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 10,701–10,800 of 14,752
Monogenic Curvature Tensor as Image Model
Sommer, G., Wietzke, L., & Zang, D. (2009) · Mathematics and visualization · doi:10.1007/978-3-540-88378-4_14 · Cited by 1
CATEGORIZATION OF SIMILAR OBJECTS USING BAG OF VISUAL WORDS AND k - NEAREST NEIGHBOUR CLASSIFIER
Artiemjew, P., Górecki, P., & Sopyła, K. (2012) · Cited by 1
Clustering for Video Retrieval
Chmelař, P., Burgetová, I., & Zendulka, J. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03730-6_31 · Cited by 1
Cooray, S. H. (2008) · Dublin City University Open Access Institutional Repository (Dublin City University) · Cited by 1
Learning to Identify Stable Keypoints
Liu, Y., & Chen, H.-T. (2012) · Interdisciplinary Information Sciences · doi:10.4036/iis.2012.107 · Cited by 1
“Lots of local feature detectors have been proposed over recent years, for example, saliency detector [7], MSER [9], SIFT-DoG [8], affine invariant detectors [10, 11], and SURF [1].”
MethodPhoto- and Video-Based Ranging and Modeling
Wang, Y.-F. (2014) · UA Campus Repository (The University of Arizona) · Cited by 1
Multimedia Content Understanding: Bringing Context to Content
Huet, B. (2012) · Graduate School and Research Center in Digital Science (EURECOM) · Cited by 1
A Hierarchical Approach to Practical Beverage Package Recognition
Yeh, M.-C., & Tai, J. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25367-6_31 · Cited by 1
A Self-trainable System for Moving People Counting by Scene Partitioning
Percannella, G., & Vento, M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21596-4_30 · Cited by 1
Fast region-based object detection and tracking using correlation of features
Senekal, F. (2010) · Cited by 1
Mitchell, H. B. (2010) · Springer eBooks · doi:10.1007/978-3-642-11216-4_13 · Cited by 1
Leveraging the cloud for connected service robotics applications
Rosa, S., Russo, L. O., Toscana, G., et al. (2015) · IEEE Conference on Emerging Technologies & Factory Automation (ETFA) · doi:10.1109/etfa.2015.7301653 · Cited by 1
Omnidirectional vision for robot localization in urban environments
Frontoni, E., Ascani, A., Mancini, A., et al. (2008) · Università Politecnica delle Marche (Università Politecnica delle Marche) · Cited by 1
Pose Estimation using a Hierarchical 3D Representation of Contours and Surfaces
Buch, A. G., Kraft, D., Kämäräinen, J., et al. (2013) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004275801050111 · Cited by 1
“Many of these works involve 2D descriptors (see e.g. (Bay et al., 2006; Belongie et al., 2002; Lowe, 1999)).”
BackgroundMethodFast vision-based scene modeling for augmented reality in unprepared man-made environments
Vigueras-Gómez, J. F., & Sclaroff, S. (2013) · Journal of Ambient Intelligence and Smart Environments · doi:10.3233/ais-130224 · Cited by 1
“Or this may also be accomplished by computing and matching point descriptors (e.g. SURF [4]), although any other features or feature detectors can be used.”
Improved SVD matching based on Delaunay triangulation and belief propagation
Dou, J., Qin, Q., & Tu, Z. (2015) · Optik · doi:10.1016/j.ijleo.2015.09.195 · Cited by 1
Semantic-enriched visual vocabulary construction in a weakly supervised context
Rizoiu, M.-A., Velcin, J., & Lallich, S. (2015) · Intelligent Data Analysis · doi:10.3233/ida-140702 · Cited by 1
Inter-slice Correspondence for 2D Ultrasound-Guided Procedures
Toews, M., Golby, A. J., & Wells, W. M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-05666-1_18 · Cited by 1
“ISC makes use of local scale-invariant image features, distinctive image patterns that can be automatically extracted in each US slice in a manner independent of in-plane translation, orientation and scale changes [9, 10].”
BackgroundMethodMPRF: Multisupport polar region features for image description
Kannan, R., Ghinea, G., Kannaiyan, S., & Swaminathan, S. (2014) · IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) · doi:10.1109/isspit.2014.7300562 · Cited by 1
Detection of saliency maximally stable color regions
Miao, J., Chu, J., & Zhang, G. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-1893-6 · Cited by 1
Domain-specific image geocoding
Li, L. T., Penatti, O. A. B., Fox, E. A., et al. (2013) · ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL) · doi:10.1145/2467696.2467727 · Cited by 1
“(6 pixels) [15], sparse SIFT (Harris-Laplace detector) [15], and sparse SURF (Fast-Hessian detector) [1].”
Efficient and Robust Feature Matching via Local Descriptor Generalized Hough Transform
Li, J., & Yang, T. (2013) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.373-375.536 · Cited by 1
Video annotation of TV content using audiovisual information
Mateus, J., Malheiro, F., Cavaco, S., Correia, N. M. R., & Jesus, R. M. (2012) · doi:10.1109/icmcs.2012.6320188 · Cited by 3
“Image Descriptors The ViewProcFlow tool supports comparison of images or image region use the information extracted with the Scale Transform (SIFT) and the Speeded Up Robust Features (SURF) [12, 13].”
MethodPractical on-line near-duplicate detection for web video
Bao, W., Ji, L., & Liu, L. (2013) · IEEE International Conference on Information Science and Technology (ICIST) · doi:10.1109/icist.2013.6747677 · Cited by 1
Dense reconstruction of underwater scenes from monocular sequences of images
Rzhanov, Y., Hu, H., & Boyer, T. (2014) · doi:10.1109/oceans-taipei.2014.6964337 · Cited by 1
He, J. Y. D., Zuo, T., Sun, B., Wu, X., & Chen, C. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2050374 · Cited by 1
“Other local feature extraction approaches, such as PCA-SIFT [15], Speeded up Robust Features (SURF) [16] and Gradient Location-Orientation Histogram (GLOH) [17] also show their robust performance against scale, rotation or even affine Automatic Target Recognition XXIV, edited by Firooz A. Sadjadi, Abhijit Mahalanobis,…”
MethodInfluentialVertical line-based descriptor for omnidirectional view image
Chong, N. S., Wong, M. L. D., & Kho, Y. H. (2014) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.1109/elinfocom.2014.6914386 · Cited by 1
“The subsequent procedure has obtained inspiration from the SURF algorithm [10] with modifications to suit the nature of a line feature.”
MethodAutomated methodology for gastric endoscopy in an e-health environment
Lee, S. K., Kim, E. S., Yoo, S., et al. (2013) · International Conference on Ubiquitous and Future Networks · doi:10.1109/icufn.2013.6614849 · Cited by 1
Efficient Image Retrieval Using Advanced Clustering SURF
Lee, Y., Ahn, H., & Rhee, S.-B. (2012) · International Conference on Network-Based Information Systems · doi:10.1109/nbis.2012.153 · Cited by 1
An evaluation of local interest regions for non-rigid object class recognition
Altun, O., & Albayrak, S. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.08.060 · Cited by 1
“SURF8 (Bay et al., 2008): Speeded Up Robust Feature centers are the extrema of Hessian determinant in both scale and space.”
BackgroundExtraction and Transfer of Gesture Information using ToF Camera
Park, W.-C., Ryu, D.-H., & Choi, T.-W. (2014) · The Journal of the Korea institute of electronic communication sciences · doi:10.13067/jkiecs.2014.9.10.1103 · Cited by 1
“그러나 ZCam이 동 일 시점에서 같은 해상도의 색상 영상과 깊이 영상을 제공하는 것과는 달리, 이후의 깊이 카메라들은 일반 적으로 색상 영상을 촬영할 수 없으며, 색상 영상을 촬영할 수 있도록 설계된 카메라라도 촬영되는 깊이 영상과 색상 영상의 해상도 및 촬영 시점이 다른 특 성을 가지고 있다[3-4].”
Experimental validation of a visual odometry system for indoor unstructured environments
Rodrigues, J., Cardeira, C., Carreira, F., Calado, J. M. F., & Oliveira, P. (2013) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2013.6766496 · Cited by 1
Color Invariants for Object Recognition
Muselet, D., & Funt, B. (2012) · Springer eBooks · doi:10.1007/978-1-4419-6190-7_10 · Cited by 1
Toward Smart Machine Tools in Taiwan
Huang, Y. H., Lee, M. R., Luo, T.-L., et al. (2014) · IT Professional · doi:10.1109/mitp.2014.99 · Cited by 1
Image understanding based on histogram of contrast
Zhang, X., & Liu, C. (2014) · Signal Image and Video Processing · doi:10.1007/s11760-014-0707-7 · Cited by 1
“Many state-of-the-art image representation methods are based on this idea, such as HOG [9], spatial pyramid [10], SIFT [11], and SURF [12].”
MethodImage Matching for Repetitive Patterns by Clustering and Transforming in Feature Space
Tanno, Y., & Kanazawa, Y. (2013) · IAPR Asian Conference on Pattern Recognition (ACPR) · doi:10.1109/acpr.2013.121 · Cited by 1
“There are various methods proposed in the past [1], [2], [3], [4], [5], [6].”
MethodInfluentialYang, Z., Schafer, J. M., & Ganz, A. (2014) · International Journal of E-Health and Medical Communications · doi:10.4018/ijehmc.2014070101 · Cited by 1
An optimal solution for RANSAC using constraint of saliency region
Zheng, J. Y., Xian, S., Zhang, W., & Liu, Y. (2012) · International Conference on Wavelet Analysis and Pattern Recognition · doi:10.1109/icwapr.2012.6294805 · Cited by 1
Object recognition algorithm using a vocabulary tree and a pre-matching array
Seo, H.-Y., & Lee, J.-J. (2010) · Artificial Life and Robotics · doi:10.1007/s10015-010-0773-z · Cited by 1
Tracking Feature Points of Fisheye Full-View Image by Normalized Image Patch
Qin, X., & Li, S. (2012) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.132.1516 · Cited by 2
Dorsal finger texture recognition: Investigating fixed-length SURF
Hartung, D., & Kuckelhahn, J. (2012) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2012.6377915 · Cited by 1
“Interest point detectors and descriptors, such as SIFT [18] and SURF [19] are able to detect correlating interest points in different samples, but do not produce a fixed length feature vector.”
BackgroundMethodAutomatic reflection removal using reflective layer image information
Prakash, D., Kalwad, P., Peddigari, V. R., et al. (2015) · International Conference on Consumer Electronics · doi:10.1109/icce.2015.7066520 · Cited by 1
“By matching corners, we get a set of points P1 and similarly by matching edges, SURF and MSER we get sets P2, P3, and P4 respectively.”
MethodDetection of dynamic objects for environment mapping by time-of-flight cameras
Dalbah, Y., Rohr, S., & Wahl, F. M. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025195 · Cited by 1
“However, the Speeded Up Robust Features (SURF) feature descriptor [16] is more efficient in terms of computational costs while maintaining the performance of the SIFT descriptor [17].”
MethodAutomatic foreground extraction in video
Wang, H., Deng, B., Li, K., et al. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854867 · Cited by 1
Kaheel, A., El-Saban, M., Izz, M., et al. (2012) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2012.117 · Cited by 1
“Comparing the proposed approach to SIFT and its speeded up version (SURF) [2].”
MethodTarget Recognition and Tracking Method Based on Multiple Templates in Complex Scenes
Gao, Z., Wang, B., Dong, M., et al. (2012) · Lecture notes in electrical engineering · doi:10.1007/978-3-642-34531-9_60 · Cited by 1
Visual Attention Mechanism for a Social Robot
Bandera, J. P., Marfil, R., Palomino, A. J., et al. (2012) · DOAJ (DOAJ: Directory of Open Access Journals) · doi:10.3233/abb-2011-0030 · Cited by 1
“The proposed detector is compared to themaximally stable extremal region detector (MSER) [34], the intensity extrema-based region detector (IBR) [46] and the Fast-Hessian [10].”
MethodDesai, A., & Lee, D.-J. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2045107 · Cited by 1
“SURF computes descriptors using integral images [2].”
Tomiyasu, F., Hirayama, T., & Mase, K. (2013) · IAPR Asian Conference on Pattern Recognition (ACPR) · doi:10.1109/acpr.2013.166 · Cited by 1
“We propose a 978-1-4799-2190-4/13 $26.00 © 2013 IEEE DOI 10.1109/ACPR.2013.166 90731 feature point tracking method based on a serial process of the corresponding feature point search and the Mean-Shift search using the speeded up robust features (SURF)[7].”
MethodInfluentialTowards a new approach for video database semantic annotation
Youcef, L. F. D., Ghomari, A., & Tani, M. Y. K. (2014) · Science and Information Conference · doi:10.1109/sai.2014.6918316 · Cited by 1
Repeatability Measurements for 2D Interest Point Detectors on 3D Models
Lang, S. R., Luerssen, M. H., & Powers, D. M. W. (2013) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-00969-8_35 · Cited by 1
The acceleration of pipeline workloads under the FPGA area and bandwidth constraints
Huang, W.-N., Cheng, S.-W., Chang, C.-W., et al. (2014) · IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA) · doi:10.1109/rtcsa.2014.6910539 · Cited by 1
“To improve the accuracy of recognition, various feature detection methods, such as the SIFT algorithm [20], [21], [22], are proposed.”
MethodPoint matching via affine region expansion
Farhan, E., & Hagege, R. R. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025076 · Cited by 1
Object matching in videos using rotational signal descriptor
Venkatrayappa, D., Montesinos, P., & Diep, D. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2077838 · Cited by 1
Mojette tomographic reconstruction for micro-CT: a bone and vessels quality evaluation
Sarkissian, H. D., Recur, B., Guédon, J., et al. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2043062 · Cited by 1
How to Exploit Marker Orientation for SIFT Image Matching
Park, G.-M., Hwang, H.-L., & Cho, H.-G. (2012) · IEEE International Conference on Computer and Information Technology (CIT) · doi:10.1109/cit.2012.147 · Cited by 1
“Famous ways of these are Lowe’s SIFT (Scale Invariant Feature Transform) algorithm [5] and Bay’s SURF (Speeded Up Robust Features) algorithm [6].”
MethodInfluentialCross-domain object recognition by output kernel learning
Guo, Z., & Wang, Z. J. (2012) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2012.6343471 · Cited by 1
I Remember Seeing This Video: Image Driven Search in Video Collections
Wang, Z., & Qureshi, F. Z. (2013) · doi:10.1109/crv.2013.31 · Cited by 1
Visual similarity analysis in loop closure through data dimensionality reduction via diffusion maps
Moreira, L. A. S., Justel, C. M., & Rosa, P. F. F. (2015) · ACM Symposium on Applied Computing · doi:10.1145/2695664.2695779 · Cited by 1
A Novel Layered DVC Structure for Wireless Surveillance System
Sun, M., Wang, Y., Yin, H., et al. (2014) · doi:10.1145/2632856.2632944 · Cited by 1
Illumination-free photometric metric for range image registration
Thomas, D., & Sugimoto, A. (2012) · doi:10.1109/wacv.2012.6163041 · Cited by 1
Component localization in face alignment
Qu, Y., Cheng, Y., Wu, D., et al. (2010) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2010.5641775 · Cited by 1
Pose Estimation of Leader Aircraft for Vision-based Formation Flight
Heo, J.-W., Kim, J., Han, D.-I., et al. (2013) · Journal of the Korean Society for Aeronautical & Space Sciences · doi:10.5139/jksas.2013.41.7.532 · Cited by 1
Investigation of a portable real time radiation mapper
Southgate, M. J., & Bowring, N. J. (2014) · doi:10.1109/csndsp.2014.6923991 · Cited by 1
Bio-inspired model with dual visual pathways for human action recognition
Cai, B., Xu, X., & Qing, C. (2014) · International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP) · doi:10.1109/csndsp.2014.6923838 · Cited by 1
“On the other hand, it relies on integral images [17] PI (x, y, t) showed as (2) to reduce the computation time of LME.”
BackgroundDecision fusion for urine particle classification in multispectral images
Hans, C., Merchant, F. A., & Shah, S. K. (2010) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/1924559.1924615 · Cited by 1
Note: An object detection method for active camera
Chen, Y., Zhang, R., Shang, L., et al. (2013) · Review of Scientific Instruments · doi:10.1063/1.4821875 · Cited by 1
Gap detection in endoscopic video sequences using graphs
Behrens, A., Takami, M., Gross, S., et al. (2011) · doi:10.1109/iembs.2011.6091636 · Cited by 1
Trajectory matching from unsynchronized videos
Hu, H., & Zhou, J. (2010) · 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/cvpr.2010.5539811 · Cited by 1
“SURFTrac [24] found the matches by searching the highest Normalized-Cross-Correlation (NCC) in Hessian domain over the local area.”
MethodInfluentialDevelopment of visual odometry algorithm for mobile robot navigation
Kicman, P. (2013) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2013.6669935 · Cited by 1
Real-time affine invariant patch matching using DCT descriptor and affine space quantization
Chen, X., Ye, F., Zhu, F., et al. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6116291 · Cited by 1
Real-Time LDCRF-Based Method for Inferring TV Viewer Interest
Naemura, M., Clippingdale, S., Takahashi, M., Okuda, M., Yamanouchi, Y., & Fujii, M. (2013) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii.2013.86 · Cited by 1
Localization using RGB-D cameras orthoimages
Mittet, M.-A., Landes, T., & Grussenmeyer, P. (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-5-425-2014 · Cited by 2
“Among the mostly used and well-known detectors, there are corners detectors like (Harris and Stephens, 1988) or GFTT from (Shi and Tomasi, 1994) and blob detectors like SIFT (Lowe, 2004), SURF (Bay et al., 2006) or ORB (Rublee et al.”
MethodCombining Features and Intensity for Wide-Baseline Non-Rigid Surface Registration
Braux-Zin, J., Dupont, R., & Bartoli, A. (2013) · British Machine Vision Conference (BMVC) · doi:10.5244/c.27.125 · Cited by 1
Stereoscopic visualization of monocular images in photo collections
Yousefi, S., Kondori, F. A., & Li, H. (2011) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2011.6096688 · Cited by 1
“Although different methods have been proposed to detect features in images [1], [2], [3], but for robustness and invariance to image transformations, SIFT feature detection can satisfy our expectation up to this level.”
MethodHarris feature vector descriptor
Wang, X., Su, J., & Cheng, H. D. (2010) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc.2010.5581008 · Cited by 1
“From then, a lot of similar work has been done, such as the Shape Context [6], GLOH [7] and SURF [8].”
MethodZhang, Q., Zaaijer, S., Wu, S., et al. (2014) · doi:10.1145/2578726.2582613 · Cited by 1
“The SURF [11] algorithm was introduced as a “speeded up” approach for detecting and describing salient points.”
MethodComputationally-efficient classification of HEp-2 cell patterns in IIF images
Gonzalez, L. F. P., Ruiz, D. D., & Pinho, M. S. (2015) · ACM Symposium on Applied Computing · doi:10.1145/2695664.2695730 · Cited by 1
“…[18], 2D Gabor Wavelets [15], Discrete Fourier Transform (DFT), Scale Invariant Feature Transform (SIFT) [17], Speeded-Up Robust Features (SURF) [4] and Histograms of Oriented Gradients (HoG) [6] When too many features are employed it is also expected that the demand of computational resources…”
BackgroundSAFE features for matching fingermarks by neighbourhoods of single minutiae
Mikaelyan, A., & Bigün, J. (2014) · International Symposium on Communications and Information Technologies · doi:10.1109/iscit.2014.7011896 · Cited by 1
Image-Based Accurate Object Retrieval Combined with Color Invariant
Cui, Y., & Xiao, B. (2010) · International Conference on Intelligent Computation Technology and Automation · doi:10.1109/icicta.2010.181 · Cited by 1
“[7] H. Bay, T. Tuytelaars, and L. V. Gool, SURF: Speeded up robust features, Computer Vision-ECCV 2006, Vol.3951, pp.404-417 [8] T. Gevers and A. W. M. Smeulders, Color-Based Object Recognition, Pattern Recognition, (32): 453-464, 1999.”
MethodTracking chessboard corners using projective transformation for augmented reality
Malek, S., Zenati-Henda, N., Benbelkacem, S., et al. (2011) · doi:10.1109/ccca.2011.6031196 · Cited by 1
“Bay et al. [16] present a novel scale-and rotation-invariant interest point detector and descriptor, named SURF (Speeded Up Robust Features).”
BackgroundA novel pair-wise image matching strategy with compact descriptors
Yang, S., Duan, L., Lin, J., et al. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738530 · Cited by 1
Local Image Feature Matching Improvements for Omnidirectional Camera Systems
Resch, B., Lang, J., & Lensch, H. P. A. (2014) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2014.168 · Cited by 1
Bandwidth Efficient Summed Area Table Generation for CUDA
Ha, S.-W., Choi, M.-H., Jun, T.-J., et al. (2012) · Journal of Korea Game Society · doi:10.7583/jkgs.2012.12.5.67 · Cited by 1
Ishii, A., Sakai, A., Mitsuhashi, M., et al. (2010) · International Symposium on Communications and Information Technologies · doi:10.1109/iscit.2010.5665126 · Cited by 1
“The effect will be lost even if SIFT[1], SURF[2], etc.”
BackgroundA geometric correction approach for chassis images with non-uniform speed by linear CCD camera
Cheng, Y., Liang, L., & Pu, J. (2012) · IEEE International Conference on Automation and Logistics (ICAL) · doi:10.1109/ical.2012.6308221 · Cited by 1
“The method we proposed uses SURF [15-17] and POC [18-21] to find corresponding point pairs between standard library images and linear CCD camera images.”
MethodSeveral methods of sensor fusion for vision tracking in mobile robots
Bahn, W., Lee, T.-J., Jang, B.-M., et al. (2012) · International Conference on Ubiquitous Robots and Ambient Intelligence · doi:10.1109/urai.2012.6463031 · Cited by 1
Augmented Reality Logo System Based on Android platform
Jung, E.-Y., Jeong, U.-K., Lim, S.-J., et al. (2011) · The KIPS Transactions PartB · doi:10.3745/kipstb.2011.18b.4.181 · Cited by 1
“영상에서 객체를 검색하는 다른 알고리즘은 SURF[9, 14] 가 존재한다.”
Multi-view oblique aerial image sparse matching
Zhang, Z., Dai, C., Mo, D., et al. (2014) · International Workshop on Earth Observation and Remote Sensing Applications · doi:10.1109/eorsa.2014.6927881 · Cited by 1
Background subtraction with a moving camera
Topçu, O., Kalem, A., & Esen, E. (2013) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2013.6531577 · Cited by 1
Objects from Animacy: Joint Discovery in Shape and Haar Feature Space
Nandi, S., Guha, P., & Venkatesh, K. S. (2008) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1109/icvgip.2008.78 · Cited by 1
Towards robust vision-based self-localization of vehicles in dense urban environments
Himstedt, M., Alempijevic, A., Zhao, L., et al. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386071 · Cited by 1
“The availability of highly distinctive and robust feature detectors as SIFT [7] and SURF [8] has also pushed the state-of-the-art in vision-based global localization.”
MethodA banner ads searching and counting system for sports videos
Chang, C. W., Chang, Y. Z., & Chen, S. W. (2011) · International Conference on Consumer Electronics, Communications and Networks (CECNet) · doi:10.1109/cecnet.2011.5768189 · Cited by 1
Computational architecture for image processing on a small unmanned ground vehicle
Ho, S., & Nguyen, H. M. (2010) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.863554 · Cited by 1
Li, L., Liu, Y., & Wang, K. (2014) · World Congress on Intelligent Control and Automation · doi:10.1109/wcica.2014.7052844 · Cited by 1
Illumination invariant 3D change detection
Diskin, Y., Asari, V. K., Hytla, P. C., et al. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2041038 · Cited by 1
Self embedding watermarking for digital images depending on edge energy
Al-Nuaimi, A., Zraqou, J. S., & Alkhadour, W. (2013) · doi:10.1109/icoia.2013.6650278 · Cited by 1
Yao, C.-W., Cheng, K.-S., & Lin, H. (2014) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2014.6918701 · Cited by 1
“For the feature-based image retrieval method, we take these candidate images for SURF [1] feature points matching and”
MethodInfluentialEfficient Image Stitching Using Fast Feature Descriptor Extraction and Matching
Rhee, S. B. (2013) · KIPS Transactions on Software and Data Engineering · doi:10.3745/ktsde.2013.2.1.065 · Cited by 1
Video error concealment using Speeded Up Robust Features and affine transformation
Ranjan, A., Midya, A., Chakraborty, J., et al. (2014) · IEEE Students’ Technology Symposium · doi:10.1109/techsym.2014.6807917 · 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.