SURF: Speeded Up Robust Features
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index; none of the 18 sources its claims cite is checked for support yet.
Overview
CoChat Summary
TL;DR
SURF is a scale- and rotation-invariant interest point detector and descriptor that uses integral images, Hessian-based detection, and Haar-wavelet responses to be faster than prior methods while matching or exceeding their repeatability and distinctiveness. It reports strong results on standard benchmarks and a museum object recognition task.
Key findings
- The Fast-Hessian detector is more than 3× faster than DoG and 5× faster than Hessian-Laplace, with comparable or better repeatability on Graffiti, Leuven, Boat, and Wall; on the first Graffiti image (800×640), computation times were 120 ms for Fast-Hessian, 400 ms for DoG, 650 ms for Hessian-Laplace, and 1800 ms for Harris-Laplace.
- SURF’s 64-dimensional descriptor outperformed GLOH, SIFT, and PCA-SIFT in most comparisons, sometimes by more than 10% improvement in recall for the same precision; SURF-128 was slightly better but slower to match.
- Joint detector-descriptor computation times on the first Graffiti image were 255 ms for U-SURF, 354 ms for SURF, 391 ms for SURF-128, and 1036 ms for SIFT.
- In museum object recognition, recognition rates were 85.7% for SURF-128, 83.8% for U-SURF, 82.6% for SURF, 78.3% for GLOH, 78.1% for SIFT, and 72.3% for PCA-SIFT.
Methods
- Design: a scale- and rotation-invariant detector/descriptor. The detector uses the determinant of the Hessian with box-filter approximations evaluated via integral images; the descriptor uses Haar-wavelet responses in a 4×4 subregion grid, producing a 64-dimensional vector, with an upright U-SURF variant and an extended SURF-128 variant.
- Data: standard evaluation sequences from Mikolajczyk (including Graffiti, Wall, Boat, Leuven, Bikes, Trees, and Ubc; Bark excluded from descriptor evaluations) and a real-life museum object recognition database of 216 images of 22 objects, with 116 test images at 320×240.
- Analysis: detector repeatability scores, descriptor recall-(1-precision) graphs under similarity-threshold and nearest-neighbour-ratio matching, recognition rates, and computation timings on a standard Linux PC (Pentium IV, 3 GHz).
Limitations
- The paper has no explicit limitations section. It states that space limitations prevent showing results on all sequences, and it assumes skew, anisotropic scaling, and perspective effects are second-order effects covered only by overall descriptor robustness.
- Evident from the text: the method is scale- and rotation-invariant but not affine-invariant; Fig. 4 notes the interest points are not affine invariant, and the descriptor does not use colour.
- Evident from the text: the object recognition experiment uses small 320×240 test images and matching without additional geometric constraints, which the authors say would reduce false positives but were omitted for comparison purposes.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
0 Valid · 2 Not valid · 12 Not checked · 30 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The number of interest points found is on average very similar for all detectors.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 4 × 4 sub-region division solution provided the best results.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“SURF outperformed the other descriptors for almost all the comparisons.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The SURF descriptor outperforms the other descriptors in a systematic and significant way, with sometimes more than 10% improvement in recall for the same level of precision.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in the results section, the performance is comparable to the one using the discretised and cropped Gaussians.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
8 more claims
Create a free account to see all 44 claims and every source verdict.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This transition marked a new era, where we moved beyond the classic approaches and task-specific feature engineering of earlier days [Lowe 2004; Bay et al. 2006; Rosten and Drummond 2006] towards models that could be trained once over large amounts of data, and then adapted for a broad variety of tasks, such as image recognition, object detection, and image segmentation [Krizhevsky et al. 2012; Sz”
From On the Opportunities and Risks of Foundation Models (2021) · cites this paper as Bay et al. 2006
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901
A performance evaluation of local descriptors
Mikolajczyk, K., & Schmid, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.188 · Cited by 6,723 · cited 14×
“This PCA-SIFT yields a 36-dimensional descriptor which is fast for matching, but proved to be less distinctive than SIFT in a second comparative study by Mikolajczyk et al. [8] and slower feature computation reduces the effect of fast matching.”
BackgroundMethodResultInfluentialMarr, D., & Hildreth, E. (1980) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1980.0020 · Cited by 6,510
PCA-SIFT: a more distinctive representation for local image descriptors
Ke, Y., & Sukthankar, R. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.183 · Cited by 3,932
Robust wide-baseline stereo from maximally stable extremal regions
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.02.006 · Cited by 3,686
Scalable Recognition with a Vocabulary Tree
Nister, D., & Stewenius, H. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.264 · Cited by 3,579
Scale & Affine Invariant Interest Point Detectors
Mikolajczyk, K., & Schmid, C. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000027790.02288.f2 · Cited by 3,436
Cited by
Items 8,201–8,300 of 14,752
DOOR HANDLE IDENTIFICATION: A THREE-STAGE APPROACH
Jauregi, E., Martínez‐Otzeta, J. M., Sierra, B., et al. (2007) · IFAC Proceedings Volumes · doi:10.3182/20070903-3-fr-2921.00088 · Cited by 4
Multi-view stereo as an inverse inference problem
Strecha, C. (2007) · Cited by 8
Generic Content Creation for 3D Displays
Zilly, F., Muller, M. G., & Kauff, P. P. (2012) · Springer eBooks · doi:10.1007/978-1-4419-9964-1_2 · Cited by 4
A fast image matching research based on MIC-SURF algorithm
Huiqing, Z., Jingli, Z., & Ruyong, D. (2015) · doi:10.1109/ccdc.2015.7161751 · Cited by 4
“3 THE PRINCIPLE OF SURF ALGORITHM Speed Up Robust Features (SURF) [8] was proposed by Bay as early as in 2006, it is the improved of SIFT [9] algorithm and a kind of scale and rotation invariant detector, it's faster than SIFT, accurate matching, and has good robustness which is invariant to illumination, scaling.”
MethodEstimation of gazing points in environment using eye tracker and omnidirectional camera
Chiba, S., Miyazaki, T., Sugaya, Y., et al. (2015) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-tw.2015.7217003 · Cited by 4
Pengenalan Gambar Menggunakan Sebagian Data Gambar
Tania, K. D. (2013) · Cited by 4
An Algebraic Technique For The Blind Separation Of Ds-Cdma Signals
Lathauwer, L. D., & Castaing, J. (2004) · INFM-OAR (INFN Catania) · doi:10.5281/zenodo.38588 · Cited by 4
Generic Object Recognition in Urban Image Databases
Baró, X., Escalera, S., Radeva, P. I., et al. (2009) · Frontiers in artificial intelligence and applications · doi:10.3233/978-1-60750-061-2-27 · Cited by 4
Storage Size Reduction for the Integral Image
Belt, H. J. W., Belt, H. J. W., & Bruijn, F. D. (2007) · Cited by 4
Fast Computation of Dense and Reliable Depth Maps from Stereo Images
Tornow, M., Grasshoff, M., Nguyen, N.-T., et al. (2012) · InTech eBooks · doi:10.5772/34976 · Cited by 4
“The normalization improves the robustness against image capture variances of both cameras.”
BackgroundAdaptive Sample Consensus for Efficient Random Optimization
Fan, L., & Pylvänäinen, T. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-10520-3_23 · Cited by 4
ASN: Image Keypoint Detection from Adaptive Shape Neighborhood
Ouellet, J.-N., & Hébert, P. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88682-2_35 · Cited by 4
GPU-Accelerated Robotic Intra-operative Laparoscopic 3D Reconstruction
Moll, M., Tang, H.-W., & Gool, L. V. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-13711-2_9 · Cited by 4
“The near real-time speed is achieved by using SURF features[2] and the efficient selection of candidate matches in the feature matching stage.”
BackgroundMethodSelf-citationPassivity-based visual motion observer: From theory to distributed algorithms
Hatanaka, T., & Fujita, M. (2010) · doi:10.1109/cacsd.2010.5612640 · Cited by 4
Content‐based image retrieval over IEEE 802.11b noisy wireless networks
Chatzistavros, E., Chatzichristofis, S. A., Zagoris, K., et al. (2014) · International Journal of Communication Systems · doi:10.1002/dac.2724 · Cited by 4
“Visual words were generated by using speeded-up robust features [44] and k -means classifier.”
MethodEfficient object classification using multiple views in manufacturing environments
Doerr, K., Samarabandu, J. K., & Wang, X. (2014) · International Conference on Information and Automation for Sustainability (ICIAfS) · doi:10.1109/iciafs.2014.7069597 · Cited by 4
NF-Features – No-Feature-Features for Representing Non-textured Regions
Dragon, R., Shoaib, M. A., Rosenhahn, B., et al. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15552-9_10 · Cited by 4
Multispectral Stereo Image Correspondence
Pistarelli, M., Sappa, A. D., & Toledo, R. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40246-3_27 · Cited by 4
A Coordinate Transformation System Based on the Human Feature Information
Chang, S.-M., Tsai, J. C., Shih, T. K., et al. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-17832-0_48 · Cited by 4
A Comparative Study of Grayscale Conversion Techniques Applied to Descriptor Based Tracking
Macêdo, S., Melo, G., & Kelner, J. (2015) · doi:10.1109/svr.2015.8 · Cited by 4
Chen, D.-Y., & Chiu, Y.-M. (2013) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2013.04.005 · Cited by 4
Smart Teddy Bear a vision-based story teller
Pham, D.-M., Dam-Nguyen, T.-N., Nguyen-Vo, T., & Tran, M. (2013) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais.2013.6720564 · Cited by 4
“There are a lot of methods to determine those keypoints such as SIFT [9], SURF [19], etc.”
MethodImprovements in visual odometry algorithm for planetary exploration rovers
Dinesh, S., Rao, K. K., Unnikrishnan, M., Brinda, V., Lalithambika, V. R., & Dhekane, M. V. (2013) · International Conference on Emerging Trends in Communication, Control, Signal Processing and Computing Applications (C2SPCA) · doi:10.1109/c2spca.2013.6749359 · Cited by 4
Sparse keypoint models for 6D object pose estimation
Sadran, E., Wurm, K. M., & Burschka, D. (2013) · European Conference on Mobile Robots · doi:10.1109/ecmr.2013.6698859 · Cited by 4
“Visual keypoints are defined as locations on the object surface that can be identified by a local visual feature descriptor, for example, SIFT [11], SURF [3], or ORB [13].”
BackgroundMulti-Scale Descriptor for Robust and Fast Camera Motion Estimation
Sung, C.-H., & Chung, M. J. (2013) · IEEE Signal Processing Letters · doi:10.1109/lsp.2013.2264672 · Cited by 4
Frame-patch matching based robust video watermarking using KAZE feature
Thanh, T. M., Hiệp, P. T., Tam, T. M., et al. (2013) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2013.6607581 · Cited by 4
Freeze detection in 2D navigation video sequences overlaid with real satellite images
Yammine, G., Khairat, A., Simmet, F., et al. (2012) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2012.6343413 · Cited by 4
Enhancing static biometric signature verification using Speeded-Up Robust Features
Guest, R., & Miguel‐Hurtado, O. (2012) · IEEE International Carnahan Conference on Security Technology (ICCST) · doi:10.1109/ccst.2012.6393561 · Cited by 4
Kabary, I. A., Giangreco, I., Schuldt, H., et al. (2013) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2013.84 · Cited by 4
“QUEST uses the JOpenSURF [17] library which we enhanced by adding multi-threading capabilities.”
MethodInfluentialLü, W., Xiang, Z., & Liu, J. (2015) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1400139 · Cited by 4
Fast quantization and matching of histogram-based image features
Reznik, Y. A., Chandrasekhar, V., Takacs, G., et al. (2010) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.862362 · Cited by 4
6DOF pose estimation using 2D-3D sensor fusion
Shin, Y.-D., Park, J., & Baeg, M.-H. (2012) · 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2012.6386413 · Cited by 4
“These approaches include feature- or descriptor-based methods using edge, intersections of straight lines, scale-invariant feature transform (SIFT), or Speeded Up Robust Feature (SURF)[1-8].”
MethodMirror Match: Reliable Feature Point Matching without Geometric Constraints
Arnfred, J. T., WINKLER, S. S., & Susstrunk, S. E. (2013) · IAPR Asian Conference on Pattern Recognition (ACPR) · doi:10.1109/acpr.2013.135 · Cited by 4
Indirect activity recognition using a target-mounted camera
Li, L., Zhang, H., Jia, W., Mao, Z., You, Y., & Sun, M. (2011) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2011.6099965 · Cited by 3
“We select feature points for motion tracking using the Speeded Up Robust Features (SURF) method [9].”
Method[Paper] Free-viewpoint Video Synthesis for Sport Scenes Captured with a Single Moving Camera
Sankoh, H., Naito, S., Harada, M., et al. (2015) · ITE Transactions on Media Technology and Applications · doi:10.3169/mta.3.48 · Cited by 4
Stereo Vision-based Visual Tracking using 3D Feature Clustering for Robust Vehicle Tracking
Lim, Y.-C., & Kang, M.-S. (2014) · International Conference on Informatics in Control, Automation and Robotics (ICINCO) · doi:10.5220/0005147807880793 · Cited by 4
Determinant of homography-matrix-based multiple-object recognition
Bangalore, N. M., Kiran, M., & Suryaprakash, A. R. K. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2003767 · Cited by 4
“The proposed method of object recognition is compared with the classical method [2], which classifies the object based on total number of matches during one to one matching.”
BackgroundMethodInfluentialA human-assisted approach for a mobile robot to learn 3D object models using active vision
Zwinderman, M., Rybski, P. E., & Kootstra, G. (2010) · doi:10.1109/roman.2010.5598696 · Cited by 4
“In our approach, we use SURF feature points as SURF is faster and more robust than SIFT [19], we also store the 3D position of these points as computed by a stereovision system.”
MethodContext-Aware Augmented Reality Authoring Tool in Digital Ecosystem
Park, J.-H., Kang, C., Oh, S., et al. (2010) · International Symposium on Ubiquitous Virtual Reality · doi:10.1109/isuvr.2010.14 · Cited by 4
“SIFT [8] and SURF [9] are remarkable recognition and tracking methods based on natural features of target objects.”
BackgroundGenerating colored point cloud under the calibration between TOF and RGB cameras
Li, X., Guo, W. P., Li, M., Chen, C., & Sun, L. (2013) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2013.6720347 · Cited by 4
“Iterative Closed Points(ICP)([14]) algorithm is very popular in registration of two point cloud, but it is very sensitive to initial relative pose transformation, in this paper , initial transformation is computed from matched 3D scale invariant features([15]).”
MethodStable Vision System for Indoor Moving Robot Using Encoder Information
Shim, E. S., Hwang, W., Anjum, M. L., et al. (2009) · IFAC Proceedings Volumes · doi:10.3182/20090909-4-jp-2010.00011 · Cited by 4
Robust visual lock-on and simultaneous localization for an unmanned aerial vehicle
Min, J., Jeong, Y., & Kweon, I. S. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5650725 · Cited by 4
A Novel CBCD Approach Using MPEG-7 Motion Activity Descriptors
Roopalakshmi, R., & Reddy, G. R. M. (2011) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2011.36 · Cited by 4
“SIFT [8] and SURF [9], are some of the popular local descriptors, which use interest points for feature extraction [10].”
BackgroundAnalysis of distributed smart camera calibration accuracy using minimal data transmission
Stone, W., & Şekercioğlu, Y. A. (2010) · IEEE International Conference on Communication Systems (ICCS) · doi:10.1109/iccs.2010.5686597 · Cited by 4
“[3] found the best tradeoff in the 4× 4 grid.”
BackgroundMethodInfluentialAn Automatic Robust Image Registration Algorithm for Aerial Mapping
Javadi, M. S., Kadim, Z., Woon, H. H., Johari, K. M., & Samudin, N. (2015) · International Journal of Image and Graphics · doi:10.1142/s0219467815400021 · Cited by 4
“Since SURF is insensitive to rotation, scale change and illumination between images, it is suitable Bay et al. , 22 is a computationally improved version of the SIFT.”
BackgroundAutomatic Registration of SAR Images with the Integrated Complementary Invariant Feature
Wang, X., Deng, K., & Yang, H. (2014) · Journal of Multimedia · doi:10.4304/jmm.9.1.67-73 · Cited by 4
Xu, W., Zhao, Q., Wang, Y., et al. (2013) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e97.d.119 · Cited by 4
“Scale-invariant feature transform (SIFT) method [8] and its variants, e.g., the SURF features [9], were applied for object tracking [10], [11] and recognition [12] by many researchers.”
MethodDong, Z., Ye, F., Li, D., et al. (2012) · Circuit World · doi:10.1108/03056121211250678 · Cited by 4
Robust Image Matching with Line Context
Guan, W., & You, S. O. (2013) · British Machine Vision Conference (BMVC) · doi:10.5244/c.27.34 · Cited by 4
Feasibility Study for Pose Estimation of Small UAS in Known 3D Environment Using Geometric Hashing
Armenakis, C., & Li-Chee-Ming, J. (2014) · Photogrammetric Engineering & Remote Sensing · doi:10.14358/pers.80.12.1117 · Cited by 4
Dual-sensor fusion for indoor user localisation
Redzic, M., Brennan, C., & O'Connor, N. E. (2011) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2072298.2071948 · Cited by 4
Lin, F.-E., Kuo, Y.-H., & Hsu, W. H. (2011) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2072298.2071928 · Cited by 4
Fast Image Stitching Based on Improved SURF Algorithm Using Meaningful Features
Ahn, H., & Rhee, S.-B. (2012) · The KIPS Transactions PartB · doi:10.3745/kipstb.2012.19b.2.093 · Cited by 4
Integrating bilingual search results for automatic junk image filtering
Yang, C., Peng, J., Feng, X., et al. (2012) · Multimedia Tools and Applications · doi:10.1007/s11042-012-1051-y · Cited by 4
Space-time Histograms And Their Application To Person Re-identification In TV Shows
Auguste, R., Martinet, J., & Tirilly, P. (2015) · ACM International Conference on Multimedia Retrieval (ICMR) · doi:10.1145/2671188.2749332 · Cited by 4
“In a similar way, Hamdoun et al.[14] use interest points obtained by a method inspired by SURF[2].”
MethodShibata, F., Ikeda, S., Kurata, T., et al. (2010) · IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2010.5643613 · Cited by 4
Permutable descriptors for orientation-invariant image matching
Takacs, G., Chandrasekhar, V., Chen, H., et al. (2010) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.863993 · Cited by 4
A Semantic Analysis Approach to Thin-Shell Ceramic Fragment Classification
Aryafar, K., & Jeppson, P. L. (2013) · International Journal of Heritage in the Digital Era · doi:10.1260/2047-4970.2.2.291 · Cited by 4
“SURF descriptors are faster than SIFT and generate comparable results [1].”
MethodResultInfluentialMultiscale Point Correspondence Using Feature Distribution and Frequency Domain Alignment
Zhao, Z., Feng, X., Teng, S., Li, Y., & Zhang, C. (2012) · Mathematical Problems in Engineering · doi:10.1155/2012/382369 · Cited by 4
Wan, T. R., Bloch, B., Danish, S. F., et al. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2007153 · Cited by 4
Corner detectors: Evaluation of information content
Zukal, M., & Číka, P. (2012) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2012.6256400 · Cited by 4
Converting image to a gateway to an information portal for digital signage
Choi, Y.-H., Kim, D., Rho, S., & Hwang, E. (2012) · Multimedia Tools and Applications · doi:10.1007/s11042-012-1315-6 · Cited by 4
Feature histogram equalization for feature contrast enhancement
Wang, C., & Ma, K. (2014) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2014.09.009 · Cited by 4
Shape matching based on graph alignment using hidden Markov models
Qian, X., & Yoon, B.-J. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5495288 · Cited by 4
Real-time pose invariant logo and pattern detection
Sidla, O., Kottmann, M., & Benešová, W. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.872977 · Cited by 4
Matching based Highlight Removal
Xu, Y., Wang, F., & Zhao, Y. (2010) · doi:10.1109/icmult.2010.5631281 · Cited by 4
“It approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster [9].”
BackgroundProbabilistic Handling of Merged Detections in Multi Target Tracking
Stephan, T., & Grinberg, M. (2012) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2012.56 · Cited by 4
“color histograms, histograms of gradients, SIFT [10] or SURF [2] etc.”
Single camera-based object detection and tracking for mobile robots
Anderson, J. K., Iftekharuddin, K. M., Threlkeld, E., et al. (2008) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.795123 · Cited by 4
“In this work, we investigate more robust features such ‘planes’ that takes advantage of SIFT/SURF type features.”
On the interoperability of local descriptors compression
Chen, J., Duan, L., Lin, J., et al. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6637905 · Cited by 4
“The compact descriptors have been widely studied in previous literatures, for instance, reducing the dimension of local descriptors like PCA-SIFT [10], GLOH [11], SURF [1] and MSR descriptors [6], as well as compressing the image-level signatures like miniBoF [7] and Ag-gregated Local Features [8].”
MethodTangruamsub, S., Takada, K., & Hasegawa, O. (2011) · Signal Processing Image Communication · doi:10.1016/j.image.2011.07.007 · Cited by 4
ART based clustering of bag-of-features for image classification
Roy, K., & G, S. V. R. (2012) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2012.6470016 · Cited by 4
“Some of the widely used keypoint based detectors and descriptors are Scale-invariant feature transform (SIFT) by Lowe [23], Speeded-up feature transform (SURF) by suggested by Herbert Bay [24], Bag-of- features[25].”
MethodGradient Ordinal Signature and Fixed-Point Embedding for Efficient Near-Duplicate Video Detection
Liu, H., Lu, H., Wen, Z., & Xue, X. (2011) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2011.2168294 · Cited by 4
A robust vehicle model construction and identification system using local feature alignment
Wang, H.-Y., & Shih, H.-C. (2013) · IEEE International Symposium on Consumer Electronics (ISCE) · doi:10.1109/isce.2013.6570250 · Cited by 4
Adaptive Iterative Closest SURF for visual scan matching, application to Visual odometry
Nemra, A., Slimani, S., Bouhamidi, M., Bouchloukh, A., & Bazoula, A. (2013) · International Conference on Systems and Control (ICSC) · doi:10.1109/icosc.2013.6750968 · Cited by 4
License Plate Detection and Segmentation Using Cluster Run Length Smoothing Algorithm
Abdullah, S. N. H. S., Sudin, M. N., Prabuwono, A. S., & Mantoro, T. (2012) · Journal of Information Technology Research · doi:10.4018/jitr.2012070103 · Cited by 4
A two-tier map representation for compact-stereo-vision-based SLAM
Herath, D. C., Kodagoda, S., & Dissanayake, G. (2011) · Robotica · doi:10.1017/s0263574711000543 · Cited by 4
“3) taken inside our lab normally generates features in excess of 90 using the SURF algorithm.”
MethodInfluentialA low-cost and robust optical flow CMOS camera for velocity estimation
Sun, K., Yu, Y., Zhou, W., et al. (2013) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2013.6739624 · Cited by 4
“Some other methods applies features extracted by SIFT [4] or SURF [5] instead of using intensities of the pixels.”
MethodA hybrid method for indoor user localisation
Redzic, M., Conaire, C. Ó., Brennan, C., et al. (2009) · Arrow@dit (Dublin Institute of Technology) · Cited by 4
Sharma, K., & Goyal, A. K. (2013) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt.2013.6726632 · Cited by 4
A multi-agent mobile robot system with environment perception and HMI capabilities
Tornow, M., Al-Hamadi, A. K., & Borrmann, V. (2013) · IEEE International Conference on Signal and Image Processing Applications (ICSIPA) · doi:10.1109/icsipa.2013.6708013 · Cited by 4
Vaiapury, K., Aksay, A., Lin, X., et al. (2011) · SAE International Journal of Aerospace · doi:10.4271/2011-01-2565 · Cited by 4
Feature correspondence in a non-overlapping camera network
Xiang, Z. J., Chen, Q., & Liu, Y. (2013) · Multimedia Tools and Applications · doi:10.1007/s11042-013-1600-z · Cited by 4
A concept for a novel surgical navigation system
Rapp, P., Sawodny, O., Tarín, C., et al. (2014) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2014.6974537 · Cited by 4
“Methods like KAZE, SIFT and SURF, although they are too CPUintensive, can be used as a reference for the faster methods in the fusion step.”
MethodSpatio-temporal action localization for human action recognition in large dataset
Megrhi, S., Jmal, M., Beghdadi, A., et al. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2082880 · Cited by 4
Vision-based navigation with pose recovery under visual occlusion and kidnapping
Kim, J., & Kweon, I.-S. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509944 · Cited by 4
“The integral images have been used for face detection and feature detection to reduce the computation time, as introduced in [22][15].”
MethodA hybrid approach for image/video content representation and identification
Chaisorn, L., & Fu, Z. (2012) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2012.6360863 · Cited by 4
Geodesic Mapping for Dynamic Surface Alignment
Tung, T., & Matsuyama, T. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.179 · Cited by 5
Compressing repeated content within large-scale remote sensing images
Hua, W., Wang, R., Zeng, X., et al. (2012) · The Visual Computer · doi:10.1007/s00371-012-0710-3 · Cited by 4
“The color blocks are for illustration, in our method, we only use the grayscale values of each block in SURF.”
MethodScale invariant control points based stereo matching for dynamic programming
Li, K., Wang, S., Yuan, M., et al. (2009) · doi:10.1109/icemi.2009.5274212 · Cited by 4
“In order to increase computational efficiency, the improved method approximate the Hessian matrixes even further [12](Fig.”
MethodUsing affine features for an efficient binary feature descriptor
Desai, A., Lee, D.-J., & Wilson, C. (2014) · doi:10.1109/ssiai.2014.6806026 · Cited by 4
An automated registration of RS images based on SURF and piecewise linear transformation
Guo, H. N., Cheng, C., & Yang, Y. (2010) · doi:10.1109/esiat.2010.5568981 · Cited by 4
Visual content layer for scalable object recognition in urban image databases
Baró, X., Escalera, S., Radeva, P. I., et al. (2009) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2009.5202828 · Cited by 4
Scale-invariant optical flow in tracking using a pan-tilt-zoom camera
Dhou, S., & Motai, Y. (2014) · Robotica · doi:10.1017/s0263574714002665 · Cited by 4
π-SIFT: A photometric and Scale Invariant Feature Transform
Park, J., Park, K.-W., Baeg, S., & Baeg, M.-H. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4761181 · Cited by 6
“Considering these issues, we focus on describing the robust features without additional dimensions as 978-1-4244-2175-6/08/$25.00 ©2008 IEEE building scale-spaces using photometric quasi-invariant features.”
BackgroundInfluentialOne-to-Many Registration of Landsat Imagery
Barazzetti, L., Scaioni, M., & Gianinetto, M. (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-w2-37-2013 · Cited by 4
“The developed methodology starts extracts corresponding points along with a feature-based matching (FBM) technique based on the SURF operator (Bay et al., 2008).”
MethodImage trimming via saliency region detection and iterative feature matching
Huang, J., & Li, Z.-N. (2009) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2009.5202746 · Cited by 4
“In our work, we adopt SURF (Speeded Up Robust Feature) [5], another emerging local feature descriptor for features selection.”
MethodRatshidaho, T. T., Tapamo, J., Claassens, J., et al. (2014) · The South African Journal of Industrial Engineering · doi:10.7166/25-1-736 · Cited by 4
Speeded-up SURF: Design of an efficient multiscale feature detector
Schweiger, F., Schroth, G., Huitl, R., et al. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738717 · Cited by 4
“In the family of scale-invariant feature detectors, multiple general-purpose GPU (GPGPU) based implementations of SIFT [6] and SURF [1] have been proposed [7, 8, 9, 10, 11].”
Occupant Monitoring System for Traffic Control Based on Visual Categorization
Yebes, J. J., Alcantarilla, P. F., & Bergasa, L. M. (2011) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2011.5940420 · Cited by 4
“• Fast Hessian detector and Modified Upright Speed Up Robust Features (M-USURF) descriptors [5], [17], [23].”
BackgroundMethodGeometric and Error Analysis for 3D Map-Matching
Olesk, A., & Wang, J. (2009) · Cited by 5
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.