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 5,101–5,200 of 14,752
Gao, X., Tang, Z., Zhang, H., et al. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125261 · Cited by 10
Pyramid transformer-based triplet hashing for robust visual place recognition
Li, Z., & Xu, P. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104167 · Cited by 11
RegSeg: An End-to-End Network for Multimodal RGB-Thermal Registration and Semantic Segmentation
Lai, W., Zeng, F., Hu, X., He, S., Liu, Z., & Jiang, Y. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3501077 · Cited by 14
“Traditional image registration techniques, such as utilizing Harris corners [21], SIFT [22], SURF [23], ORB [24], involve key points extraction and point features matching, followed by the calculation of image transformation parameters based on the matched point coordinates to achieve image…”
Advances and Trends in Terrain Classification Methods for Off‐Road Perception
Arafin, T., Hosen, M. A., Najdovski, Z., Wei, L., Rokonuzzaman, M., & Johnstone, M. (2025) · Journal of Field Robotics · doi:10.1002/rob.22586 · Cited by 17
“Previously, Flitchkin et al. (Filitchkin and Byl 2012) achieved remarkable success by classifying terrain using BOVW generated from SURF features for LittleDog, attaining an impressive 100% classification accuracy.”
InfluentialRangelov, D., Waanders, S., Waanders, K., van Keulen, M., & Miltchev, R. I. (2025) · Lights · doi:10.3390/lights1010001 · Cited by 14
Graphcut-based interactive segmentation using colour and depth cues
He, H., McKinnon, D. H., Warren, M., et al. (2010) · QUT ePrints (Queensland University of Technology) · Cited by 10
Multi-camera epipolar plane image feature detection for robust view synthesis
Jorissen, L., Goorts, P., Rogmans, S., et al. (2015) · 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video · doi:10.1109/3dtv.2015.7169362 · Cited by 10
Towards Brain-based Sensor Fusion for Navigating Robots
Jacobson, A., & Milford, M. J. (2012) · QUT ePrints (Queensland University of Technology) · Cited by 11
Shah, S. A. A., Bennamoun, M., & Boussaïd, F. (2014) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2014.7008123 · Cited by 10
“These state-of-the-art techniques include renowned spin images [18], SISI/LD-SIFT [19], VD-LSD [20], EM descriptor [3], 3D-SURF [9] and 3D-Div descriptor [21].”
MethodInfluentialMulti-sensor indoor pedestrian navigation system with vision aiding
Keßler, C., Ascher, C., Flad, M., et al. (2012) · Gyroscopy and Navigation · doi:10.1134/s2075108712020058 · Cited by 10
“In our studies, image descriptor vectors based on Speeded Up Robust Features (SURF) [18], Scale Invariant Feature Transform (SIFT) [19] and Harris SIFT [20] have been investigated.”
MethodInfluentialEnabling low bitrate mobile visual recognition
Su, Y.-C., Chiu, T.-H., Chen, Y., Yeh, C.-Y., & Hsu, W. H. (2013) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2502081.2502110 · Cited by 9
Zhou, W., Li, H., Wang, M., Lu, Y., & Tian, Q. (2012) · International Conference on Internet Multimedia Computing and Service · doi:10.1145/2382336.2382338 · Cited by 10
Bringing Videos to Social Media
Kopf, S., Wilk, S., & Effelsberg, W. (2012) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2012.86 · Cited by 10
Feature-based background registration in wide-area motion imagery
Wu, Y., Chen, G., Blasch, E., et al. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.918804 · Cited by 10
“In this work, we use the SURF feature detector and descriptor [3] for WAMI registration do to its computation efficiency.”
MethodInfluentialAn efficient framework on large-scale video genre classification
Zhang, N., & Guan, L. (2010) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2010.5662069 · Cited by 10
Object classification based on visual and extended features for video surveillance application
Islam, M. K., Jahan, F., Min, J.-H., et al. (2011) · Cited by 12
Alberti, M., Folkesson, J., & Jensfelt, P. (2014) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 10
Multimodal joint visual attention model for natural human-robot interaction in domestic environments
Domhof, J., Chandarr, A., Rudinac, M., et al. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353703 · Cited by 10
Context Forest for Object Class Detection
Modolo, D., Vezhnevets, A. S., & Ferrari, V. (2015) · British Machine Vision Conference (BMVC) · doi:10.5244/c.29.188 · Cited by 10
“For the appearance and location properties, we extract SURF [7], LAB and SIFT [34] features on a dense grid at multiple scales.”
MethodMultiple Feature Extraction Techniques in Image Stitching
Taherim, S., & Archana, B. (2015) · International Journal of Computer Applications · doi:10.5120/ijca2015905747 · Cited by 10
Human activity recognition based on pose points selection
Xu, K., Jiang, X., & Sun, T. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351339 · Cited by 10
“HOG/HOF[1] compute histograms of gradient and histograms of flow, 3D-SIFT[4] extended 2D-sift descriptor from static images to video sequences and SURF Xinghao Jiang is the corresponding author. descriptor[3] provide comparable or even better results than SIFT while it can be calculated in a relatively efficient way.”
BackgroundMethodResultInfluentialThe impact of tattoo segmentation on the performance of tattoo matching
Yi, H., Yu, P., Xu, X., et al. (2015) · IEEE International WIE Conference on Electrical and Computer Engineering · doi:10.1109/wiecon-ece.2015.7443995 · Cited by 10
“To perform this study, Scale-Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF) [15-16] are used to match tattoo images and four different settings are designed: both probe and gallery sets with segmentation, both probe and gallery sets without segmentation, and probe set with segmentation and ga…”
MethodA hybrid approach for brain image registration with local constraints
Hsu, W. (2016) · Integrated Computer-Aided Engineering · doi:10.3233/ica-160533 · Cited by 10
“In the current study, we apply the SURF descriptor [8], using a Haar wavelet as a feature descriptor that features scale and rotational invariance, enhanced reliability, partitioning ability, robustness, and faster calculation speed.”
Langenhan, C., & Petzold, F. (2011) · Cumulative Index of Computer Aided Architectural Design · Cited by 10
Reliable features matching for humanoid robots
Pretto, A., Menegatti, E., & Pagello, E. (2007) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/ichr.2007.4813922 · Cited by 10
Intelligent arm manipulation system in life science labs using H20 mobile robot and Kinect sensor
Ali, M. M., Liu, H., Stoll, N., et al. (2016) · IEEE International Conference on Intelligent Systems · doi:10.1109/is.2016.7737449 · Cited by 10
Wang, H., Zhao, D. Y., Ma, H., et al. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48896-7_64 · Cited by 10
A REAL-TIME REGISTRATION METHOD OF AUGMENTED REALITY BASED ON SURF AND OPTICAL FLOW
Li, H., Ming, Q., & Wu, Y. (2012) · Cited by 10
Robust Registration of Dynamic Facial Sequences
Sarıyanidi, E., Güneş, H., & Cavallaro, A. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2639448 · Cited by 10
Wang, H., Yoon, S. M., Han, D. K., & Ko, H. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.05.010 · Cited by 11
A vegetable category recognition system: a comparison study for caffe and Chainer DNN frameworks
Ikeda, M., Oda, T., & Barolli, L. (2017) · Soft Computing · doi:10.1007/s00500-017-2959-y · Cited by 10
“In Sakai et al. (2015), authors proposed an object detection system based on SIFT (Lowe 2004) and SURF (Bay et al. 2006) methods.”
MethodVision based counting of texture-less objects using shape and color features
Verma, N. K., Sharma, T., Rajurkar, S. D., et al. (2016) · doi:10.1109/iciinfs.2016.8262946 · Cited by 10
“Third method tackled this limitation by using SURF features which make use of scale space theory [36].”
MethodDeep 3D Human Pose Estimation Under Partial Body Presence
Vosoughi, S., & Amer, M. A. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451031 · Cited by 11
Heading Direction Estimation Using Deep Learning with Automatic Large-scale Data Acquisition
Berriel, R. F., Tabelini, L., Cardoso, V. B., Guidolini, R., Badue, C. S., Souza, A. F. D., & Oliveira-Santos, T. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489154 · Cited by 10
“, SIFT [9], SURF [10], HOG [11], among others) and classical machine learning methods.”
MethodAutomatic wide field registration and mosaicking of OCTA images using vascularity information
Díaz, M., de Moura, J., Novo, J., et al. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.09.205 · Cited by 10
TemplateFree: product detection on retail store shelves
Sun, H., Zhang, J., & Akashi, T. (2019) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.23051 · Cited by 10
“…non-learning matching by manual features methods, for example, histogram of oriented gradients (HOG) [17] and speeded up robust features (SURF) [18], have a great performance once, they are gradually outperformed by deep learning methods with the improvement of image recognition and object…”
MethodInitial RTAB-Map Navigation Analysis for Service Robot
Murwantara, I. M., Sutrisno, S., & Vinsens, M. (2019) · International Conference on New Media Studies (CONMEDIA) · doi:10.1109/conmedia46929.2019.8981853 · Cited by 11
Local descriptor for retinal fundus image registration
Ramli, R., Idris, M. Y. I., Hasikin, K. B., et al. (2020) · IET Computer Vision · doi:10.1049/iet-cvi.2019.0623 · Cited by 10
“To find the best feature point for the proposed FiSP, we employed a total of five feature point extraction methods that previously used in the existing feature-based RIR techniques [15, 17, 19–22, 26, 27], namely Harris corner [42], SIFT [34], SURF [35, 43], Ghassabi's [22] and D-Saddle [15].”
MethodClassification of Retina Diseases from OCT using Genetic Programming
Abdulrahman, H., & Khatib, M. M. (2020) · International Journal of Computer Applications · doi:10.5120/ijca2020919973 · Cited by 10
Detecting Visual Objects by Edge Crawling
Grycuk, R., Wojciechowski, A., Wei, W., & Siwocha, A. (2020) · Journal of Artificial Intelligence and Soft Computing Research · doi:10.2478/jaiscr-2020-0015 · Cited by 13
“SURF (Speeded-Up Robust Features) is local feature detector and descriptor [5] and a newer version of SIFT (Scale-Invariant Feature Transform) [28] enhanced in terms of speed.”
Efficient Multisource Remote Sensing Image Matching Using Dominant Orientation of Gradient
Liang, D., Ding, J., & Zhang, Y. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3052472 · Cited by 10
“Recently,matchingmethodsbased onlocalinvariantfeatures,suchasscaleinvariantfeaturetrans-form(SIFT)[10],speededuprobustfeature[11]andKAZE[12], havebeenwidelyutilizedinthefiledofRSimagematch-ing[13]–[15].”
FSD-BRIEF: A Distorted BRIEF Descriptor for Fisheye Image Based on Spherical Perspective Model
Zhang, Y., Song, J., Ding, Y., Yuan, Y., & Wei, H. (2021) · Sensors · doi:10.3390/s21051839 · Cited by 10
ImageDataset2Vec: An image dataset embedding for algorithm selection
Dias, L. V., de Miranda, P. B. C., do Nascimento, A. C. A., Cordeiro, F. R., Mello, R. F., & Prudêncio, R. B. C. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115053 · Cited by 11
Towards Diversified IoT Image Recognition Services in Mobile Edge Computing
Ding, C., Zhou, A., Ma, X., Zhang, N., Hsu, C., & Wang, S. (2021) · IEEE Transactions on Cloud Computing · doi:10.1109/tcc.2021.3109385 · Cited by 15
“That is, when capturing the the data, the IoT device first uses feature extraction algorithms [24], [25] to pre-process it or sends the raw image data to the MEC platform to pre-process it [18].”
MethodSaliency Guided Discriminative Learning for Insect Pest Recognition
Luo, Q., Li, W., Tian, L., & Zhu, L. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533421 · Cited by 10
Sheng, D., Chai, Y., Li, X., Feng, C., Lin, J., Silva, C. T., & Rizzo, J. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636640 · Cited by 10
XAI Feature Detector for Ultrasound Feature Matching
Wang, Z., Zhu, H., Ma, Y., et al. (2021) · Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc46164.2021.9629944 · Cited by 10
“Speeded Up Robust Feature (SURF) [3] is an optimized version of SIFT.”
MethodRelative Pose Estimation for Light Field Cameras Based on LF-Point-LF-Point Correspondence Model
Zhang, S., Jin, D., Dai, Y., & Yang, F. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3144891 · Cited by 11
SAR Offset Tracking Based on Feature Points
Peng, L., Wang, H., Ng, A. H., et al. (2022) · Frontiers in Earth Science · doi:10.3389/feart.2021.724965 · Cited by 10
Infrared and Visible Image Fusion with Deep Neural Network in Enhanced Flight Vision System
Gao, X., Shi, Y., Zhu, Q., et al. (2022) · Remote Sensing · doi:10.3390/rs14122789 · Cited by 10
Automated Detection of Threat Materials in X-Ray Baggage Inspection Systems (XBISs)
Kayalvizhi, R., Malarvizhi, S., Choudhury, S. D., et al. (2022) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2022.3182771 · Cited by 10
RWN: Robust Watermarking Network for Image Cropping Localization
Ying, Q., Hu, X., Zhang, X., Qian, Z., Li, S., & Zhang, X. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897870 · Cited by 12
Loop Closure Detection via Locality Preserving Matching With Global Consensus
Ma, J., Zhang, K., & Jiang, J. (2022) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2022.105926 · Cited by 11
Dumitrescu, F., Ceachi, B., Truică, C., et al. (2022) · Aerospace · doi:10.3390/aerospace9090520 · Cited by 10
Location Learning for AVs: LiDAR and Image Landmarks Fusion Localization with Graph Neural Networks
Kang, Q., She, R., Wang, S., Tay, W. P., Navarro, D. N., & Hartmannsgruber, A. (2022) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc55140.2022.9922179 · Cited by 13
3D EDGE DETECTION AND COMPARISON USING FOUR-CHANNEL IMAGES
Betsas, T., & Georgopoulos, A. (2022) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlviii-2-w2-2022-9-2022 · Cited by 10
Digital image forgery: taxonomy, techniques, and tools–a comprehensive study
Chaitra, B., & Reddy, P. V. B. (2022) · International Journal of Systems Assurance Engineering and Management · doi:10.1007/s13198-022-01829-5 · Cited by 16
“The detection accuracy obtained from various techniques and methods are BusterNet 93.02%, SPT 96.99%, PCA 97.79%, Enhanced SURF 98%, SVD 98.8%, PCA-DCT 98.97%, DCT 98.06%, Improved DCT 98.58%, Efficient DCT 98.59%, DyWT 98.74% and CNN with 99.03%.”
MethodInfluentialExploiting Frame Similarity for Efficient Inference on Edge Devices
Ying, Z., Zhao, S., Zhang, H., Mishra, C. S., Bhuyan, S., Kandemir, M., Sivasubramaniam, A., & Das, C. R. (2022) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs54860.2022.00107 · Cited by 24
“, a vector generated from input image, such as SURF [47], HoG [48], Down-sampling [16], etc.”
MethodTurbidity-adaptive underwater image enhancement method using image fusion
Han, B., Wang, H., Luo, X., Liang, C., Yang, X., Liu, S., & Lin, Y. (2022) · Frontiers of Mechanical Engineering · doi:10.1007/s11465-021-0669-8 · Cited by 10
Kuang, Z., Wei, W., Yan, Y., Li, J., Lu, G., Peng, Y., Li, J., & Shang, W. (2022) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2022.3217147 · Cited by 11
A Real-Time Registration Algorithm of UAV Aerial Images Based on Feature Matching
Liu, Z., Xu, G., Xiao, J., Yang, J., Wang, Z., & Cheng, S. (2023) · Journal of Imaging · doi:10.3390/jimaging9030067 · Cited by 10
Rong, 苏. S., Jiayu, 刘. L., Qiao, X., et al. (2023) · Laser & Optoelectronics Progress · doi:10.3788/lop223228 · Cited by 10
Xu, J., Yao, C., Ma, H., et al. (2023) · Remote Sensing · doi:10.3390/rs15102658 · Cited by 10
Dong, H., Chen, X., Dusmanu, M., Larsson, V., Pollefeys, M., & Stachniss, C. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161381 · Cited by 15
“Local feature descriptors [25], [6], [34] are used to represent characteristics of image patches and are designed”
Enhanced Change Detection Performance Based on Deep Despeckling of Synthetic Aperture Radar Images
Ihmeida, M., & Shahzad, M. S. (2023) · IEEE Access · doi:10.1109/access.2023.3307208 · Cited by 10
“Most image registration algorithms rely on robust extraction of key points either using shallow extraction methods such as Scale-Invariant Feature Transform (SIFT) [16], SpeededUp Robust Features (SURF) [17] or deep methods including convolutional neural networks (CNNs) [18], Siamese networks [19], and spatial transfo…”
MethodIncremental Learning for Simultaneous Augmentation of Feature and Class
Hou, C., Gu, S., Xu, C., & Qian, Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3307670 · Cited by 10
SkyNet: Multi-Drone Cooperation for Real-Time Person Identification and Localization
Peng, J., Li, Q., Tan, Y., Zhao, D., Yuan, Z., Chen, J., Wang, H., & Jiang, Y. M. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10228978 · Cited by 15
“Many studies of multi-view object alignment use carefully selected feature markers to extract object features and match them into another view, such as SIFT [33], SURF [34], and HOG [35].”
BackgroundCt-LVI: A Framework Toward Continuous-Time Laser-Visual-Inertial Odometry and Mapping
Wang, Z., Zhang, L., Zhao, S., & Zhou, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3335989 · Cited by 14
“After that, we extract SURF corners and calculate the corresponding feature descriptors [53] of 2 S a and 2 S b .”
MethodImage retrieval using unsupervised prompt learning and regional attention
Zhang, B.-J., Liu, G., & Li, Z. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122913 · Cited by 12
Homography Guided Temporal Fusion for Road Line and Marking Segmentation
Wang, S., Nguyen, C. V., Liu, J., Zhang, K., Luo, W., Zhang, Y., Muthu, S., Maken, F. A., & Li, H. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00105 · Cited by 16
“SIFT [33], SURF [5, 4], ORB [43], LPPM [34], GMS [7], and BEBLID [47] are commonly used for feature extraction, and RANSAC [14], MAGAC [2], and LRLS [17] are applied for outlier rejection.”
MethodMobile-UI-Repair: a deep learning based UI smell detection technique for mobile user interface
Ali, A., Xia, Y., Navid, Q., Khan, Z. A., Khan, J. A., Aldakheel, E. A., & Khafaga, D. S. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2028 · Cited by 15
“Speeded-up robust features (SURF) ( Bay, Tuytelaars & Van Gool, 2006 ): represents an enhancement of the SIFT technique.”
MethodLightweight Violence Detection Model Based on 2D CNN with Bi-Directional Motion Attention
Wang, J., Zhao, D., Li, H., et al. (2024) · Applied Sciences · doi:10.3390/app14114895 · Cited by 10
Good Edgels to Track: Beating the Aperture Problem with Epipolar Geometry
Piccini, T., Persson, M., Nordberg, K., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16181-5_50 · Cited by 10
A Bayesian Approach to Multi-view 4D Modeling
Huang, C.-H. P., Cagniart, C., Boyer, E., & Ilić, S. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0832-y · Cited by 10
“Motion cues have to be balanced with priors encoding the deformation range.”
BackgroundAge and Gender Estimation Using Multiple-Image Features
Ku, C.-L., Chiou, C.-H., Gao, Z., Tsai, Y.-J., & Fuh, C. (2013) · Lecture notes in computer science · doi:10.1007/978-3-319-02961-0_55 · Cited by 10
Object Recognition for Manipulation Tasks in Real Domestic Settings: A Comparative Study
Martínez, L., Loncomilla, P., & Ruíz-del-Solar, J. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-18615-3_17 · Cited by 10
“The SURF method [8] is similar to SIFT, but rectangular functions are used instead of Gaussians for computing the scale-space.”
MethodA feature clustering algorithm for scale-space analysis of image structures
Lakemond, R., McKinnon, D. H., Fookes, C., et al. (2008) · QUT ePrints (Queensland University of Technology) · Cited by 10
Feature coverage for better homography estimation: An application to image stitching
Bostancı, E., Kanwal, N., & Clark, A. F. (2012) · Open Access at Essex (University of Essex) · Cited by 10
BRISK based target localization for fixed-wing UAV's vision-based autonomous landing
Pan, C., Hu, T., & Shen, L. (2015) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2015.7279706 · Cited by 10
Achievements and Challenges in Recognizing and Reconstructing Civil Infrastructure
Brilakis, I., Dai, F., & Radopoulou, S. C. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34091-8_7 · Cited by 10
Hybrid ensemble of classifiers for logo and trademark symbols recognition
Cyganek, B. (2014) · Soft Computing · doi:10.1007/s00500-014-1323-8 · Cited by 10
2D Face Alignment and Pose Estimation Based on 3D Facial Models
Chen, S.-C., Wu, C., Lin, S.-Y., & Hung, Y. (2012) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2012.60 · Cited by 10
“In this paper, we propose a 3D face alignment algorithm based on Active Shape Model, and use SpeededUp Robust Features (SURF) descriptors [10] to build local texture models.”
MethodRobustly registering range images using local distribution of albedo
Thomas, D., & Sugimoto, A. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2010.11.016 · Cited by 10
“[19] proposed a descriptor called speeded-up robust features (SURF) that makes use of an integral image to speed up computation and comparison.”
Iterative Random Visual Word Selection
Urruty, T., Gbèhounou, S., Le, H. T., et al. (2014) · doi:10.1145/2578726.2578758 · Cited by 10
Podroužek, J., Bucher, C. G., & Deodatis, G. (2013) · Structural Safety · doi:10.1016/j.strusafe.2013.10.005 · Cited by 10
Autonomous exploration using rapid perception of low-resolution image information
Murali, V. N., & Birchfield, S. T. (2011) · Autonomous Robots · doi:10.1007/s10514-011-9262-z · Cited by 10
“Scale space processing emphasizes extracting information from multiple scales and is the basis of popular feature detection algorithms such as SIFT (Lowe 2004) and SURF (Bay et al. 2008).”
MethodInformation driven sensor placement for robust active object recognition based on multiple views
Stampfer, D., Lutz, M., & Schlegel, C. (2012) · IEEE International Conference on Technologies for Practical Robot Applications · doi:10.1109/tepra.2012.6215667 · Cited by 10
Robust outliers detection in image point matching
Beckouche, S., Leprince, S., Sabater, N., et al. (2011) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2011.6130241 · Cited by 10
Multi-model classification method in heterogeneous image databases
Kachouri, R., Djemal, K., & Maaref, H. (2010) · Pattern Recognition · doi:10.1016/j.patcog.2010.07.001 · Cited by 11
COMPARISON OF TWO STRUCTURE AND MOTION STRATEGIES
Roncella, R., Re, C., & Forlani, G. (2012) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsarchives-xxxviii-5-w16-343-2011 · Cited by 16
“SURF (Speeded Up Robust Features) (Bay et al., 2008) has invariance properties similar to SIFT, but requires less computing time.”
Deformable Template Tracking in 1ms
Tan, D. J., Holzer, S., Navab, N., & Ilić, S. (2014) · British Machine Vision Conference (BMVC) · doi:10.5244/c.28.27 · Cited by 10
“To detect and match features, most of the literature [20, 21, 22, 24, 25] use keypoint descriptors such as SIFT [17], SURF [2] or randomized trees [15].”
MethodKey-Region Detection for Document Images -- Application to Administrative Document Retrieval
Gao, H., Rusiñol, M., Karatzas, D., et al. (2013) · Proceedings of the International Conference on Document Analysis and Recognition · doi:10.1109/icdar.2013.53 · Cited by 10
Fuzzy based Multiple Dictionary Bag of Words for Image Classification
Sujatha, K. S., Keerthana, P., Priya, S., et al. (2012) · Procedia Engineering · doi:10.1016/j.proeng.2012.06.264 · Cited by 10
Discovering inherent event taxonomies from social media collections
Dao, M.-S., Boato, G., & DeNatale, F. G. B. (2012) · International Conference on Multimedia Retrieval · doi:10.1145/2324796.2324852 · Cited by 10
“From the algorithmic viewpoint, Gist descriptors are achieved through dominant colors analysis [8], saliency derives from the analysis of dominant colors within the salient area (computed as in [1]), while perspective-invariant correspondences are calculated based on SURF [4].”
MethodInfluentialDynamic camera calibration method for free-viewpoint experience in sport videos
Sankoh, H., Sugano, M., & Naito, S. (2012) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2393347.2396399 · Cited by 10
“Next, the corresponding feature points between frame t and frame t +1 are extracted based on SURF (Speeded Up Robust Feature) descriptors [12] as shown in Figure 3, since the descriptors are known to be robust for image translations like zooming in/out and rotations that accompany usual…”
MethodComparison between feature-based and phase correlation methods for ROV vision-based speed estimation
Ferreira, F., Orsenigo, F., Veruggio, G., et al. (2010) · IFAC Proceedings Volumes · doi:10.3182/20100906-3-it-2019.00078 · Cited by 10
A new image registration method robust to noise
Chen, G., & Coulombe, S. (2012) · Multidimensional Systems and Signal Processing · doi:10.1007/s11045-012-0202-7 · Cited by 10
“Our method performs very well in noisy environments, whereas existing methods such as [8] and [9] will fail if the noise level is too high.”
MethodFigueroa, N., Dong, H., & Saddik, A. E. (2015) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2629673 · Cited by 9
“In the past years, RGB images have been used to extract visual appearance information from the scenes with the well-known Scale Invariant Feature Transform (SIFT) [Lowe 2004] and Speed Up Robust Features (SURF) [Bay et al. 2008] algorithms.”
MethodCloud computing based mobile augmented reality interactive system
Chiu, P.-H., Tseng, P., & Feng, K. (2014) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc.2014.6953084 · Cited by 11
“There are many approaches to detect feature points such as FAST corner detection [2], SIFT feature detection [3], SURF feature detection [4] and so on.”
MethodAn inexpensive monocular vision system for tracking humans in industrial environments
Mosberger, R., & Andreasson, H. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631419 · Cited by 12
“Several state-of-the-art image feature descriptors including SURF [18], BRIEF [19] and the recent BRISK [20] descriptor have been evaluated in combination with the popular Support Vector Machine [21] and Random Forest [22] classifiers, where the latter have shown clearly and consistently superior…”
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.