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 7,901–8,000 of 14,752
Feature-matching based motion prediction for high efficiency video coding in cloud
Zhang, X., Wang, S., Wang, S., et al. (2015) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew.2015.7169778 · Cited by 4
Descriptor-based adaptive tracking-by-detection for visual sensor networks
Panti, B., Monteiro, P., Pereira, F. M. B., et al. (2015) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew.2015.7169807 · Cited by 4
“Considering that the goal is to develop a distributed visual tracker, real-valued local descriptors such as SIFT [4] and SURF [5] may seem an appropriate choice.”
BackgroundEnsemble classifier for joint object instance and category recognition on RGB-D data
Seib, V., Memmesheimer, R., & Paulus, D. W. R. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7350776 · Cited by 5
Feature Evaluation with High-Resolution Images
Cordes, K., Grundmann, L., & Östermann, J. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23192-1_31 · Cited by 5
“New approaches in feature detection [2,3,11,14,16,17] and description [1,2,3,7,11,15,16] usually use the reference test set and the evaluation protocols provided in [14,15].”
MethodInfluentialREGISTRATION OF LIDAR POINT CLOUDS USING IMAGE FEATURES
Majji, M., Junkins, J. L., & Katake, A. B. (2010) · Cited by 4
Tamošiūnas, M., Kadiķis, R., Saknīte, I., et al. (2016) · Journal of Biomedical Optics · doi:10.1117/1.jbo.21.4.045003 · Cited by 4
Sirius Implications for Future Warehouse-Scale Computers
Hauswald, J., Laurenzano, M. A., Zhang, Y., et al. (2016) · IEEE Micro · doi:10.1109/mm.2016.37 · Cited by 4
Weinmann, M. (2016) · Springer eBooks · doi:10.1007/978-3-319-29246-5_4 · Cited by 5
Neural network based 2D/3D fusion for robotic object recognition
Caron, L.-C., Song, Y., Filliat, D., et al. (2014) · Cited by 4
Nearest Position Estimation Using Omnidirectional Images and Global Appearance Descriptors
Berenguer, Y., Payá, L., Peidró, A., et al. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-27149-1_40 · Cited by 4
User Positioning Method Based on Image Similarity Comparison Using Single Camera
Song, J., Hur, S., Park, Y., et al. (2015) · 한국통신학회논문지 · doi:10.7840/kics.2015.40.8.1655 · Cited by 4
“또한 MF(Magnetic field) 와 같은 지구 의 고유자원을 이용한 위치추정 기술 [3] 도 이러한 문제를 극복하기 위해 카메라를 이용한 측 위 기법 [9,10,16] 들이 많이 연구되고 있으며 , 그 예로는 SLAM(Simultaneous Localization and Mapping) [6-8] , Marker 처리 연구 [13,16] 그러나 SURF 알고리즘 [11] 은 특징점 검출과 함께 특 Ⅲ .”
Khedher, M. I., & El‐Yacoubi, M. A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-25903-1_30 · Cited by 4
Feature Extraction and Learning Using Context Cue and Rényi Entropy Based Mutual Information
Pan, H., Olsen, S. I., & Zhu, Y. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27677-9_5 · Cited by 4
Texture Descriptors Based on Dijkstra's Algorithm for Medical Image Analysis
Ghidoni, S., Nanni, L., Brahnam, S., & Menegatti, E. (2014) · Studies in health technology and informatics · doi:10.3233/978-1-61499-474-9-74 · Cited by 5
“methods used in medical image analysis include the scale-invariant feature transform (SIFT) [1], speeded up robust feature (SURF) [2], histogram of oriented gradients (HOG) [3], gradient location and orientation histogram (GLOH) [4], region covariance matrix (RCM) [5], edgelet [6], gray level co-occurrence matrix (GLC…”
MethodDocTr: a unifying framework for tracking physical documents and organisational structures
Trullemans, S., Vercruysse, A., & Signer, B. (2016) · ACM SIGCHI Symposium on Engineering Interactive Computing Systems (EICS) · doi:10.1145/2933242.2933254 · Cited by 5
“Nowadays, more advanced solutions, such as the Scale Invariant Feature Transformation (SIFT) [21] algorithm proposed by Lowe or the Speed Up Robust Features (SURF) [1] algorithm, are used for document recognition.”
MethodOnline Multi-Modal Robust Non-Negative Dictionary Learning for Visual Tracking
Zhang, X., Guan, N., Tao, D., Qiu, X., & Luo, Z. (2015) · PLoS ONE · doi:10.1371/journal.pone.0124685 · Cited by 5
Building Internal Scene Representation in Cognitive Agents
Jaszuk, M., & Starzyk, J. A. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-19090-7_36 · Cited by 4
Rochman, D., & Luna, E. D. (2016) · Computer-Aided Design and Applications · doi:10.1080/16864360.2016.1199761 · Cited by 4
Improved data visualisation through multiple dissimilarity modelling
Rice, I. (2016) · Information Sciences · doi:10.1016/j.ins.2016.07.073 · Cited by 5
“Following the creation of a SURF bag-of-words [3] analysis we map the 156 feature vectors (500 features from the bag were used for each image) into a 2-dimensional visualisation space.”
MethodKeypoint trajectory coding on compact descriptor for video analysis
Tian, D., Sun, H., & Vetro, A. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532341 · Cited by 4
“Examples of such features include scale-invariant feature transform (SIFT) [1], speeded-up robust features (SURF) [2], histogram of oriented gradients (HoG) [3] [4], etc.”
BackgroundDigital Surveying in Cultural Heritage
Stylianidis, E., & Georgopoulos, A. (2016) · Advances in library and information science (ALIS) book series · doi:10.4018/978-1-5225-0680-5.ch006 · Cited by 4
Interactive Feature Growing for Accurate Object Detection in Megapixel Images
Schöning, J., Faion, P., & Heidemann, G. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46604-0_39 · Cited by 4
Exploiting software information for an efficient memory hierarchy
Komuravelli, R. (2014) · Cited by 4
SRI-SURF: A better SURF powered by scaled-RAM interpolator on FPGA
Jia, X., Guo, K., Wang, W., et al. (2016) · International Conference on Field Programmable Logic and Applications (FPL) · doi:10.1109/fpl.2016.7577363 · Cited by 4
BDSB: Binary descriptor with shared pixel blocks
Oszust, M. (2016) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2016.09.013 · Cited by 5
S-SIFT: A Shorter SIFT without Least Discriminability Visual Orientation
Zhong, S.-H., Liu, Y., & Wu, G. (2012) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2012.134 · Cited by 4
Quantitative review of local descriptors for visual search
Bianco, S., Schettini, R., Mazzini, D., et al. (2013) · IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin) · doi:10.1109/icce-berlin.2013.6697972 · Cited by 4
“This seems to contraddict the authors of FREAK and SURF who claim in [7] and [8] that their descriptors are faster than SIFT.”
MethodResultMulti-sensor optical remote sensing image registration based on Line-Point Invariant
Wang, X., & Xu, Q. (2016) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2016.7729610 · Cited by 4
“In this section, the proposed method is compared with some typical keypoint-based method such as SIFT [2], SURF [3] and SIFT-LIKE [4].”
MethodLicense plate detection using point of interest detectors and descriptors
Horák, K., Klečka, J., & Nováček, P. (2016) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2016.7760926 · Cited by 4
Underwater marking AUV using paraffin wax
Song, S., & Yu, S. (2016) · IEEE/OES Autonomous Underwater Vehicles · doi:10.1109/auv.2016.7778716 · Cited by 4
Effects of Water Currents in a Continuous Attractor Neural Network for SLAM Applications
Zaffari, G. B., dos Santos, M. M., Drews, P., et al. (2016) · doi:10.1109/lars-sbr.2016.62 · Cited by 4
Image-based nutrition composition analysis with a local orientation descriptor
Chen, J.-C., Lin, K. W., Ting, C.-W., et al. (2016) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2016.7844893 · Cited by 4
“Thus, rather than widely-used f eatures for object recognition, such as SIFT [20], SURF [37] and LBP [38], the features for food must be handled relative to variations in rotation, scale, deformation and texture.”
BackgroundThe Graph Matching Optimization methodology for thin object recognition in pick and place tasks
Willaume, P., Parrend, P., Gancel, E., et al. (2016) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2016.7850132 · Cited by 4
High resolution satellite image indexing and retrieval using SURF features and bag of visual words
Bouteldja, S., & Kourgli, A. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2268803 · Cited by 4
“The Speeded up robust features algorithm [4] is a scale and rotation-invariant interest point detector/descriptor which is computationally very fast.”
MethodA Framework for Profiling and Performance Monitoring of Heterogeneous Applications
Mistry, P., Ukidave, Y., Schaa, D., & Kaeli, D. R. (2013) · Cited by 4
An improved feature image matching algorithm based on Locality-Sensitive Hashing
Wu, T., & Miao, Z. (2016) · International Conference on Signal Processing · doi:10.1109/icsp.2016.7877927 · Cited by 4
“FREAK descriptor proposed by Alahi is a local invariant feature, which set the sampling keypoint and select the corresponding dot pair by simulating the imaging characteristics of the human retina, and it has more robustness and faster calculation process than SIFT and SURF.”
InfluentialA Method for Identifying Fatigue State of Driver's Face Based on Improved AAM Algorithm
Li, Z., Peng, J., Chen, L., et al. (2017) · International Journal of Software Science and Computational Intelligence · doi:10.4018/ijssci.2017040103 · Cited by 4
Human detection in video surveillance using texture features
Sabri, N., Ibrahim, Z., Saad, M. M., et al. (2016) · IEEE International Conference on Control System, Computing and Engineering · doi:10.1109/iccsce.2016.7893543 · Cited by 4
High-Speed Object Tracking with Its Application in Golf Playing
Lyu, C., Liu, Y., Jiang, X., et al. (2017) · International Journal of Social Robotics · doi:10.1007/s12369-017-0404-0 · Cited by 4
Hannat, M., Zrira, N., Raoui, Y., & Bouyakhf, E. H. (2016) · doi:10.1109/icmcs.2016.7905537 · Cited by 4
“In the appearance based image description approach, objects will be better described with visual feature points, by using methods such as SIFT or SURF [1] because of their invariance to the scale, the orientation and almost to the illumination.”
MethodNoise stable image registration using RANdom RESAmple Consensus
Nakazawa, A. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899742 · Cited by 4
“Since RANSAC uses sparse feature points in registration, it is robust for image noises when combined with the robust local feature descriptors such as SIFT [1] or SURF [2].”
MethodFeature Learning for Footnote-Based Document Image Classification
Abuelwafa, S., Mhiri, M., Hedjam, R., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59876-5_71 · Cited by 4
Real-Time Image Registration via Optical Flow Calculation
Popovic, V., Seyid, K., Çoğal, Ö., Akın, A., & Leblebici, Y. (2017) · Springer eBooks · doi:10.1007/978-3-319-59057-8_9 · Cited by 4
Informative image selection for crowdsourcing-based mobile location recognition
Wang, H., Zhao, D. Y., & Ma, H. (2017) · Multimedia Systems · doi:10.1007/s00530-017-0562-9 · Cited by 4
Multimodal Indexable Encryption for Mobile Cloud-Based Applications
Ferreira, B., Leitao, J. C. A., & Domingos, H. (2017) · IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) · doi:10.1109/dsn.2017.31 · Cited by 4
“Example: an object-recognition algorithm [3] finds multiple points of interest in an image.”
BackgroundMethodInfluentialThe Bag-of-Words Methods with Pareto-Fronts for Similar Image Retrieval
Gabryel, M. (2017) · Communications in computer and information science · doi:10.1007/978-3-319-67642-5_31 · Cited by 4
Food Category Recognition Using SURF and MSER Local Feature Representation
Razali, M. N., Manshor, N. B., Halin, A. B. A., Yaakob, R., & Mustapha, N. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70010-6_20 · Cited by 4
Wolf, M. (2017) · Springer eBooks · doi:10.1007/978-3-319-69523-5_5 · Cited by 4
Luo, A., An, F., Zhang, X., et al. (2017) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2017.2774813 · Cited by 4
Infrared and Visible Image Registration Based on Hypercolumns
Zhao, Z., Zhao, L., Qi, Y., et al. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-7305-2_45 · Cited by 4
Kim, J. S. (2017) · Library Hi Tech · doi:10.1108/lht-10-2016-0115 · Cited by 4
Optical and acoustic image evaluation method for backtracking of AUV
Song, S., Kim, B., & Yu, S. (2017) · OCEANS 2017 – Anchorage · Cited by 4
Semantic indoor scenes recognition based on visual saliency and part-based features
Tokuhara, K., Madokoro, H., & Sato, K. (2017) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2017.8279297 · Cited by 4
An Improved EMD‐Based Dissimilarity Metric for Unsupervised Linear Subspace Learning
Yu, X., Yu, Z., Pang, W., Li, M., & Wu, L. (2018) · Complexity · doi:10.1155/2018/8917393 · Cited by 4
“1 3 5 10 12 [16] 1 3 5 10 12 [2] Accumulate the 16 histograms Dimensionality for each block: 192”
MethodA CNN based framework for stable image feature selection
Han, C., Tao, X., Duan, Y., et al. (2017) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2017.8309192 · Cited by 4
Image retrieval based on saliency for urban image contents
Guissous, K., & Gouet-Brunet, V. (2017) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2017.8310131 · Cited by 5
“Such an orientation has been exploited in several approaches and applications, with the aim of describing the image content (e.g. the histogram of oriented gradients (HOG) [32], SIFT [33] and SURF [34] descriptors which are based on the gradient orientation).”
BackgroundInfluentialParallel video processing using embedded computers
Fu, B., Mohan, A., Li, Y., et al. (2017) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2017.8308597 · Cited by 4
Enabling autonomous navigation in a commercial off-the-shelf toy robot for robotic gaming
Piumatti, G., Pratticò, F. G., Paravati, G., et al. (2018) · International Conference on Consumer Electronics · doi:10.1109/icce.2018.8326232 · Cited by 4
Song, H. C., Lee, G. H., Shim, D.-S., et al. (2018) · International Journal of Control Automation and Systems · doi:10.1007/s12555-017-0253-5 · Cited by 4
“Varieties of features were introduced, including SIFT [7], Haar-like features [8], color features [9–11], HOG [12], speed-up robust features (SURF) [13], and local binary pattern (LBP) [14].”
MethodRobust and efficient method for matching features in omnidirectional images
Zhu, Q., Zhang, Z., & Zeng, D. (2018) · Optical Engineering · doi:10.1117/1.oe.57.4.043110 · Cited by 4
Image Specific Cross Cohort Normalization for Face Pair matching
Garain, J., Kumar, R. K., Kumar, D., et al. (2018) · Procedia Computer Science · doi:10.1016/j.procs.2018.05.021 · Cited by 4
SURF–MSER Based 3D Mapping Using RGB-D Camera on Automated Vehicle
Verma, N. K., Mustafa, A., Dhar, N. K., & Sarraf, V. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-1135-2_29 · Cited by 4
Reliable Loop Closure Detection Using 2-channel Convolutional Neural Networks for Visual SLAM
Ma, J., Qian, K., Ma, X., et al. (2018) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2018.8483560 · Cited by 4
“The visual features like SIFT[5], Surf[6] and ORB[7] are commonly used in these systems and have achieved great success in the past years.”
MethodEfficient Algorithms for the Summed Area Tables Primitive on GPUs
Chen, P., Wahib, M., Takizawa, S., et al. (2018) · Proceedings · doi:10.1109/cluster.2018.00064 · Cited by 4
Espinosa, N., Lenz, A., Groß, W., et al. (2018) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2018.8518770 · Cited by 4
“Therefore, for a precise calculation of stereo correspondence between nadir images, the Speeded-Up Robust Features (SURF) were used instead [4].”
MethodEnhance Neighbor Reversibility in Subspace Learning for Image Retrieval
Liu, R., Zhao, Y., & Wei, S. (2018) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2018.2879581 · Cited by 4
“Local features, such as SIFT [24] and SURF [25], are widely used in early works such as [11]–[13], [26], [27].”
MethodContent-Based Image Retrieval System Via Deep Learning Method
Tian, X., Zheng, Q., & Xing, J. (2018) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac.2018.8577661 · Cited by 4
The Utilization of Feature based Viola-Jones Method for Face Detection in Invariant Rotation
Soon, T. K., Samad, A., Khilwani, N., et al. (2018) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2018.091211 · Cited by 4
MuSE: Multimodal Searchable Encryption for Cloud Applications
Ferreira, B., Leitao, J. C. A., & Domingos, H. (2018) · IEEE Symposium on Reliable Distributed Systems (SRDS) · doi:10.1109/srds.2018.00029 · Cited by 8
Deep learned Inter-Channel Colored Texture Pattern: a new chromatic-texture descriptor
Jacob, I. J., Srinivasagan, K. G., Darney, P. E., & Jayapriya, K. (2019) · Pattern Analysis and Applications · doi:10.1007/s10044-019-00780-9 · Cited by 5
Quality Inspection System for Robotic Laser Welding of Double-Curved Geometries
Mikkelstrup, A. F., Thomsen, M. R., Stampe, K., Endelt, B., Boll, J., Kristiansen, E., & Kristiansen, M. (2019) · Procedia Manufacturing · doi:10.1016/j.promfg.2019.08.008 · Cited by 4
BALG: An alternative for fast and robust feature matching
Huang, Z., Wei, Z., & Zhang, G. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.02.017 · Cited by 4
A Stereo Visual Obstacle Detection Approach Using Fuzzy Logic and Neural Network in Agriculture
Yan, J. H., & Liu, Y. K. (2018) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2018.8665288 · Cited by 4
“Excellent feature extraction algorithms in recent years include FAST[20], SIFT[21], SURF[22], ORB[23], BRISK[24], and Harris[25].”
MethodWide or Narrow? A Visual Attention Inspired Model for View-Type Classification
Tong, S., Loh, Y. P., Liang, X., & Kumada, T. (2019) · IEEE Access · doi:10.1109/access.2019.2908856 · Cited by 4
“To solve this problem, the Speeded-up Robust Features (SURF) [22] is used to better capture the texture and edge features in a direction invariant manner.”
MethodA 135-mW 1.70TOPS Sparse Video Sequence Inference SoC for Action Classification
Chen, T., Lee, C., Liu, C., et al. (2019) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2019.2907406 · Cited by 4
“them with features stored in a database [6], [7] or perform classifications [8] on the features to recognize objects.”
BackgroundMeasurement of 3-DOF Planar Motion of the Object Based on Image Segmentation and Matching
Yang, S., Shi, X., Zhang, G., Lv, C., & Yang, X. (2019) · Nanomanufacturing and Metrology · doi:10.1007/s41871-019-00041-7 · Cited by 4
“Secondly, several groups of matching points are extracted from sequential images by SURF [20, 21] operators to calculate motion parameters.”
MethodImages Based Indoor Positioning Using AI and Crowdsourcing
Shahid, E., Arain, Q. A., Kumari, S., et al. (2019) · International Conference on Educational and Information Technology · doi:10.1145/3318396.3318415 · Cited by 4
“They must be distinguishing, stationary in the map, robust and repeatable against the noise [6].”
BackgroundAn Efficient and Geometric-Distortion-Free Binary Robust Local Feature
Guo, J.-M., Chang, L.-Y., & Lee, J.-D. (2019) · Sensors · doi:10.3390/s19102315 · Cited by 4
Feature Based Image Registration using Heuristic Nearest Neighbour Search
Vijay, S. T., & Pournami, P. N. (2018) · International Computer Science and Engineering Conference · doi:10.1109/icsec.2018.8712669 · Cited by 4
“Feature extraction is done using SIFT and SURF.”
MethodEXTRACTION OF VINEYARD MACROSTRUCTURE FROM SUB-OPTIMAL SEQUENCES OF AERIAL IMAGERY
Finn, A., Melville-Smith, A., & Brinkworth, R. S. A. (2019) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-iv-2-w5-103-2019 · Cited by 4
“Such features are typically extracted using algorithms like SIFT (scale invariant feature transformation) (Lowe, 1999) and SURF (speeded up robust features) (Bay et al., 2008).”
MethodA Fast Feature Extraction Process for Visual SLAM
Tang, P., Wang, Z., Qi, N., et al. (2019) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec.2019.8729330 · Cited by 4
“And the SIFT corner detection algorithm [4] proposed by David and the SURF corner detection algorithm [5] proposed by Bay have proved to be particularly successful in many applications.”
MethodBayesian place recognition based on bag of objects for intelligent vehicle localisation
Wang, X., Hu, Z., Tao, Q., Huang, G., & Mu, M. (2019) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2018.5431 · Cited by 4
Vision‐based, terrain‐aided navigation with decentralized fusion and finite set statistics
McCabe, J. S., & DeMars, K. J. (2019) · NAVIGATION Journal of the Institute of Navigation · doi:10.1002/navi.320 · Cited by 4
MFL Data Feature Extraction based on KPCA-BOMW Model
Jiang, L., Liu, J., Zhang, H., et al. (2019) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2019.8832515 · Cited by 4
“Literature [12] introduces SURF extraction algorithm in detail.”
MethodIterative machine learning based rotational alignment of brain 3D CT data
Chmelík, J., Jakubíček, R., Vičar, T., et al. (2019) · doi:10.1109/embc.2019.8857858 · Cited by 4
“Scale Invariant Feature Transform (SIFT) [8] uses the eigenvalues, but adds the steps to ensure scale-invariance and it has also faster version speeded up robust features (SURF) [9].”
Method3-D Point Cloud Reconstruction of Infrared Images Based on Improved Structure from Motion
Kong, Y., Leung, H., Zhang, B., Xing, S., & Chen, Y. (2018) · European Conference on Electrical Engineering and Computer Science (EECS) · doi:10.1109/eecs.2018.00063 · Cited by 6
Boyraz, Ö. F., Pala, M. A., Çimen, M. E., et al. (2019) · Academic Perspective Procedia · doi:10.33793/acperpro.02.03.58 · Cited by 4
“SURF, (Speeded-up Robust Features) Hessian matrisinin determinantını kullanarak özellik noktalarını tespit eder [12].”
MethodAn efficient edge-feature constraint visual SLAM
Liu, W., Mo, Y., & Jiao, J. (2019) · International Conference on Artificial Intelligence, Information Processing and Cloud Computing (AIIPCC) · doi:10.1145/3371425.3371455 · Cited by 4
Object Detection Using Point Feature Matching Based on SURF Algorithm
Dey, M., Saha, A., & De, A. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-3666-3_36 · Cited by 4
A Machine Learning Based Approach to Crack Detection in Asphalt Pavements
Balaji, A. J., Balaji, G. T., Dinesh, M. S., Nair, B. B., & Ram, D. S. H. (2018) · IEEE India Conference · doi:10.1109/indicon45594.2018.8987039 · Cited by 4
Vayssade, J.-A., Jones, G., Paoli, J.-N., et al. (2020) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0009169301030110 · Cited by 4
Aligning Points to Lines: Provable Approximations
Jubran, I., & Feldman, D. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2980836 · Cited by 6
“At the first frame of the video we detect a set P of ”interesting points” (features) using a SURF feature detector [38], and draw virtual objects on top of the image.”
MethodInvariant Feature Extraction for Component-based Facial Recognition
Hassan, A., & Viriri, S. (2020) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2020.0110386 · Cited by 4
Shostko, I., Teviashev, A., Kulia, Y., et al. (2020) · doi:10.32782/cmis/2608-59 · Cited by 4
MacLeod, L., KING, D. J., & Dempster, E. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-52249-0_38 · Cited by 4
“U-SURF is not invariant to image rotation and therefore performs better with images where the camera is unlikely to shift.”
MethodInfluentialTHAIWRITTENNET: THAI HANDWRITTEN SCRIPT RECOGNITION USING DEEP NEURAL NETWORKS
Mookdarsanit, P., & Mookdarsanit, L. (2020) · Azerbaijan Journal of High Performance Computing · doi:10.32010/26166127.2020.3.1.75.93 · Cited by 4
Real-time visualization of sword trajectories in fencing matches
Takahashi, M., Yokozawa, S., Mitsumine, H., Itsuki, T., Naoe, M., & Funaki, S. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09249-y · Cited by 4
GF-2 Panchromatic and Multispectral Remote Sensing Image Registration Algorithm
Wang, S., Wang, X., & Li, J. (2020) · IEEE Access · doi:10.1109/access.2020.3012555 · Cited by 4
Mc’Okeyo, P. O., Nex, F., Persello, C., et al. (2020) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-1-2020-309-2020 · Cited by 4
Experiments on Stereo Visual Odometry in Feature-Less Volcanic Fields
Otsu, K., Otsuki, M., & Kubota, T. (2014) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-07488-7_25 · Cited by 4
“The proposed hybrid detector is compared with common detectors including Harris [10], Shi-Tomasi [22], FAST [18, 19], DoG (Difference of Gaussians) [13], Fast Hessian [3], and STAR based on CenSurE [1].”
Method
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.