan, T. (2010) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2009.2037923 · Cited by 82
“We also showed the number of patches of the local feature descriptor (Surf) [34] scene classification.”
BackgroundBudrionis, A., Plikynas, D., Daniušis, P., & Indriulionis, A. (2020) · Assistive Technology · doi:10.1080/10400435.2020.1743381 · Cited by 117
“The conducted systematic literature review revealed that smartphone-based computer vision tools for blind individuals often rely on rather outdated image/video-processing meth-ods (e.g., SURF (Bay et al., 2006) and SIFT (Lowe, 2004), among others) that do not reflect current state of the art.”
BackgroundInfluentialKonstantinidis, F. K., Kansizoglou, I., Santavas, N., Mouroutsos, S. G., & Gasteratos, A. C. (2020) · Machines · doi:10.3390/machines8040088 · Cited by 87
A Study of Mobile Sensing Using Smartphones
Liu, M. (2013) · International Journal of Distributed Sensor Networks · doi:10.1155/2013/272916 · Cited by 94
“Pattern recognition is far more complicated than (9); there are many good algorithms in pattern recognition area, like SIFT [19–23] and SVM [24–29].”
BackgroundAn adaptive appearance-based map for long-term topological localization of mobile robots
Dayoub, F., & Duckett, T. (2008) · 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2008.4650701 · Cited by 80
A visual odometry framework robust to motion blur
Pretto, A., Menegatti, E., Bennewitz, M., Burgard, W., & Pagello, E. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152447 · Cited by 82
“As in [1], we use the determinant of the Hessian of the scaled image for selecting both location and characteristic scale of”
BackgroundMethodResultInfluentialImage retrieval by addition of spatial information based on histograms of triangular regions
Ali, N., Bajwa, K. B., Sablatnig, R., & Mehmood, Z. (2016) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2016.04.002 · Cited by 82
I know what you did last summer: object-level auto-annotation of holiday snaps
Gammeter, S., Bossard, L., Quack, T., & Gool, L. V. (2009) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2009.5459180 · Cited by 87
Self-citationFast loop-closure detection using visual-word-vectors from image sequences
Bampis, L., Amanatiadis, A. A., & Gasteratos, A. C. (2017) · The International Journal of Robotics Research · doi:10.1177/0278364917740639 · Cited by 85
“, 2010), and execution time, owing to the expensive extraction and matching of SURF features (Bay et al., 2006).”
BackgroundBeyond Cartesian Representations for Local Descriptors
Ebel, P., Trulls, E., Yi, K. M., Fua, P., & Mishchuk, A. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00034 · Cited by 99
“This includes classical hand-crafted pipelines such as SIFT [23] or SURF [5].”
MethodA Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation
Qi, S., Zhang, Y., Wang, C., Zhou, J., & Cao, X. (2021) · ACM Computing Surveys · doi:10.1145/3479428 · Cited by 98
Few-Shot Steel Surface Defect Detection
Wang, H., Li, Z., & Wang, H. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3128208 · Cited by 118
Overview of Underwater 3D Reconstruction Technology Based on Optical Images
Hu, K., Wang, T., Shen, C., Weng, C., Zhou, F., Xia, M., & Weng, L. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11050949 · Cited by 85
“There are many feature-detection techniques that are frequently employed, including speeded-up robust features (SURF) [77], scale-invariant feature transform (SIFT) [78] and Harris.”
MethodVisual SLAM for Flying Vehicles
Steder, B., Grisetti, G., Stachniss, C., & Burgard, W. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2004521 · Cited by 94
Pham, M.-T., Gao, Y., Hoang, V.-D. D., & Cham, T. (2010) · 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/cvpr.2010.5540117 · Cited by 93
Accurate and Linear Time Pose Estimation from Points and Lines
Vakhitov, A., Funke, J., & Moreno-Noguer, F. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46478-7_36 · Cited by 95
Pornography classification: The hidden clues in video space–time
Moreira, D., Avila, S., Pérez, M., Moraes, D., Testoni, V., Junior, E. A. D. V., Goldenstein, S. K., & Rocha, A. D. R. (2016) · Forensic Science International · doi:10.1016/j.forsciint.2016.09.010 · Cited by 95
“The TRoF detector is directly inspired by the still-image Speeded-Up Robust Features (SURF) detector [36], which is very fast.”
BackgroundMethodInfluentialPeople occupancy detection and profiling with 3D depth sensors for building energy management
Diraco, G., Leone, A., & Siciliano, P. A. (2015) · Energy and Buildings · doi:10.1016/j.enbuild.2015.01.043 · Cited by 95
Quantifying ice loss in the eastern Himalayas since 1974 using declassified spy satellite imagery
Maurer, J. M., Rupper, S., & Schaefer, J. M. (2016) · The cryosphere · doi:10.5194/tc-10-2203-2016 · Cited by 81
“In summary, epipolar images are generated by computing homography transformations via automated point detectors and descriptors (Bay et al., 2006; Fusiello and Irsara, 2008).”
MethodMade to measure: Bespoke landmarks for 24-hour, all-weather localisation with a camera
Linegar, C., Churchill, W., & Newman, P. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487208 · Cited by 76
“Landmarks are described by a feature descriptor (e.g. SIFT, SURF, BRIEF).”
MethodInfluentialAppearance-invariant place recognition by discriminatively training a convolutional neural network
López-Antequera, M., Gomez-Ojeda, R., Petkov, N., & González-Jiménez, J. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.04.017 · Cited by 80
A Quaternion-Based Certifiably Optimal Solution to the Wahba Problem With Outliers
Yang, H., & Carlone, L. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00175 · Cited by 95
Generative Hierarchical Features from Synthesizing Images
Xu, Y., Shen, Y., Zhu, J., Yang, C., & Zhou, B. (2021) · 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/cvpr46437.2021.00441 · Cited by 125
“Traditional methods used manually designed features [40, 3, 7] for pattern matching and object detection.”
MethodWatermarking schemes for digital images: Robustness overview
Evsutin, O. O., & Dzhanashia, K. (2021) · Signal Processing Image Communication · doi:10.1016/j.image.2021.116523 · Cited by 81
Classification of Breast Cancer Histopathological Images Using DenseNet and Transfer Learning
Wakili, M. A., Shehu, H. A., Sharif, M. H., Sharif, M. H. U., Umar, A., Kusetoğulları, H., İnce, İ. F., & Uyaver, Ş. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/8904768 · Cited by 113
Digital Restoration of Cultural Heritage With Data-Driven Computing: A Survey
Basu, A., Paul, S., Ghosh, S., Das, S., Chanda, B., Bhagvati, C., & Snåšel, V. (2023) · IEEE Access · doi:10.1109/access.2023.3280639 · Cited by 113
Correlated Light and Electron Cryo-Microscopy
Briegel, A., Chen, S., Koster, A. J., Plitzko, J. M., Schwartz, C. L., & Jensen, G. J. (2010) · Methods in enzymology on CD-ROM/Methods in enzymology · doi:10.1016/s0076-6879(10)81013-4 · Cited by 89
UAV-Based Stereo Vision for Rapid Aerial Terrain Mapping
Stefanik, K. V., Gassaway, J., Kochersberger, K. B., & Abbott, A. L. (2011) · GIScience & Remote Sensing · doi:10.2747/1548-1603.48.1.24 · Cited by 89
Multisensor Navigation Systems: A Remedy for GNSS Vulnerabilities?
Grejner‐Brzezinska, D. A., Toth, C. K., Moore, T., Raquet, J. F., Miller, M., & Kealy, A. (2016) · Proceedings of the IEEE · doi:10.1109/jproc.2016.2528538 · Cited by 84
Crowd Map: Accurate Reconstruction of Indoor Floor Plans from Crowdsourced Sensor-Rich Videos
Chen, S., Li, M., Ren, K., & Qiao, C. (2015) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2015.9 · Cited by 92
Fast and Efficient FPGA-Based Feature Detection Employing the SURF Algorithm
Bouris, D., Nikitakis, A., & Papaefstathiou, I. (2010) · IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM) · doi:10.1109/fccm.2010.11 · Cited by 80
Geometric Correspondence Network for Camera Motion Estimation
Tang, J., Folkesson, J. B., & Jensfelt, P. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2794624 · Cited by 84
“In addition, we also listed results of SIFT, SURF, DAISY [48] and KAZE [49] as baseline hand crafted features in this test.”
MethodJorquera-Chavez, M., Fuentes, S., Dunshea, F. R., Warner, R. D., Poblete, T., & Jongman, E. C. (2019) · Animals · doi:10.3390/ani9121089 · Cited by 94
MS-HLMO: Multiscale Histogram of Local Main Orientation for Remote Sensing Image Registration
Gao, C., Li, W., Tao, R., & Du, Q. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3193109 · Cited by 100
Iterative Deep Homography Estimation
Cao, S.-Y., Hu, J., Sheng, Z., & Shen, H. (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/cvpr52688.2022.00192 · Cited by 120
“well-known feature extractors are SIFT [18], SURF [4], and ORB [4].”
Vehicle Detection for Autonomous Driving: A Review of Algorithms and Datasets
Karangwa, J., Liu, J., & Zeng, Z. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3292278 · Cited by 103
Zhuang, Y., Jiang, N., Hu, H., & Yan, F. (2012) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2012.2216475 · Cited by 84
Hybrid Feature Tracking and User Interaction for Markerless Augmented Reality
Lee, T., & Höllerer, T. (2008) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr.2008.4480766 · Cited by 84
“While more distinctive image features that are invariant to scale and orientation [22, 1] can be detected robustly for tracking over multiple frames, their complex computation makes the approach inappropriate for real-time applications that require around 30 frames per second(fps) [28].”
BackgroundLarge-scale knowledge transfer for object localization in ImageNet
Guillaumin, M., & Ferrari, V. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248055 · Cited by 72
Lin, B., Sun, Y., Qian, X., Goldgof, D. B., Gitlin, R. D., & You, Y. (2015) · International Journal of Medical Robotics and Computer Assisted Surgery · doi:10.1002/rcs.1661 · Cited by 87
“Many feature descriptors have been presented, such as SURF (41), SIFT (40) and binary robust independent elementary features (BRIEF) (56).”
MethodInfluentialLearning to Detect Features in Texture Images
Zhang, L., & Rusinkiewicz, S. M. (2018) · 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/cvpr.2018.00662 · Cited by 86
“We compare our detector to hand-crafted detectors including SIFT [11], SURF [2], MSER [12], WADE [18], SFOP [4], Harris Laplace [13] (HarrLap), Hessian Laplace [13] (HessLap), Harris Affine [13] (HarrAff) and Hessian Affine [13] (HessAff).”
MethodJaguar: Low Latency Mobile Augmented Reality with Flexible Tracking
Zhang, W., Han, B., & Hui, P. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240561 · Cited by 91
“There is a huge body of feature extraction algorithms, such as SIFT [33], SURF [14], ORB [41], FAST+FREAK [12] and BRISK [30].”
MethodNeural best-buddies: sparse cross-domain correspondence
Aberman, K., Liao, J., Shi, M., Lischinski, D., Chen, B., & Cohen‐Or, D. (2018) · ACM Transactions on Graphics · doi:10.1145/3197517.3201332 · Cited by 99
“Pairwise key-point localization, comparison to SIFT [Lowe 2004], SURF [Bay et al. 2006] and Deep Semantic Feature Matching [Ufer and Ommer 2017].”
BackgroundMethodInfluentialBOLD - Binary online learned descriptor for efficient image matching
Balntas, V., Tang, L. H. Y., & Mikolajczyk, K. (2015) · 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/cvpr.2015.7298850 · Cited by 83
When to use what feature? SIFT, SURF, ORB, or A-KAZE features for monocular visual odometry
Chien, H.-J., Chuang, C.-C., Chen, C., & Klette, R. (2016) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2016.7804434 · Cited by 98
Satellite image-based localization via learned embeddings
Kim, D.-K., & Walter, M. R. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989239 · Cited by 95
Ayhan, B., Dao, M., Kwan, C., Chen, H.-M., Bell, J. F., & Kidd, R. D. (2017) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2017.2716923 · Cited by 79
“We further performed experiments for the two-step image registration algorithm using SIFT features instead of SURF features.”
MethodInfluentialDetecting Fake News on Social Media
Shu, K., & Liu, H. (2019) · Synthesis lectures on data mining and knowledge discovery · doi:10.1007/978-3-031-01915-9 · Cited by 129
Recognizing Global Reservoirs From Landsat 8 Images: A Deep Learning Approach
Fang, W., Wang, C., Chen, X., Wan, W., Li, H., Zhu, S., Fang, Y., Liu, B., & Hong, Y. E. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2929601 · Cited by 81
“The speeded up robust features (SURF) operator [57] was used in BoVW to extract the feature description of the image.”
MethodVisDrone-SOT2019: The Vision Meets Drone Single Object Tracking Challenge Results
Du, D., Zhu, P., Wen, L., Bian, X., Ling, H., Hu, Q., Zheng, J., Peng, T., Wang, X., Zhang, Y., et al. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00029 · Cited by 85
“Our modifications are: 1) We estimate camera motion across frames using features matching (SURF features [1]) and homography transformation matrix estimation.”
MethodMotion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection
Ye, N., Wang, C., Fan, H., & Liu, S. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01287 · Cited by 103
Autonomous adaptive exploration using realtime online spatiotemporal topic modeling
Girdhar, Y., Giguère, P., & Dudek, G. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913507325 · Cited by 94
“To generate a visual vocabulary, we first extract visual features such as scale-invariant feature transform (SIFT; Lowe, 2004) or speeded up robust features (SURF; Bay et al., 2006) from an unrelated dataset, with high visual diversity.”
Galland, O., Bertelsen, H. S., Guldstrand, F., et al. (2016) · Journal of Geophysical Research Solid Earth · doi:10.1002/2015jb012564 · Cited by 79
Li, L., Liu, Y., Jiang, T., Wang, K., & Fang, M. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2646719 · Cited by 79
“In the experiments, we used the speeded up robust features algorithm [29] to extract the image feature points and computed optical flow from the continuously matched image feature points.”
MethodAggregating Deep Convolutional Feature Maps for Insulator Detection in Infrared Images
Zhao, Z., Fan, X., Xu, G., Zhang, L., Qi, Y., & Zhang, K. (2017) · IEEE Access · doi:10.1109/access.2017.2757030 · Cited by 83
“[34] E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, ‘‘ORB: An efficient alternative to SIFT or SURF,’’ in Proc.”
MethodInfluentialExploiting Image-trained CNN Architectures for Unconstrained Video ClassificationPreprint
Zha, S., Luisier, F., Andrews, W. D., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.04144 · Cited by 79
FIVR: Fine-Grained Incident Video Retrieval
Kordopatis-Zilos, G., Papadopoulos, S., Patras, I., & Kompatsiaris, I. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2905741 · Cited by 79
Towards Codebook-Free: Scalable Cascaded Hashing for Mobile Image Search
Zhou, W., Yang, M., Li, H., Wang, X., Lin, Y., & Tian, Q. (2014) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2014.2301979 · Cited by 77
Real-time video stabilization without phantom movements for micro aerial vehicles
Aguilar, W. G., & Ángulo, C. (2014) · EURASIP Journal on Image and Video Processing · doi:10.1186/1687-5281-2014-46 · Cited by 79
“E Rublee, V Rabaud, K Konolige, G Bradski, ORB: an efficient alternative to SIFT or SURF, in 2011 IEEE International Conference on Computer Vision (ICCV) (Barcelona, 6–13 Nov 2011), pp. 2564–2571 18.”
MethodInfluentialA hybrid feature extraction approach for brain MRI classification based on Bag-of-words
Elhamzi, W., Elhamzi, W., Charfi, I., & Atri, M. (2018) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2018.10.010 · Cited by 88
Qin, R. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.06.005 · Cited by 92
“Given that the minimal solver requires only one pair of corresponding points, the blunders yielded by typical point feature matches (e.g. SIFT/SURF) (Bay et al., 2006; Lowe, 2004) can be effectively eliminated through a RANSAC (Random Sampling Consensus) estimator (Fischler and Bolles, 1981).”
MethodDeep Graphical Feature Learning for the Feature Matching Problem
Zhang, Z., & Lee, W. S. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00519 · Cited by 88
“Earlier works with hierarchical handcrafted features such as hierarchical structured image pyramid rely on strong local features to construct scale invariant visual features [16, 1, 24].”
BackgroundVision-Based Measurement for Localization of Objects in 3-D for Robotic Applications
Lins, R. G., Givigi, S. N., & Kurka, P. R. G. (2015) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2015.2440556 · Cited by 78
“An important task for extracting geometric characteristics is to locate homologous point in both acquired images using a technique of local feature matching [27].”
MethodFast feature-based video stabilization without accumulative global motion estimation
Xu, J., Chang, H.-W., Yang, S., & Wang, M. (2012) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2012.6311347 · Cited by 82
“The reason for the difference in processing speed lies in two factors: (1) ORB is more efficient than SIFT and SURF, (2) ORB has the smallest number of features in motion estimation step, as illustrated in Fig.”
MethodInfluentialMinati, L., Frasca, M., Yoshimura, N., & Koike, Y. (2018) · IEEE Access · doi:10.1109/access.2018.2799145 · Cited by 79
“The video frames were de-multiplexed, de-interlaced, converted to gray-scale and undistorted, after which feature identification and matching was performed by means of the speeded-up robust features (SURF) technique [41].”
MethodPerformance evaluation of a multi-image 3D reconstruction software on a low-feature artefact
Koutsoudis, A., Vidmar, B., & Arnaoutoglou, F. (2013) · Journal of Archaeological Science · doi:10.1016/j.jas.2013.07.007 · Cited by 77
Juefei-Xu, F., & Savvides, M. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2329460 · Cited by 77
Context-Aware Personal Navigation Using Embedded Sensor Fusion in Smartphones
Saeedi, S., Moussa, A., & El‐Sheimy, N. (2014) · Sensors · doi:10.3390/s140405742 · Cited by 90
SIFT match verification by geometric coding for large-scale partial-duplicate web image search
Zhou, W., Li, H., Lu, Y., & Tian, Q. C. (2013) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/2422956.2422960 · Cited by 79
Fundus image quality assessment: survey, challenges, and future scope
Raj, A., Tiwari, A. K., & Martini, M. G. (2019) · IET Image Processing · doi:10.1049/iet-ipr.2018.6212 · Cited by 86
A Robust Approach for Securing Audio Classification Against Adversarial Attacks
Esmaeilpour, M., Cardinal, P., & Koerich, A. L. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2956591 · Cited by 89
Aslan, M. F., Durdu, A., & Sabancı, K. (2019) · Neural Computing and Applications · doi:10.1007/s00521-019-04365-9 · Cited by 80
“The speeded up robust features (SURF) algorithm [10] is also used to extract local features like SIFT.”
MethodHuang, G., Hu, Z., Wu, J., Xiao, H., & Zhang, F. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2974928 · Cited by 80
“ods, such as scale-invariant feature transform (SIFT) [42], speeded up robust feature (SURF) [43], and oriented FAST and rotated BRIEF (ORB) [44], provide an opportunity for”
BackgroundTsai, S. S., Chen, D. M., Chandrasekhar, V., Gabriel Takacs, A., Cheung, N. M., Vedantham, R., Grzeszczuk, R., & Girod, B. (2010) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1873951.1874293 · Cited by 75
“a descriptor, such as SIFT [9], SURF [4], or CHoG [5, 7], is generated from a local image patch around each interest point.”
MethodImage-based thermographic modeling for assessing energy efficiency of buildings façades
González‐Aguilera, D., Lagüela, S., Rodríguez‐Gonzálvez, P., & Hernández‐López, D. (2013) · Energy and Buildings · doi:10.1016/j.enbuild.2013.05.040 · Cited by 82
Halimeh, J. C., & Roser, M. (2009) · 2009 IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2009.5164347 · Cited by 76
“The main goal of the approach discussed in this a = arccos (8Ii~l) ,”
Background
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.