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 3,801–3,900 of 14,752
Sidiropoulos, P., & Müller, J. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2734693 · Cited by 16
Dixit, A., & Bag, S. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09230-9 · Cited by 17
Lou, X. P., Zhu, Y., Punithakumar, K., Le, L. H., & Li, B. (2020) · IEEE Access · doi:10.1109/access.2020.3035772 · Cited by 18
“Preprocessing and feature extraction by means of the speeded up robust features (SURF) algorithm [31], [32] are performed .”
MethodAn improved parking space recognition algorithm based on panoramic vision
Zhang, J., Liu, T., Yin, X., et al. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10370-1 · Cited by 16
“In order to reduce the time complexity of the subsequent algorithm, the paper firstly extracts the candidate corner points of parking space by using the corner detection algorithm, common corner detection algorithms include HARRIS algorithm [3]、FAST algorithm [17]、SIFT algorithm [9]、 and SURF algorithm [1].”
MethodSmartphone-Based Indoor Visual Navigation with Leader-Follower Mode
Xu, J., Dong, E., Ma, Q., Wu, C., & Yang, Z. (2021) · ACM Transactions on Sensor Networks · doi:10.1145/3448417 · Cited by 18
“In Pair-Navi, we leverage ORB feature point [47], which has comparative matching accuracy with the state-of-the-art SIFT [39] and SURF [5], yet is far more efficient in computation.”
MethodRegistration of Consecutive Frames From Wireless Capsule Endoscopy for 3D Motion Estimation
Oliveira, M., Araújo, H. J., Figueiredo, I. N., Pinto, L., Curto, E., & Perdigoto, L. (2021) · IEEE Access · doi:10.1109/access.2021.3108234 · Cited by 16
Kuriakose, B., Shrestha, R., & Sandnes, F. E. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9658913 · Cited by 24
“…of local visual descriptors that have been widely used in the patch feature extraction include Local Binary Patterns (LBP) [17], Scale Invariant Feature Transform (SIFT) [18], Speeded Up Robust Features (SURF) [19], Histogram of Oriented Gradients (HOG) [20], and Oriented Texture Curves (OTC) [21].”
Pose Measurement at Small Scale by Spectral Analysis of Periodic Patterns
André, A. N., Sandoz, P., Jacquot, M., et al. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01607-7 · Cited by 16
“Some methods rely on the use of multiple cameras to recon-structtheobjectanditsposeviawell-knownfeaturematching techniques such as SIFT or SURF (Bay et al. 2006; Moreels and Perona 2007).”
MethodEdge Computing Based on Federated Learning for Machine Monitoring
Tsai, Y.-H., Chang, D.-M., & Hsu, T.-C. (2022) · Applied Sciences · doi:10.3390/app12105178 · Cited by 25
MD-SLAM: Multi-cue Direct SLAM
Giammarino, L. D., Brizi, L., Guadagnino, T., Stachniss, C., & Grisetti, G. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981147 · Cited by 24
Research on Adaptive ORB-SURF Image Matching Algorithm Based on Fusion of Edge Features
Han, L., Wang, J., Zhang, Y., et al. (2022) · IEEE Access · doi:10.1109/access.2022.3212151 · Cited by 16
Gaze Tracking on Any Surface with Your Phone
Cao, J., Lin, C., Liu, Y., & Li, Z. (2022) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3560905.3568544 · Cited by 17
“To this end, we adopt the SURF operator [8] to perform feature extraction for the iris boundary pixel candidates obtained from both eye frames.”
MethodA Review of Common Techniques for Visual Simultaneous Localization and Mapping
Dai, Y., Wu, J., & Wang, D. (2023) · Journal of Robotics · doi:10.1155/2023/8872822 · Cited by 25
MASIC: Deep Mask Stereo Image Compression
Deng, X., Deng, Y., Yang, R., Yang, W., Timofte, R., & Xu, M. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3253702 · Cited by 23
Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects
Maag, K., Chan, R., Uhlemeyer, S., Kowol, K., & Gottschalk, H. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26348-4_28 · Cited by 16
“More advanced approaches utilize local level features [4,56], still they cannot fully address the problem of semantic gap [75], which describes the disparity between different representation systems [36].”
Geng, J., Zhang, X., Yan, Y., Sun, M., Zhang, H., Assaad, M. M., Ren, J., & Li, X. (2023) · Cognitive Computation · doi:10.1007/s12559-023-10172-1 · Cited by 17
Moving From Narrative to Interactive Multi-Modal Sentiment Analysis: A Survey
Ma, J., Rong, L., Zhang, Y., & Tiwari, P. (2023) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3610288 · Cited by 24
Attention-Enhanced Cross-Modal Localization Between Spherical Images and Point Clouds
Zhao, Z., Yu, H., Lyu, C., Yang, W. T., & Scherer, S. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3306377 · Cited by 21
Mukherjee, N., & Sengupta, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17254-0 · Cited by 23
An Efficient Wi-Fi–Vision Map Construction and Self-Maintenance Method for Indoor Localization
Tang, C., Sun, W., Zhang, X., et al. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3331392 · Cited by 16
Color Transfer for Images: A Survey
Lv, C., Zhang, D., Geng, S., Wu, Z., & Huang, H. F. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3635152 · Cited by 29
“Comparing to the sparse correspondence frameworks, such methods attempt to detect the continuous semantic regions in images to generate color scheme.”
Liu, F., Zhang, Z., & Li, S. (2023) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2023.3332075 · Cited by 18
“Traditional methods often rely on hand-crafted features to establish this correspondence [22], [23].”
MethodLi, D., Cheng, B., Xiang, S., et al. (2024) · Measurement · doi:10.1016/j.measurement.2023.114098 · Cited by 16
Automated Camera Calibration via Homography Estimation with GNNs
D’Amicantonio, G., Bondarev, E., & De, P. H. N. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00577 · Cited by 21
“The approaches mentioned in related work [2,4,21,22,27,31,35] extract and match these features in images and then estimate the homography matrix via Direct Linear Transformation (DLT) [13].”
MethodThe Prospect of Artificial Intelligence-Based Wood Surface Inspection: A Review
Yi, L. P., Akbar, M. F., Wahab, M. N. A., Rosdi, B. A., Fauthan, M. ‘., & Shrifan, N. H. M. M. (2024) · IEEE Access · doi:10.1109/access.2024.3412928 · Cited by 24
“The Bag of Words (BoW) approach is implemented, in which the features are extracted using the Speeded UP Robust Features (SURF) algorithm [35] and clustered by K-means clustering to create a visual dictionary as input data.”
MethodIntroduction to the Third Generation Simulation Dataset: Data Collection and Trajectory Extraction
Ammourah, R., Beigi, P., Fan, B., Hamdar, S. H., Hourdos, J., Hsiao, C.-C., James, R., Khajeh-Hosseini, M., Mahmassani, H. S., Monzer, D., et al. (2024) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981241257257 · Cited by 28
Medical image registration and its application in retinal images: a review
Nie, Q., Zhang, X., Hu, Y., Gong, M., & Liu, J. (2024) · Visual Computing for Industry Biomedicine and Art · doi:10.1186/s42492-024-00173-8 · Cited by 29
“The warped images from both networks are used as image pairs and sent to the networks themselves to ensure that they could be returned to their original state, maximizing the similarity between the original and reversed images.”
MethodNever Get Lost Again: Vision Based Navigation Using StreetView Images
Taneja, A., Ballan, L., & Pollefeys, M. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16814-2_7 · Cited by 16
Automatic Motorcycle Detection on Public Roads
Silva, R., Aires, K. R. T., Veras, R. D. M. S., Santos, T., Lima, K. A. B., & Soares, A. C. B. (2013) · CLEI electronic journal · doi:10.19153/cleiej.16.3.4 · Cited by 16
A Comparison of Feature Detectors with Passive and Task-Based Visual Saliency
Harding, P., & Robertson, N. M. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02230-2_73 · Cited by 16
“The detectors are again well above chance level in all cases, with both SIFT and SURF the strongest performers, with 30%, 48% and 83% of SIFT points overlapping the 10%, 20% and 50% thresholds respectively.”
MethodInfluentialVision Based Gesture Recognition for Alphabetical Hand Gestures Using the SVM Classifier
Sultana, A., Tech, M., & Rajapuspha, T. (2012) · Cited by 16
A Survey of Extended Methods to the Bag of Visual Words for Image Categorization and Retrieval
Dammak, M., Mejdoub, M., & Amar, C. B. (2014) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004750506760683 · Cited by 16
Random interest regions for object recognition based on texture descriptors and bag of features
Nanni, L., Brahnam, S., & Lumini, A. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.07.097 · Cited by 15
Feature selection using visual saliency for content-based image retrieval
Zdziarski, Z., & Dahyot, R. (2012) · Irish Signals and Systems Conference · doi:10.1049/ic.2012.0194 · Cited by 16
A Video Text Detection and Tracking System
Yusufu, T., Wang, Y., & Fang, X. (2013) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2013.106 · Cited by 19
“Hessian matrix was used to compute the principal curvature and eliminate the false key points in SIFT algorithm, while SURF [17] makes use of integral images to efficiently compute a rough approximation of Hessian matrix.”
MethodTransferring spatial perception between robots operating in a shared workspace
Leitner, J., Harding, S., Frank, M., Förster, A., & Schmidhuber, J. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385642 · Cited by 18
Action recognition using 3D DAISY descriptor
Cao, X., Zhang, H., Deng, C., Liu, Q., & Liu, H. (2013) · Machine Vision and Applications · doi:10.1007/s00138-013-0545-6 · Cited by 17
“To deal with the additional temporal domain in a video, Scovanner et al. [31] extended the SIFT [21] to 3D SIFT , and Willems et al. [37] extended the SURF [3] descriptor to ESURF.”
BackgroundMethodA new moving objects detection method based on improved SURF algorithm
Pan, J., Chen, W., & Peng, W. (2013) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2013.6561051 · Cited by 16
Use of geometric features of principal components for indexing a biometric database
Jayaraman, U., Prakash, S., & Gupta, P. (2012) · Mathematical and Computer Modelling · doi:10.1016/j.mcm.2012.06.005 · Cited by 16
A statistical study of the correlation between interest points and gaze points
Nauge, M., Larabi, M., & Fernández-Maloigne, C. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.912089 · Cited by 16
Tolias, G., Kalantidis, Y., & Avrithis, Y. (2012) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2393347.2393379 · Cited by 16
Two-view matching with view synthesis revisited
Mishkin, D., Perďoch, M., & Matas, J. (2013) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2013.6727054 · Cited by 15
Semantic Kernels Binarized - A Feature Descriptor for Fast and Robust Matching
Zilly, F., Riechert, C., Eisert, P., & Kauff, P. P. (2011) · Conference on Visual Media Production · doi:10.1109/cvmp.2011.11 · Cited by 18
“We compared the runtime of SKB-A, SIFT, SURF, and BRIEF-256 descriptors when describing 8372 feature points.”
BackgroundMethodInfluentialEnhanced imaging colonoscopy facilitates dense motion-based 3D reconstruction
Alcantarilla, P. F., Bartoli, A., Chadebecq, F., et al. (2013) · doi:10.1109/embc.2013.6611255 · Cited by 16
Accurate image registration for MAP image super-resolution
Vrigkas, M., Nikou, C., & Kondi, L. P. (2013) · Signal Processing Image Communication · doi:10.1016/j.image.2012.12.008 · Cited by 16
Exploiting spatial overlap to efficiently compute appearance distances between image windows.
Alexe, B., Petrescu, V., & Ferrari, V. (2011) · Edinburgh Research Explorer (University of Edinburgh) · Cited by 17
Stanciu, S. G., Hristu, R., Boriga, R. E., & Stanciu, G. A. (2010) · Microscopy and Microanalysis · doi:10.1017/s1431927610000371 · Cited by 16
“Descriptor-based matching of local features extracted from different images containing similar objects or scenes can also provide the premises for object recognition ~ Lowe, 1999; Bay et al., 2006; Stanciu et al., 2009 !”
BackgroundLi, X., & Wang, J. (2012) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2012.6418946 · Cited by 16
Image based information access for mobile phones
Chen, X., Koskela, M., & Hyväkkä, J. (2010) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2010.5529886 · Cited by 24
Performance Analysis of Content-Based Identification Using Constrained List-Based Decoding
Farhadzadeh, F., Voloshynovskiy, S., & Koval, O. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2206026 · Cited by 16
PHOTOGRAMMETRIC MEASUREMENTS IN FIXED WING UAV IMAGERY
Gülch, E. (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-xxxix-b1-381-2012 · Cited by 16
Comparative analysis of invariant schemes for logo classification
Arafat, S. Y., Saleem, M., & Hussain, S. A. (2009) · International Conference on Emerging Technologies · doi:10.1109/icet.2009.5353163 · Cited by 16
Disparity search range estimation: Enforcing temporal consistency
Min, D., Yea, S., Arican, Z., et al. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5496135 · Cited by 16
A retargeting method for stereoscopic 3D video
Liu, Y., Sun, L., & Yang, S. (2015) · Computational Visual Media · doi:10.1007/s41095-015-0016-2 · Cited by 16
HEp-2 cell classification: The role of Gaussian Scale Space Theory as a pre-processing approach
Qi, X., Zhao, G., Chen, J., & Pietikäinen, M. (2015) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.12.011 · Cited by 20
“In the ICPR 2014 contest, Ensafi et al. [25] used Sparse Coding (SC) to encode the SIFT and SURF features, and Manivannan et al. [10] used the Localconstrained Linear Coding (LLC) [27] to encode four types of features.”
MethodA Precise Method for Cloth Configuration Parsing Applied to Single-Arm Flattening
Sun, L., Aragón-Camarasa, G., Khan, A., Rogers, S., & Siebert, P. (2016) · International Journal of Advanced Robotic Systems · doi:10.5772/62513 · Cited by 16
“Later, [23] they extend their work by removing the SURF [24] featurebased correspondence term and extending the boundary term.”
BackgroundA Picture is Worth a Thousand Words: Share Your Real-Time View on the Road
Wang, X., Ding, L., Wang, Q., et al. (2016) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2016.2592685 · Cited by 16
“[22] propose a speeded-up robust feature (SURF).”
Real-time, large-scale duplicate image detection method based on multi-feature fusion
Chen, M., Li, Y., Zhang, Z., Hsu, C., & Wang, S. (2016) · Journal of Real-Time Image Processing · doi:10.1007/s11554-016-0632-9 · Cited by 17
“[17] also proposed an accelerated algorithm for SIFT features: the speed-up robust feature (SURF).”
MethodMultimodal image matching using self similarity
Huang, J., You, S. O., & Zhao, J. (2011) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2011.6176359 · Cited by 16
A scene-based dependable indoor navigation system
Ko, D. W., Kim, Y. N., Lee, J. H., & Suh, I. H. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759248 · Cited by 17
Ancient Roman Coin Retrieval: A Systematic Examination of the Effects of Coin Grade
Fare, C., & Arandjelović, O. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-56608-5_32 · Cited by 16
“Most of these methods are local feature based, employing local feature descriptors such as SIFT [10] or SURF [11].”
MethodLocal image features matching for real-time seabed tracking applications
Żak, B., & Hożyń, S. (2017) · Journal of Marine Engineering & Technology · doi:10.1080/20464177.2017.1386266 · Cited by 18
Copy-Move Tampering Detection based on Local Binary Pattern Histogram Fourier Feature
Soni, B., Das, P. K., & Thounaojam, D. M. (2017) · International Conference on Computer and Communication Technology · doi:10.1145/3154979.3155001 · Cited by 16
“SIFT given by [11] and SURF given by [4] local features are widely used in key-points based copy-move forgery detection scheme.”
MethodReal-Time Video Stitching Using Camera Path Estimation and Homography Refinement
Yoon, J., & Lee, D. (2017) · Symmetry · doi:10.3390/sym10010004 · Cited by 16
Heterogeneous transfer learning techniques for machine learning
Iqbal, M. S., Luo, B., Khan, T., Mehmood, R., & Sadiq, M. (2018) · Iran Journal of Computer Science · doi:10.1007/s42044-017-0004-z · Cited by 16
Likitlersuang, J., Koh, R. G. L., Gong, X., Jovanovic, L. I., Bólivar-Tellería, I., Myers, M., Zariffa, J., & Márquez-Chin, C. (2018) · Topics in Spinal Cord Injury Rehabilitation · doi:10.1310/sci2403-265 · Cited by 21
An accurate retrieval through R-MAC+ descriptors for landmark recognition
Magliani, F., & Prati, A. (2018) · International Conference on Distributed Smart Cameras · doi:10.1145/3243394.3243686 · Cited by 20
“Also with the actual GPUs, it is possible to extract features faster than the old hand-crafted methods (like SIFT [15] and SURF [5]) [29].”
MethodResearch on optimization of image fast feature point matching algorithm
Wu, M. (2018) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-018-0354-y · Cited by 16
Robust visible-infrared image matching by exploiting dominant edge orientations
Chen, H., Xue, N., Zhang, Y., Lu, Q., & Xia, G.-S. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.10.036 · Cited by 18
Cebollada, S., Payá, L., Mayol-Cuevas, W. W., & Reinoso, Ó. (2019) · Applied Sciences · doi:10.3390/app9030377 · Cited by 16
Stereo Matching Methods for Imperfectly Rectified Stereo Images
Nguyen, P. H., & Ahn, C. W. (2019) · Symmetry · doi:10.3390/sym11040570 · Cited by 16
Wan, X., Liu, J. G., Li, S., et al. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2907933 · Cited by 16
Wang, J., Song, J., Zhao, L., et al. (2019) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2019.05.002 · Cited by 16
Wang, K., Kumar, V., Zeng, X., Koehl, L., Tao, X., & Chen, Y. (2019) · International Journal of Computational Intelligence Systems · doi:10.2991/ijcis.d.190704.002 · Cited by 21
“The traditional approaches such as HOG [30], SIFT [21], and SURF [31], which heavily dependent on the manually extracted features are not robust regarding the illumination conditions, image scale changes and image rotations.”
Pruning strategies for efficient online globally consistent mosaicking in fetoscopy
Tella-Amo, M., Peter, L., Shakir, D. I., et al. (2019) · Journal of medical imaging · doi:10.1117/1.jmi.6.3.035001 · Cited by 16
Yousefi, B., Sharifipour, H. M., Eskandari, M., Ibarra‐Castanedo, C., Laurendeau, D., Watts, R., Klein, M. T., & Maldague, X. (2019) · Electronics · doi:10.3390/electronics8111301 · Cited by 15
Split-Attention Multiframe Alignment Network for Image Restoration
Yu, Y., Liu, M., Feng, H., Xu, Z., & Li, Q. (2020) · IEEE Access · doi:10.1109/access.2020.2967028 · Cited by 15
“The registration algorithms involved in the comparison include SURF + homography, PWC-Net, our SAMANet and the combination of SAMANet and the proposed ghost removal modules WRDM and AFM.”
BackgroundMethodInfluentialLearning to find reliable correspondences with local neighborhood consensus
Wang, Y., Mei, X., Ma, Y., Huang, J., Fan, F., & Ma, J. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.04.016 · Cited by 16
Gurevich, I. B., & Yashina, V. V. (2020) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661820030086 · Cited by 16
A Siamese Network Utilizing Image Structural Differences For Cross-Category Defect Detection
Luan, C., Cui, R., Сун, Л., & Lin, Z. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9191128 · Cited by 17
RCPNet: Deep-Learning based Relative Camera Pose Estimation for UAVs
Yang, C., Liu, Y., & Zell, A. (2020) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas48674.2020.9214000 · Cited by 23
“Visual SLAM, as the mainstream of SLAM, estimates camera motion by extracting sparse keypoints (e.g., SIFT [1], SURF [2]) or directly from pixels as in dense SLAM systems [3], [4].”
BackgroundMünster, S., Maiwald, F., Lehmann, C. U., Lazariv, T., Hofmann, M., & Niebling, F. (2020) · Workshop on Structuring and Understanding of Multimedia heritAge Contents (SUMAC) · doi:10.1145/3423323.3425748 · Cited by 18
Fully Autonomous UAV-Based Action Recognition System Using Aerial Imagery
Han, P., & Razi, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-64556-4_22 · Cited by 15
Map3D: Registration-Based Multi-Object Tracking on 3D Serial Whole Slide Images
Deng, R., Yang, H., Jha, A., Lu, Y., Chu, P., Fogo, A. B., & Huo, Y. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3069154 · Cited by 17
“SURF [6] was employed in this study to improve initial alignment.”
MethodInfluentialAn Efficient System for Automatic Blood Type Determination Based on Image Matching Techniques
Odeh, N., Toma, A., Mohammed, F., et al. (2021) · Applied Sciences · doi:10.3390/app11115225 · Cited by 16
Out-of-boundary View Synthesis Towards Full-Frame Video Stabilization
Xu, Y., Zhang, J., & Tao, D. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00480 · Cited by 22
Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes
Song, W., Suganuma, M., Liu, X., Shimobayashi, N., Maruta, D., & Okatani, T. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00597 · Cited by 27
Gong, C., Li, J., Bhatti, U. A., et al. (2021) · Security and Communication Networks · doi:10.1155/2021/3084153 · Cited by 16
“[26] in 2006, which has the characteristics of rotation invariance, scale invariance, and strong real-time performance.”
BackgroundRetractedBeyond Learning: Back to Geometric Essence of Visual Odometry via Fusion-Based Paradigm
Jin, Y., Wei, N., Fu, M., Liu, H., & Zhang, W. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3121483 · Cited by 17
Research on Real-Time Disconnector State Evaluation Method Based on Multi-Source Images
Huang, S., Shang, B., Song, Y., Zhang, N., Wang, S., & Ning, S. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3137864 · Cited by 16
Gong, X., Yao, F., Ma, J., et al. (2022) · Remote Sensing · doi:10.3390/rs14112606 · Cited by 16
LiDAR Odometry by Deep Learning-Based Feature Points with Two-Step Pose Estimation
Liu, T., Wang, Y., Niu, X., Chang, L., Zhang, T., & Liu, J. (2022) · Remote Sensing · doi:10.3390/rs14122764 · Cited by 17
Nie, H., Fu, Z., Tang, B., Li, Z., Chen, S., & Wang, L. (2022) · Remote Sensing · doi:10.3390/rs14122946 · Cited by 22
Accelerating parallel digital image correlation computation with feature mesh interpolation
Chi, Y., & Pan, B. (2022) · Measurement · doi:10.1016/j.measurement.2022.111554 · Cited by 16
Mikulík, A., Radenović, F., Chum, O., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16808-1_9 · Cited by 16
Compact Local Directional Texture Pattern for Local Image Description
Zeng, H., Zhang, R., Huang, M., & Wang, X. (2015) · Advances in Multimedia · doi:10.1155/2015/360186 · Cited by 16
“Bay proposes SURF (Speeded Up Robust Features) descriptor, which speeds up the gradient computations using integral images [4].”
BackgroundEvaggelos Spyrou, A., Iakovidis, D. K., Niafas, S., & Koulaouzidis, A. (2015) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2015.05.013 · Cited by 21
“Contemporary feature extraction approaches [21,22] involve both the automatic detection of salient key-points within frames and the estimation of numeric descriptors from the neighborhood of each key-point.”
BackgroundMethodGeneralized Descriptor Compression for Storage and Matching
Johnson, M. (2010) · British Machine Vision Conference (BMVC) · doi:10.5244/c.24.23 · Cited by 15
“[2], and the GLOH descriptor proposed by Mikolajczyk and Schmid in [13].”
BackgroundMethodHuman-centric panoramic imaging stitching
Ozawa, T., Kitani, K., & Koike, H. (2012) · Augmented Human International Conference · doi:10.1145/2160125.2160145 · Cited by 17
Digital Libraries Applications: CBIR, Education, Social Networks, eScience/Simulation, and GIS
Fox, E. A., & Leidig, J. P. (2014) · Synthesis lectures on information concepts, retrieval, and services · doi:10.2200/s00565ed1v01y201401icr032 · Cited by 19
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.