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 6,801–6,900 of 14,752
Globally exponentially convergent observer for vision-based range estimation
Dani, A. P., El-Rifai, K., & Dixon, W. E. (2010) · IEEE International Symposium on Intelligent Control · doi:10.1109/isic.2010.5612878 · Cited by 6
3D Registration in Dark Environments Using RGB-D Cameras
Yousif, K., Bab‐Hadiashar, A., & Hoseinnezhad, R. (2013) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2013.6691470 · Cited by 6
“SIFT/SURF features are matched by finding the Euclidean based nearest neighbor in the descriptor vector space.”
MethodInfluentialA Real-Time Pineapple Matching System Based on Speeded-Up Robust Features
Li, B., Wang, M., & Li, L. (2010) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis.2010.59 · Cited by 6
“In this way, each sub-region has a fourdimensional descriptor vector v for its intensity structure [9-11]:”
BackgroundMethodAutomatic geolocation of targets tracked by aerial imaging platforms using satellite imagery
Shukla, P. K., Goel, S., Singh, P. P., & Lohani, B. (2014) · 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-8-1213-2014 · Cited by 5
Visibility improvement of aerial imagery by a locally tuned nonlinear enhancement technique
Arigela, S., & Asari, V. K. (2012) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai.2012.6202492 · Cited by 6
3D wide baseline correspondences using depth-maps
Marcon, M., Frigerio, E., Sarti, A., et al. (2012) · Signal Processing Image Communication · doi:10.1016/j.image.2012.01.009 · Cited by 6
Vision-Based Autonomous Landing for Small-Scale Unmanned Rotorcraft
Jeon, D., Cho, K., & Kim, D.-H. (2011) · IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing Workshops (ISORCW) · doi:10.1109/isorcw.2011.37 · Cited by 6
“Another method to annotate reference of landing is letting SURF (Speeded Up Robust Features) [5] system determine it.”
MethodActive Comparison of Prediction Models
Sawade, C., Landwehr, N., & Scheffer, T. (2012) · Cited by 6
Fast road detection and tracking in aerial videos
Zhou, H., Kong, H., Álvarez, J. M., et al. (2014) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2014.6856523 · Cited by 6
FIM: A Real-Time Content Based Sample Image Matching System
Luo, Y., Li, Y., Tu, J., & Xu, C. (2013) · International Conference on Image and Graphics · doi:10.1109/icig.2013.116 · Cited by 6
Efficient and effective transformed image identification
Awrangjeb, M., & Lu, G. (2008) · IEEE Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2008.4665141 · Cited by 6
“The recently proposed Fast-Hessian detector in the SURF (speeded up robust features) detector-descriptor scheme [4] used a basic approximation of the Hessian matrix and relied on the integral images to reduce the computational cost.”
BackgroundMethodInfluentialReal Time Interactive Image Segmentation Using User Indicated Real-World Seeds
Gomes, R. B., Aroca, R. V., de Carvalho, B. M., et al. (2012) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2012.33 · Cited by 6
Thomas, J., Kareem, A., & Bowyer, K. W. (2012) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2012.6351066 · Cited by 6
“For feature extraction we use scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Feature) first introduced in [5].”
MethodImproved Tracking of Multiple Vehicles Using Invariant Feature-Based Matching
Choi, J.-Y., Choi, J., & Yang, Y.-K. (2007) · Springer eBooks · doi:10.1007/978-3-540-77046-6_80 · Cited by 6
Method of item recognition based on SIFT and SURF
Chen, W., XIE, W., & Zeng, R. (2014) · Mathematical Structures in Computer Science · doi:10.1017/s0960129513000820 · Cited by 6
Describing 3D Geometric Primitives Using the Gaussian Sphere and the Gaussian Accumulator
Toony, Z., Laurendeau, D., & Gagné, C. (2015) · 3D Research · doi:10.1007/s13319-015-0074-3 · Cited by 6
“After voxelizing the 3D surface, SURF features [2] are extracted from each voxel, used to build a visual vocabulary, and then a Hough Transform-like voting method is used to build the histogram for each set of words.”
MethodHead Nod and Shake Gesture Interface for a Self-portrait Camera
Chu, S., & Tanaka, J. (2012) · Cited by 6
Passive 3D Scene Reconstruction via Hyperspectral Imagery
Miller, C. A., & Walls, T. J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14249-4_39 · Cited by 6
“Table 1 shows an example using four different feature point detectors (SURF, BRISK, FAST, and ORB [12,13,14,15]), comparing the full-spectrum images to those generated when the full spectrum is split into three subsets.”
MethodCBDF: Compressed Binary Discriminative Feature
Geng, L.-C., Jodoin, P., Su, S., & Li, S. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.07.120 · Cited by 6
Improving performance on object recognition for real-time on mobile devices
Piao, J.-C., Jung, H.-S., Hong, C.-P., & Kim, S. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2999-1 · Cited by 6
Mobile multi-view object image search
Çalışır, F., Baştan, M., Ulusoy, Ö., & Güdükbay, U. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3659-9 · Cited by 7
Object recognition to support indoor robot navigation
Takacs, M., Bencze, T., Szabo-Resch, M. Z., et al. (2015) · IEEE International Symposium on Computational Intelligence and Informatics (CINTI) · doi:10.1109/cinti.2015.7382930 · Cited by 6
Fast keypoint detection in video sequences
Baroffio, L., Cesana, M., Redondi, A. E. C., et al. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7471895 · Cited by 6
A novel rotation adaptive object detection method based on pair Hough model
Liu, Y., Huang, L., Liu, X., et al. (2016) · Neurocomputing · doi:10.1016/j.neucom.2015.12.105 · Cited by 6
Image classification using pairwise local observations based Naive Bayes classifier
Hsu, S.-C., Chen, I.-C., & Huang, C.-L. (2015) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2015.7415311 · Cited by 8
“The first category is the edge-based feature point detection such as Scale Invariant Feature (SIFT) [1], Speed-up Robust Feature (SURF) [2], and Harris corner detection [3].”
MethodHierarchical multi-VLAD for image retrieval
Wang, Y., Duan, L., Lin, J., Wang, Z., & Huang, T. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351684 · Cited by 6
“In general, state-of-the-art image search systems are built upon a visual vocabulary with an inverted indexing structure, which quantizes local features (e.g., SIFT [1] or SURF [2]) of query and database images into centroids.”
MethodContent-Based Image Retrieval with LIRe and SURF on a Smartphone-Based Product Image Database
Chen, K., & Hennebert, J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-07491-7_24 · Cited by 6
“Local feature SURF (SpeededUp Robust Features) [1] is also employed for the product identification task.”
MethodGeometric corner extraction in retinal fundus images
Lee, J. A., Lee, B. H., Xu, G., Ong, E. P., Wong, D. W. K., Liu, J., & Lim, T. H. (2014) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2014.6943553 · Cited by 6
“SURF uses Hessian-matrix based detector to identify blob-like interest points which are claimed to be superior than other state-of-the-art feature extraction methods with regard to repeatability and stability.”
MethodInfluentialBold, S., Sosorbaram, B., & Lee, S. R. (2016) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-0557-2_36 · Cited by 6
A REAL-TIME ROBOT VISION APPROACH COMBINING VISUAL SALIENCY AND UNSUPERVISED LEARNING
Ramík, D. M., Sabourin, C., & Madani, K. (2011) · Field Robotics · doi:10.1142/9789814374286_0028 · Cited by 6
Vehicle Model Recognition in Video
Lee, S., Gwak, J., & Jeon, M. (2015) · Cited by 6
Thermal Face Recognition Using Local Patterns
Hermosilla, G., Farías, G., Vargas, H., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-12568-8_60 · Cited by 6
Evaluation of Interest Point Matching Methods for Projective Reconstruction of 3D Scenes
Brito, D. N., Nunes, C. F. G., Pádua, F. L. C., et al. (2016) · IEEE Latin America Transactions · doi:10.1109/tla.2016.7459626 · Cited by 6
“Neste trabalho, são avaliados os impactos de cinco métodos de correspondência de pontos no que se refere à exatidão e eficiência do processo de reconstrução projetiva de cenas estáticas, quais sejam: SIFT [10], SURF [11], ORB [12], FREAK [13] e BRISK [14].”
BackgroundSIFT-FANN: An efficient framework for spatio-spectral fusion of satellite images
Rai, K. K., Rai, A., Dhar, K., et al. (2016) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-016-0576-3 · Cited by 6
“Many researchers have proposed different keypoint detectors for images of varying scale, SIFT and SURF being the most significant ones.”
MethodCenter Symmetric Local Multilevel Pattern Based Descriptor and Its Application in Image Matching
Zeng, H., Wang, X., & Gu, Y. (2016) · International Journal of Optics · doi:10.1155/2016/1584514 · Cited by 6
“The SURF (Speeded Up Robust Features) descriptor uses integral image to compute the gradient histograms and it can speed up the computations effectively while preserving the quality of SIFT [7].”
MethodAn optimisation approach to the design of a fast, compact and distinctive binary descriptor
Oszust, M. (2016) · Signal Image and Video Processing · doi:10.1007/s11760-016-0907-4 · Cited by 6
“Another, high-dimensional, real-valued descriptor that in some cases outperforms SIFT is SURF [3].”
BackgroundMethodInfluentialOnline human assisted and cooperative pose estimation of 2D cameras
Manzo, G., Serratosa, F., & Vento, M. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.05.012 · Cited by 6
Stable Keypoint Recognition using Viewpoint Generative Learning
Yoshida, T., Saitô, H., Shimizu, M., et al. (2013) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004295203100315 · Cited by 6
“SURF (Bay et al., 2006) is designed to have faster computation than SIFT without degrading its performance.”
MethodInfluentialSynchronizing Multi-User Photo Galleries with MRF
Sansone, E., Boato, G., & Dao, M.-S. (2014) · Cited by 6
A Sparse Hybrid Map for Vision-Guided Mobile Robots.
Dayoub, F., Cielniak, G., & Duckett, T. (2011) · QUT ePrints (Queensland University of Technology) · Cited by 9
Structure-guided image completion via regularity statistics
Yang, S., Liu, J., Song, S., et al. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7471969 · Cited by 6
“We begin with Speeded Up Robust Features (SURF, [12]) points detection and compute SURF descriptors for each feature point k .”
MethodA Modular Software Framework for Eye–Hand Coordination in Humanoid Robots
Leitner, J., Harding, S., Förster, A., & Corke, P. (2016) · Frontiers in Robotics and AI · doi:10.3389/frobt.2016.00026 · Cited by 6
“Most object detection applications have been using hand-crafted features, such as SIFT (Lowe, 1999) or SURF (Bay et al., 2006), or extensions of these for higher robustness (Stückler et al., 2013).”
MethodComputer-aided diagnostics of facial and oral cancer
Bourass, Y., Zouaki, H., & Bahri, A. (2015) · World Conference on Complex Systems · doi:10.1109/icocs.2015.7483252 · Cited by 10
“A large variety of local visual features to represent the images were proposed during the last decade such as GLOH (Gradient Location and Orientation Histogram) [15], SIFT (Scale Invariant Feature Transform) [21], SURF (Speeded Up Robust Features) [22], and many others [16, 17, 18].”
BackgroundPhytoplankton feature extraction from microscopic images based on SURF-PCA
Chang, L., Wang, R., Zheng, H., et al. (2016) · OCEANS 2016 - Shanghai · doi:10.1109/oceansap.2016.7485699 · Cited by 6
“SURF approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be compared and computed much faster [3].”
Saliency-context two-stream convnets for action recognition
Chen, Q.-Q., Liu, F., Li, X., Liu, B., & Zhang, Y. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532925 · Cited by 7
“We also resort to SURF feature and optical flow matches, since they provide complementary information as shown in [1].”
MethodLearning to sketch human facial portraits using personal styles by case-based reasoning
Jin, B., Xu, S., & Geng, W. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4457-8 · Cited by 6
An image registration algorithm based on FREAK-FAST for visual SLAM
Liu, F., Lv, Q., Huican, L., et al. (2016) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2016.7554334 · Cited by 6
“SURF [8] is a new scale and rotation invariant key point detecting and describing algorithm, with the performance of robust and fast computing.”
BackgroundMethodObtaining the consensus of multiple correspondences between graphs through online learning
Moreno‐García, C. F., & Serratosa, F. (2016) · Pattern Recognition Letters · doi:10.1016/j.patrec.2016.09.003 · Cited by 6
A workflow approach for mosaicking UAV images
Wu, Z., Yue, P., Zhang, M., et al. (2016) · International Conference on Agro-Geoinformatics · doi:10.1109/agro-geoinformatics.2016.7577706 · Cited by 6
“In the workflow, the first subprocess is to extract the features of each image by using the Speeded Up Robust Features (SURF) algorithm [5].”
MethodNovel Keypoint Registration for Fast and Robust Pose Detection on Mobile Phones
Kobayashi, T., Kato, H., & Yanagihara, H. (2013) · IAPR Asian Conference on Pattern Recognition (ACPR) · doi:10.1109/acpr.2013.67 · Cited by 6
“In contrast to common descriptors such as SIFT [2] and SURF [10], they use simple binary tests between pixels in an image patch to describe the patch and are therefore sufficiently fast on mobile phones.”
MethodEmbedded Multimodal Registration of Visible Images on Long-Wave Infrared Video in Real Time
Inostroza, F., Cárdenas, J., Godoy, S. E., et al. (2016) · Euromicro Conference on Digital System Design (DSD) · doi:10.1109/dsd.2016.99 · Cited by 6
“Some solutions are based on features from the images such as the Scale Invariant Feature Transform (SIFT) algorithm [4], [5] or the Speeded Up Robust Features (SURF) algorithm [6].”
MethodAugmented skeletal joints for temporal segmentation of sign language actions
Seddik, B., Gazzah, S., Château, T., & Amara, N. E. B. (2014) · IEEE International Conference on Image Processing, Applications and Systems (IPAS) · doi:10.1109/ipas.2014.7043295 · Cited by 6
Edge information based object classification for NAO robots
Tarvas, K., Bolotnikova, A., & Anbarjafari, G. (2016) · Cogent Engineering · doi:10.1080/23311916.2016.1262571 · Cited by 6
The Application of Social Media Image Analysis to an Emergency Management System
Jing, M., Scotney, B., Coleman, S., & McGinnity, T. M. (2016) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1109/ares.2016.24 · Cited by 6
“To accelerate fast image processing for social media image analysis, we introduced a new image feature descriptor which incorporates the SIP framework with SURF [2].”
MethodNguyen, T. H., Kim, D. H., Lee, C. H., et al. (2016) · Lecture notes in electrical engineering · doi:10.1007/978-3-319-50904-4_70 · Cited by 6
Producing Usable Simulation Terrain Data from UAS-Collected Imagery
Spicer, R. P., McAlinden, R., & Conover, D. (2016) · Cited by 6
Surf points based Moving Target Detection and Long-term Tracking in Aerial Videos
Zhu, J.-J., Sun, W. J., Guo, B., et al. (2016) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2016.11.023 · Cited by 6
“Surf [24] takes advantage of Sift detector and reduces computational cost by cutting down point descriptor dimensions.”
BackgroundMethodFaceMatch: Real-World Face Image Retrieval
Borovikov, E., & Vajda, S. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-4859-3_36 · Cited by 6
“Having several image descriptors per face (HAAR, SURF, SIFT, ORB, LBPH), we experimented with similarity distance-based and similarity rank-based feature combination strategies.”
MethodThe effect of angles and distance on image-based, three-dimensional reconstructions
Chen, S., Laefer, D. F., Byrne, J., et al. (2017) · doi:10.1201/9781315210469-350 · Cited by 6
Benam, A., Drew, M. S., & Atkins, M. S. (2017) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2017.7950483 · Cited by 7
“We took the same approach as SURF for blob detection.”
MethodInfluentialModeling Objects as Aspect Transition Graphs to Support Manipulation
Ku, L. Y., Miller, E. G., & Grupen, R. A. (2017) · Springer proceedings in advanced robotics · doi:10.1007/978-3-319-60916-4_8 · Cited by 6
An Analytical Study of SIFT and SURF in Image Registration
Gupta, V., & Cecil, K. (2014) · Cited by 6
Ground Truth Accuracy and Performance of the Matching Pipeline
Maier, J., Humenberger, M., Zendel, O., & Vincze, M. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.133 · Cited by 8
Pairwise registration in indoor environments using adaptive combination of 2D and 3D cues
Villota, J. C. P., da Silva, F. L., Jacomini, R. D. S., & Costa, A. H. R. (2017) · Image and Vision Computing · doi:10.1016/j.imavis.2017.08.008 · Cited by 6
Wavelet Transform Based Face Recognition Using SURF Descriptors
Ameen, M. M., Eleyan, A., & Eleyan, G. (2017) · International Journal of Electronics and Electrical Engineering · doi:10.18178/ijeee.5.1.94-98 · Cited by 6
“determinant of Hessian blob detector with integral images [9].”
BackgroundMethodInfluentialWindsurf: the best way to SURF
Bartolini, I., & Patella, M. (2017) · Multimedia Systems · doi:10.1007/s00530-017-0567-4 · Cited by 8
“Subsequent algorithms (like SURF [9]) improved performance of SIFT both in efficiency (SURF feature extraction is one order of magnitude faster and its descriptors are half the size of SIFT, i.”
MethodYu, S., Moon, B., Kim, D., Kim, S., Choe, W., Lee, S., & Paik, J. (2017) · Multidimensional Systems and Signal Processing · doi:10.1007/s11045-017-0534-4 · Cited by 6
Chen, S., Li, X. S., Zhang, Y., Feng, R., & Zhang, C. (2017) · Remote Sensing · doi:10.3390/rs9121244 · Cited by 6
“compared with the manual features-based floating-point feature matching algorithm SURF, the binary feature atching algorith BRIEF, and the learning-based atching algorith atch et, the experi ental results based on three aerial i ages are given in Figures 5–7.”
MethodInfluentialAlvarez, A. B., Ponnusamy, G., & Alioto, M. (2017) · IEEE Asian Solid-State Circuits Conference (A-SSCC) · doi:10.1109/asscc.2017.8240261 · Cited by 6
A vision-based perception framework for outdoor navigation tasks applicable to legged robots
Sun, J., Meng, Y., Tan, J., Sun, C., Zhang, J., Ding, N., Qian, H., & Zhang, A. (2017) · Chinese Automation Congress · doi:10.1109/cac.2017.8243269 · Cited by 6
“The SURF features was used on Little Dog[15] in 2011.”
MethodA two‐stage sampling for robust feature matching
Chou, C., Seo, Y. W., & Wang, C. (2018) · Journal of Field Robotics · doi:10.1002/rob.21778 · Cited by 5
“…using Examples of three common challenges in matching features from two images k -nearest neighbors from an initial matches of salient features (Bay, Tuytelaars, & Gool, 2006; Lowe, 1999; Rublee, Rabaud, Konolige, & Bradski, 2011), and then reject, using 8-point (Zisserman & Hartley, 2004) or…”
MethodFootnote-based document image classification using 1D convolutional neural networks and histograms
Mhiri, M., Abuelwafa, S., Desrosiers, C., et al. (2017) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2017.8310140 · Cited by 6
Tunnel Brightness Compensation With Spatial–Temporal Visual-Content Preservation
Fang, J., & Xue, J. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2808934 · Cited by 6
“For a real-time performance analysis, two different approaches are considered: 1) replacing SIFT [38] point matching with more efficient speeded-up robust feature point [45] matching, 2) replacing the MATLAB compiler with a C/C++ compiler, which will boost the efficiency by about ten times.”
Calibrating Cameras in Poor-Conditioned Pitch-Based Sports Games
Zeng, R., Lakemond, R., Denman, S., Sridharan, S., Fookes, C., & Morgan, S. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461667 · Cited by 5
Zhao, X., Min, H., Xu, Z., Wu, X., Li, X., & Sun, P. (2018) · Journal of Sensors · doi:10.1155/2018/2987819 · Cited by 6
“The comparison with other detectors and descriptors, like SIFT, SURF [40], KAZE [41], and AKAZE [42], has been carried out in [41].”
Recovering Affine Features from Orientation- and Scale-Invariant Ones
Baráth, D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20887-5_17 · Cited by 6
“An approach is proposed for recovering affine correspondences from orientation- and scale-invariant features obtained by, for instance, SIFT or SURF detectors.”
BackgroundMonitoring Excavation Slope Stability Using Drones
Xiao, Y., Kamat, V. R., & Lee, S. H. (2018) · ASCE Construction Research Congress (CRC) · doi:10.1061/9780784481264.017 · Cited by 6
Aerial mapping of rice crops using mosaicing techniques for vegetative index monitoring
B., J. P. R., P., C. A. D., Petró, E., et al. (2018) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2018.8453283 · Cited by 6
“For this application two different algorithms were implemented (SURF [23] and the ORB [24] ), in order to test which algorithm provides better results for the application, in terms of execution time and quality of the generated mosaic (which is the best descriptor of rice crops).”
MethodA Novel Automatic Image Stitching Algorithm for Ceramic Microscopic Images
Li, K., & Ding, G. (2018) · International Conference on Audio, Language and Image Processing · doi:10.1109/icalip.2018.8455766 · Cited by 6
A binary method of multisensor image registration based on angle traversal
Liang, H., Liu, C., He, B., et al. (2018) · Infrared Physics & Technology · doi:10.1016/j.infrared.2018.10.025 · Cited by 6
A Point-Line Feature based Visual SLAM Method in Dynamic Indoor Scene
Wang, R., Wang, Y., Wan, W., et al. (2018) · doi:10.1109/upinlbs.2018.8559749 · Cited by 6
“The feature extraction operators such as PCA-SIFT [11], SURF [12] and CenSurE [13], which resist rotation and scaling deformation, have achieved good results in feature extraction and matching between sequence images [14].”
MethodTerrain Relative Navigation With Anonymous Features
McCabe, J. S., & DeMars, K. J. (2019) · AIAA SciTech Forum · doi:10.2514/6.2019-0923 · Cited by 6
SLAM-based 3D Line Reconstruction
Zhou, H., Zhou, D., Peng, K., et al. (2018) · World Congress on Intelligent Control and Automation · doi:10.1109/wcica.2018.8630629 · Cited by 6
“Owning to the SFM (structure from motion) techniques[1], sparse point cloud of the scene can be easily obtained using distinctive feature points like SIFT[2], ORB[3], SURF[4] and so on.”
MethodMulti-Layer Feature Based Shoeprint Verification Algorithm for Camera Sensor Images
Wang, X., Wu, Y., & Zhang, T. (2019) · Sensors · doi:10.3390/s19112491 · Cited by 6
A Comparative Study on Image Registration Techniques for SAR Images
Sreeja, G. B., & Saraniya, O. (2019) · doi:10.1109/icaccs.2019.8728390 · Cited by 6
Homography‐based traffic sign localisation and pose estimation from image sequence
Cui, Z., Liu, Y., & Ren, F. (2019) · IET Image Processing · doi:10.1049/iet-ipr.2019.0023 · Cited by 6
“Aiming to overcome these problems, we first utilise both SIFT [25] and SURF [31] features as well as their descriptors to increase the number of feature points.”
MethodMulti-view reconstructive preserving embedding for dimension reduction
Wang, H., Feng, L., Kong, A., & Jin, B. (2019) · Soft Computing · doi:10.1007/s00500-019-04395-4 · Cited by 7
“B Lin Feng whb08421005@mail.dlut.edu.cn 1 Department of Computer Science and Technology, Information Science and Technology College, Dalian Maritime University, Dalian 116026, China 2 School of Computer Science and Technology, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technolog…”
BackgroundImage Stitching Development By Combining SIFT Detector And SURF Descriptor For Aerial View Images
Akhyar, R. M., & Tjandrasa, H. (2019) · International Conference on Information & Communication Technology and System (ICTS) · doi:10.1109/icts.2019.8850941 · Cited by 6
EVALUATING THE ACCURACY OF 3D OBJECT RECONSTRUCTION FROM THERMAL IMAGES
Mizginov, V. A., & Kniaz, V. V. (2019) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlii-2-w18-129-2019 · Cited by 6
“Firstly, we want to compare the accuracy of keypoint matching for four algorithms: SIFT (Lowe, 1999), SURF (Bay et al., 2006), LF-Net (Ono et al., 2018), and CAE-64 (Knyaz et al., 2017).”
MethodInfluentialSelf-Recognition Grasping Operation with a Vision-Based Redundant Manipulator System
Li, T., Zheng, S., Shu, X., Wang, C., & Liu, C. (2019) · Applied Sciences · doi:10.3390/app9235172 · Cited by 6
Comparison of Camera and Laser Scanner based 3D Point Cloud
Rehman, Y., Uddin, H. M. A., Siddique, T. H. M., Haris, Jafri, S. R. U. N., & Ahmed, A. F. (2019) · International Conference on Emerging Trends in Engineering, Sciences and Technology (ICEEST) · doi:10.1109/iceest48626.2019.8981708 · Cited by 6
Image Features Detection and Tracking for Image Based Target Augmented Reality Application
Mokhtar, M. K., Mohamed, F., Sunar, M. S., et al. (2019) · doi:10.1109/game47560.2019.8980604 · Cited by 6
“Handcrafted descriptors are such as SIFT [2], SUFT [3] and ORB [4] which are quite popular previously.”
MethodEvasion Attacks On Svm Classifier
Maria, James, M., Mruthula, M., Bhaskaran, V., & Asha, S. B. (2019) · International Conference on Advances in Computing and Communications (ICACC) · doi:10.1109/icacc48162.2019.8986189 · Cited by 6
Accuracy Characterization of the Vehicle State Estimation from Aerial Imagery
Morales, E. S., Kruber, F., Botsch, M., Huber, B., & Higuera, A. G. (2020) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv47402.2020.9304705 · Cited by 6
Weeping and Gnashing of Teeth: Teaching Deep Learning in Image and Video Processing Classes
Bovik, A. C. (2020) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai49293.2020.9094606 · Cited by 7
“My prepared course materials covered the essential topics of image formation, sampling and Fourier theory, wavelets, linear and nonlinear filtering, image coding, and feature detection using LoG and DoG, SIFT and SURF, using them for picture quality prediction, texture analysis, edge, boundary, and line detection, vis…”
InfluentialVisual feedback control of quadrotor by object detection in movies
Shao, L., Nagata, F., Ochi, H., et al. (2020) · Artificial Life and Robotics · doi:10.1007/s10015-020-00609-3 · Cited by 6
A Feature Fusion Approach to Classifying Targets Underneath Foliage via Wideband LFMB SAR Systems
Raj, R. G., Peters, M. F., & Brozena, J. M. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.2998411 · Cited by 6
Machine Learning Based Features Matching for Fatigue Crack Detection
Kong, X., Zhang, Z., Meng, L., et al. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.06.063 · Cited by 6
Social Media for Mental Health: Data, Methods, and Findings
Kamarudin, N. S., Beigi, G., Manikonda, L., & Liu, H. (2020) · Lecture notes in social networks · doi:10.1007/978-3-030-41251-7_8 · Cited by 13
“In order to extract visual features from the dataset, the authors pair OpenCV and Speeded Up Robust Features (SURF [7]).”
TEMPORAL REPETITION DETECTION FOR GROUND VISIBILITY ASSESSMENT
von Gioi, R. G., Hessel, C., Dagobert, T., et al. (2020) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-2-2020-829-2020 · Cited by 6
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.