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 2,001–2,100 of 14,752
Troniak, D. M., Sattar, J., Gupta, A., et al. (2013) · doi:10.1109/crv.2013.12 · Cited by 36
Global image signature for visual loop-closure detection
Carrasco, P. L. N., Font, F. B., & Oliver, G. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9522-4 · Cited by 39
An Improved FAST+SURF Fast Matching Algorithm
Li, A., Jiang, W., Yuan, W., Dai, D., Zhang, S., & Wei, Z. (2017) · Procedia Computer Science · doi:10.1016/j.procs.2017.03.110 · Cited by 39
UNDERWATER PHOTOGRAMMETRY IN VERY SHALLOW WATERS: MAIN CHALLENGES AND CAUSTICS EFFECT REMOVAL
Agrafiotis, P., Skarlatos, D. P., Forbes, T., Poullis, C., Skamantzari, M., & Georgopoulos, A. (2018) · 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-2-15-2018 · Cited by 55
“For that, a commercial software performing SfM-MVS was used, the Agisoft’s Photoscan as well as other key point descriptors such as SIFT (Lowe, 1999) and SURF (Bay et al., 2006).”
MethodAn FPGA implementation for real-time edge detection
Jiang, J., Liu, C., & Ling, S. (2015) · Journal of Real-Time Image Processing · doi:10.1007/s11554-015-0521-7 · Cited by 36
“3, box-filter kernels are employed instead of Gaussian differential kernels to simplify the Gaussian differential convolution [25].”
D2-Net: A Trainable CNN for Joint Detection and Description of Local FeaturesPreprint
Dusmanu, M., Rocco, I., Pajdla, T., Pollefeys, M., Šivic, J., Torii, A., & Sattler, T. (2019) · arXiv (Cornell University) · Cited by 113
Mapping, planning and exploration with Pose SLAM
Carreño, R. V. (2013) · UPCommons institutional repository (Universitat Politècnica de Catalunya) · doi:10.5821/dissertation-2117-94927 · Cited by 39
Ahmad, J., Sajjad, M., Mehmood, I., Rho, S., & Baik, S. W. (2015) · Journal of Real-Time Image Processing · doi:10.1007/s11554-015-0536-0 · Cited by 39
They are Not Equally Reliable: Semantic Event Search Using Differentiated Concept Classifiers
Chang, X., Yu, Y., Yang, Y., & Xing, E. P. (2016) · 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.2016.208 · Cited by 35
“A usual MED system first extracts low-level features from videos of interest to capture salient gradient [34, 5], color [51] or motion [52] patterns, and then encode these with a pre-trained codebook to get a succinct representation.”
BackgroundA machine learning approach for cross-domain plant identification using herbarium specimens
Chulif, S., Lee, S. H., Chang, Y. L., & Chai, K. C. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07951-6 · Cited by 36
“Various feature descriptors such as scale-invariant feature transform [6], histogram of gradients [7], and speeded-up robust features [8] are employed together with conventional machine learning classification algorithms like K-nearest neighbors [9] and support vector machines [10] for plant identification.”
MethodA Novel Fingerprint Positioning Method Applying Vision-Based Definition for WIFI-Based Localization
Tang, C., Sun, W., Zhang, X., Zheng, J. Q., Wu, W., & Sun, J. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3280903 · Cited by 41
“…AP of the i th fingerprint point can be written as follows : B. Image Feature Calculation Based on ORB Scale-invariant feature transform [39] (SIFT), speeded up robust features [40] (SURF), and oriented FAST and rotated BRIEF [41] (ORB) are currently several common feature extraction algorithms.”
MethodGrebner, T., Riekenbrauck, R., & Waldschmidt, C. (2023) · IEEE Transactions on Radar Systems · doi:10.1109/trs.2023.3347734 · Cited by 40
Meng, Z., Du, X., Xia, J., Ma, Z., & Zhang, T. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.108900 · Cited by 38
Exploring Deep Learning-Based Visual Localization Techniques for UAVs in GPS-Denied Environments
Al-Jarrah, O. Y., Shatnawi, A. S., Shurman, M. M., Ramadan, O. A., & Muhaidat, S. (2024) · IEEE Access · doi:10.1109/access.2024.3440064 · Cited by 53
“There are various algorithms for feature extraction, description, and matching, including Scale-Invariant Feature Transform (SIFT) [27], [28], Speeded Up Robust Features (SURF) [29], Oriented FAST and Rotated BRIEF (ORB) [30], Harris corner detection, and Random Sample Consensus (RANSAC) [31], [32].”
MethodEngineering crop flower morphology facilitates robotization of cross-pollination and speed breeding
Xie, Y., Zhang, T., Yang, M., Lyu, H.-C., Zou, Y.-P., Sun, Y., Xiao, J. Y., Lian, W., Tao, J., Han, H., et al. (2025) · Cell · doi:10.1016/j.cell.2025.07.028 · Cited by 41
An Improvement Stereo Vision Images Processing for Object Distance Measurement
Tsung-Shiang, H., & Wang, T.-C. (2015) · International Journal of Automation and Smart Technology · doi:10.5875/ausmt.v5i2.460 · Cited by 35
A Feature Point Matching Based on Spatial Order Constraints Bilateral-Neighbor Vote
Meng, F., Li, X., & Pei, J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2456633 · Cited by 33
Orientation Covariant Aggregation of Local Descriptors with Embeddings
Tolias, G., Furon, T., & Jeǵou, H. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10599-4_25 · Cited by 34
Hand-Eye Calibration and Inverse Kinematics of Robot Arm Using Neural Network
Wu, H., Tizzano, W., Andersen, T. T., Axel, N., & Ravn, O. (2014) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-05582-4_50 · Cited by 36
Digitizing paper forms with mobile imaging technologies
Dell, N. L., Breit, N., Chaluco, T., Crawford, J., & Borriello, G. (2012) · ACM Symposium on Computing for Development (ACM DEV) · doi:10.1145/2160601.2160604 · Cited by 39
Ground tests for vision based determination and control of formation flying spacecraft trajectories
Gasbarri, P., Sabatini, M., & Palmerini, G. B. (2014) · Acta Astronautica · doi:10.1016/j.actaastro.2013.11.035 · Cited by 35
Uniting Keypoints: Local Visual Information Fusion for Large-Scale Image Search
Liu, Z., Li, H., Zhou, W., Hong, R., & Tian, Q. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2399851 · Cited by 35
“After the small patch is detected, it is described by a discriminative descriptor, such as SIFT [17], SURF [20] in image search applications.”
MethodAutomatic orientation and 3D modelling from markerless rock art imagery
Lerma, J. L., Navarro, S., Cabrelles, M., Seguí, A. E., & Hernández‐López, D. (2012) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2012.08.002 · Cited by 35
Towards improving the efficiency of sequence-based SLAM
Liu, Y., & Zhang, H. (2013) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2013.6618095 · Cited by 34
Integrated vision-based robotic arm interface for operators with upper limb mobility impairments
Jiang, H., Wachs, J. P., & Duerstock, B. S. (2013) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr.2013.6650447 · Cited by 37
Xue, K., Liu, Y., Ogunmakin, G., Chen, J., & Zhang, J. (2012) · Machine Vision and Applications · doi:10.1007/s00138-012-0426-4 · Cited by 40
“Since SURF features are faster to extract than SIFT features [26], we use them instead of SIFT features in the on-line registration method.”
MethodVideo Event Detection Using Motion Relativity and Feature Selection
Wang, F., Sun, Z., Jiang, Y., & Ngo, C. (2014) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2014.2315780 · Cited by 35
A SLAM Overview from a User’s Perspective
Frese, U., Wagner, R., & Röfer, T. (2010) · Künstliche Intell. · doi:10.1007/s13218-010-0040-4 · Cited by 42
On the design of a novel JPEG quantization table for improved feature detection performance
Chao, J., Chen, H., & Steinbach, E. G. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738345 · Cited by 32
Content-Based Prediction of Movie Style, Aesthetics, and Affect: Data Set and Baseline Experiments
Tarvainen, J., Sjöberg, M., Westman, S., Laaksonen, J. T., & Oittinen, P. T. (2014) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2014.2357688 · Cited by 42
“Lastly, we modeled the difference between adjacent video frames with three measures: the raw average pixel-wise RGB difference, the Euclidean distance between Census Transform (Centrist) [77] features and the average measured movement length of matching SURF key-points [78] between the frames.”
MethodThe Nature-Inspired BASIS Feature Descriptor for UAV Imagery and Its Hardware Implementation
Fowers, S. G., Lee, D.-J., Ventura, D. A., & Archibald, J. K. (2012) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2012.2223631 · Cited by 34
“Feature descriptors take feature points obtained from a detector [20]–[23], and compute a unique description of each point [20], [24]–[26].”
BackgroundMethodLearning salient visual word for scalable mobile image retrieval
Yang, X., Qian, X., & Mei, T. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2014.12.017 · Cited by 35
Review of person re‐identification techniques
Saghafi, M. A., Hussain, A., Zaman, H. B., & Saad, M. H. M. (2014) · IET Computer Vision · doi:10.1049/iet-cvi.2013.0180 · Cited by 53
Accurate 3D face reconstruction from weakly calibrated wide baseline images with profile contours
Lin, Y., Medioni, G. G., & Choi, J. (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.2010.5539793 · Cited by 39
Fully pipelined FPGA-based architecture for real-time SIFT extraction
Vourvoulakis, J. V., Kalomiros, J. A., & Lygouras, J. N. (2015) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2015.11.013 · Cited by 35
Multiple Object Tracking Using SIFT Features and Location Matching
Ha, S.-W., & Moon, Y. H. (2011) · Cited by 35
Saeed, A., Abdelkader, A., Khan, M., et al. (2017) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1145/3055031.3055078 · Cited by 35
A Convolutional Neural Network Model for Predicting a Product's Function, Given Its Form
Dering, M. L., & Tucker, C. S. (2017) · Journal of Mechanical Design · doi:10.1115/1.4037309 · Cited by 38
Kuželka, K., & Surový, P. (2018) · European Journal of Remote Sensing · doi:10.1080/22797254.2017.1419442 · Cited by 35
MSFD: Multi-Scale Segmentation-Based Feature Detection for Wide-Baseline Scene Reconstruction
Mustafa, A., Kim, H., & Hilton, A. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2872906 · Cited by 30
“Existing feature detectors such as Harris [1], [2], SIFT [3], SURF [4], FAST [5], KAZE [6] and MSER [7] often yield sparse and non-uniformly distributed feature sets for widebaseline matching and reconstruction, as seen in later sections.”
InfluentialA Disocclusion Inpainting Framework for Depth-Based View Synthesis
Luo, G., Zhu, Y., Weng, Z., & Li, Z. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2899837 · Cited by 36
“In the motion compensation process, SURF [60] is used to detect and describe the feature points in the reference frame and the current frame.”
MethodAdvance Intelligent Video Surveillance System (AIVSS): A Future Aspect
Rai, M., Husain, A. A., Maity, T., & Yadav, R. K. (2019) · IntechOpen eBooks · doi:10.5772/intechopen.76444 · Cited by 35
“Nonetheless, identification and extrac - tion are computationally requesting and consequently cannot be utilized as a part of systems with restricted computational power [ 17].”
BackgroundMatching RGB and Infrared Remote Sensing Images with Densely-Connected Convolutional Neural Networks
Zhu, R., Yu, D., Ji, S., & Lü, M. (2019) · Remote Sensing · doi:10.3390/rs11232836 · Cited by 36
Deep Learning for Underwater Visual Odometry Estimation
Teixeira, B., Silva, H. M., Matos, A. C., & Silva, E. (2020) · IEEE Access · doi:10.1109/access.2020.2978406 · Cited by 41
Li, M., Chen, R., Liao, X., Guo, B., Zhang, W., & Guo, G. (2020) · Remote Sensing · doi:10.3390/rs12050869 · Cited by 39
“The establishment of the positioning feature database mainly includes image acquisition, bundle adjustment, and feature descriptor matching for SURF and 3D object co-ordinates.”
MethodInfluentialWeakly Supervised Instance Segmentation of Electrical Equipment Based on RGB-T Automatic Annotation
Ma, J., Qian, K., Zhang, X., & Ma, X. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3001796 · Cited by 35
“Harris [32], SIFT [33], and SURF [34] have been widely used in image registration, but these features are unstable for heterogeneous images.”
Vision System for Automatic On-Tree Kiwifruit Counting and Yield Estimation
Mekhalfi, M. L., Nicolò, C., Ianniello, I., Calamita, F., Goller, R., Barazzuol, M., & Melgani, F. (2020) · Sensors · doi:10.3390/s20154214 · Cited by 43
LSTM and Filter Based Comparison Analysis for Indoor Global Localization in UAVs
Yusefi, A., Durdu, A., Aslan, M. F., & Sungur, C. (2021) · IEEE Access · doi:10.1109/access.2021.3049896 · Cited by 37
“Feature-based methods use a range of feature detectors such as SURF (Speeded Up Robust Features) [27], FAST (Features from Accelerated Segment Test) [28], SIFT (Scale-Invariant Feature Transform) [29], ORB (Oriented FAST and Rotated BRIEF) [30] and Harris and Stephens [31] to detect key points.”
MethodMeng, L., Zhou, J. P., Liu, S., Ding, L., Zhang, J., Wang, S., & Lei, T. (2021) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2021.102403 · Cited by 40
Xu, Y., Huang, J., Wang, J., Wang, Y., Qin, H., & Nan, K. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3094228 · Cited by 41
A survey of 3D object detection
Liang, W. G., Xu, P., Guo, L., Bai, H., Zhou, Y., & Chen, F. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11137-y · Cited by 45
“The feature extraction methods include SIFT [27, 68], HOG [57] and SURF [2].”
MethodLin, Q., Yang, L., Zhong, P., & Zou, H. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107331 · Cited by 37
Leveraging Deep Statistics for Underwater Image Enhancement
Wang, Y., Cao, Y. H., Zhang, J., Wu, F., & Zha, Z.-J. (2021) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3489520 · Cited by 42
“We employ speeded-up robust features (SURF) [57] to compute and match key points of original underwater images and processed images, and the test result was shown in Figure 15(b) As can be observed, by removing the color shift and enhancing the contrast in underwater images, our UIE-Net significantly increases the num…”
MethodEfficient and Accurate Stitching for 360° Dual-Fisheye Images and Videos
Lo, I.-C., Shih, K.-T., & Chen, H. H. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3130531 · Cited by 35
Xia, W., Han, D., Li, D., Wu, Z., Han, B., & Wang, J. (2022) · Annals of Applied Biology · doi:10.1111/aab.12804 · Cited by 45
Contextual Similarity Distillation for Asymmetric Image Retrieval
Wu, H., Wang, M., Zhou, W., Li, H., & Tian, Q. C. (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/cvpr52688.2022.00927 · Cited by 55
Spectral Clustering with a Convex Regularizer on Millions of Images
Collins, M. D., Liu, J., Xu, J. W., Mukherjee, L., & Singh, V. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10578-9_19 · Cited by 41
SLAM in with the Combined Kalman-Information Filter
Cadena, C., & Neira, J. (2010) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2010.08.003 · Cited by 40
“In these cases, appearance can be coded using a descriptor vector d, thenM = {μ, ξ, , d}, for example SIFT [33] or SURF [34].”
MethodSMD: A Locally Stable Monotonic Change Invariant Feature Descriptor
Gupta, R. K., & Mittal, A. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88688-4_20 · Cited by 37
EAGLE: A novel descriptor for identifying plant species using leaf lamina vascular features
Charters, J., Wang, Z., Chi, Z., et al. (2014) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2014.6890557 · Cited by 35
“This approach leverages the discriminative power of robust local feature detectors such as SIFT [19] and SURF [20], effectively focusing EAGLE feature extraction on the most distinctive parts of an image, which are typically the edges and venation structure based on our experimentation.”
MethodAssembly manipulation of small objects by dual‐arm manipulator
Shauri, R. L. A., & Nonami, K. (2011) · Assembly Automation · doi:10.1108/01445151111150604 · Cited by 38
Local Feature Based Person Reidentification in Infrared Image Sequences
Jüngling, K., & Arens, M. (2010) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2010.75 · Cited by 36
Stereoscopic depth perception in video see-through augmented reality within action space
Kytö, M., Mäkinen, A., Tossavainen, T., & Oittinen, P. T. (2014) · Journal of Electronic Imaging · doi:10.1117/1.jei.23.1.011006 · Cited by 36
UAV-Video Registration Using Block-Based Features
Hafiane, A., Palaniappan, K., & Seetharaman, G. S. (2008) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2008.4779192 · Cited by 34
Geometrically Invariant Object-Based Watermarking using SIFT Feature
Pham, V. Q., Miyaki, T., Yamasaki, T., et al. (2007) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2007.4379868 · Cited by 35
“Besides, we can improve the speed of our method by replacing SIFT by any faster matching methods such as SURF [9].”
MethodLandslide monitoring by fixed-base terrestrial stereo-photogrammetry
Roncella, R., Forlani, G., Fornari, M., et al. (2014) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-ii-5-297-2014 · Cited by 35
Into Darkness: Visual Navigation Based on a Lidar-Intensity-Image Pipeline
Barfoot, T. D., McManus, C., Anderson, S., Dong, H., Beerepoot, E., Tong, C. H., Furgale, P., Gammell, J. D., & Enright, J. P. (2016) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-28872-7_28 · Cited by 38
“The introduction of Bouguet’s Camera Calibration Toolbox for Matlab [4], and its subsequent C implementation in OpenCV [5] drastically reduced the learning curve associated with camera calibration.”
BackgroundMethodInfluentialVisual Recognition of Ancient Inscriptions Using Convolutional Neural Network and Fisher Vector
Amato, G. M., Falchi, F., & Vadicamo, L. (2016) · Journal on Computing and Cultural Heritage · doi:10.1145/2964911 · Cited by 45
From Marker to Markerless in Augmented Reality
Oufqir, Z., Abderrahmani, A. E., & Satori, K. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-0947-6_57 · Cited by 49
Zaffar, M., Khaliq, A., Ehsan, S., Milford, M. J., & McDonald-Maier, K. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.09107 · Cited by 50
“The early techniques employed for image matching in VPR consisted of handcrafted feature descriptors [15] [16].”
MethodPVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose EstimationPreprint
He, Y., Sun, W. M., Huang, H., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.04231 · Cited by 35
Implementation of a Map Relative Localization System for Planetary Landing
Johnson, A., Cheng, Y., Trawny, N., et al. (2023) · Journal of Guidance Control and Dynamics · doi:10.2514/1.g006780 · Cited by 34
Underwater Surface Normal Reconstruction via Cross-Grained Photometric Stereo Transformer
Ju, Y., Li, L., Zhong, X., et al. (2024) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2024.3458110 · Cited by 34
“Matching methods [20], [21], [22] are limited to fixed lighting and rely on rich texture features.”
A comprehensive review of research on surface defect detection of PCBs based on machine vision
He, Z., Lian, Y., Wang, Y., & Lu, Z. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.106437 · Cited by 58
Muzzle-Based Cattle Identification Using Speed up Robust Feature Approach
Abd, S. A., Gaber, T., Tharwat, A., et al. (2015) · International Conference on Intelligent Networking and Collaborative Systems (INCoS) · doi:10.1109/incos.2015.60 · Cited by 34
“Thus, there is no need do downscale the image into different scales which makes SURF fast compared with SIFT [13], [14].”
BackgroundMethodResultInfluentialAn Evaluation of Open Source SURF Implementations
Gossow, D., Decker, P., & Paulus, D. W. R. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-20217-9_15 · Cited by 37
Scale-only visual homing from an omnidirectional camera
Liu, M., Pradalier, C., Pomerleau, F., & Siegwart, R. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6224900 · Cited by 36
Robust people counting using sparse representation and random projection
Foroughi, H., Ray, N., & Zhang, H. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.02.009 · Cited by 32
“In Conte et al.'s [50] method, SURF [53] features are extracted from images, which is followed by a Support Vector Regression (ϵ-SVR) function to estimate the number of people present in the scene.”
Method[Survey paper] A Review of Video Retrieval Based on Image and Video Semantic Understanding
Haseyama, M., Ogawa, T., & Yagi, N. (2012) · ITE Transactions on Media Technology and Applications · doi:10.3169/mta.1.2 · Cited by 38
Active matching for visual tracking
Chli, M., & Davison, A. J. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2009.07.010 · Cited by 34
“While SIFT [19] or SURF [20] features would be particularly useful for matching due to their highly descriptive and distinctive nature (especially in the presence of only weak priors) the cost associated with their extraction renders them unsuitable for frame-rate matching (depending on the number of features tracked…”
MobileAR Browser - A generic architecture for rapid AR-multi-level development
Engelke, T., Becker, M., Wuest, H., Keil, J., & Kuijper, A. (2013) · Expert systems with applications · doi:10.1016/j.eswa.2012.11.003 · Cited by 40
Field-Programmable System-on-Chip for Localization of UGVs in an Indoor iSpace
Rodríguez-Araújo, J., Rodriguez-Andina, J. J., Fariña, J., et al. (2014) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2013.2294112 · Cited by 34
A Taxonomy of Vision Systems for Ground Mobile Robots
Martínez-Gómez, J., Fernández‐Caballero, A., García-Varea, I., Rodriguez, L., & Romero-González, C. (2014) · International Journal of Advanced Robotic Systems · doi:10.5772/58900 · Cited by 35
“• Speed-up Robust Features (SURF) [143].”
Multiple-view object recognition in band-limited distributed camera networks
Yang, A. Y., Maji, S., Christoudias, C. M., Darrell, T., Malik, J., & Sastry, S. (2009) · ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC) · doi:10.1109/icdsc.2009.5289410 · Cited by 34
Accelerating mobile augmented reality on a handheld platform
Lee, S. E., Zhang, Z. F. Y., Srinivasan, S., et al. (2009) · Proceedings, IEEE International Conference on Computer Design/Proceedings - IEEE International Conference on Computer Design · doi:10.1109/iccd.2009.5413123 · Cited by 34
Pugeault, N., Wörgötter, F., & Krüger, N. (2010) · International Journal of Humanoid Robotics · doi:10.1142/s0219843610002209 · Cited by 34
Dynamic hand gesture recognition based on SURF tracking
Bao, J., Song, A., Guo, Y., et al. (2011) · International Conference on Electric Information and Control Engineering · doi:10.1109/iceice.2011.5777598 · Cited by 34
An Informative Feature Selection Method Based on Sparse PCA for VHR Scene Classification
Chaib, S., Gu, Y., & Yao, H. (2015) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2015.2501383 · Cited by 34
Marginalizing stacked linear denoising autoencoders
Chen, M., Weinberger, K. Q., Xu, Z., & Sha, F. (2015) · Journal of Machine Learning Research · doi:10.5555/2789272.2912118 · Cited by 31
A Two-Step Approach for Longitudinal Registration of Retinal Images
Saha, S., Xiao, D., Frost, S. M., & Kanagasingam, Y. (2016) · Journal of Medical Systems · doi:10.1007/s10916-016-0640-0 · Cited by 34
RGB-D sensor-based visual SLAM for localization and navigation of indoor mobile robot
-, W. P. L. J. Z. Y., Li, Z., & Su, C. (2016) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm.2016.7606899 · Cited by 36
Geometric Graph Matching Using Monte Carlo Tree Search
Pinheiro, M. A., Kybic, J., & Fua, P. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2636200 · Cited by 33
“Appearance node attributes or descriptors [21], [22] are often used to prune matches between incompatible points in RANSAC-like methods.”
MethodMedical Image Tamper Detection Based on Passive Image Authentication
Ulutaş, G., Üstübıoğlu, A., Üstübioğlu, B., Nabiyev, V. V., & Ulutaş, M. (2017) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-017-9961-x · Cited by 34
Feature matching evaluation for multimodal correspondence
Gesto, M., Tombari, F., González‐Aguilera, D., López-Fernández, L., & Rodríguez‐Gonzálvez, P. (2017) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.05.007 · Cited by 34
Enhancing Mastcam Images for Mars Rover Mission
Dao, M., Kwan, C., Ayhan, B., & Bell, J. F., III (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59081-3_24 · Cited by 35
A brain-inspired SLAM system based on ORB features
Zhou, S.-C., Yan, R., Li, J., Chen, Y., & Tang, H. (2017) · Machine Intelligence Research · doi:10.1007/s11633-017-1090-y · Cited by 36
“Therefore, many methods aimed at speeding up the computation of SIFT have been published [26 − 32] .”
MethodA-RANSAC: Adaptive random sample consensus method in multimodal retinal image registration
Hossein‐Nejad, Z., & Nasri, M. (2018) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2018.06.002 · Cited by 34
Region duplication detection based on hybrid feature and evaluative clustering
Lin, C., Lu, W., Huang, X., Liu, K., Sun, W., & Lin, H. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7342-9 · Cited by 34
“The Scale-Invariant Feature Transform (SIFT) [49] or the Speeded Up Robust Features (SURF) [9] is usually extracted from the whole image as feature points.”
Keypoint Encoding for Improved Feature Extraction From Compressed Video at Low Bitrates
Chao, J., & Steinbach, E. G. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2502552 · Cited by 34
Palacios, F., Diago, M. P., & Tardáguila, J. (2019) · Sensors · doi:10.3390/s19173799 · Cited by 37
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.