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 10,901–11,000 of 14,752
UEC at TRECVID 2011 SIN and MED task
Hizume, K., & Yanai, . (2011) · Cited by 1
A procedure for semi‐Automatic Orthophoto Generation from High Resolution Satellite Imagery
Alrajhi, M., Jacobsen, K., & Heipke, C. (2013) · 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-xl-7-w2-7-2013 · Cited by 1
“First tests showed, the Scale Invariant Feature Transform - SIFT (Lowe 2004) in general is suitable and can be used also under the difficult conditions of deserts, but finally the Speeded-Up Robust Features (SURF) algorithm (Bay et al. 2006) has been selected because of faster processing.”
MethodOff-road Place Recognition using Fused Image Features
Foehst, T., Arndt, M. F., Berns, K., et al. (2010) · German Conference on Robotics · Cited by 1
IMAGE-BASED NAVIGATION OF FOREST HARVESTERS
Schulze, M. (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-b3-59-2012 · Cited by 1
“In order to improve the speed of this algorithm, SURF features are detected instead of SIFT.”
MethodInfluentialModel-based feature refinement by ellipsoidal face tracking
Jung, S.-U., & Nixon, M. S. (2012) · ePrints Soton (University of Southampton) · Cited by 1
On the Improvement of Image Feature Matching under Perspective Transformations
Neto, V. F. D. C., & Campos, M. F. M. (2010) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2010.31 · Cited by 1
“Recently, a large number of works have been published that perform matching of small image patches based on visual feature descriptors, such as SIFT [1], [2], PCA-SIFT [3], GLOH [4], SURF [5], MSER [6] and ASIFT [7].”
BackgroundVisual odometry for an omnidirectional-drive robot
Pretto, A., Menegatti, E., Takahashi, M., et al. (2009) · International Symposium on Mechatronics and its Applications · doi:10.1109/isma.2009.5164787 · Cited by 1
Ferreira, A. L. S., dos Santos, S. R., & de Miranda, L. C. (2012) · Symposium on Virtual and Augmented Reality (SVR) · doi:10.1109/svr.2012.14 · Cited by 1
“Apesar de sua boa precisão o SIFT é um método computacionalmente caro, o que levou pesquisadores a inventarem novos algoritmos invariantes a escala como o Principal Component Analysis SIFT (PCASIFT) e o Speeded Up Robust Feature (SURF) com precisões similares – ou melhores – e computacionalmente mais rápidos [16][17].”
BackgroundAirborne vehicle detection using SURF-descriptors and Support Vector Machines
Kozempel, K., Hausburg, M., & Reulke, R. (2011) · doi:10.1109/fists.2011.5973598 · Cited by 1
Registration of vector data and aerial thermal images using modified mutual information
Douterloigne, K., Gautama, S., & Philips, W. R. (2011) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2011.6049192 · Cited by 1
“Usually SIFT or SURF feature points are chosen [8].”
BackgroundProposed Method for Detecting Objects
Elsalamony, H. A. (2014) · International Journal of Computer Applications · doi:10.5120/18722-9946 · Cited by 1
“The experiments of SURF have assumed the integrated images to compute a rough approximation of the Hessian matrix, and this is tending to faster than SIFT [9], [10].”
BackgroundMethodInfluentialImproved SURF Descriptor Based on Triangle Partition
Luan, Z., Zhai, Y., & Wei, X. (2013) · Advanced materials research · doi:10.4028/www.scientific.net/amr.718-720.2296 · Cited by 1
Extracting the Path of Frame Center Points Using Spatial Transformation and Motion Estimation
Dinh, T. N., Kim, J. H., & Lee, G.-S. (2011) · IEEE International Conference on Computer and Information Technology (CIT) · doi:10.1109/cit.2011.53 · Cited by 1
“SURF [1] feature points are located and their descriptors are calculated for the current frame, n F .”
BackgroundMethodInfluentialLarge Scale Specific Object Recognition by Using GIFTS Image Feature
Nakano, H., Mori, Y., Morita, C., & Nagai, S. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23234-8_4 · Cited by 1
“Lowe [1], many image local features with high recognition accuracy were developed such as SURF with better computational time and PCA-SIFT with fewer dimensions in the feature vectors [2,3,4].”
MethodLocal Features for Range and Vision-Based Robotic Automation
Vikstén, F. (2010) · Cited by 1
PEGUS: An Image-Based Robust Pose Estimation Method
Mehta, S. S., Barooah, P., Dixon, W. E., Pasiliao, E. L., & Curtis, J. W. (2012) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2012.18 · Cited by 2
Marker-free Object Recognition on Tabletops
Rayar, F., & Renaudeau, A. (2015) · doi:10.1145/2817721.2823508 · Cited by 1
“In our first experiments, SURF descriptors [3] have been used, but led to bad recognition rate.”
MethodAutomated Evaluation of Interest Point Detectors
Lang, S. R., Luerssen, M. H., & Powers, D. M. W. (2014) · International Journal of Software Innovation · doi:10.4018/ijsi.2014010107 · Cited by 1
“After testing each detector on the BSDS images we can see that SIFT and SURF are particularly susceptible to affine rotations greater than 30◦ [11], and this is reflected in the results for Y and Z rotation in figures 6 and 8.”
MethodInfluentialA Study on the Algorithm for Multi Cognitive Unstructured Pattern Matching
Roh, C., & Na, W. (2015) · Indian Journal of Science and Technology · doi:10.17485/ijst/2015/v8i25/80974 · Cited by 1
EFFICIENT INERTIALLY AIDED VISUAL ODOMETRY TOWARDS MOBILE AUGMENTED REALITY
Aksoy, G. (2013) · Cited by 1
Nanjing University in TRECVID 2010.
Lin, Y., Yang, Y., Ling, K., et al. (2010) · TRECVID · Cited by 1
3D MAPPING TECHNIQUES USING A STEREO BOOM ON LOW-FLYING VEHICLES
Fanto, P. L., Gassaway, J., & Kochersberger, K. B. (2012) · Cited by 1
Photometric Based 3D Registration
Soontranon, N., Pierrot, F., & Mouaddib, E. M. (2013) · Cited by 1
Objects from Animacy: Discovery in Joint Shape and Haar Feature Space
Nandi, S., Guha, P., & Venkatesh, K. S. (2008) · Cited by 1
Scherbinin, V. V., & Kravchenko, P. P. (2014) · Cited by 1
Principal Objects Detection Using Graph-Based Segmentation and Normalized Histogram
Nam, B. N. (2012) · Cited by 1
Mining Robotics Sensors Perception Sensors on a Mine Safety Platform
Hlophe, K., & Dickens, J. S. (2011) · Cited by 1
Brain Structures Identification Based on Feature Descriptor Algorithm for Traumatic Brain Injury
Serrano, M. L., Moreno, F. G., González, P. S., et al. (2013) · Cited by 1
UEC at TRECVID 2010 Semantic Indexing Task
Shimoda, Y., Noguchi, A., & Yanai, . (2010) · Cited by 1
Flying Depth Camera for Indoor Mapping and Localization
Belmonte, L. M., Castillo, J. C., Fernández‐Caballero, A., et al. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-19695-4_25 · Cited by 1
Estimation of Human Body Orientation Using Histogram of Oriented Gradients.
Kittipanya-ngam, P., Ong, S. G., & Eng, H. L. (2011) · Machine Vision and Applications · Cited by 1
Cross-Domain Concept Detection with Dictionary Coherence by Leveraging Web Images
Sun, Y., Sudo, K., & Taniguchi, Y. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14442-9_47 · Cited by 1
An improved registration method using the criterion of five-coplanar points
Chen, J. (2015) · Optik · doi:10.1016/j.ijleo.2015.10.023 · Cited by 1
Méndez-Porras, A., Alfaro-Velásco, J., Jenkins, M., et al. (2015) · doi:10.1109/clei.2015.7359996 · Cited by 1
Image Matching Algorithm for Remote Sensing based on FAST-9 and SURF
Wu, H., Yang, W. P., & Liu, J. (2015) · International Workshop on Materials Engineering and Computer Sciences (IWMECS) · doi:10.2991/iwmecs-15.2015.65 · Cited by 1
“To solve this problem, Bay et al in 2006 proposed the SURF (Speeded-Up Robust Feature) algorithm [5], which are close to or exceed the performance of the various aspects of SIFT.”
MethodTowards a Robust Scale Invariant Feature Correspondence
El-Mashad, S. Y., & Shoukry, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19941-2_4 · Cited by 1
“Features Detection and extraction: the interest points are detected and extracted using SURF (Speeded Up Robust Features) [12].”
MethodIntegral Spiral Image for Fast Hexagonal Image Processing
Coleman, S., Scotney, B., & Gardiner, B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41184-7_54 · Cited by 1
“Integral images are also a key aspect of the SURF detector [1] and have also been used for adaptive thresholding [2] and object detection [3].”
MethodForensic Sketch Matching Using SURF
Kotha, D. K., & Rath, S. K. (2012) · Advances in intelligent systems and computing · doi:10.1007/978-81-322-0740-5_64 · Cited by 1
“To extract the descriptors, we first construct a square region centered at the interest point and oriented along the orientation decided by a special selection method as described in [2].”
BackgroundMethodInfluentialTwo stage ensemble selection algorithm
Baczyńska, P., & Burduk, R. (2015) · Applied Computer Science · Cited by 1
Stroboscopic Image Synthesis of Sports Player from Hand-Held Camera Sequence
Hasegawa, K., & Saitô, H. (2015) · doi:10.1109/iccvw.2015.99 · Cited by 1
Comparative study of visual feature extraction methods for building retrieval on urban databases
Evaggelos Spyrou, A., Kesidis, A. L., Kolliopoulos, P., Tsenoglou, T., Bratsolis, E., Gyftakis, S., Charou, E., & Vassilas, N. (2015) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa.2015.7388022 · Cited by 1
Sparsity based Single Object Tracking
Abraham, G., Narayanankutty, K. A., & Soman, K. P. (2013) · INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY · doi:10.24297/ijct.v9i2.4167 · Cited by 1
Goeller, A., Dion, J., Soriano, T., et al. (2015) · doi:10.1115/detc2015-47398 · Cited by 1
Three new methods for color and texture based image matching in Content-Based Image Retrieval
He, D. (2010) · Library and Archives Canada (Government of Canada) · Cited by 1
1 An Automatic Stranger Removal Photography System Using Panoramic Inpainting
Kumara, W. G. C. W., Shih, T. K., & Chang, #.-M. (2015) · Cited by 1
Multi-target Tracking Using Sample-Based Data Association for Mixed Images
Zhang, T.-H., Chen, H.-T., & Tang, C. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27857-5_12 · Cited by 1
Ground Truth Correspondence Between Nodes to Learn Graph-Matching Edit-Costs
Cortés, X., Serratosa, F., & Moreno‐García, C. F. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23192-1_10 · Cited by 1
Sampling and Clustering of the Space of Human Poses from Tracked, Skeletonised Colour+Depth Images
Stommel, M., & Beetz, M. (2013) · Cited by 1
Tahoun, M., Hassanien, A. E., & Reulke, R. (2015) · Lecture notes in geoinformation and cartography · doi:10.1007/978-3-319-18407-4_21 · Cited by 1
Fast Keypoint Reduction for Image Retrieval by Accelerated Diverse Density Computation
Wada, T., & Mukai, Y. (2015) · doi:10.1109/icdmw.2015.156 · Cited by 1
Incremental Discriminant Learning for Heterogeneous Domain Adaptation
Han, P., & Wu, X. (2015) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2015.186 · Cited by 1
“SURF features [2] are extracted for all the images.”
MethodImproved Object Recognition with Decision Trees Using Subspace Clustering
Peralta, B., & Caro, L. A. (2016) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2016.p0041 · Cited by 2
Xiong, X., & Choi, B.-J. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-32645-5_43 · Cited by 1
Sheta, B. I., Elhabiby, M., & El‐Sheimy, N. (2012) · GEOMATICA · doi:10.5623/cig2012-056 · Cited by 1
Supervised hashing binary code with deep CNN for image retrieval
Li, J., & Li, J. (2015) · International Conference on Biomedical Engineering and Informatics (BMEI) · doi:10.1109/bmei.2015.7401584 · Cited by 1
A New Approach for Vehicle Recognition and Tracking in Multi-camera Traffic System
Jiang, W., Lu, Z., Jin, H., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27137-8_12 · Cited by 1
The design and implementation of interactive game based on PTAM
Zhang, F., Guo, J., Wang, B., et al. (2015) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2015.7407848 · Cited by 1
“And then, select a 16*16 image block centered with the feature point [10].”
BackgroundAn efficient and robust rotation invariant descriptor
Xi, D., Sun, Y., Miao, J., et al. (2015) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2015.7407946 · Cited by 1
Image content modeling and retrieval using sparse representation
Ranjan, R., Gupta, S., & Venkatesh, K. S. (2015) · International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip.2015.7414795 · Cited by 1
Orientation and scale invariant binary descriptor based on Haar wavelet
Yao, M., Jia, K., & Siu, W.-C. (2015) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2015.7415428 · Cited by 1
Improvement of H.265/HEVC encoding for 8K UHDTV by detecting motion complexity
Orihashi, S., Harada, R., Matsuo, Y., et al. (2016) · International Conference on Consumer Electronics · doi:10.1109/icce.2016.7430599 · Cited by 1
Geometric Indexing for Recognition of Places
Lara-Álvarez, C. A., Rojas‐Domínguez, A., & Bayro-Corrochano, E. J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-12568-8_67 · Cited by 1
“Ideal keypoints must be invariant to viewpoint changes, illumination and occlusions; keypoint detectors such as SIFT [3], SURF [4], MSER [5] have been successfully used for many applications.”
MethodHuang, X., Wang, J., Zhang, M., et al. (2011) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2011.6100375 · Cited by 1
“In order to solve this problem, Bay[7][8][9] puts forward SURF operator with DoH (Determinant, of the Hessian) which is simplified and approximate.”
BackgroundInfluentialLearning Hierarchical Feature Representation in Depth Image
Liu, Y., Lasang, P., Sun, Q., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16811-1_39 · Cited by 1
A Simple Visual Words Selection Strategy for Pedestrian Detection
Zhang, X., Chen, G., Saruta, K., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14249-4_63 · Cited by 1
Accurate scale estimation based on unsynchronized camera network
Mhiri, R., Vasseur, P., Mousset, S., et al. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351593 · Cited by 1
Characterizing Multi-media Retrieval Applications
Lu, Y., Wang, X., Zhang, W., et al. (2015) · Proceedings of the International Conference on Parallel Processing · doi:10.1109/icpp.2015.36 · Cited by 1
FSSGR: Feature Selection System to Dynamic Gesture Recognition
Santos, D. G. S., Neto, R. C., Fernandes, B., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23222-5_29 · Cited by 1
Landmark-based feature tracking for endoscopic motion analysis
Friedl, S., Morgus, B., Kage, A., et al. (2011) · Fraunhofer-Publica (Fraunhofer-Gesellschaft) · Cited by 1
A Performance Evaluation of Feature Descriptors for Image Stitching in Architectural Images
Balasubramanian, P., Verma, V. K., & Mittal, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16631-5_38 · Cited by 1
Generic models for adaptive robust feature extraction in video
Cauwelaert, D. V. (2008) · Ghent University Academic Bibliography (Ghent University) · Cited by 1
Thakoor, K. A. (2016) · IEEE Intelligent Systems · doi:10.1109/mis.2016.21 · Cited by 2
McAllister, P., Zheng, H., Bond, R., & Moorhead, A. (2015) · IEEE International Symposium on Technology and Society (ISTAS) · doi:10.1109/istas.2015.7439433 · Cited by 1
AN EFFICIENT/ENHANCED CONTENT BASED IMAGE RETRIEVAL FOR A COMPUTATIONAL ENGINE
Shriram (2014) · Journal of Computer Science · doi:10.3844/jcssp.2014.272.284 · Cited by 1
“ROI (Speed up Robust Feature) is one of the most frequently used interest point detectors and descriptors which were developed by Bay et al .”
BackgroundFeng, Q., Xu, M., & Zhang, X. (2016) · Cluster Computing · doi:10.1007/s10586-016-0551-3 · Cited by 1
“Orientation of a SURF feature point contains very robust information [3,47].”
MethodInfluentialRetractedDistributed 3D Object Recognition System Using Smartphones
Ibrahim, M., Elgendy, O. A., & Farouk, M. (2015) · doi:10.15849/icit.2015.0015 · Cited by 1
“For on-line applications relying only on a regular PC, each one of the three steps (detection, description, matching) has to be fast [18].”
BackgroundInfluentialA Novel Binary Feature Descriptor for Accelerated Robust Matching
Chen, C., & Xu, Z. (2013) · Journal of Convergence Information Technology · doi:10.4156/jcit.vol8.issue3.9 · Cited by 1
“So we use Haar-wavelet responses instead of gradient of intensity based on SURF descriptors.”
MethodInfluentialPerson Re-identification by Combining Features in a Learning Based Framework
Oğul, B. B., & Temizel, A. (2013) · International Conference on Imaging for Crime Detection and Prevention (ICDP) · doi:10.1049/ic.2013.0256 · Cited by 1
Wang, C., Ji, M., Zhang, Y., et al. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2229882 · Cited by 1
“ORB feature is more stable compared with Harris and FAST, and it is easier for project implementation compared with other feature descriptor like SIFT[8], SURF[9], BRISK[10], BRIEF[11] and so on.”
MethodRAFI - A Stereo Vision Based Autonomous Mobile Area Mapping Robot with 16 DOF
Hossain, M. S., Aziz, A., & Rahman, M. W. (2013) · International Journal of Artificial Intelligence & Applications · doi:10.5121/ijaia.2013.4111 · Cited by 1
Tsuchiya, Y., Takauji, H., & HANAJIMA, N. (2013) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.79.1110 · Cited by 1
Powerful Combination of Color Descriptor and LBP Descriptor for Image Retrieval
Chifa, N., Badri, A., Ruichek, Y., et al. (2016) · International Journal of Computer Applications Technology and Research · doi:10.7753/ijcatr0504.1006 · Cited by 1
Kato, D., Muto, K., Mitsumine, H., et al. (2014) · Journal of the Robotics Society of Japan · doi:10.7210/jrsj.32.576 · Cited by 1
Experimental Evaluation of the Bag-of-Features Model for Unsupervised Learning of Images
Afonso, M., & Teixeira, L. F. (2015) · British Machine Vision Conference (BMVC) · doi:10.5244/c.29.146 · Cited by 1
“Among the different methods, the detectors used in this study were: SIFT (Scale-Invariant Feature Transform) [12], SURF (Speeded Up Robust Features) [4], FAST (Features from Accelerated Segment Test) [20], STAR - derived from CenSurE (Center Surrounded Extrema) [1] and ORB (Oriented FAST and Rotated BRIEF) [21] and th…”
MethodAn Improvement to Media Discovery Service Using Image Identification Technique
Fu, Y. C., & Yang, L. (2011) · doi:10.5594/m001068 · Cited by 1
Guessing an Unknown Class by Online Fast Attributes Learning and Transfer
Kimura, D., Kankuekul, P., & Hasegawa, O. (2014) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.26.830 · Cited by 1
Position and Rotation Estimation for Mobile Robots in Outside of Recording Path Using Ego-motion
Hagiwara, Y., Shoji, T., & Imamura, H. (2013) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.133.356 · Cited by 1
Image Key Points Detection and Matching
Medvedev, M., & Shleymovich, M. P. (2013) · Proceedings of the Spring/Summer young researchers' colloquium on software engineering · doi:10.15514/syrcose-2013-7-26 · Cited by 1
“Another useful method of key point extraction is SURF (Speeded Up Robust Features) [1].”
BackgroundMethodInfluentialA Survey on Data Association Methods in VSLAM
Vidhya, S. S., Akki, C. B., & Prakash, S. (2015) · International Journal of Engineering Trends and Technology · doi:10.14445/22315381/ijett-v30p216 · Cited by 1
“SURF: Speeded Up Robust Features (SURF) is a scale and rotation invariant descriptor presented in [3].”
MethodIMPACT ASSESSMENT OF IMAGE FEATURE EXTRACTORS ON THE PERFORMANCE OF SLAM SYSTEMS
Pire, T., Fischer, T., & Faigl, J. (2015) · Acta Polytechnica CTU Proceedings · doi:10.14311/app.2015.1.0045 · Cited by 1
“ORB – Oriented FAST and Rotated BRIEF [10] is another attempt to achieve a scale and rotation invariant BRIEF, as a computationally efficient alternative to SIFT and SURF.”
MethodInfluentialCupec, R., Nyarko, E. K., Kitanov, A., & Petrovic, I. K. (2009) · European Conference on Mobile Robots · Cited by 2
Global Image Registration Based on Invariant Representation of Polar Complex Exponential Transform
Yi, M., Guo, B., & Yan, C. (2014) · Journal of information science and engineering · doi:10.6688/jise.2014.30.3.18 · Cited by 1
“Theoretically speaking, the SIFT or SURF-based descriptor has a shorter feature matching time with respect to IPCETs descriptor.”
BackgroundOn Calibration and Alignment of Point Clouds in a Network of RGB-D Sensors for Tracking
Xu, G., & Payandeh, S. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27863-6_52 · Cited by 1
Kalman Filter Correction with Rational Non-linear Functions: Application to Visual-SLAM.
Féraud, T., Chapuis, R., Aufrère, R., et al. (2011) · Cited by 1
ON-LINE 3D BODY MODELLING FOR AUGMENTED REALITY
Almeida, L., Menezes, P. J., & Dias, J. M. M. (2012) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0003866304720479 · Cited by 1
A Hierarchical Registration Method of the Chang’E-1 Stereo Images
Ye, M., & Huang, J. (2013) · Lecture notes in electrical engineering · doi:10.1007/978-3-642-41407-7_24 · Cited by 1
Phan, T. T., Nguyen, T.-N. D., & Lê, T. H. (2016) · Indian Journal of Science and Technology · doi:10.17485/ijst/2016/v9i17/92297 · Cited by 1
“SURF_LBPi = {SURFiLBPi} (10) Figure 1 shows the process of SURF_LBP feature Integration.”
BackgroundAn Adaptive Approach for Keypoints Description Using Fractional Derivative
Si, S., Hu, F., Wang, Z., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23989-7_62 · Cited by 1
Image Representation Optimization Based on Locally Aggregated Descriptors
Chen, S., Ding, G., Li, C., & Guo, Y. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-31750-2_9 · Cited by 1
Co-Registration of 2D Imagery and 3D Point Cloud Data
Weinmann, M. (2016) · Springer eBooks · doi:10.1007/978-3-319-29246-5_5 · Cited by 1
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.