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 4,801–4,900 of 14,752
He, Q., Wang, C., Zeng, S., Liang, Z., Duan, H., Yang, J., Pan, F., He, Y., Huang, W., & Guan, T. M. (2023) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22952 · Cited by 13
“We evaluated the performances of our proposed method for image registration, with SURF and HistReg as base-line methods.”
MethodTransCNNLoc: End-to-end pixel-level learning for 2D-to-3D pose estimation in dynamic indoor scenes
Tang, S., Li, Y., Wan, J., Li, Y., Zhou, B., Guo, R., Wang, W., & Feng, Y. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.12.006 · Cited by 14
Copy–move forgery detection in digital image forensics: A survey
Farhan, M. H., Shaker, K., & Al-Janabi, S. T. F. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18399-2 · Cited by 15
“In 2006, the SURF detector algorithm was developed by Bay et al. [49].”
Improved ORB Algorithm Through Feature Point Optimization and Gaussian Pyramid
Borman, R. I., Harjoko, A., & Wahyono, W. (2024) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2024.0150228 · Cited by 11
AbHE: All Attention-Based Homography Estimation
Huo, M., Zhang, Z., Ren, X., Yang, X., & Ye, C. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3374320 · Cited by 20
“In the feature point extraction step, classical feature extractors such as oriented FAST and rotated BRIEF (ORB) [8], speeded up robust features (SURF) [9], and scale-invariant feature transform (SIFT) [10] are widely used.”
MethodUnsupervised Homography Estimation With Pixel-Level SVDD
Zhou, Z., Zhu, Q. X., Feng, M., Wang, Y., Luo, J., Miao, Z., Chen, L., & Mo, Y. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3394899 · Cited by 12
“Classic feature extraction methods include SIFT [7], SURF [8] and ORB [9].”
MethodAdvancing Crowd Object Detection: A Review of YOLO, CNN and ViTs Hybrid Approach*
Ali, M. A. M., Aly, T., Raslan, A. T., Gheith, M. H., & Amin, E. A. (2024) · Journal of Intelligent Learning Systems and Applications · doi:10.4236/jilsa.2024.163011 · Cited by 24
Diving deep into human action recognition in aerial videos: A survey
Kapoor, S., Sharma, A., & Verma, A. (2024) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2024.104298 · Cited by 16
Jafarzadeh, P., Zelioli, L., Virjonen, P., Farahnakian, F., Nevalainen, P., & Heikkonen, J. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20587-z · Cited by 15
“While traditional approaches need hand-crafted features like Harris Corner Detection [16], Scale-Invariant Feature Transform (SIFT) [17], or Speeded-Up Robust Features (SURF) [18].”
LiftFeat: 3D Geometry-Aware Local Feature Matching
Liu, Y., Lai, W., Zhao, Z., Xiong, Y., Zhu, J., Cheng, J., & Xu, Y. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127853 · Cited by 36
“Early methods such as SIFT [12] and SURF [13] propose well-designed handcrafted descriptors.”
Ceiling vision-based active SLAM framework for dynamic and wide-open environments
An, S.-Y., Lee, L.-K., & Oh, S. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9453-0 · Cited by 12
“All vision-basedSLAMapproaches have their ownparticular way of defining visual features such as a fast corner (Rosten et al. 2010), SIFT (Lowe 2004), SURF (Bay et al. 2006).”
BackgroundPredicting types of clothing using SURF and LDP based on Bag of Features
Surakarin, W., & Chongstitvatana, P. (2015) · International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) · doi:10.1109/ecticon.2015.7207101 · Cited by 15
“The visual vocabulary is constructed to represent the dictionary by clustering local feature from training dataset SURF is used to locate structures and detect the interest points.”
BackgroundInfluentialA Hybrid Feature Extractor using Fast Hessian Detector and SIFT
Güzel, M. S. (2015) · Technologies · doi:10.3390/technologies3020103 · Cited by 11
A study on interest point guided visual saliency
Zhang, X., Wang, S., Ma, S., et al. (2015) · Picture Coding Symposium · doi:10.1109/pcs.2015.7170096 · Cited by 11
“For SURF descriptor, the Determinant of Hessian (DoH) operator is used for extracting the feature points.”
MethodInfluentialVisual information retrieval in endoscopic video archives
Carlos, J. R., Lux, M., Giró-i-Nieto, X., Muñoz, P., & Anagnostopoulos, N. (2015) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2015.7153618 · Cited by 13
NimbRo@Home: Winning Team of the RoboCup@Home Competition 2012
Stückler, J., Badami, I., Droeschel, D., Gräve, K., Holz, D., McElhone, M., Nieuwenhuisen, M., Schreiber, M., Schwarz, M., & Behnke, S. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39250-4_10 · Cited by 11
“Our robots recognize objects by matching SURF features [1] in RGB images to an object model database [10].”
MethodToolbox for ear biometric recognition evaluation
Emeršič, Ž., & Peer, P. (2015) · IEEE EUROCON - International Conference on Computer as a Tool (EUROCON) · doi:10.1109/eurocon.2015.7313758 · Cited by 11
“Histogram of Oriented Gradients (HOG) [14], Speeded Up Robust Features (SURF) [15], Maximally Stable Extremal Regions (MSER) [16] and SIFT Scale-Invariant Feature Transform (SIFT) [17], and three different databases.”
BackgroundMethodInfluentialA cloud infrastructure for target detection and tracking using audio and video fusion
Liu, K., Liu, B., Blasch, E., et al. (2015) · IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2015.7301299 · Cited by 11
Towards consistent reconstructions of indoor spaces based on 6D RGB-D odometry and KinectFusion
Dong, H., Figueroa, N., & Saddik, A. E. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942798 · Cited by 12
Real-Time Hand Pose Recognition Based on a Neural Network Using Microsoft Kinect
Sorce, S., Gentile, V., & Gentile, A. (2013) · International Conference on Broadband and Wireless Computing, Communication and Applications (BWCCA) · doi:10.1109/bwcca.2013.60 · Cited by 11
Keypoint-based image processing for landmine detection in GPR data
Sakaguchi, R. T., Morton, K. D., Collins, L. M., et al. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.918361 · Cited by 11
“An approximation of this method was used for the popular image matching algorithm - Speed-ed up Robust Features (SURF).(8) This algorithm works by calculating the Hessian matrix at each pixel location after a 2-dimensional Gaussian smoothing of the image.”
MethodIMShare: instantly sharing your mobile landmark images by search-based reconstruction
Dai, L., Yue, H., Sun, X., & Wu, F. (2012) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2393347.2393428 · Cited by 10
Redondo-Cabrera, C., López-Sastre, R. J., Acevedo-Rodríguez, J., et al. (2014) · Image and Vision Computing · doi:10.1016/j.imavis.2014.08.007 · Cited by 11
“The most recent improvements have been achieved by incorporating multiple local features such as SIFT [11], SURF [12] or color SIFT [6], into the BoW pipeline [13, 6].”
Automatic building exterior mapping using multilayer feature graphs
Lu, Y., Song, D., Xu, Y., Perera, A. G. A., & Oh, S. (2013) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2013.6653887 · Cited by 14
“[7], [14], [15] and line features [8]–[10] are often employed as landmarks.”
Low rank driven robust facial landmark regression
Deng, J., Sun, Y., Liu, Q., & Lu, H. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.09.052 · Cited by 11
Feature Optimization for Long-Range Visual Homing in Changing Environments
Zhu, Q., Liu, X., & Cai, C. (2014) · Sensors · doi:10.3390/s140203342 · Cited by 11
Robust tracking with interest points: A sparse representation approach
Babu, R. V., Parate, P., & Äniruddha Acharya, K. (2014) · Image and Vision Computing · doi:10.1016/j.imavis.2014.10.006 · Cited by 11
Application of the One-factor CIR Interest Rate Model to Catastrophe Bond Pricing under Uncertainty
Nowak, P., & Romaniuk, M. (2014) · Journal of Automation Mobile Robotics & Intelligent Systems · doi:10.14313/jamris_3-2014/23 · Cited by 14
Dynamic face recognition system in recognizing facial expressions for service robotics
Luo, R. C., Lin, P. H., Wu, Y. C., & Huang, C. (2012) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2012.6266054 · Cited by 12
A feature-based object tracking approach for realtime image processing on mobile devices
Fan, L., Riihimaki, M., & Kunttu, I. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5651003 · Cited by 11
“Related Work: A common theme in many successful tracking methods is the extraction of a set of local features from images to be matched [1, 2, 3, 4, 5, 6].”
BackgroundOnline learning 3D context for robust visual tracking
Zhong, B., Shen, Y., Chen, Y., Xie, W., Cui, Z., Zhang, H., Chen, D., Wang, T., Liu, X., Peng, S., et al. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.06.083 · Cited by 10
A Generic Approach for Systematic Analysis of Sports Videos
Zhang, N., Duan, L., Li, L., Huang, Q., Du, J., Gao, W., & Guan, L. (2012) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2168752.2168760 · Cited by 14
“Similar to SIFT, SURF is also a scale and rotation-invariant interesting point feature extraction algorithm, which focuses on the computational efficiency [Bay et al. 2006].”
MethodAdopting Feature-Based Visual Odometry for Resource-Constrained Mobile Devices
Fularz, M., Nowicki, M., & Skrzypczyński, P. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11755-3_48 · Cited by 11
Match Box: Indoor Image Matching via Box-Like Scene Estimation
Šrajer, F., Schwing, A. G., Pollefeys, M., & Pajdla, T. (2014) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2014.56 · Cited by 8
“Either the space of considered local transformations is modified, which in-fluences computational efficiency and discriminative properties, or the distance metrics are adapted [23, 4, 3, 6, 10, 5].”
BackgroundActivity-aware adaptive compression
Chen, S., Xia, P., & Nahrstedt, K. (2013) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2502081.2508116 · Cited by 11
Evaluation of two-part algorithms for objects’ depth estimation
Kouskouridas, R., Gasteratos, A. C., & Badekas, E. (2012) · IET Computer Vision · doi:10.1049/iet-cvi.2009.0094 · Cited by 11
A realistic augmented reality racing game using a depth-sensing camera
Clark, A., & Piumsomboon, T. (2011) · ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry (VRCAI) · doi:10.1145/2087756.2087851 · Cited by 11
A comparative study of local detectors and descriptors for mobile document classification
Rusinol, M., Chazalon, J., Ogier, J.-M., & Lladós, J. (2015) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2015.7333831 · Cited by 11
“• SURF: is a local descriptor proposed in [14] which is based on the computation of Haar wavelet responses in a dense fashion within the key-point frames.”
BackgroundC-SURF: Colored Speeded Up Robust Features
Fu, J., Jing, X., Sun, S., Lu, Y., & Wang, Y. (2013) · Communications in computer and information science · doi:10.1007/978-3-642-35795-4_26 · Cited by 13
StereoSnakes: Contour Based Consistent Object Extraction for Stereo Images
Ju, R., Ren, T., & Wu, G. (2015) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.201 · Cited by 11
Compressed matching for feature vectors
Klein, S. T., & Shapira, D. (2015) · Theoretical Computer Science · doi:10.1016/j.tcs.2015.12.021 · Cited by 11
Stereo Pictorial Structure for 2D articulated human pose estimation
López‐Quintero, M. I., Marín-Jiménez, M. J., Muñoz‐Salinas, R., et al. (2015) · Machine Vision and Applications · doi:10.1007/s00138-015-0742-6 · Cited by 11
A geometrical-model-based face recognition
Huang, Y., & Chen, S.-Y. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351375 · Cited by 11
“In the forward recognition, the feature points (FP) of the input image are detected by a feature point detection algorithm (such as SIFT[7] or SURF[8]) and the detected FP are used to found their corresponding ones from the enrolled image through a block matching scheme.”
Real-time Visual Object Tracking via CamShift-Based Robust Framework
Chen, X., Wu, H., Li, X., et al. (2012) · International Journal of Fuzzy Systems · doi:10.30000/ijfs.201206.0010 · Cited by 11
Vision based object follower automated guided vehicle using compressive tracking and stereo-vision
Verma, N. K., Nama, P., Kumar, G., Siddhant, A., Ocean, Raj, A., Dhar, N. K., & Salour, A. (2015) · doi:10.1109/ibss.2015.7456637 · Cited by 13
Large scale face identification by combined iconic features and 3D joint invariant signatures
Cadoni, M. I., Lagorio, A., & Grosso, E. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.05.008 · Cited by 10
A comparative study of local feature extraction algorithms for Web pornographic image recognition
Geng, Z., Li, Z., Zhang, J., et al. (2015) · IEEE International Conference on Progress in Informatics and Computing · doi:10.1109/pic.2015.7489815 · Cited by 11
“Average time-consuming of recognizing each image for different dimensions of feature vectors using six feature algorithms ems) From FigA, it can be seen that, the recognition method based on ORB is the fastest, especially that it only needs 769 91 ms for each image when the dimension of features is 100+ 72, and compar…”
MethodInfluentialEXTENSION AND EVALUATION OF THE AGAST FEATURE DETECTOR
Zhang, H., Wohlfeil, J., & Grießbach, D. (2016) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-iii-4-133-2016 · Cited by 11
“Based on this concept, FAST is an order of magnitude faster than other feature detectors such as SIFT (Lowe, 2004), SURF (Bay et al., 2006), etc. FAST has obvious advantages from many points of view.”
BackgroundMethodA survey on compact features for visual content analysis
Baroffio, L., Redondi, A. E. C., Tagliasacchi, M., & Tubaro, S. (2016) · APSIPA Transactions on Signal and Information Processing · doi:10.1017/atsip.2016.13 · Cited by 11
Robotic Visual Tracking of Relevant Cues in Underwater Environments with Poor Visibility Conditions
Maldonado-Ramírez, A., & Torres-Méndez, L. A. (2016) · Journal of Sensors · doi:10.1155/2016/4265042 · Cited by 11
“As keypoint detector and descriptor we have used SURF [15], SIFT [16], and ORB [32].”
MethodRegional foremost matching for internet scene images
Shen, X., Tao, X., Zhou, C., Gao, H., & Jia, J. (2016) · ACM Transactions on Graphics · doi:10.1145/2980179.2980249 · Cited by 10
Visual localization and loop closing using decision trees and binary features
Schlegel, D., & Grisetti, G. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759679 · Cited by 11
Real-time tracking based on weighted compressive tracking and a cognitive memory model
Du, B., Sun, Y., Wu, C., Zhang, L., & Zhang, L. (2017) · Signal Processing · doi:10.1016/j.sigpro.2017.04.003 · Cited by 12
Analysis of Carotid Artery Transverse Sections in Long Ultrasound Video Sequences
Říha, K., Zukal, M., & Hlawatsch, F. (2017) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2017.08.933 · Cited by 11
“The specific318 values of Hough transform parameters that we used in our experiments (cf.319 the subsection “Preliminary Artery Parameter Estimation”) are as follows:320 resolution of the Hough space field = 1px, minimal distance between the cen-321 ters of detected circles = 1 px, threshold for circle center detectio…”
MethodInfluentialSocial Relevance Feedback Based on Multimedia Content Power
Ntalianis, K., Doulamis, A. D., Tsapatsoulis, N., & Mastorakis, N. E. (2017) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2017.2766250 · Cited by 11
Rare Chinese character recognition by Radical Extraction Network
Yan, Z., Yan, C., & Zhang, C. (2017) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2017.8122728 · Cited by 11
“CNNs have impressive ability to learn better hierarchical visual representations than traditional hand-crafted features such as SIFT [15], SURF [16], Haar-like features [17], and Fisher Vector [18], since all parameters in a CNN are learned from data.”
BackgroundA feature based method for real time vehicle detection and classification from on-road videos
Sajib, M. S. R., & Tareeq, S. M. (2017) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccitechn.2017.8281786 · Cited by 11
“SVM [22] is a strong binary classifier.”
4-Share VCS Based Image Watermarking for Dual RST Attacks
Degadwala, S., & Gaur, S. (2018) · Lecture notes in computational vision and biomechanics · doi:10.1007/978-3-319-71767-8_77 · Cited by 11
Mao, K., Lu, D., Dazhi, E., & Tan, Z. (2018) · Sensors · doi:10.3390/s18061871 · Cited by 13
Multi-faced Object Recognition in an Image for Inventory Counting
Sharma, T., Rajurkar, S. D., Molangur, N., Verma, N. K., & Salour, A. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-1135-2_26 · Cited by 11
Integration of Pipelines and Open Issues in Heritage Digitization
Fantini, F., & Cipriani, L. (2018) · MDPI eBooks · doi:10.3390/books978-3-03842-685-1-8 · Cited by 11
Karbasian, H., Purohit, H., Handa, R., Malik, A. N., & Johri, A. (2018) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3278721.3278781 · Cited by 11
Unsupervised Feature Extraction – A CNN-Based Approach
Trosten, D. J., & Sharma, P. K. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20205-7_17 · Cited by 11
RISAS: A novel rotation, illumination, scale invariant appearance and shape feature
Wu, K., Li, X., Ranasinghe, R., Dissanayake, G., & Liu, Y. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989461 · Cited by 14
Hubless keypoint-based 3D deformable groupwise registration
Agier, R., Valette, S., Kéchichian, R., Fanton, L., & Prost, R. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101564 · Cited by 13
Indirect Visual Simultaneous Localization and Mapping Based on Linear Models
Chien, C.-H., Hsu, C.-C. J., Wang, W., & Chiang, H. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2952722 · Cited by 11
Learning Robust Feature Descriptor for Image Registration With Genetic Programming
Wu, Y., Su, Q., Ma, W., et al. (2020) · IEEE Access · doi:10.1109/access.2020.2968339 · Cited by 11
Fast Image Index for Database Management Engines
Grycuk, R., Najgebauer, P., Kordos, M., et al. (2020) · Journal of Artificial Intelligence and Soft Computing Research · doi:10.2478/jaiscr-2020-0008 · Cited by 11
“As an example image descriptor, we use Speeded-Up Robust Features (SURF) to detect and describe local features of an image [4].”
MethodHardness-Aware Dictionary Learning: Boosting Dictionary for Recognition
Wang, L., Li, S., Wang, S., Kong, D., & Yin, B. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3017916 · Cited by 12
Visual odometry errors and fault distinction for integrity monitoring
Fu, Y., Wang, S., Zhai, Y., & Zhan, X. (2020) · Aerospace Systems · doi:10.1007/s42401-020-00062-x · Cited by 12
“In the feature extraction stage, there are kinds of feature points that can be selected, such as Harris, scale invariant feature transform (SIFT) [10], speeded up robust features (SURF) [2], oriented FAST and rotated BRIEF (ORB) [15], etc. ORB is chosen in this work after trading off the real-time capability and robus…”
MethodMonocular Visual Odometry using Learned Repeatability and Description
Huang, H., Ye, H., Sun, Y., & Liu, M. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197406 · Cited by 13
“Compared with traditional methods in local feature detection [29]–[31] and description [15], [32], [33], learningbased approaches [12]–[14], [34], [35] exhibit a competitive performance in both matching accuracy and efficiency.”
MethodDual-Y network: infrared-visible image patches matching via semi-supervised transfer learning
Mao, Y., & He, Z. (2020) · Applied Intelligence · doi:10.1007/s10489-020-01996-7 · Cited by 11
“Feature points are extracted from infrared-visible images by manual descriptors, such as SIFT [23], SURF [3], ORB [26] and other manually designed descriptors.”
MethodJiang, F., Li, N., & Zhou, L. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2019.1761 · Cited by 11
“Other commonly used statistical-based approaches are SIFT [36], LPQ [37], SURF [38] etc. Filter-based approaches mainly include the Gabor filter and wavelet transform.”
MethodPit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars
Martínez, J., Doubov, S., Fan, J., Bârsan, I. A., Wang, S., Máttyus, G., & Urtasun, R. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340924 · Cited by 20
YOLOv3-Based Matching Approach for Roof Region Detection from Drone Images
Yeh, C.-C., Chang, Y.-L., Alkhaleefah, M., Hsu, P., Eng, W., Koo, V. C., Huang, B., & Chang, L. (2021) · Remote Sensing · doi:10.3390/rs13010127 · Cited by 11
Agarwal, R., Shekhawat, N. S., & Luhach, A. K. (2021) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2021.103854 · Cited by 11
Face Recognition of Children Using AI Classification Approaches
Kamble, V. H., & Dale, M. P. (2021) · International Conference on Emerging Smart Computing and Informatics (ESCI) · doi:10.1109/esci50559.2021.9396891 · Cited by 11
Leveraging semantic segmentation for hybrid image retrieval methods
Ouni, A., Royer, E., Chevaldonné, M., & Dhome, M. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06087-3 · Cited by 12
“We consider the vector length of the proposed methods is 64 if during the building of the signature the descriptor used is SURF or KAZE.”
MethodInfluentialDetection of Inflatable Boats and People in Thermal Infrared with Deep Learning Methods
Kowalski, M., Pałka, N., Młyńczak, J., et al. (2021) · Sensors · doi:10.3390/s21165330 · Cited by 11
“Finally, global matching approaches such as scale invariant feature transform (SIFT) and speeded-up robust features (SURF) [18,19] are used.”
MethodAccurate and Robust Stereo Direct Visual Odometry for Agricultural Environment
Yu, T., Zhou, J., Wang, L., & Xiong, S. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561074 · Cited by 11
“For indirect methods, a certain feature(e.g., ORB [9], SURF [10]) points are extracted from images and tracked by feature matching or optical flow.”
MethodLi, R., Pan, J., Yang, Y., Wei, N., Yan, B., Liu, H., Yang, Y., & Qin, H. (2021) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.102007 · Cited by 12
3D Digitization of Tangible Heritage
Pavlidis, G. P., & Koutsoudis, A. (2022) · Springer eBooks · doi:10.1007/978-3-030-60016-7_47 · Cited by 12
Extrinsic Self-Calibration of the Surround-View System: A Weakly Supervised Approach
Chen, Y., Zhang, L., Shen, Y., Zhao, B. N., & Zhou, Y. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3144889 · Cited by 11
A passive image forensic scheme based on an adaptive and hybrid techniques
Alhaidery, M. M. A., & Taherinia, A. H. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12374-5 · Cited by 12
A Review on Sign Language Recognition (SLR) System: ML and DL for SLR
Das, S., Biswas, S. K., Chakraborty, M., et al. (2021) · IEEE International Conference on Intelligent Systems, Smart and Green Technologies (ICISSGT) · doi:10.1109/icissgt52025.2021.00045 · Cited by 11
Hendre, M., Patil, S., & Abhyankar, A. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11686-2 · Cited by 11
“After the invention of SIFT, many feature detection methods [15–19] are developed which are mostly based on the idea of SIFT algorithm.”
MethodChen, Q., Yang, H., Mars, J., & Tang, L. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/2980024.2872368 · Cited by 12
Copy move forgery detection with similar but genuine objects
Roy, A., Konda, A., & Chakraborty, R. S. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8297050 · Cited by 11
“, based on an approximation of the Hessian matrix of an given image point as described in [18].”
MLFNet: Monocular lifting fusion network for 6DoF texture-less object pose estimation
Jiang, J., He, Z., Zhao, X., Zhang, S., Wu, C., & Wang, Y. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.06.096 · Cited by 11
den Haan, J., de Ruyter, F. J. H., Lochocki, B., Kroon, M. A. G. M., Kemper, E. M., Teunissen, C. E., van Berckel, B. N. M., Scheltens, P., Hoozemans, J. J. M., van de Kreeke, A., et al. (2022) · Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring · doi:10.1002/dad2.12347 · Cited by 16
Jiang, Z., Gao, X., Li, Y., Wang, H., Zhang, Y., & Fang, X. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/ac87c6 · Cited by 11
“The commonly used scale-invariant feature transform (SIFT) [24] and speeded-up robust features (SURF) [25, 26] operators store enormous data and have a slow calculation speed.”
PCB Hardware Trojan Run-Time Detection Through Machine Learning
Piliposyan, G., & Khursheed, S. (2022) · IEEE Transactions on Computers · doi:10.1109/tc.2022.3230877 · Cited by 12
Self-supervised Correspondence Estimation via Multiview Registration
Banani, M. E., Rocco, I., Novotný, D., Vedaldi, A., Neverova, N., Johnson, J., & Graham, B. V. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00127 · Cited by 12
GeoFill: Reference-Based Image Inpainting with Better Geometric Understanding
Zhao, Y., Barnes, C., Zhou, Y., Shechtman, E., Amirghodsi, S., & Fowlkes, C. C. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00182 · Cited by 25
Yao, C., Zhang, H., Zhu, J., et al. (2023) · IEEE Access · doi:10.1109/access.2023.3288594 · Cited by 11
Autonomous Robotic Bin Picking Platform Generated From Human Demonstration and YOLOv5
Park, J.-H., Han, C., Jun, M. B., & Yun, H. (2023) · Journal of Manufacturing Science and Engineering · doi:10.1115/1.4063107 · Cited by 12
Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares
Muhle, D., Koestler, L., Murthy, J. K., & Cremers, D. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01259 · Cited by 12
A new era in quantification of animal social behaviors
Choi, J. D., & Kumar, V. (2023) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2023.105528 · Cited by 15
CapsLoc3D: Point Cloud Retrieval for Large-Scale Place Recognition Based on 3D Capsule Networks
Zhang, J., Zhang, Y., Liao, M., Tian, R., Coleman, S., & Kerr, D. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3346953 · Cited by 14
“However, such methods were not very successful as noted in [6], [7], and [8].”
MethodZhang, H., Zheng, D., Zhang, Y., Cao, J., Lin, W., & Ling, B. W. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3356029 · Cited by 16
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.