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 4,501–4,600 of 14,752
Burst Ranking for Blind Multi-Image Deblurring
Peña, F. A. G., Fernández, P. D. M., Ren, T. I., Leandro, J. D. J. G., & Nishihara, R. M. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2936073 · Cited by 14
Unsupervised Exemplar-Based Learning for Improved Document Image Classification
Abuelwafa, S., Pedersoli, M., & Cheriet, M. (2019) · IEEE Access · doi:10.1109/access.2019.2940884 · Cited by 15
Zhao, X., Min, H., Xu, Z., & Wang, W. (2019) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2019.09.001 · Cited by 13
Adaptive fractional masks and super resolution based approach for image enhancement
Shukla, A. K., Pandey, R. K., & Yadav, S. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08968-6 · Cited by 13
“To make the proposed algorithm fast and efficient, we have used the SURF transform [8], which is an alternative of SIFT transform.”
MethodX-ray of Tire Defects Detection via Modified Faster R-CNN
Chen, J., Li, Y., & Zhao, J. (2019) · International Conference on Safety Produce Informatization (IICSPI) · doi:10.1109/iicspi48186.2019.9095873 · Cited by 13
Image mosaicking using improved auto-sorting algorithm and local difference-based harris features
Vishwakarma, A., & Bhuyan, M. K. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09124-w · Cited by 13
“SURF-based methods are affected due to the variations in colour and illumination, and affine transformations.”
MethodInfluentialKeypoint-Based Local Descriptors for Target Recognition in SAR Images: A Comparative Analysis
Dong, G., Liu, H., & Chanussot, J. (2020) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2020.3005597 · Cited by 16
Anbu, T., Joe, M. M., & Murugeswari, G. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09585-z · Cited by 13
RetractedRiver segmentation for autonomous surface vehicle localization and river boundary mapping
Meier, K. C., Chung, S., & Hutchinson, S. (2020) · Journal of Field Robotics · doi:10.1002/rob.21989 · Cited by 15
“In this section, we compare how well SIFT (Lowe, 2004), SURF (Bay et al., 2006), BRISK (Leutenegger et al., 2011), and ORB (Rublee et al., 2011) match symmetric and stereo symmetric pairs for our river segmentation algorithm.”
MethodRobust Feature Matching with Spatial Smoothness Constraints
Huang, X., Wan, X., & Peng, D. (2020) · Remote Sensing · doi:10.3390/rs12193158 · Cited by 14
LCD – Line Clustering and Description for Place Recognition
Taubner, F., Tschopp, F., Novković, T., Siegwart, R., & Furrer, F. (2020) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv50981.2020.00101 · Cited by 21
Coarse-To-Fine Visual Localization Using Semantic Compact Map
Liao, Z., Shi, J., Qi, X., Zhang, X., Wang, W., He, Y., Liu, X., & Wei, R. (2020) · doi:10.1109/iccr51572.2020.9344376 · Cited by 16
“To ensure robustness in urban scenarios, researchers must carefully design features [5], [6] unaffected by viewpoints and highly dynamic objects.”
BackgroundLu, J., Jia, H., Li, T., Li, Z., Ma, J., & Zhu, R. (2021) · Remote Sensing · doi:10.3390/rs13091657 · Cited by 15
“The process performs through algorithms, such as scale-invariant feature transform (SIFT) [6], speeded up robust features (SURF) [7], oriented FAST and rotated BRIEF (ORB) [8], accelerated KAZE features (AKAZE) [9], etc. Feature matching refers to matching the key points based on the particular…”
BackgroundMethod3DTNet: Learning Local Features Using 2D and 3D Cues
Xing, X., Cai, Y., Lu, T., Cai, S., Yang, Y., & Wen, D. (2018) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2018.00057 · Cited by 15
Fast registration of segmented images by normal sampling
Kybic, J., Dolejší, M., & Borovec, J. (2015) · IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2015.7301311 · Cited by 13
Event-based location matching for consumer image collections
Das, M., Farmer, J., Gallagher, A., et al. (2008) · doi:10.1145/1386352.1386397 · Cited by 13
Android-based object recognition for the visually impaired
Saeed, N. N., Salem, M. A. ‐., & Khamis, A. M. (2013) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs.2013.6815497 · Cited by 13
“SIFT and SURF [17]) ORB is less robust to viewing condition changes, especially changes”
BackgroundMethodInfluentialLococo: low complexity corner detector
Mainali, P., Yang, Q., Lafruit, G., Lauwereins, R., & Gool, L. V. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5494944 · Cited by 17
Self-citationHigh performance vision tracking system for mobile robot using sensor data fusion with Kalman filter
Park, J., Hwang, W., Kwon, H.-I., et al. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5650367 · Cited by 13
Bouchot, J.-L., Stübl, G., & Moser, B. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.889865 · Cited by 14
Mobile Augmented Reality for Enhancing E-Learning and E-Business
You, S. O., & Neumann, U. (2010) · International Conference on Internet Technology and Applications · doi:10.1109/itapp.2010.5566168 · Cited by 13
“However, the high dimensionality of SIFT descriptor (and its variations [8][9]) is a significant drawback, especially for mobile or large-scale dataset applications.”
BackgroundAutomatic registration of LiDAR and optical imagery using depth map stereo
Kim, H.-J., Correa, C. D., & Max, N. (2014) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccphot.2014.6831821 · Cited by 13
“SURF also showed robustness against the relatively assigned colors in LiDAR depth maps.”
MethodInfluentialUdayan, J. D., Kim, H. S., & Kim, J. (2014) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1400141 · Cited by 15
Visual Odometry Based on Structural Matching of Local Invariant Features Using Stereo Camera Sensor
Núñez, P., Vázquez-Martín, R., & Bandera, A. J. (2011) · Sensors · doi:10.3390/s110707262 · Cited by 13
“In order to evaluate the proposed Visual Odometry method, different detectors and descriptors have been used in different real scenarios: corner-like image features (Harris corners [13]), faster but less stables, and SIFT [11] or SURF [12], more stables but higher computational load.”
MethodSensor Fusion in Computer Vision
Yılmaz, A. (2007) · doi:10.1109/urs.2007.371863 · Cited by 13
Design and evaluation of an embedded system based SLAM applications
Vincke, B., Elouardi, A., & Lambert, A. (2010) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2010.5708329 · Cited by 15
“Methods for detecting interest points have been provided by Harris [11], Shi-Tomasi [12], FAST [13], SIFT[14], SURF [15] or others.”
MethodImage Mosaic Based on SURF Feature Matching
Hong, J., Wu, L., Zhang, H., et al. (2009) · doi:10.1109/icise.2009.650 · Cited by 13
Audio Features in Music Information Retrieval
Grzywczak, D., & Gwardys, G. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-09912-5_16 · Cited by 14
Superpixel-based image recognition for food images
Zheng, J., Wang, Z. J., & Ji, X. (2016) · IEEE Canadian Conference on Electrical and Computer Engineering (CCECE) · doi:10.1109/ccece.2016.7726860 · Cited by 13
“Low-level features are often hand crafted, such as Scale Invariant Feature Transform (SIFT) [1], Speeded Up Robust Features (SURF) [2] and color descriptors [3].”
MethodDeep Learning—A New Era in Bridging the Semantic Gap
Markowska–Kaczmar, U., & Kwaśnicka, H. (2018) · Intelligent systems reference library · doi:10.1007/978-3-319-73891-8_7 · Cited by 17
Massive 3D digitization of sculptures: Methodological approaches for improving efficiency
Malik, U. S., & Guidi, G. (2018) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/364/1/012015 · Cited by 13
Stereo-Based vs. Monocular 6-DoF Pose Estimation Using Point Features: A Quantitative Comparison
Azad, P., Asfour, T., & Dillmann, R. (2009) · Informatik aktuell · doi:10.1007/978-3-642-10284-4_6 · Cited by 13
Tracking honey bee dances from sparse optical flow fields
Landgraf, T., & Rojas, R. F. (2007) · Refubium (Universitätsbibliothek der Freien Universität Berlin) · doi:10.17169/refubium-22713 · Cited by 13
Indexing of CNN Features for Large Scale Image Search
Liu, R., Zhao, Y., Wei, S., & Yang, Y. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1508.00217 · Cited by 14
Local Features in Image and Video Processing - Object Class Matching and Video Shot Detection
Lankinen, J. (2014) · LUTPub (LUT University) · Cited by 13
Local Feature Detectors, Descriptors, and Image Representations: A SurveyPreprint
Uchida, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.08368 · Cited by 20
Cresson, R., Grizonnet, M., & Michel, J. (2018) · doi:10.1002/9781119457091.ch5 · Cited by 13
Active Classification: Theory and Application to Underwater InspectionPreprint
Hollinger, G. A., Mitra, U., & Sukhatme, G. S. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1106.5829 · Cited by 13
Spacecraft Homography Pose Estimation with Single-Stage Deep Convolutional Neural Network
Chen, S., Yang, W., Wang, W., Mai, J., Liang, J., & Zhang, X. (2024) · Sensors · doi:10.3390/s24061828 · Cited by 12
“Examples of such feature extraction methods include SIFT [5], FAST [6], SURF [7], ORB [8], FPFH [9], etc.”
MethodA Comprehensive Review of Pill Image Recognition
My, L. N. T. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.060793 · Cited by 19
Lee, C., Rhee, C. E., & Lee, H. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2580400 · Cited by 12
“LP_SIFT uses an integral image to generate a scale space similar to SURF.”
MethodInfluentialKeypoint trajectory estimation using propagation based tracking
Fanani, N., Ochs, M., Bradler, H., et al. (2016) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2016.7535500 · Cited by 12
Run-Time Safety Monitoring Framework for AI-Based Systems: Automated Driving Cases
Osman, M. H., Kugele, S., & Shafaei, S. (2019) · Asia-Pacific Software Engineering Conference (APSEC) · doi:10.1109/apsec48747.2019.00066 · Cited by 13
“Classical approaches like HOG [6], SURF [7] or deep neural networks [8] can be used for this purpose.”
MethodReal-Time Panorama and Image Stitching with Surf-Sift Features
Degadwala, S., Chakraborty, U., Kuri, P., et al. (2021) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict50816.2021.9358586 · Cited by 12
Panetta, K. A., Kezebou, L., Oludare, V., Intriligator, J. M., & Agaian, S. С. (2021) · AI · doi:10.3390/ai2040041 · Cited by 17
“…methods used more traditional approaches for detecting vehicles in scenes and leaned towards the use of feature descriptors such as SIFT [15], SURF [16,17], and HOG [18] to retrieve relevant features, and using traditional machine learning techniques such as SVM [19,20], K-Means clustering…”
MethodDesign of Weapon Detection System
Sarkar, S., Ahire, S., Rahate, S., et al. (2022) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc54411.2022.9885601 · Cited by 12
Detecting Maritime Obstacles Using Camera Images
Kang, B.-S., & Jung, C.-H. (2022) · Journal of Marine Science and Engineering · doi:10.3390/jmse10101528 · Cited by 12
Dudek, T., & Kujawski, A. (2022) · Energies · doi:10.3390/en15249506 · Cited by 17
Self-Supervised Feature Learning for Long-Term Metric Visual Localization
Chen, Y., & Barfoot, T. D. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3227866 · Cited by 14
HVC-Net: Unifying Homography, Visibility, and Confidence Learning for Planar Object Tracking
Zhang, H., & Ling, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20047-2_40 · Cited by 12
A Comprehensive Review on Real Time Object Detection using Deep Learing Model
Goswami, P. K., & Goswami, G. (2022) · International Conference on System Modeling & Advancement in Research Trends (SMART) · doi:10.1109/smart55829.2022.10046972 · Cited by 12
Pansharpening With Spatial Hessian Non-Convex Sparse and Spectral Gradient Low Rank Priors
Liu, P. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3263103 · Cited by 12
“Moreover, some interest-point-detectors based on the Hessian can well detect the image corners, strong texture and edge parts [48], [49].”
BackgroundObject SLAM Based on Spatial Layout and Semantic Consistency
Ji, X., Liu, P., Niu, H., Chen, X., Ying, R., & Wen, F. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3316258 · Cited by 18
Zhao, Z., Lyu, J., Chu, Y., Liu, K., Cao, D., Wu, C., Qin, L., & Qin, S. (2023) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2023.102639 · Cited by 16
Real-Time Object Detection Overview: Advancements, Challenges, and Applications
Alsharabi, N. (2023) · مجلة جامعة عمران · doi:10.59145/jaust.v3i6.73 · Cited by 21
Li, J., Bi, G., Wang, X., Nie, T., & Huang, L. P. (2024) · Remote Sensing · doi:10.3390/rs16020214 · Cited by 15
Batch Normalization Free Rigorous Feature Flow Neural Network for Grocery Product Recognition
Selvam, P., Faheem, M., Dakshinamurthi, V., Nevgi, A., Bhuvaneswari, R., Deepak, K., & Sundar, K. J. A. (2024) · IEEE Access · doi:10.1109/access.2024.3400844 · Cited by 26
“Previously, hand-crafted feature approaches like Histogram of Oriented Gradients (HOG) [21] and Speeded Up Robust Features (SURF) [22] held a strong reputation.”
MethodQuantitative Analysis of Deep Learning-Based Object Detection Models
Elgazzar, K., Mostafi, S., Dennis, R., & Osman, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3401610 · Cited by 13
“Numerous other techniques exist that can perform object detection, such as corner detection [8], threshold segmentation [9], and the use of other feature descriptors, such as Speeded-up Robust Features (SURF) [10], SIFT [5], [6], [7], and Histograms of Oriented Gradients (HOG) [11].”
MethodAn Efficient and Fast Image Mosaic Approach for Highway Panoramic UAV Images
Zheng, H., Chang, Z., Li, Y., Zhu, J., Wang, W. R., Yang, Q., Xie, C., Zhang, J., & Liu, J. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3403228 · Cited by 15
“Among the classic feature point image mosaic algorithms, SIFT [8], [9], speeded-up robust features [10], accelerate-KAZE (AKAZE) [11], etc., SIFT has a pivotal position and created the upsurge of the development of image mosaic technology.”
BackgroundSURF feature descriptor for image analysis
Kumar, A. (2024) · Imaging and Radiation Research · doi:10.24294/irr.v6i1.5643 · Cited by 12
Abioye, O. A., Evwiekpaefe, A. E., & Awujoola, A. J. (2024) · Science Journal of University of Zakho · doi:10.25271/sjuoz.2024.12.2.1261 · Cited by 17
“Furthermore, these methods primarily rely on feature extraction techniques like scale-invariant feature transform (Lowe, 1999), speed robust features (Bay et al., 2006), and local binary patterns (Ojala et al., 2002).”
MethodMa, H., Chen, M., Xu, J., Yang, Y., Zhao, Y., & Liu, Y. (2024) · Science Advances · doi:10.1126/sciadv.adq5009 · Cited by 13
“SIFT key points are detected independently in each image ( 38 ), and feature vectors describing local image gradients around these key points are extracted.”
3D Microscopy Vision Using Multiple View Geometry and Differential Evolutionary Approaches
Tafti, A. P., Kirkpatrick, A. B., Owen, H. A., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14364-4_14 · Cited by 12
Retrieving images using saliency detection and graph matching
Huang, S., Wang, W., & Zhang, H. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025624 · Cited by 11
Xin, X., Zhu Li, B., & Katsaggelos, A. K. (2013) · Signal Processing Image Communication · doi:10.1016/j.image.2012.11.003 · Cited by 12
Physical activity recognition based on motion in images acquired by a wearable camera
Zhang, H., Li, L., Jia, W., Fernstrom, J. D., Sclabassi, R. J., Mao, Z., & Sun, M. (2011) · Neurocomputing · doi:10.1016/j.neucom.2011.02.014 · Cited by 14
Kataoka, H., Tamura, K., Iwata, K., et al. (2014) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e97.d.296 · Cited by 12
Retina enhanced SIFT descriptors for video indexing
Strat, S. T., Benoît, A., & Lambert, P. (2013) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2013.6576582 · Cited by 15
“In [12], this preprocessing allowed to design two kinds of descriptors based on OpponentSURF.”
MethodNew paradigm of learnable computer vision algorithms based on the representational MDL principle
Potapov, A. S., Malyshev, I. A., Puysha, A. E., et al. (2010) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.849532 · Cited by 12
“i b b i i S N G L N N r H G f L δ + + + = ∑ = w (8)”
Research on a novel non-rigid registration for medical image based on SURF and APSO
Wang, A., Wang, Z., Lv, D., & Fang, Z. (2010) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2010.5648148 · Cited by 14
Structural and visual similarity learning for Web page archiving
Law, M. T., Gutierrez, C. S., Thome, N., & Gancarski, S. (2012) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2012.6269849 · Cited by 15
Ship Image Recognition using HOG
MATSUMOTO, Y. (2013) · The Journal of Japan Institute of Navigation · doi:10.9749/jin.129.105 · Cited by 14
Visual word expansion and BSIFT verification for large-scale image search
Zhou, W., Li, H., Lu, Y., Wang, M., & Tian, Q. (2013) · Multimedia Systems · doi:10.1007/s00530-013-0330-4 · Cited by 13
Unsupervised object discovery via self-organisation
Kinnunen, T., Kämäräinen, J., Lensu, L. T., & Kalviainen, H. A. (2012) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.07.013 · Cited by 12
“• Speeded-Up Robust Features (SURF) Bay et al. (2006).”
A Target Tracking Algorithm Based on Improved Camshift and UKF
Yan, Z., Liang, W., & Lv, H. (2014) · Journal of Software Engineering and Applications · doi:10.4236/jsea.2014.713094 · Cited by 12
Real-time RGB-D registration and mapping in texture-less environments using ranked order statistics
Yousif, K., Bab‐Hadiashar, A., & Hoseinnezhad, R. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942925 · Cited by 13
User assisted disparity remapping for stereo images
Tasli, H. E., & Alatan, A. A. (2013) · Signal Processing Image Communication · doi:10.1016/j.image.2013.08.003 · Cited by 12
Multi Scale Shape Index for 3D Object Recognition
Bonde, U., Badrinarayanan, V., & Cipolla, R. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-38267-3_26 · Cited by 10
“They use a Hessian-based interest point detector that encodes an extension of 2D SURF features to 3D [2].”
MethodClassification approach for automatic laparoscopic video database organization
Twinanda, A. P., Marescaux, J., de Mathelin, M., & Padoy, N. (2015) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-015-1183-4 · Cited by 16
Adaptive Sampling for Feature Detection, Tracking, and Recognition on Mobile Platforms
Ebrahimi, M., & Mayol-Cuevas, W. W. (2011) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2011.2163450 · Cited by 12
Data detection for Smartphone visible light communications
Boubezari, R., Minh, H. L., Ghassemlooy, Z. F., et al. (2014) · doi:10.1109/csndsp.2014.6923981 · Cited by 12
“For instance, Speeded Up Robust Features (SURF) is a robust approach [9].”
BackgroundAccelerating Boosting-Based Face Detection on GPUs
Oro, D., Fern'ndez, C., Segura, C., Martorell, X., & Hernando, J. (2012) · Proceedings of the International Conference on Parallel Processing · doi:10.1109/icpp.2012.12 · Cited by 12
Evaluation of fisheye-camera based visual multi-session localization in a real-world scenario
Mühlfellner, P., Furgale, P., Derendarz, W., & Philippsen, R. (2013) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2013.6629447 · Cited by 13
Online parameter tuning for object tracking algorithms
Chau, D. P., Thonnat, M., Brémond, F., & Corvée, E. (2014) · Image and Vision Computing · doi:10.1016/j.imavis.2014.02.003 · Cited by 14
“We experiment this method with three object trackers: an appearance tracker [Chau et al., 2011a], a tracker based on KLT [Shi & Tomasi, 1994] and a tracker based on Surf [Bay et al., 2008].”
MethodByrne, J., & Shi, J. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.152 · Cited by 14
“Work has progressed from PCA-SIFT [6] and SURF [1] which show close performance to SIFT with lower dimensionality and faster preprocessing.”
BackgroundMethodMobile Image Analysis: Android vs. iOS
Cobârzan, C., Hudelist, M. A., Schoeffmann, K., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14442-9_9 · Cited by 12
Inertial-Kinect Fusion for Outdoor 3D Navigation
Qayyum, U., & Kim, J. (2013) · ANU Open Research (Australian National University) · Cited by 12
Automatic image scaling for place recognition in changing environments
Pepperell, E., Corke, P., & Milford, M. J. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139316 · Cited by 12
“FAB-MAP – along with SLAM systems such as MonoSLAM [2] and FrameSLAM [4] – uses feature descriptors, such as Speeded Up Robust Features (SURF) [11] to represent places, providing invariance to scale and rotation (and hence camera viewpoint).”
MethodFast Active SLAM for Accurate and Complete Coverage Mapping of Unknown Environments
Lenac, K., Kitanov, A., Maurović, I., Đakulović, M., & Petrovic, I. K. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-08338-4_31 · Cited by 12
An efficient image matching method using Speed Up Robust Features
Zhang, B., Jiao, Y., Ma, Z., Li, Y., & Zhu, J. (2014) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2014.6885757 · Cited by 15
“Therefore Bay [9] proposed a box filter method is used to approximate Gaussian filtering in order to improve the computing speed and take speed up the convolution of the integral image.”
MethodInfluentialFusion of Depth and Color Images for Dense Simultaneous Localization and Mapping
Conway, D. T., & Junkins, J. L. (2014) · Journal of Image and Graphics · doi:10.12720/joig.2.1.64-69 · Cited by 12
“Algorithms like Lucas-Kanade optical flow or SURF have been used for this task but often fail to match features over widely varying viewpoints [4] [5].”
MethodBastos, R., & Dias, M. S. (2008) · Repositório do ISCTE-IUL · Cited by 12
A survey on context-aware mobile visual recognition
Min, W., Jiang, S., Wang, S., et al. (2016) · Multimedia Systems · doi:10.1007/s00530-016-0523-8 · Cited by 12
Gender Identification of Human Brain Image with A Novel 3D Descriptor
Yuan, L., Chen, F., Zeng, L., Wang, L., & Hu, D. (2015) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2015.2448081 · Cited by 15
Optimizing tone mapping operators for keypoint detection under illumination changes
Rana, A., Valenzise, G., & Dufaux, F. (2016) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2016.7813340 · Cited by 12
An evaluation of HDR image matching under extreme illumination changes
Rana, A., Valenzise, G., & Dufaux, F. (2016) · Visual Communications and Image Processing · doi:10.1109/vcip.2016.7805556 · Cited by 12
Wireless vision-based fuzzy controllers for moving object tracking using a quadcopter
Algabri, M., Mathkour, H. I., Mekhtiche, M. A., Bencherif, M. A., Alsulaiman, M., Arafah, M. A., & Ghaleb, H. (2017) · International Journal of Distributed Sensor Networks · doi:10.1177/1550147717705549 · Cited by 11
4D Augmented City Models, Photogrammetric Creation and Dissemination
Niebling, F., Maiwald, F., Barthel, K., & Latoschik, M. E. (2018) · Communications in computer and information science · doi:10.1007/978-3-319-76992-9_12 · Cited by 13
Cross-Domain Co-Occurring Feature for Visible-Infrared Image Matching
Li, J., Li, C., Yang, T., et al. (2018) · IEEE Access · doi:10.1109/access.2018.2820680 · Cited by 12
Human action recognition using autoencoder
Xiao, Q., & Si, Y. (2017) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/compcomm.2017.8322824 · Cited by 12
“Local features always describe patches of an image independently, and then the patches can be compared and combined to build a space–time model [8], such as SURF [9] and HOG [10].”
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.