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 8,501–8,600 of 14,752
MGFNet: a multiscale gated fusion network for multimodal semantic segmentation
Wu, H., Li, Z., & Wen, Z. (2025) · The Visual Computer · doi:10.1007/s00371-025-03912-x · Cited by 11
“Bay et al. [24] proposed an approach that involves extracting local features from an image invariant to various transformations such as scaling and rotation.”
Chang, R.-I., Yang, C., & Hsu, T. (2025) · Electronics · doi:10.3390/electronics14112254 · Cited by 4
ViT-SIR: vision transformer-based shoe image retrieval with enhanced feature representation
Li, J., & Tang, Y. (2025) · The Visual Computer · doi:10.1007/s00371-025-03913-w · Cited by 4
“…tasks primarily relied on traditional machine learning methods such as Local Binary Pattern (LBP) [29], Hu Moments [30], Haar-like feature extraction [31], Scale-Invariant Feature Transform (SIFT) [32], Histogram of Oriented Gradients (HOG) [33], and Speeded Up Robust Features (SURF) [34].”
Fang, R. S., Zhang, P., Zhang, T., Yan, Z., Kim, D., Sun, E., Kuranov, R. V., Kweon, J., Huang, A. S., & Zhang, H. F. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3580383 · Cited by 14
“For real-time identification of shared landmark points, features such as SIFT, SURF, ORB, and Harris features have been used to identify matching features between images from other modalities [67], [68].”
Unsupervised Multimodal UAV Image Registration via Style Transfer and Cascade Network
Bi, X., Qie, R., Tao, C., Zhang, Z., & Xu, Y. (2025) · Remote Sensing · doi:10.3390/rs17132160 · Cited by 7
YOLOv8-C2fSE- An Improved Accuracy Model for Object Detection
Modupalli, B. M., & Prithvi, P. (2025) · International Conference on Recent Advances in Information Technology · doi:10.1109/rait65068.2025.11089214 · Cited by 3
Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence
Qian, Q., Chen, H., Tomizuka, M., Keutzer, K., Wang, Q., & Xu, C. (2025) · 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/cvpr52734.2025.01081 · Cited by 8
“Traditional methods rely on hand-crafted features such as SIFT [30] and SURF [3] to find correspondences.”
Can Generative Video Models Help Pose Estimation?
Cai, R., Zhang, J. Y., Henzler, P., Li, Z., Snavely, N., & Martin-Brualla, R. (2025) · 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/cvpr52734.2025.01562 · Cited by 11
“The classic approach to computing the pose between two images is to extract image features [5, 35, 41], find correspondences [37], and then compute the fundamental matrix [18, 34, 38] while rejecting outliers [16].”
Jónatas, R., Aleixo, R., Amaral, S., et al. (2025) · Journal of Hydraulic Engineering · doi:10.1061/jhend8.hyeng-14126 · Cited by 3
AI-Powered Automated Inspection for Optimized Asset Management in Electrical Distribution Networks
Silva, M. F. D., Santos, M. F. D., Masson, J. E. N., et al. (2025) · Journal of Control Automation and Electrical Systems · doi:10.1007/s40313-025-01197-y · Cited by 3
“For the feature detection stage in this study, the SIFT algo-rithm is employed due to its efficiency and invariance to scale changes (Alcantarilla & Solutions, 2011; Bay et al., 2006; Masson et al., 2019; Siegwart et al., 2011).”
TMSS-YOLO: An industrial tool detection method based on improved YOLOv11
Yang, G., Zhang, Z., Sang, H., Tang, H., & Wang, M. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04816-y · Cited by 5
“Subsequent use of feature descriptors like SIFT [6], HOG [7], and SURF [8] improvedrepresentationbutremainedconstrainedbymanual design and high computational cost.”
Khan, A. S., Abbass, M. J., & Khan, A. (2025) · Sensors · doi:10.3390/s25195992 · Cited by 5
Magiccolor: Multi-Instance Sketch Colorization
Zhang, Ma, Y., Wang, B., Chen, Q., & Wang, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01411 · Cited by 14
“In the past, traditional methods [2, 46] relied on hand-designed features to establish corresponding relationships.”
On kNN Classification and Local Feature Based Similarity Functions
Amato, G. M., & Falchi, F. (2013) · Communications in computer and information science · doi:10.1007/978-3-642-29966-7_15 · Cited by 3
Visual lock-on to invisible target for unmanned aerial vehicle
Min, J., Kim, J., Jung, Y., et al. (2012) · Electronics Letters · doi:10.1049/el.2012.0996 · Cited by 3
A comparison of image features for registering LWIR and visual images
Cronje, J., & de Villiers, J. (2012) · Cited by 3
Embedded vision-based SLAM: A model-driven approach
Piat, J., Márquez-Gámez, D., & Devy, M. (2013) · Conference on Design and Architectures for Signal and Image Processing · Cited by 3
Shirt pattern recognizing and tracking behavior analysis using SURF on the moving human target
How, G. C., Fai, Y. C., Su, E. L. M., et al. (2015) · Asian Control Conference (ASCC) · doi:10.1109/ascc.2015.7244810 · Cited by 3
The influence of the similarity measure to relevance feedback
Mironică, I., Ionescu, B. E., & Vertan, C. (2012) · Cited by 3
Efficient exploration for real-time robot indoor 3D mapping
Du, J., Meiqin, L., & Weihua, S. (2015) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2015.7260590 · Cited by 6
“The SURF features [21] are extracted from the color images frame by frame.”
MethodAssessing Cross-Cut Shredded Document Assembly
Saboia, P., & Goldenstein, S. K. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-12568-8_34 · Cited by 3
The neural-SIFT feature descriptor for visual vocabulary object recognition
Jansen, S., Shantia, A., & Wiering, M. (2015) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2015.7280660 · Cited by 3
From Sensorimotor Primitives to Manipulation and Imitation Strategies in Humanoid Robots
Asfour, T., Do, M., Welke, K., Bierbaum, A., Azad, P., Vahrenkamp, N., Gärtner, S., Ude, A., & Dillmann, R. (2011) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-19457-3_22 · Cited by 3
Alignment of visual maps in multirobot FastSLAM
Ballesta, M., Gil, A., Reinoso, Ó., Juliá, M., & Jiménez, L. M. (2009) · Computational intelligence · Cited by 3
A Remote Sensing Image Matching Algorithm Based on the Feature Extraction
Wu, C., Song, C., Chen, D., et al. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-31362-2_32 · Cited by 3
Initializing Vision Based Trackers Using Semantic Texton Forests
Park, M.-W., Jog, G. M., & Brilakis, I. (2011) · Proceedings of the ... ISARC · doi:10.22260/isarc2011/0069 · Cited by 3
Stommel, M., Duemcke, M., & Herzog, O. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24455-1_31 · Cited by 3
Panoramic Image Search by Similarity and Adjacency for Similar Landscape Discovery
Zhao, M. Y., Ohshima, H., & Tanaka, K. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35063-4_21 · Cited by 3
An evaluation of local features on satellite images
Tahoun, M., Shabayek, A. E. R., Hassanien, A. E., & Reulke, R. (2015) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2015.7296453 · Cited by 3
“SURF (Speeded-Up Robust Features) is a local invariant Interest point or blob detector [2].”
MethodVehicle identification using distance-based appearance model
Shih, H.-C., & Wang, H.-Y. (2015) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2015.7301728 · Cited by 3
A Flexible Method for Localisation and Classification of Footprints of Small Species
Geng, H., Russell, J. C., Shin, B.-S., et al. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25346-1_25 · Cited by 3
“[1] in 2006.”
Localization independent of location based on place recognition and GPS observations
Saito, T., & KURODA, Y. (2012) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2012.6426958 · Cited by 3
“The anteriorly-directed camera with a fish-eye lens employs Fast Hessian region detectors and U-SURF descriptors [12].”
MethodMulti-View Representation Based Face Sketch Synthesis
Peng, C., Li, J., Wang, N., et al. (2014) · doi:10.1145/2632856.2632879 · Cited by 3
“The two local feature descriptors explored in this paper are Speeded Up Robust Features (SURF) [1] and Multi-scale Local Binary Pattern (MLBP) [8] since both of them have been shown to be very successful in describing face images in recent years.”
BackgroundMethodFusing Multiple Independent Estimates via Spectral Clustering for Robust Visual Tracking
Kim, J., Min, J., Kweon, I. S., et al. (2012) · IEEE Signal Processing Letters · doi:10.1109/lsp.2012.2205916 · Cited by 3
“In all the reported results, we use a fixed set of parameters: 300 hypotheses for each target object, 8 Gaussian kernels for color and SURF models and 5 Gaussian kernels for the velocity model.”
MethodInfluentialMalashin, R. O. (2014) · Journal of Optical Technology · doi:10.1364/jot.81.000327 · Cited by 3
Towards practical space-variant based face recognition and authentication
Grosso, E., Lagorio, A., Pulina, L., & Tistarelli, M. (2014) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf.2014.6914258 · Cited by 3
“The SURF descriptor [13] is based on a more structured approach, where the Hessian matrix is used to extract the salient points, and Haar wavelets are applied to compute the feature descriptor.”
MethodA coarse-to-fine logo recognition method in video streams
Zhao, C., Wang, J., Xie, C., & Lu, H. (2014) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2014.6890576 · Cited by 3
“Many state-of-the-art approaches for template matching have been used for logo detection and recognition[2, 5, 3].”
BackgroundA Vision-Based Vehicle Speed Warning System
Huang, S.-C., Lin, C.-C., & Wang, M. (2012) · doi:10.1109/uic-atc.2012.110 · Cited by 3
Robot localization using a complementary laser/camera filter
Muhieddine, A., Asmar, D., & Shammas, E. (2014) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2014.7090527 · Cited by 3
A Zoned Image Patch Permutation Descriptor
Tian, T., Sethi, I. K., Ming, D., & Patel, N. V. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2352172 · Cited by 3
“Lowe’s SIFT [4] has become a performance benchmark for its excellent invariance to various affine deformations, and Bay et al. proposed SURF [5] as an approximation to SIFT, which gives a comparable performance meanwhile retaining most desirable properties.”
MethodInfluentialThe role of homing in visual topological navigation
Liu, M., Pradalier, C., Pomerleau, F., et al. (2012) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-a-010034748 · Cited by 3
A novel framework for CBCD using integrated color and acoustic features
Roopalakshmi, R. (2014) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-014-0062-z · Cited by 3
Evaluation of two-view geometry methods with automatic ground-truth generation
Lakemond, R., Fookes, C., & Sridharan, S. (2013) · Image and Vision Computing · doi:10.1016/j.imavis.2013.09.002 · Cited by 3
A fast and robust traffic sign recognition method using ring of RIBP histograms based feature
Yin, S., Ouyang, P., Liu, L., et al. (2014) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2014.7090728 · Cited by 3
“Hence, according to Table III and Table IV, this proposed feature greatly improves the processing time than SIFT and SURF, meanwhile achieves comparable discrimination performance comparing with SIFT and higher discrimination performance comparing with SURF.”
BackgroundMethodInfluentialDigital image inpainting using speeded up robust feature
Chavan, T. R., & Nandedkar, A. V. (2014) · International Conference on Advances in Computing, Communications and Informatics (ICACCI) · doi:10.1109/icacci.2014.6968221 · Cited by 3
“A BRIEF ON SURF Speeded-Up Robust Features (SURF) [12] is a fast and robust algorithm for local, similarity invariant image representation, proposed by Herbert Bay.”
MethodInfluentialSpringer, D., Simmet, F., Niederkorn, D., et al. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738359 · Cited by 3
“Unlike other Global Motion Estimation (GME) schemes, we omit SIFT [10] or SURF [11] keypointbased feature transforms but perform a fast motion vector analysis of HEVC rate distortion optimization (RDO) results.”
MethodInfluentialFast shared boosting for large-scale concept detection
Borgne, H. L., & Honnorat, N. (2010) · Multimedia Tools and Applications · doi:10.1007/s11042-010-0607-y · Cited by 4
Chikano, M., Kise, K., Iwamura, M., et al. (2012) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.10.003 · Cited by 3
Region categorization with mobile applications
Gao, J. (2010) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1873951.1874111 · Cited by 3
“We implemented the SURF algorithm [1] on a mobile device.”
MethodSpeed-up multi-stage non-cooperative iris recognition
Yang, K., & Du, E. Y. (2012) · International Journal of Biometrics · doi:10.1504/ijbm.2012.049746 · Cited by 4
“In order to accelerate this process, a similar set of box fi lters as in Bay et al., 2006 is applied to approximate the Gaussian second order derivatives.”
MethodInfluentialEfficient subwindow search with submodular score functions
An, S., Peursum, P., Liu, W., et al. (2011) · doi:10.1109/cvpr.2011.5995355 · Cited by 3
“In object localization, local features are extracted (e.g. SIFT [12] and SURF[4]) and a score function is used to find the optimal subimage wherein the score function is maximized among all possible subimages.”
MethodVisual based navigation for power line inspection by using virtual environments
Cerón, A., Mondragon, I. F., & Prieto, F. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2083478 · Cited by 3
An image-to-image loop-closure detection method based on unsupervised landmark extraction
Sarıyanidi, E., Şencan, O., & Temeltaş, H. (2012) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2012.6232174 · Cited by 3
“A visual vocabulary is formed by clustered SURF features [2] and the statistics of the words are kept inside this vocabulary — the aforementioned marginal probabilities”
BackgroundOffline learning of prototypical negatives for efficient online Exemplar SVM
Takami, M., Bell, P. R. F., & Ommer, B. (2014) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2014.6836075 · Cited by 3
An iterative combination scheme for multimodal visual feature detection
Guerra‐Filho, G. (2013) · Neurocomputing · doi:10.1016/j.neucom.2012.08.065 · Cited by 3
“The Hessian matrix is the foundation of the detection step for SURF features [13].”
MethodPedestrian Recognition by Using a Kernel-Based Multi-modality Approach
Sîrbu, A.-M., Rogozan, A., Dioşan, L. S., et al. (2014) · International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC) · doi:10.1109/synasc.2014.42 · Cited by 3
“…approach) or • pedestrians’ appearance (actual approach) by defining a space of properties (descriptors like HOG, Speeded Up Robust Features (SURF) [5], Colour Self Similarity (CSS) [6], Haar walvet representation [7]) and a classifier (Support Vector Machines, AdaBoost [8], Artificial Neural…”
BackgroundXu, J., Zhang, C., & Goto, S. (2011) · International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS) · doi:10.1109/ispacs.2011.6146085 · Cited by 3
A faithful restoration of haze images using an optimized transmission map
Kponou, E. A., Wang, Z., Wei, P., et al. (2014) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2014.7003774 · Cited by 3
Towards location recognition using range images
Al-Nuaimi, A., Huitl, R., Taifour, S., et al. (2013) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2013.6618361 · Cited by 3
Automatic Tracking Algorithm in Coaxial Near-Infrared Laser Ablation Endoscope for Fetus Surgery
Hu, Y., Yamanaka, N., & Masamune, K. (2014) · International Journal of Optomechatronics · doi:10.1080/15599612.2014.916016 · Cited by 3
Self-Organizing Mapping of Robotic Environments Based on Neural Networks
Figueiredo, M., Botelho, S. S. D. C., Drews, P., et al. (2012) · Proceedings - Brazilian Symposium on Neural Networks/Proceedings of the ... Brazilian Symposium on Neural Networks · doi:10.1109/sbrn.2012.17 · Cited by 3
Aircraft ground monitoring with high performance computing multicore enabled video tracking
Jia, B., Ling, H., Blasch, E., Sheaff, C., Chen, G., & Wang, Z. (2014) · IEEE/AIAA Digital Avionics Systems Conference (DASC) · doi:10.1109/dasc.2014.6979498 · Cited by 3
Image-based camera motion estimation using prior probabilities
Sargent, D., Park, S. Y., Spofford, I. S., et al. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.878244 · Cited by 3
A Space Variant Gradient Based Corner Detector for Sparse Omnidirectional Images
Kerr, D., Coleman, S., & Scotney, B. W. (2010) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-010-0211-9 · Cited by 3
A fast UAV image stitching method on GeoSOT
Zhe, Y., Weixin, Z., Chen, D., et al. (2015) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2015.7326136 · Cited by 3
“SURF (Speed Up Robust Features) is the stitching algorithm based on image characteristics, scale and rotation invariance, the splicing effect of which is better than the former feature detector[12, 13].”
Park, H., Mitsumine, H., & Fujii, M. (2011) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e94.d.938 · Cited by 3
“The total number of reference features, which were found from the scene using SURF by fixing the distance ratio threshold to 0.65 in advance in an offline step [6], was 480.”
MethodInfluentialYin, H., Sun, M., Wang, Y., et al. (2014) · doi:10.1109/vcip.2014.7051594 · Cited by 3
“Surf [10] is used to find pairs of matching features between two frames first.”
MethodEnvironment map building and localization for robot navigation based on image sequences
Shen, Y., Liu, J., & Du, X. (2008) · Journal of Zhejiang University. Science A · doi:10.1631/jzus.a071442 · Cited by 3
Exploring the Best Classification from Average Feature Combination
Hou, J., Liu, W., & Karimi, H. R. (2014) · Abstract and Applied Analysis · doi:10.1155/2014/602763 · Cited by 5
Tracking small targets in wide area motion imagery data
Mathew, A., & Asari, V. K. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2002880 · Cited by 3
“PROPOSED METHOD The first step involved is the image registration step, performed using the SURF (Speeded Up Robust Features) descriptor [2].”
MethodOptical-Flow Perspective Invariant Registration
Clark, A., & Green, R. R. (2011) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2011.23 · Cited by 3
“2) SURF [2] was implemented by designing an interface to the original author’s own libraries, available from their website4.”
MethodVajda, P., Ivanov, I., Lee, J., & Ebrahimi, T. (2011) · International Journal of Computer Games Technology · doi:10.1155/2011/706893 · Cited by 3
Sequence-based autonomous robot navigation by log-polar image transform and epipolar geometry
Fu, Y., Hsiang, T.-R., & Chung, S. (2010) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2010.5642030 · Cited by 3
“The proposed visual homing method intends to extend the applicable local region of the SIFT visual homing methods [3] [11] in order to reduce the number of intermediate waypoints, since scale-invariant features, such as SIFT [9] or Speed Up Robust Feature (SURF) [13], are adopted in most feature based visual homing m…”
BackgroundMethodReduction of computational effort in satellite image matching
Kaveev, I. N., Ташлинский, А. Г., & Kurbanaliev, R. M. (2012) · Pattern Recognition and Image Analysis · doi:10.1134/s105466181201021x · Cited by 3
Local feature selection for efficient binary descriptor coding
Monteiro, P., Ascenso, J., & Pereira, F. M. B. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025818 · Cited by 3
Three-dimensional lunar surface reconstruction based on remote sensing imagery from Chang E-2
Yang, A., Li, X., Xie, J., et al. (2014) · Survey Review · doi:10.1179/1752270614y.0000000111 · Cited by 3
ORB tracking via random model and sample consensus
Xie, X., & Wu, H. (2012) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2012.6469676 · Cited by 3
Modeling arthroscopic camera with haptic devices in image-based virtual environments
Rasool, S., Sourin, A., Pestrikov, V., et al. (2014) · IEEE Haptics Symposium · doi:10.1109/haptics.2014.6775489 · Cited by 3
“We used SURF (Speeded-Up Robust Features) algorithm [22] for extracting feature points from the images, while library FLANN (Fast Library for Approximate Nearest Neighbors) [23] was used for comparing the features.”
MethodBhat, S., R, R. B. D., Rangarajan, K., & Ramakrishna, K. A. (2014) · Defence Science Journal · doi:10.14429/dsj.64.7785 · Cited by 3
UPC at MediaEval 2013 Hyperlinking Task
Ventura, C., Tella-Amo, M., & Giró-i-Nieto, X. (2013) · Cited by 3
Image Processing Based a Wireless Charging System with Two Mobile Robots
Kim, J.-O., Moon, C., & Ahn, H. (2013) · Lecture notes in electrical engineering · doi:10.1007/978-94-007-6738-6_95 · Cited by 3
A novel algorithm for refinement of vision-based two-view pose estimates
Mehta, S. S., Barooah, P., Susca, S., et al. (2009) · doi:10.1109/cdc.2009.5400510 · Cited by 3
Robust invariant descriptors for visual object recognition
Ganesharajah, B., Mahesan, S., & Pinidiyaarachchi, U. A. J. (2011) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciinfs.2011.6038059 · Cited by 3
Fatigue driving detecting method based on time-space features in real driving conditions
Li, Z., Peng, J., Chen, L., et al. (2015) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2015.7334107 · Cited by 3
Zhang, X., Hirai, S., & Zhang, P. (2010) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2010.5723368 · Cited by 3
“SURF (Speeded-UP Robust Feature), first presented in 2006 [13], uses the ‘Fast-Hessian’ to approximate the Laplacian, describing a distribution of Haar-wavelet responses within the area of the point of interest.”
BackgroundMethodVISION-AIDED CONTEXT-AWARE FRAMEWORK FOR PERSONAL NAVIGATION SERVICES
Saeedi, S., Moussa, A., & El‐Sheimy, N. (2012) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsarchives-xxxix-b4-231-2012 · Cited by 3
Controlling generic visualization environments using handheld devices and natural feature tracking
Celozzi, C., Lamberti, F., Paravati, G., et al. (2011) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2011.5955232 · Cited by 3
“During the experimental tests, the following feature extraction algorithms (each one with the appropriate matching algorithm) were taken into account: Harris SIFT [19], SURF [26] and SiftGPU [20].”
MethodSurvey of local invariant feature description
Huang, W., Wei, Y., Xie, Y., & Jin, H. (2013) · Chinese Automation Congress · doi:10.1109/cac.2013.6775758 · Cited by 3
Interest point detection for vision based mobile robot navigation
Hanajík, M., Ravas, R., & Smieško, V. (2011) · IEEE World Symposium on Applied Machine Intelligence and Informatics (SAMI) · doi:10.1109/sami.2011.5738876 · Cited by 3
Robustifying Descriptor Instability Using Fisher Vectors
Everts, I., van Gemert, J. C., Mensink, T., & Gevers, T. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2365955 · Cited by 5
Visual Object Detection using Frequent Pattern Mining
Sait, Y. A., & Ravindran, B. (2010) · Cited by 3
A Flow-based Interest Point Detector for Action Recognition in Videos
Yadav, G. K., & Sethi, A. (2014) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/2683483.2683524 · Cited by 3
“Other interest point detectors inspired from SIFT have also been reported such as SURF [1].”
MethodSharing 3D object with multiple clients via networks using vision-based 3D object tracking
Shinozuka, Y., & Saitô, H. (2014) · Virtual Reality International Conference · doi:10.1145/2617841.2620723 · Cited by 3
Towards off-the-shelf computer vision for user interaction in consumer homes
Walsh, R., & Hornsby, A. (2011) · International Conference on Consumer Electronics · doi:10.1109/icce.2011.5722495 · Cited by 3
Fast Scene Recognition and Camera Relocalisation for Wide Area Augmented Reality Systems
Guan, T., Duan, L., Chen, Y., & Yu, J. (2010) · Sensors · doi:10.3390/s100606017 · Cited by 3
Comparative evaluation of pedestrian detection methods for mobile bus surveillance
Leoputra, W. S., Venkatesh, S., & Tan, T. (2009) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2009.4960386 · Cited by 3
Rapid Processing of Unmanned Aerial Vehicles Imagery for Disaster Management
Arthur, M., Al-Tahir, R., & Trinidad, D. D. (2012) · Cited by 3
A Complete Real-Time Feature Extraction and Matching System Based on Semantic Kernels Binarized
Schaffner, M., Hager, P. A., Cavigelli, L., Fang, Z., Greisen, P., Gürkaynak, F. K., Smolić, A., Kaeslin, H., & Luca Benini, C. (2015) · IFIP advances in information and communication technology · doi:10.1007/978-3-319-23799-2_7 · Cited by 3
“The SIFT, SURF and BRIEF descriptors were all parameterized using the default configuration.”
BackgroundMethodInfluentialApplication of human visual system models to LCD image analysis
Šabanovič, E., & Matuzevičius, D. (2015) · IEEE Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE) · doi:10.1109/aieee.2015.7367313 · Cited by 3
“6) SURF (Speeded Up Robust Features) blob detector [16], [17] based on Hessian.”
MethodYousif, K., Bab‐Hadiashar, A., & Hoseinnezhad, R. (2014) · RMIT Research Repository (RMIT University Library) · Cited by 3
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.