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 3,201–3,300 of 14,752
Penza, V., Du, X., Stoyanov, D. V., Forgione, A., Mattos, L. S., & Momi, E. D. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.12.010 · Cited by 20
Segments Graph-Based Approach for Document Capture in a Smartphone Video Stream
Zhukovsky, A. E., Nikolaev, D., Arlazarov, V. V., et al. (2017) · doi:10.1109/icdar.2017.63 · Cited by 21
“More specifically, we detected 256 key points with SURF [18], use BRIEF [19] to describe them, match descriptors with standard brute force matching and then run classic RANSAC [20] to evaluate homography matrix and number of inliers.”
MethodScale-Free Registrations in 3D: 7 Degrees of Freedom with Fourier Mellin SOFT Transforms
Bülow, H., & Birk, A. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-018-1067-5 · Cited by 25
“…al. (2013), Guo et al. (2016) for overviews and comparisons or visual point features (e.g., Lindeberg 1993; Smith and Brady 1997; Lowe 1999, 2001; Bay et al. 2006; Rosten and Drummond 2006; Roth-ganger et al. 2006; Bay et al. 2008) based on 2D texture information if this texture information is…”
BackgroundA Multi-Modal Person Recognition System for Social Robots
Al-Qaderi, M., & Rad, A. B. (2018) · Applied Sciences · doi:10.3390/app8030387 · Cited by 22
“The authors are aware of the availability of stronger descriptors like Scale-Invariant Feature Transform (SIFT) [41] and Speeded-Up Robust Features (SURF) [42], both of which can be used to generate feature vectors with hi h discrimination power.”
MethodReal-Time Visual Place Recognition Based on Analyzing Distribution of Multi-scale CNN Landmarks
Xin, Z., Cui, X., Zhang, J., Yang, Y., & Wang, Y. (2018) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-018-0804-x · Cited by 20
“Local features such as SIFT [7], SURF [8], ORB [9] are generally operated as visual words in bag-of-words models [10, 11], which work effectively in many computer vision applications [12, 13].”
MethodTraining a deep learning architecture for vehicle detection using limited heterogeneous traffic data
Mittal, D., Reddy, A. S. S., Ramadurai, G., Mitra, K., & Ravindran, B. (2018) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets.2018.8328279 · Cited by 25
“Then, SIFT and SURF features are extracted for all the patches. k-means clustering is done separately on the SIFT and SURF features extracted from all the patches.”
MethodInfluentialReal-Time Force-Feedback Micromanipulation Using Mobile Microrobots With Colored Fiducials
Guix, M., Wang, J.-X., An, Z., Adam, G., & Cappelleri, D. J. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2854909 · Cited by 21
An extensive review on spectral imaging in biometric systems: Challenges & advancements
Munir, R., & Khan, R. A. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.102660 · Cited by 21
“35 SURF Speeded Up Robust Features [89]”
High-Throughput and Area-Optimized Architecture for rBRIEF Feature Extraction
Pham, T. H., Tran, P. D., & Lam, S.-K. (2018) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2018.2881105 · Cited by 21
“invariant feature transform (SIFT) [2] and speeded up robust features (SURF) [3] were originally introduced as feature”
MethodA Multi-modal Neural Embeddings Approach for Detecting Mobile Counterfeit Apps
Rajasegaran, J., Karunanayake, N., Gunathillake, A., Seneviratne, S., & Jourjon, G. (2019) · International World Wide Web Conference (WWW) · doi:10.1145/3308558.3313427 · Cited by 25
An improved vehicle panoramic image generation algorithm
Zhang, J., Yin, X., Luan, J., & Liu, T. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07890-w · Cited by 21
“matching algorithm, SURF was proposed in [2].”
Fake News Detection by Image Montage Recognition
Steinebach, M., Gotkowski, K., & Liu, H. (2019) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3339252.3341487 · Cited by 24
“The Speeded Up Robust Features (SURF) detector [5] is partly inspired by SIFT and is an attempt to be faster and more robust than SIFT.”
MethodIVPR: An Instant Visual Place Recognition Approach Based on Structural Lines in Manhattan World
Pei, L., Liu, K., Zou, D., Li, T., Wu, Q., Zhu, Y., Li, Y., He, Z., Chen, Y., & Sartori, D. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2941359 · Cited by 23
“Bay proposed speeded-up robust features (SURF) [17] that is three times faster than SIFT.”
MethodHuynh, H. X., Truong, B. Q., Thanh, K. T. N., & Truong, Q. D. (2020) · Vietnam Journal of Computer Science · doi:10.1142/s2196888820500116 · Cited by 23
A Novel Stereo Matching Algorithm for Digital Surface Model (DSM) Generation in Water Areas
Yang, W., Li, X., Yang, B., & Fu, Y. (2020) · Remote Sensing · doi:10.3390/rs12050870 · Cited by 25
“In In other words, the block is treated as a rigid body on both the left and right images. other words, the block is treated as a rigid body on both the left and right images.”
BackgroundIdentify the full inertial parameters of a non-cooperative target with eddy current detumbling
Meng, Q., Zhao, C., Ji, H., et al. (2020) · Advances in Space Research · doi:10.1016/j.asr.2020.05.044 · Cited by 21
Ullah, A., Muhammad, K., Hussain, T., et al. (2020) · IEEE Access · doi:10.1109/access.2020.3029834 · Cited by 21
“algorithms such as scale invariant feature transform SIFT [3], speeded up robust features (SURF) [4], and oriented FAST and rotated BRIEF (ORB), etc.”
MethodTransformation-Aware Embeddings for Image Provenance
Bharati, A., Moreira, D., Flynn, P. J., Rocha, A. D. R., Bowyer, K. W., & Scheirer, W. J. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3050061 · Cited by 23
SmartFit: Smartphone Application for Garment Fit Detection
Foysal, K. H., Chang, H. J., Bruess, F., & Chong, J. W. (2021) · Electronics · doi:10.3390/electronics10010097 · Cited by 23
“The SURF feature point extracting procedure consists of the genera ion f the integral image, the approximati n of the Hessian determinant and performing non-maximal suppression [36] as shown n Figure 5.”
MethodInfluentialEfficient Object Detection Model for Real-time UAV Application
Vaddi, S., Kim, D., Kumar, C., Shad, S. A., & Jannesari, A. (2021) · Computer and Information Science · doi:10.5539/cis.v14n1p45 · Cited by 23
“Traditionally hand-tuned features were used for object recognition and detection, such as Scale-Invariant Feature Transform (SIFT) (Lowe, 1999), Speeded-Up Robust Features (SURF) (Bay & Van, 2006), and Histogram of Oriented Gradient (HOG) (Mizuno et al., 2012).”
MethodWang, D., Wang, Z., Li, X., et al. (2007) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icosc.2007.4338364 · Cited by 21
Feng, R., Du, Q., Shen, H., & Li, X. (2021) · Remote Sensing · doi:10.3390/rs13081475 · Cited by 23
“Taking the feature point extraction as an example, the scale-invariant feature transform (SIFT) [17], the speeded-up robust feature (SURF) [18], and the extended SIFT or SURF [15,16] are well-known operators.”
MethodTexture-Generic Deep Shape-From-Template
Fuentes-Jimenez, D., Pizarro, D., Casillas-Pérez, D., Collins, T., & Bartoli, A. (2021) · IEEE Access · doi:10.1109/access.2021.3082011 · Cited by 24
“It usually solves wide-baseline registration using feature-based matching methods like SURF [35] and SIFT [36], which are then cleaned from mismatches using specific methods for deformable registration [14], [37].”
MethodEVALUATING HAND-CRAFTED AND LEARNING-BASED FEATURES FOR PHOTOGRAMMETRIC APPLICATIONS
Remondino, F., Menna, F., & Morelli, L. (2021) · 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-xliii-b2-2021-549-2021 · Cited by 27
Deep Features for Training Support Vector Machines
Nanni, L., Ghidoni, S., & Brahnam, S. (2021) · Journal of Imaging · doi:10.3390/jimaging7090177 · Cited by 23
A Video Summarization Method Based on Spectral Clustering
Cirne, M., & Pedrini, H. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41827-3_60 · Cited by 21
“In this process, many image descriptors that encompass spatial and temporal features are evaluated, such as SIFT (Scale-Invariant Feature Trans-form) [12], SURF (Speeded Up Robust Features) [5] and ORB (Oriented FAST and Rotated BRIEF 1 ) [17].”
MethodA framework for infrastructure-free warehouse navigation
Gadd, M., & Newman, P. M. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139650 · Cited by 20
“We choose to detect and match points of interest across frames using SURF features [17], due to their robustness to viewpoint changes (the robot does not revisit locations with exactly the same attitude) and speed of implementation, yet our framework is easily adaptable for swapping this subsystem out.”
MethodSpatially-Sensitive Affine-Invariant Image Descriptors
Bronstein, A. M., & Bronstein, M. M. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15552-9_15 · Cited by 21
Experiences in building a visual SLAM system from open source components
Hertzberg, C., Wagner, R., Birbach, O., Hammer, T., & Frese, U. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980140 · Cited by 25
Field Testing of an Integrated Surface/Subsurface Modeling Technique for Planetary Exploration
Furgale, P., Barfoot, T. D., Ghafoor, N., Williams, K. K., & Osinski, G. R. (2010) · The International Journal of Robotics Research · doi:10.1177/0278364910378179 · Cited by 25
Hashmi, M. F., Anand, V., & Keskar, A. G. (2014) · International Conference on Computer and Communication Technology · doi:10.1109/iccct.2014.7001483 · Cited by 22
Objects Tracking from Natural Features in Mobile Augmented Reality
Ng, G. W., Khan, R. U., Adruce, S. A. Z., et al. (2013) · Procedia - Social and Behavioral Sciences · doi:10.1016/j.sbspro.2013.10.297 · Cited by 21
Beyond 2D-grids: a dependence maximization view on image browsing
Quadrianto, N., Kersting, K., Tuytelaars, T., & Buntine, W. (2010) · Multimedia Information Retrieval · doi:10.1145/1743384.1743440 · Cited by 25
Self-citationFlyphone: Visual Self-Localisation Using a Mobile Phone as Onboard Image Processor on a Quadrocopter
Erhard, S., Wenzel, K. E., & Zell, A. (2009) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-009-9360-8 · Cited by 23
Video copy detection based on Speeded Up Robust Features and Locality Sensitive Hashing
Zhang, Z., Cao, C., Zhang, R., & Zou, J. (2010) · IEEE International Conference on Automation and Logistics (ICAL) · doi:10.1109/ical.2010.5585375 · Cited by 21
Part-Based Recognition of Handwritten Characters
Uchida, S., & Liwicki, M. (2010) · International Conference on Frontiers in Handwriting Recognition · doi:10.1109/icfhr.2010.90 · Cited by 21
“In the following, those steps are detailed, while assuming a recognition problem of isolated handwritten characters and employing SURF [4] for detecting and describing local parts.”
MethodInfluentialToward Community Sensing of Road Anomalies Using Monocular Vision
Chen, H.-T., Lai, C.-Y., & Shih, C.-A. (2016) · IEEE Sensors Journal · doi:10.1109/jsen.2016.2517194 · Cited by 21
Vourvoulakis, J. V., Kalomiros, J. A., & Lygouras, J. N. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5042-x · Cited by 21
“During the last two decades, many feature extraction algorithms have been proposed, such as Scale Invariant Feature Transform (SIFT) [22, 23], Speeded Up Robust Features (SURF) [2, 3], BRIEF [5], BRISK [20].”
MethodLayout-based computation of web page similarity ranks
Bozkır, A. S., & Sezer, E. A. (2017) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2017.10.008 · Cited by 21
Enhanced copy–paste forgery detection in digital images using scale‐invariant feature transform
Selvaraj, P., & Karuppiah, M. (2019) · IET Image Processing · doi:10.1049/iet-ipr.2019.0842 · Cited by 24
Intelligent Video Surveillance
Ma, Y., & Qian, G. (2009) · CRC Press eBooks · doi:10.1201/9781439813300 · Cited by 22
Hierarchical Multi-Modal Place Categorization.
Pronobis, A., & Jensfelt, P. (2011) · Cited by 21
A System for Assisting the Visually Impaired in Localization and Grasp of Desired Objects
Thakoor, K. A., Mante, N. T., Zhang, C., Siagian, C., Weiland, J. D., Itti, L., & Medioni, G. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16199-0_45 · Cited by 22
Wu, J., Hu, H., Song, Y., et al. (2024) · NDT & E International · doi:10.1016/j.ndteint.2024.103130 · Cited by 20
Aktaş, A., Serbes, G., Yiğit, M. H., Aydın, N., Uzun, H., & İlhan, H. O. (2024) · IEEE Access · doi:10.1109/access.2024.3521643 · Cited by 27
“In a subsequent study, they used descriptor-based features (KAZE [55], SURF [56], MSER [57]) and texture features (DWT, DTCWT), classified with traditional machine learning and ensemble methods [24].”
Fernandes, S. L., & Bala, J. G. (2014) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-13728-5_13 · Cited by 22
Instrument classification in laparoscopic videos
Primus, M. J., Schoeffmann, K., & Böszörményi, L. (2015) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2015.7153616 · Cited by 22
“Additionally to the classification of instruments based on ORB features we further evaluate scale-invariant feature transform (SIFT) [7] and speeded-up robust feature (SURF) [8].”
MethodRobust Keypoint Detection Using Higher-Order Scale Space Derivatives: Application to Image Retrieval
Park, U., Park, J.-S., & Jain, A. K. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2321755 · Cited by 20
Recognizing locations with Google Glass: A case study
Altwaijry, H., Moghimi, M. K., & Belongie, S. (2014) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2014.6836105 · Cited by 21
Joint Alignment and Modeling of Correlated Behavior Streams
Presti, L. L., Sclaroff, S., & Rozga, A. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.100 · Cited by 25
“With respect to other sparse feature representations (SIFT [14], SURF [3]), STIP offers the advantage of considering interest points with a temporal duration.”
BackgroundSketch Retrieval via Dense Stroke Features
Ma, C., Yang, X., Zhang, C., Ruan, X., & Yang, M. (2013) · British Machine Vision Conference (BMVC) · doi:10.5244/c.27.65 · Cited by 19
“While several key point detectors such as difference of Gaussian (DoG) [12], Hessian operator [1], and Harris-Laplace detector [15] are available for locating local features, they are designed mainly for finding salient points.”
BackgroundCombining local and global visual feature similarity using a text search engine
Amato, G. M., Bolettieri, P., Falchi, F., Gennaro, C., & Rabitti, F. (2011) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2011.5972519 · Cited by 20
A data driven method for feature transformation
Dikmen, M., Hoiem, D., & Huang, T. S. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6248069 · Cited by 21
Design and Evaluation of a Teleoperated Robotic 3-D Mapping System using an RGB-D Sensor
Du, J., Mouser, C., & Sheng, W. (2015) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2015.2461186 · Cited by 20
“The speeded up robust features [12] features were selected to estimate camera poses from consecutive frames.”
MethodObject Recognition Using Hough-transform C lustering of SURF Features
Seib, V., Kusenbach, M., Thierfelder, S., et al. (2014) · Cited by 20
Game theoretic hypergraph matching for multi-source image correspondences
Zhang, H., & Ren, P. (2016) · Pattern Recognition Letters · doi:10.1016/j.patrec.2016.07.011 · Cited by 20
Stochastic Fuzzy Modeling for Ear Imaging Based Child Identification
Kumar, M., Insan, A., Stoll, N., et al. (2015) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2015.2468195 · Cited by 20
“Thus, the proposed method was observed performing better than the benchmark image matching methods of histograms of oriented gradients (HOGs) [24], SIFT [4], speeded-up robust features (SURFs) [25], and affine-SIFT (ASIFT) [7] in matching the ear-geometries between the two photographs which have been taken under field…”
MethodInfluentialPanoptes: servicing multiple applications simultaneously using steerable cameras
Jain, S., Nguyen, V., Gruteser, M., & Bahl, P. (2017) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1145/3055031.3055085 · Cited by 26
Rani, R., Kumar, R., & Singh, A. P. (2017) · Pattern Analysis and Applications · doi:10.1007/s10044-017-0641-8 · Cited by 21
Contextual Bag-of-Words for Robust Visual Tracking
Zeng, F., Ji, Y., & Levine, M. D. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2778561 · Cited by 23
A Hardware-Oriented Algorithm for Ultra-High-Speed Object Detection
Li, J., Liu, X., Liu, F., Xu, D., Gu, Q., & Ishii, I. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2895294 · Cited by 21
“[2], [18], which is a scale- and rotation-invariant descriptor performs”
BackgroundMethodA visual SLAM method based on point-line fusion in weak-matching scene
Fang, B., & Zhan, Z. (2020) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881420904193 · Cited by 20
“Although features such as Scale Invariant Feature Transform (SIFT) 26 and Speeded Up Robust Features (SURF) 27 are better in quality than ORB, their time consumption is difficult to meet the real-time requirements of vSLAM, and GPU acceleration is required.”
Background3D finger vein biometric authentication with photoacoustic tomography
Zhan, Y., Rathore, A. S., Milione, G., et al. (2020) · Applied Optics · doi:10.1364/ao.400550 · Cited by 20
Infusion port level detection for intravenous infusion based on Yolo v3 neural network
Huang, Z., Li, Y., Zhao, T., Peng, Y. H., Fan, Y., & Li, J. (2021) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2021175 · Cited by 23
Cross-Dataset Point Cloud Recognition Using Deep-Shallow Domain Adaptation Network
Wang, F., Li, W., & Xu, D. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3092818 · Cited by 22
Mars Image Super-Resolution Based on Generative Adversarial Network
Wang, C., Zhang, Y., Zhang, Y., Tian, R., & Ding, M. (2021) · IEEE Access · doi:10.1109/access.2021.3101858 · Cited by 22
“We select SURF [43], which has a better execution efficiency than the SIFT algorithm [44], to calculate the number of feature points in the Earth and Mars images, as shown in Figure 4.”
MethodCopy-move image forgery detection based on evolving circular domains coverage
Lu, S., Hu, X., Wang, C., Lü, C., Han, S., & Han, Y. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12755-w · Cited by 22
Wu, Y., Wang, M., Liu, X., Wang, Z., Ma, T., Zhi-min, L., Liu, D., Xie, Y., Li, X., & Wang, X. (2021) · Remote Sensing · doi:10.3390/rs13193853 · Cited by 24
Ren, Z., & Wang, L. (2022) · Sensors · doi:10.3390/s22041463 · Cited by 21
Zhao, K., Liu, J., Wang, Q., Wu, X.-J., & Tu, J. (2022) · IEEE Access · doi:10.1109/access.2022.3169031 · Cited by 22
Learning Token-Based Representation for Image Retrieval
Wu, H., Wang, M., Zhou, W., Yang, H., & Li, H. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i3.20173 · Cited by 12
“Traditionally local features (Lowe 2004; Bay, Tuytelaars, and Van Gool 2006; Liu et al. 2015) are extracted using hand-crafted detectors and descriptors.”
Wąsala, M., Szolc, H., & Kryjak, T. (2022) · Electronics · doi:10.3390/electronics11142259 · Cited by 21
Focal Length and Object Pose Estimation via Render and Compare
Ponimatkin, G., Labbé, Y., Russell, B. C., Aubry, M., & Šivic, J. (2022) · 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/cvpr52688.2022.00380 · Cited by 26
Qiu, Q., Tan, Y., Ma, K., Tian, M., Xie, Z., & Tao, L. (2022) · Ore Geology Reviews · doi:10.1016/j.oregeorev.2022.105262 · Cited by 23
Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation
Wang, Z., Huo, X., Chen, Z., Zhang, J., Sheng, L., & Xu, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19824-3_11 · Cited by 21
Comparison of multimodal RGB-thermal fusion techniques for exterior wall multi-defect detection
Yang, X., Guo, R., & Li, H. (2023) · Journal of Infrastructure Intelligence and Resilience · doi:10.1016/j.iintel.2023.100029 · Cited by 49
Dai, Y., & Wu, J. (2023) · IEEE Access · doi:10.1109/access.2023.3261665 · Cited by 22
Semi-Supervised Bolt Anomaly Detection Based on Local Feature Reconstruction
Peng, Y., Liu, C.-W., Yan, Y., Ma, N., Wang, D., Liu, C., & Chen, Q. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3278293 · Cited by 23
“Though the existing classical key-point detection algorithms [10], [11], [12], [13] can obtain accurate results in complex environments, they are no longer stable in complex scenarios as some key areas needed to be detected are lost or damaged.”
BackgroundZhang, H., Tang, C., Sun, X., et al. (2023) · Agronomy · doi:10.3390/agronomy13061469 · Cited by 20
DETR-SPP: a fine-tuned vehicle detection with transformer
Krishnendhu, S. P., & Mohandas, P. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16502-7 · Cited by 35
“SURF is an efficient and robust feature-based method for vehicle detection [3].”
Sequence Matching for Image-Based UAV-to-Satellite Geolocalization
Wang, Z., Shi, D., Qiu, C., Jin, S., Li, T., Shi, Y., Liu, Z., & Qiao, Z. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3359605 · Cited by 27
Brain-inspired sensor fusion for navigating robots
Milford, M. J., & Jacobson, A. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630980 · Cited by 21
Sparse Camera Network for Visual Surveillance -- A Comprehensive SurveyPreprint
Song, M., Tao, D., & Maybank, S. J. (2013) · BIROn (Birkbeck, University of London) · doi:10.48550/arxiv.1302.0446 · Cited by 30
A Probabilistic Feature Map-Based Localization System Using a Monocular Camera
Kim, H., Lee, D., Oh, T., Choi, H., & Myung, H. (2015) · Sensors · doi:10.3390/s150921636 · Cited by 19
A New Global Alignment Method for Feature Based Image Mosaicing
Elibol, A., García, R., Delaunoy, O., & Gracias, N. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-89646-3_25 · Cited by 20
“In both methods mentioned feature detection is based on Hessian or Laplacian detectors (the “Difference of Gaussians” of SIFT is an approximation to the Laplacian, and SURF uses an approximation to the Hessian).”
MethodSiagian, C., Chang, C. K., & Itti, L. (2014) · Journal of Field Robotics · doi:10.1002/rob.21505 · Cited by 23
Topological SLAM Using Omnidirectional Images: Merging Feature Detectors and Graph-Matching
Romero, A., & Cazorla, M. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-17688-3_43 · Cited by 19
Romberg, S., Lienhart, R. W., & Hörster, E. (2012) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-012-0006-4 · Cited by 21
ARMEN: Assistive robotics to maintain elderly people in natural environment
Leroux, C., Lebec, O., Ghezala, M. W. B., et al. (2013) · IRBM · doi:10.1016/j.irbm.2013.01.012 · Cited by 20
Besbes, B., Rogozan, A., & Bensrhair, A. (2010) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2010.5547965 · Cited by 21
Video stabilization for vehicular applications using SURF-like descriptor and KD-tree
Huang, K.-Y., Tsai, Y., Tsai, C.-C., et al. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5653052 · Cited by 20
“Features are represented with the SURF-like [9] descriptor.”
MethodInfluentialKawewong, A., Tongprasit, N., & Hasegawa, O. (2011) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2011.05.007 · Cited by 20
Variational learning of finite Dirichlet mixture models using component splitting
Fan, W., Bouguila, N., & Ziou, D. (2013) · Neurocomputing · doi:10.1016/j.neucom.2013.03.049 · Cited by 24
Semi-parametric learning for visual odometry
Guizilini, V., & Ramos, F. T. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364912472245 · Cited by 21
Measures of Similarity Between Objects Based on Qualitative Shape Descriptions
Falomir, Z., Abril, L. G., Museros, L., & Ortega, J. A. (2013) · Spatial Cognition and Computation · doi:10.1080/13875868.2012.700463 · Cited by 20
“Finally, it is worth mentioning that some invariant feature descriptors and detectors methods (such as SIFT by Lowe (2004), SURF by Bay et al. (2006), SIFT C Vocabulary Tree by Csurka et al. (2004), Harris-Affine and Hessian-Affine by Mikolajczyk et al. (2005), MSER by Matas et al. (2002), etc.),…”
MethodUsing Normalized Compression Distance for image similarity measurement: an experimental study
Vázquez, P., & Marco, J. (2011) · The Visual Computer · doi:10.1007/s00371-011-0651-2 · Cited by 20
High-throughput 3D reconstruction of plant shoots for phenotyping
Kumar, P., Connor, J. N., & Mikiavcic, S. (2014) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2014.7064306 · Cited by 20
“Speeded up robust feature (SURF) [15] feature detector and descriptor are used to detect and match points across images.”
MethodToward an assisted indoor scene perception for blind people with image multilabeling strategies
Mekhalfi, M. L., Melgani, F., Bazi, Y., & Alajlan, N. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.11.017 · Cited by 21
A Review of Codebook Models in Patch-Based Visual Object Recognition
Ramanan, A., & Niranjan, M. (2011) · Journal of Signal Processing Systems · doi:10.1007/s11265-011-0622-x · Cited by 21
Lip pattern recognition based on local feature extraction
Bakshi, S., Raman, R., & Sa, P. K. (2011) · IEEE India Conference · doi:10.1109/indcon.2011.6139357 · Cited by 22
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.