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 2,401–2,500 of 14,752
AT&T Research at TRECVID 2009 Content-based Copy Detection
Liu, Z., Shahraray, B., & Liu, T. (2009) · TRECVID · Cited by 33
A novel image registration approach via combining local features and geometric invariants
Lu, Y., Gao, K., Zhang, T., & Xu, T. (2018) · PLoS ONE · doi:10.1371/journal.pone.0190383 · Cited by 30
Li, Y., Hu, W., Li, H., Dong, H., Zhang, B., & Tian, Q. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2988175 · Cited by 34
“…with handcrafted features, such as the gray level cooccurrence matrix [1], histograms of oriented gradients [4], scale-invariant feature transform [5], speed-up robust features [6], and local binary pattern [7], were intensively investigated for object classification in building damage assessment.”
BackgroundSIFT Meets CNN: A Decade Survey of Instance RetrievalPreprint
Zheng, L., Yang, Y. P., & Tian, Q. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.01807 · Cited by 30
Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose EstimationPreprint
Kehl, W., Milletarì, F., Tombari, F., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.06038 · Cited by 30
CattNIS: Novel identification system of cattle with retinal images based on feature matching method
Saygılı, A., Cihan, P., Ermutlu, C. Ş., Aydın, U., & Aksoy, Ö. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.108963 · Cited by 33
Early Diagnosis of Autism: A Review of Video-Based Motion Analysis and Deep Learning Techniques
Yang, Z., Zhang, Y., Ning, J., Wang, X., & Wu, Z. (2025) · IEEE Access · doi:10.1109/access.2024.3523872 · Cited by 36
Nair, R. R., & Babu, T. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.121 · Cited by 30
Zhao, Z., Wu, C. W., Kong, X., Li, Q., Guo, Z., Lv, Z., & Du, X. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3562319 · Cited by 56
“The feature extraction stage includes a variety of traditional algorithms, including Harris corner point [20], SIFT [21], SURF [22], FAST [23], ORB [24], and so on.”
MethodA hybrid probabilistic neural model for person tracking based on a ceiling-mounted camera
Yan, W., Weber, C., & Wermter, S. (2011) · Journal of Ambient Intelligence and Smart Environments · doi:10.3233/ais-2011-0111 · Cited by 30
MSIDX: Multi-Sort Indexing for Efficient Content-Based Image Search and Retrieval
Tiakas, E., Rafailidis, D., Dimou, A., & Daras, P. (2013) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2013.2247989 · Cited by 30
“%) is achieved in all datasets, except SURF-5000d which returns mAP between 40% and 50%.”
MethodInfluentialCompact descriptors for mobile visual search and MPEG CDVS standardization
Duan, L., Gao, F., Chen, J., Lin, J., & Huang, T. (2013) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2013.6571989 · Cited by 30
A review of object representation based on local features
Cao, J., Mao, D., Cai, Q., Li, H., & Du, J. (2013) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/jzus.cide1303 · Cited by 31
Egocentric Real-time Workspace Monitoring using an RGB-D camera
Damen, D., Gee, A. P., Mayol-Cuevas, W. W., & Calway, A. D. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385829 · Cited by 29
“SURF features [1] are extracted from the intensity image in each keyframe and their global 3D position found from the depth image and estimated camera pose.”
MethodIakovidou, C., Anagnostopoulos, N., Kapoutsis, A. C., Boutalis, Y. S., & Chatzichristofis, S. A. (2014) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2014.6849821 · Cited by 29
“Some among the most widely employed POI detectors are corner detectors Harris [13], ShiTomasi [14], and FAST [15] and blob detectors SIFT [16], SURF [17], to name a few.”
MethodAn interactive augmented reality coloring book
Clark, A., Dünser, A., & Grasset, R. (2011) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2011.6143487 · Cited by 30
Temporally consistent disparity maps from uncalibrated stereo videos
Bleyer, M., & Gelautz, M. (2009) · doi:10.1109/ispa.2009.5297701 · Cited by 29
“To compute these rectification matrices, we determine a set of correspondences between left and right images using the computational efficient SURF features [2].”
MethodMulti-sensor semantic mapping and exploration of indoor environments
Jebari, I., Bazeille, S., Battesti, E., Tekaya, H., Klein, M., Tapus, A., Filliat, D., Meyer, C., Ieng, S.-H., Benosman, R. B., et al. (2011) · IEEE International Conference on Technologies for Practical Robot Applications · doi:10.1109/tepra.2011.5753498 · Cited by 28
Interframe Coding of Canonical patches for Low Bit-rate Mobile Augmented Reality
Makar, M., Tsai, S. S., Chandrasekhar, V., Chen, D. M., & Girod, B. (2013) · International Journal of Semantic Computing · doi:10.1142/s1793351x13400011 · Cited by 30
Evaluation of feature point detection in high dynamic range imagery
Přibyl, B., Chalmers, A. G., Zemčík, P., Hooberman, L., & Čadík, M. (2016) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2016.02.007 · Cited by 28
Learning coherent vector fields for robust point matching under manifold regularization
Wang, G., Wang, Z., Chen, Y., Liu, X., Ren, Y., & Lei, P. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.08.009 · Cited by 29
Globally consistent alignment for planar mosaicking via topology analysis
Xia, M., Yao, J., Xie, R., Li, L., & Zhang, W. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.01.020 · Cited by 29
Stratoulias, D., Tolpekin, V. A., de By, R., Zurita‐Milla, R., Retsios, V., Bijker, W., Hasan, M. A., & Vermote, E. F. (2017) · Remote Sensing · doi:10.3390/rs9101048 · Cited by 29
Deep compare: A study on using convolutional neural networks to compare image patches
Zagoruyko, S., & Komodakis, N. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.10.007 · Cited by 32
A Survey of Recent Advances in Texture Representation.
Liu, L., Chen, J., Fieguth, P., Zhao, G., Chellappa, R., & Pietikäinen, M. (2018) · Cited by 34
The Impact of Augmented Reality on Art Engagement: Liking, Impression of Learning, and Distraction
Aitamurto, T., Boin, J.-B., Chen, K., Cherif, A., & Shridhar, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-91584-5_13 · Cited by 39
“After a query frame is captured, visual features (SURF) [4] are extracted and aggregated into a compact low-dimensional signature (REVV) [9] that retains most of the visual information of the image.”
MethodGenetic Programming for Automatic Global and Local Feature Extraction to Image Classification
Bi, Y., Zhang, M., & Xue, B. (2018) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2018.8477911 · Cited by 29
Díaz-Paz, J. P., da Silva, R. L., Zhong, B., Huang, H., & Lobaton, E. J. (2018) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8512614 · Cited by 30
Detection of Waste Containers Using Computer Vision
Valente, M., Silva, H., Caldeira, J. M. L. P., et al. (2019) · Applied System Innovation · doi:10.3390/asi2010011 · Cited by 29
An Improved ORB Algorithm of Extracting and Matching Features
Lei, Y., Yu, Z., & Gong, Y. (2015) · International Journal of Signal Processing Image Processing and Pattern Recognition · doi:10.14257/ijsip.2015.8.5.12 · Cited by 28
“In 2006, Bay, et al., proposed a registration algorithm after SIFT algorithm based on fast robust characteristic--SURF algorithm [4].”
MethodModeling of facial aging and kinship: A survey
Georgopoulos, M., Panagakis, Y., & Pantić, M. (2018) · Image and Vision Computing · doi:10.1016/j.imavis.2018.05.003 · Cited by 35
Trivizakis, E., Ioannidis, G., Melissianos, V., Papadakis, G. Z., Tsatsakis, A. M., Spandidos, D. A., & Kostas Marias, A. (2019) · Oncology Reports · doi:10.3892/or.2019.7312 · Cited by 29
Automated Defect Detection and Visualization for the Robotic Airport Runway Inspection
Gui, Z., & Li, H. (2020) · IEEE Access · doi:10.1109/access.2020.2986483 · Cited by 29
Joint 3D Reconstruction and Object Tracking for Traffic Video Analysis Under IoV Environment
Cao, M., Zheng, L., Jia, W., & Liu, X. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.2995768 · Cited by 30
“In case of feature detector, there are SIFT [27], SURF [28], ORB [29], SuperPoint [30], and so on.”
MethodComparison of SURF and HOG extraction in classifying the blood image of malaria parasites using SVM
Muhathir, M., Rizal, R. A., Sihotang, J. S., et al. (2019) · International Conference of Computer Science and Information Technology (ICoSNIKOM) · doi:10.1109/icosnikom48755.2019.9111647 · Cited by 29
Deep learning-based fetoscopic mosaicking for field-of-view expansion
Bano, S., Vasconcelos, F., Tella-Amo, M., et al. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02242-8 · Cited by 29
“FEAT extract speeded up robust features [6] from a pair of images and performs an exhaustive search for feature matching to estimate the homography.”
MethodNaus, K., Wąż, M., Szymak, P., et al. (2020) · Measurement · doi:10.1016/j.measurement.2020.108630 · Cited by 29
Loop-Closure Detection Using Local Relative Orientation Matching
Ma, J., Ye, X., Zhou, H., Mei, X., & Fan, F. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3074520 · Cited by 29
Wang, T., Wang, Z., Cao, Y. Q., et al. (2021) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2021.04.031 · Cited by 29
Attention Aware Wavelet-based Detection of Morphed Face Images
Aghdaie, P., Chaudhary, B., Soleymani, S., Dawson, J. M., & Nasrabadi, N. M. (2021) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb52358.2021.9484398 · Cited by 33
Active Pose Relocalization for Intelligent Substation Inspection Robot
Qian, J., Liu, Y., Yan, Y., et al. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3186368 · Cited by 29
“Specifically, the speeded up robust features (SURF), as a widely used feature detector in robotics motion estimation due to its low computation time [31], [32], is utilized to find the matching points D c and D r between the calibration image I c and the real time inspection image I r .”
MethodVisual-LiDAR SLAM Based on Unsupervised Multi-channel Deep Neural Networks
An, Y., Shi, J., Gu, D., & Liu, Q. (2022) · Cognitive Computation · doi:10.1007/s12559-022-10010-w · Cited by 28
“Oriented fast and rotated brief (ORB) [13], features from scale-invariant (SIFT) [14], and speeded up robust features (SURF) [15] can be used in the feature extraction stage.”
MethodA Survey of 3D Ear Recognition Techniques
Ganapathi, I. I., Ali, S. S., Prakash, S., Vu, N., & Werghi, N. (2022) · ACM Computing Surveys · doi:10.1145/3560884 · Cited by 34
“Thus, in literature, popular 2D keypoint detection techniques such as speeded up robust features (SURF) [16] are used to locate keypoints in 2D, which are then mapped to 3D.”
MethodInfluentialDeng, G., Huang, T., Lin, B., Liu, H., Yang, R., & Jing, W. (2022) · Sensors · doi:10.3390/s22187090 · Cited by 33
“This method uses feature matching algorithms such as SIFT [11] and SURF [12] to register the image to be recognized as a standard image to read meter readings, and it is not conducive to dealing with multiple meter readings in complex backgrounds.”
A Survey of FPGA-Based Vision Systems for Autonomous Cars
Castells‐Rufas, D., Ngo, V., Borrego-Carazo, J., Codina, M., Sanchez, C., Gil, D., & Carrabina, J. (2022) · IEEE Access · doi:10.1109/access.2022.3230282 · Cited by 36
Ciratefi: An RST-invariant template matching with extension to color images
de Araújo, S. A., & Kim, H. Y. (2011) · Integrated Computer-Aided Engineering · doi:10.3233/ica-2011-0358 · Cited by 29
“The recently developed algorithms based on scale and rotation-invariant keypoints and local features, like SIFT (Scale Invariant Feature Transform) [24], GLOH (Gradient Location and Orientation Histogram) [26] and SURF (Speeded Up Robust Features) [6] have been widely used for image matching tasks.”
A hybrid localization approach for UAV in GPS denied areas
Rady, S., Kandil, A. A., & Badreddin, E. (2011) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2011.6147631 · Cited by 36
Evaluating 3D spatial pyramids for classifying 3D shapes
López-Sastre, R. J., García-Fuertes, A., Redondo-Cabrera, C., et al. (2013) · Computers & Graphics · doi:10.1016/j.cag.2013.04.003 · Cited by 29
An Unsupervised Hierarchical Feature Learning Framework for One-Shot Image Recognition
Guo, Z., & Wang, Z. J. (2013) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2012.2234729 · Cited by 32
Kloihofer, W., & Kampel, M. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.866 · Cited by 29
Finger knuckle print recognition based on SURF algorithm
Zhu, L. (2011) · International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) · doi:10.1109/fskd.2011.6019781 · Cited by 29
“The gray regions are equal to zero([12])”
BackgroundMethodInfluentialHsu, C.-C. J., Lu, M.-C., & Lu, Y.-Y. (2011) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2011.2108076 · Cited by 29
Image Registration Techniques Based on the Scale Invariant Feature Transform
Lakshmi, K. D., & Vaithiyanathan, V. (2016) · IETE Technical Review · doi:10.1080/02564602.2016.1141076 · Cited by 30
“It introduces the concept of integral images for the computations involving image matrices to speed up processes at various stages [10].”
BackgroundMethodInfluentialComparison of tracking algorithms implemented in OpenCV
Janků, P., Koplík, K., Dulík, T., & Szabó, I. (2016) · MATEC Web of Conferences · doi:10.1051/matecconf/20167604031 · Cited by 31
Camera Based Two Factor Authentication Through Mobile and Wearable Devices
Azimpourkivi, M., Topkara, U., & Cărbunar, B. (2017) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3131904 · Cited by 38
“ORB vs. SURF.”
MethodInfluentialAccelerated nonrigid image registration using improved Levenberg–Marquardt method
Dong, J., Lü, K., Xue, J., Dai, S., Zhai, R., & Pan, W. (2017) · Information Sciences · doi:10.1016/j.ins.2017.09.059 · Cited by 29
Fundamentals of Computer Vision
Snyder, W. E., & Qi, H. (2017) · Cambridge University Press eBooks · doi:10.1017/9781316882641 · Cited by 35
A passive camera based determination of a non-cooperative and unknown satellite's pose and shape
Volpe, R., Palmerini, G. B., & Sabatini, M. (2018) · Acta Astronautica · doi:10.1016/j.actaastro.2018.06.061 · Cited by 30
A neuro-fuzzy system for automated detection and classification of human intestinal parasites
Nkamgang, O. T., Tchiotsop, D., Tchinda, B. S., & Fotsin, H. B. (2018) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2018.10.007 · Cited by 29
Generative Model for Zero-Shot Sketch-Based Image Retrieval
Verma, V. K., Mishra, A., Mishra, A. K., & Rai, P. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00097 · Cited by 32
Non-rigid registration of serial section images by blending transforms for 3D reconstruction
Kajihara, T., Funatomi, T., Makishima, H., Aoto, T., Kubo, H., Yamada, S., & Mukaigawa, Y. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.07.001 · Cited by 32
Certifiable relative pose estimation
García-Salguero, M., Briales, J., & González-Jiménez, J. (2021) · Image and Vision Computing · doi:10.1016/j.imavis.2021.104142 · Cited by 36
Pedestrians’ detection in thermal bands – Critical survey
Negied, N. K., Hemayed, E. E., & Fayek, M. B. (2015) · Journal of Electrical Systems and Information Technology · doi:10.1016/j.jesit.2015.06.002 · Cited by 29
“In the training phase, they used a combination of multiple cues to find interest points in the images and use SURF (SpeedUp Robust Features; Tuytelaars et al., 2006) as features to describe these points.”
MethodA multi-stage approach for non-cooperative iris recognition
Yang, K., & Du, E. Y. (2011) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2011.6084192 · Cited by 28
“The Fast Hessian Detector [13] is used to find the potential feature points which are invariant to scale, shift, rotation and contrast.”
MethodInfluentialOverview of image-based 3D reconstruction technology
Niu, Y., Liu, L., Huang, F., Huang, S., & Chen, S. (2024) · Journal of the European Optical Society Rapid Publications · doi:10.1051/jeos/2024018 · Cited by 36
“In 2006, Bay et al. proposes a new scale and rotation invariant detector and descriptor called SURF (Speeded-Up Robust Features) [58].”
BackgroundSmart environments in digital agriculture: a systematic review and taxonomy
Avila, F. R. D., & Barbosa, J. L. V. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110393 · Cited by 29
SDALF: Modeling Human Appearance with Symmetry-Driven Accumulation of Local Features
Bazzani, L., Cristani, M., & Murino, V. (2014) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-6296-4_3 · Cited by 28
Real-time vehicle detection using Haar-SURF mixed features and gentle AdaBoost classifier
Sun, S., Zhize, X., Wang, X., Guan, H., Wu, W., & Xu, D. (2015) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2015.7162227 · Cited by 29
Video Object Retrieval by Trajectory and Appearance
Lai, Y. C., & Yang, C. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2358022 · Cited by 29
“[25] proposed speedup robust feature (SURF).”
MethodCounting moving persons in crowded scenes
Conte, D., Foggia, P., Percannella, G., & Vento, M. (2013) · Machine Vision and Applications · doi:10.1007/s00138-013-0491-3 · Cited by 28
Kazemzadeh, F., Haider, S. A., Scharfenberger, C., et al. (2014) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2014.2307992 · Cited by 28
Montironi, M. A., Castellini, P., Stroppa, L., & Paone, N. (2014) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2014.03.004 · Cited by 34
Bak, A., Bouchafa, S., & Aubert, D. (2011) · Machine Vision and Applications · doi:10.1007/s00138-011-0389-x · Cited by 28
LIRE: open source image retrieval in Java
Lux, M. (2013) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2502081.2502226 · Cited by 34
Swarm exploration and navigation on mars
Sand, S., Zhang, S., Muhlegg, M., Falconí, G. P., Zhu, C., Kruger, T. E., & Nowak, S. (2013) · International Conference on Localization and GNSS · doi:10.1109/icl-gnss.2013.6577272 · Cited by 29
3D reconstruction of bat flight kinematics from sparse multiple views
Bergou, A. J., Swartz, S. M., Breuer, K., & Taubin, G. (2011) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2011.6130443 · Cited by 28
“Refining user click locations to the nearest SURF or Harris image feature [3, 17].”
MethodFrom Bits to Images: Inversion of Local Binary Descriptors
d'Angelo, E., Jacques, L., Alahi, A., & Vandergheynst, P. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.228 · Cited by 33
On-Board Vision Processing for Small UAVs: Time to Rethink Strategy
Ehsan, S., & McDonald-Maier, K. D. (2009) · NASA/ESA Conference on Adaptive Hardware and Systems (AHS) · doi:10.1109/ahs.2009.6 · Cited by 28
Automated Target-Free Network Orienation and Camera Calibration
Stamatopoulos, C., & Fraser, C. S. (2014) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-ii-5-339-2014 · Cited by 34
Convolutional neural random fields for action recognition
Liu, C., Liu, J., He, Z., Zhai, Y., Hu, Q., & Huang, Y. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.03.019 · Cited by 28
Multi-scale feature extraction and adaptive matching for copy-move forgery detection
Bi, X., Pun, C., & Yuan, X. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-4276-3 · Cited by 29
The Image Classification with Different Types of Image Features
Gabryel, M., & Damaševičius, R. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59063-9_44 · Cited by 28
Penza, V., Momi, E. D., Enayati, N., et al. (2017) · Frontiers in Robotics and AI · doi:10.3389/frobt.2017.00015 · Cited by 28
“• SURF feature detection (Bay et al., 2006) is parallelized; • Super pixels (SP) is executed in parallel to the disparity computation; • The pixel correspondence during the disparity calculation is parallelized.”
Leveraging deep visual features for content-based movie recommender systems
Filho, R. J. R., Wehrmann, J., & Barros, R. C. (2017) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2017.7965908 · Cited by 36
Darvishi, M., Schlögel, R., Bruzzone, L., & Cuozzo, G. (2018) · Remote Sensing · doi:10.3390/rs10030409 · Cited by 26
“SURF detector considers integral images for image convolutions and Fast-Hessian matrix.”
BackgroundMethodInfluentialFLIRT: Interest Regions for 2D Range Data with Applications to Robot Navigation
Tipaldi, G. D., Braun, M., & Arras, K. O. (2013) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-28572-1_48 · Cited by 28
Scene Recognition for Indoor Localization of Mobile Robots Using Deep CNN
Woźniak, P., Afrisal, H., Esparza, R. G., & Kwolek, B. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00692-1_13 · Cited by 31
“Several local handcrafted features for visual place recognition have been investigated, such as SIFT [15] or SURF [2], binary-based local features such as BRISK [12] or ORB [21], and other feature descriptors such as lines [32], corner and edges [9], and HOUP [23].”
MethodCross-Domain Visual Representations via Unsupervised Graph Alignment
Yang, B., & Yuen, P. C. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33015613 · Cited by 33
Ma, T., Ma, J., & Yu, K. (2019) · Remote Sensing · doi:10.3390/rs11080951 · Cited by 28
“Many methods are specially designed to work with multispectral images and can achieve better robustness and efficiency than these progressive SIFT-like or SURF-like algorithms.”
InfluentialMultilevel similarity model for high-resolution remote sensing image registration
Wang, X., Li, J., Li, J., & Yan, H. (2019) · Information Sciences · doi:10.1016/j.ins.2019.07.023 · Cited by 29
Cascaded Face Sketch Synthesis Under Various Illuminations
Zhang, M., Li, Y., Wang, N., Yuan, C., & Gao, X. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2942514 · Cited by 29
Better and Faster: Exponential Loss for Image Patch Matching
Wang, S., Li, Y., Liang, X., Quan, D., Yang, B., Wei, S., & Jiao, L. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00491 · Cited by 28
“Early methods, such as SIFT [23] and SURF [6], mainly focus on the design of hand-crafted feature descriptors.”
MethodA Vision-Based Odometer for Localization of Omnidirectional Indoor Robots
Patruno, C., Colella, R., Nitti, M., Renò, V., Mosca, N., & Stella, E. (2020) · Sensors · doi:10.3390/s20030875 · Cited by 29
“Currently, the most e ff ective keypoint detectors are the Scale Invariant Feature Transform (SIFT) [21], the Speeded-Up Robust Features (SURF) [31], the Binary Robust Invariant Scalable Keypoints (BRISK) [32] and the Features from Accelerated Segment Test (FAST) [33].”
MethodDerksen, D., Inglada, J., & Michel, J. (2020) · Remote Sensing · doi:10.3390/rs12030513 · Cited by 36
Kanwal, K., Ahmad, K. T., Khan, R., Abbasi, A. T., & Li, J. (2020) · Symmetry · doi:10.3390/sym12040612 · Cited by 35
“The”
MethodInfluentialVNPlant-200 – A Public and Large-Scale of Vietnamese Medicinal Plant Images Dataset
Quoc, T. N., & Hoang, V. T. (2020) · Lecture notes in networks and systems · doi:10.1007/978-3-030-49264-9_37 · Cited by 28
Deep Learning Methods for Animal Recognition and Tracking to Detect Intrusions
Sayagavi, A. V., Sudarshan, T. S. B., & Ravoor, P. C. (2020) · Smart innovation, systems and technologies · doi:10.1007/978-981-15-7062-9_62 · Cited by 28
Object scale selection of hierarchical image segmentation with deep seeds
Al‐Huda, Z., Peng, B., Yang, Y. T., & Algburi, R. N. A. (2020) · IET Image Processing · doi:10.1049/ipr2.12020 · Cited by 28
“…regions belonging to different labels will have higher costs if their appearance is closer, and, D k,m is described as the Euclidean distance of SURF [36], and SIF [37] distance of two regions r k and r m : where 𝜂 is used as a weight factor for distance adjustment and satisfies 𝜂 1 + 𝜂 2 =…”
MethodTraffic Sign Detection and Recognition Using Multi-Scale Fusion and Prime Sample Attention
Cao, J., Zhang, J., & Huang, W. F. (2020) · IEEE Access · doi:10.1109/access.2020.3047414 · Cited by 31
Paul, S. K., Chowdhury, M. T., Nicolescu, M., Nicolescu, M. N., & Feil-Seifer, D. (2021) · Transactions on computational science and computational intelligence · doi:10.1007/978-3-030-71051-4_10 · Cited by 39
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.