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 1,401–1,500 of 14,752
New Verification Strategy for Finger-Vein Recognition System
Hsia, C. (2017) · IEEE Sensors Journal · doi:10.1109/jsen.2017.2772799 · Cited by 59
3D reconstruction of disaster scenes for urban search and rescue
Verykokou, S., Ioannidis, C., Athanasiou, G., Doulamis, N. D., & Amditis, A. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5450-y · Cited by 62
A spatial-spectral SIFT for hyperspectral image matching and classification
Li, Y., Li, Q., Liu, Y., & Xie, W. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.08.032 · Cited by 51
Learning Long-Term Temporal Features With Deep Neural Networks for Human Action Recognition
Yu, S., Xie, L., Liu, L., & Xia, D. (2019) · IEEE Access · doi:10.1109/access.2019.2962284 · Cited by 55
“Local features are effective tool in image recognition, which represent image through feature descriptors, such as Scale-Invariant Feature Transform (SIFT) [56], Speeded Up Robust Features (SURF) [57].”
MethodLv, Y., Zhang, X., Xiong, W., Cui, Y., & Cai, M. (2019) · Remote Sensing · doi:10.3390/rs11243006 · Cited by 55
Fully Automatic UAV Image-Based Sensor Orientation
Barazzetti, L., Remondino, F., Scaioni, M., et al. (2010) · Virtual Community of Pathological Anatomy (University of Castilla La Mancha) · Cited by 51
Undistorting the Past: New Techniques for Orthorectification of Archaeological Aerial Frame Imagery
Verhoeven, G., Sevara, C., Karel, W., Ressl, C., Doneus, M., & Briese, C. (2013) · Natural science in archaeology · doi:10.1007/978-3-319-01784-6_3 · Cited by 79
Training a Convolutional Neural Network for Appearance-Invariant Place RecognitionPreprint
Gomez-Ojeda, R., López-Antequera, M., Petkov, N., & González-Jiménez, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.07428 · Cited by 70
Wang, K., Liu, Y., & Li, L. (2015) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2015.2403471 · Cited by 50
“To improve the robustness of the controller, the simple unpredictable random function features [11] are used.”
MethodAttentive Deep Stitching and Quality Assessment for 360$^{\circ }$ Omnidirectional Images
Li, J., Zhao, Y., Ye, W., Yu, K., & Ge, S. (2019) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2953950 · Cited by 56
“Some classical feature detectors [12], [13] usually perform well on conventional planar natural images but may lack invariant properties in handling dual-fisheye images, which may cause distortions or shape breakages in stitching regions.”
BackgroundDRONET: Multi-Tasking Framework for Real-Time Industrial Facility Aerial Surveillance and Safety
Ajakwe, S. O., Ihekoronye, V. U., Kim, D., & Lee, J. (2022) · Drones · doi:10.3390/drones6020046 · Cited by 56
A Novel Approach for UAV Image Crack Detection
Li, Y., Ma, J., Zhao, Z., & Shi, G. (2022) · Sensors · doi:10.3390/s22093305 · Cited by 56
SoccerTrack: A Dataset and Tracking Algorithm for Soccer with Fish-eye and Drone Videos
Scott, A., Uchida, I., Onishi, M., Kameda, Y., Fukui, K., & Fujii, K. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00401 · Cited by 74
CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation
Moreau, A., Piasco, N., Bennehar, M., Tsishkou, D., Stanciulescu, B., & Fortelle, A. D. L. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00030 · Cited by 92
“While hand-crafted descriptors such as SIFT [21, 22] and SURF [5] have known great success, the focus has shifted in recent years to learn features extraction from large amounts of visual data.”
BackgroundA systematic survey of public computer vision datasets for precision livestock farming
Bhujel, A., Wang, Y., Lu, Y., Morris, D., & Dangol, M. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.109718 · Cited by 81
Fast and accurate surface alignment through an isometry-enforcing game
Albarelli, A., Rodolà, E., & Torsello, A. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.01.020 · Cited by 50
Fast geometric re-ranking for image-based retrieval
Tsai, S. S., Chen, D., Takacs, G., et al. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5648942 · Cited by 50
“By representing images or objects using sets of local features [7, 8, 9], recognition can be achieved by matching features between the query image and candidate database image.”
BackgroundMethodBAUM-2: a multilingual audio-visual affective face database
Erdem, Ç. E., Turan, C., & Aydın, Z. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-1986-2 · Cited by 55
Fast and robust passive copy-move forgery detection using SURF and SIFT image features
Pandey, R. C., Singh, S. K., Shukla, K. K., & Agrawal, R. (2014) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciinfs.2014.7036519 · Cited by 49
Rank Preserving Sparse Learning for Kinect Based Scene Classification
Tao, D., Jin, L., Zhao, Y., & Li, X. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2013.2264285 · Cited by 47
Dense SIFT and Gabor descriptors-based face representation with applications to gender recognition
Wang, J.-G., Li, J., Lee, C. Y., & Yau, W. (2010) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2010.5707370 · Cited by 61
“SURF [31] or Daisy [26], which aims to speed up the computation of the dense local descriptors.”
InfluentialDeformation and illumination invariant feature point descriptor
Moreno-Noguer, F. (2011) · 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.2011.5995529 · Cited by 56
“Since it is relatively slow to compute, most of the subsequent works have focused in developing faster descriptors [1, 6, 10, 17, 24].”
BackgroundPoint cloud matching based on 3D self-similarity
Huang, J., & You, S. O. (2012) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2012.6238913 · Cited by 51
Vision-based high-speed manipulation for robotic ultra-precise weed control
Michaels, A., Haug, S., & Albert, A. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354156 · Cited by 50
“Using OpenCV’s SURF features implementation [23] and ’brute force’ matcher we estimated the homography between the reference image and the actual camera image to apply position based visual servoing (PBVS).”
MethodLiu, L.-C., Fang, C.-Y., & Chen, S.-W. (2016) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2016.2597299 · Cited by 55
Multiple-Oriented and Small Object Detection with Convolutional Neural Networks for Aerial Image
Chen, C., Zhong, J., & Tan, Y. (2019) · Remote Sensing · doi:10.3390/rs11182176 · Cited by 54
Corner Detection Using Second-Order Generalized Gaussian Directional Derivative Representations
Zhang, W., & Sun, C. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2949302 · Cited by 50
Hasheminasab, S. M., Zhou, T., & Habib, A. F. (2020) · Remote Sensing · doi:10.3390/rs12030351 · Cited by 53
Attend and Guide (AG-Net): A Keypoints-Driven Attention-Based Deep Network for Image Recognition
Bera, A., Wharton, Z., Liu, Y., Bessis, N., & Behera, A. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3064256 · Cited by 58
Copy Move Forgery Detection based on double matching
Lyu, Q., Luo, J., Liu, K., Yin, X., Liu, J., & Lu, W. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103057 · Cited by 56
An Efficient Insect Pest Classification Using Multiple Convolutional Neural Network Based Models
Ung, H. T., Ung, H. Q., Nguyễn, T. T., & Nguyen, B. T. (2022) · Frontiers in artificial intelligence and applications · doi:10.3233/faia220287 · Cited by 52
Okuyama, K., & Yanai, . (2012) · Springer eBooks · doi:10.1007/978-1-4614-3501-3_54 · Cited by 51
“As local features, we use SURF (Speeded-Up Robust Features) [3].”
MethodParticle Filter SLAM with High Dimensional Vehicle Model
Törnqvist, D., Schön, T. B., Karlsson, R., & Gustafsson, F. (2009) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-008-9301-y · Cited by 53
PUnDA: Probabilistic Unsupervised Domain Adaptation for Knowledge Transfer Across Visual Categories
Gholami, B., Rudovic, O. O., & Pavlović, V. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.387 · Cited by 50
Sanín, C., Zhang, H., Shafiq, S. I., Waris, M. M., de Oliveira, C. S., & Szczerbicki, E. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2018.01.062 · Cited by 54
An IoT-Based Anti-Counterfeiting System Using Visual Features on QR Code
Yan, Y., Zou, Z., Xie, H., Gao, Y., & Zheng, L. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3035697 · Cited by 60
“Speeded up robust feature (SURF) [29] accelerates this process by approximating the determinant of the Hessian matrix with box filters.”
MethodVS-Net: Voting with Segmentation for Visual Localization
Huang, Z., Zhou, H., Li, Y., Yang, B., Xu, Y., Zhou, X., Bao, H., Zhang, G., & Li, H. (2021) · 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/cvpr46437.2021.00604 · Cited by 68
A robust registration method for UAV thermal infrared and visible images taken by dual-cameras
Meng, L., Zhou, J. P., Liu, S., Wang, Z., Zhang, X., Ding, L., Shen, L., & Wang, S. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.08.018 · Cited by 54
Trivedi, J. D., Devi, M. S., & Solanki, B. (2023) · Archives for Technical Sciences · doi:10.59456/afts.2023.1528.039j · Cited by 49
Multimodal Remote Sensing Image Matching Based on Weighted Structure Saliency Feature
Wan, G., Ye, Z., Xu, Y., Huang, R., Zhou, Y., Xie, H., & Tong, X. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3347259 · Cited by 71
Deep Multiview Clustering by Pseudo-Label Guided Contrastive Learning and Dual Correlation Learning
Hu, S., Zhang, C., Zou, G., Lou, Z., & Ye, Y. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3354731 · Cited by 87
“Two features are adopted for representation, i.e., SIFT [29] and SURF [30] feature.”
RelPose++: Recovering 6D Poses from Sparse-view Observations
Lin, A., Zhang, J. Y., Ramanan, D., & Tulsiani, S. (2024) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv62453.2024.00126 · Cited by 111
“The classic SfM and SLAM pipelines for pose estimation from sets of images or video streams involve computing matches [23] between discriminative hand-crafted local features [2, 22].”
BackgroundMethodA computer vision based framework for visual gun detection using SURF
Tiwari, R. K., & Verma, G. K. (2015) · International Conference on Electrical, Electronics, Signals, Communication and Optimization · doi:10.1109/eesco.2015.7253863 · Cited by 51
“There are two contributions of our visual gun detection framework- first one is that there has been no other research work on visual gun detection (to the best knowledge of authors) and second it can detect multiple objects in the images unlike any other point detector such as SIFT [5], SURF [6], BRISK [7] etc.”
Cloud-based realtime robotic Visual SLAM
Benavidez, P. J., Muppidi, M., Rad, P., Prevost, J. J., Jamshidi, M. M., & Endowed, L. B. (2015) · IEEE International Systems Conference (SysCon) · doi:10.1109/syscon.2015.7116844 · Cited by 53
“[4] E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, "ORB: An efficient alternative to SIFT or SURF," in Computer Vision (ICCV), 2011 IEEE International Conference on, 2011, pp. 2564-2571.”
MethodMobile Museum Guide Based on Fast SIFT Recognition
Ruf, B., Kokiopoulou, E., & Detyniecki, M. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-14758-6_14 · Cited by 59
“Although the SURF algorithm is faster than the SIFT one, for low resolution images SURF’s performance is unacceptable.”
MethodInfluentialEfficient Visual Object Tracking with Online Nearest Neighbor Classifier
Gu, S., Zheng, Y., & Tomasi, C. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19315-6_21 · Cited by 56
Schoeffmann, K., Taschwer, M., & Boeszoermenyi, L. (2010) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/1730836.1730867 · Cited by 54
“SURF[3] for the ROI search.”
Robust RGB-D simultaneous localization and mapping using planar point features
Gao, X., & Zhang, T. (2015) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2015.03.007 · Cited by 56
Underwater SLAM: Challenges, state of the art, algorithms and a new biologically-inspired approach
Guth, F., Silveira, L., Botelho, S. S. D. C., Drews, P., & Ballester, P. L. (2014) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob.2014.6913908 · Cited by 63
“The image features are detected using Bag of Features [36] of SURF descriptors.”
MethodInfluentialError propagations for local bundle adjustment
Eudes, A., & Lhuillier, M. (2009) · 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.2009.5206824 · Cited by 63
Feature extraction for underwater visual SLAM
Aulinas, J., Carreras, M., Lladó, X., Salví, J., García, R., Prados, R., & Pétillot, Y. (2011) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans-spain.2011.6003474 · Cited by 79
“More robust approaches are SIFT [23] and more recently SURF [24], which produce rotation and scale invariant features.”
MethodBayesian Tracking for Video Analytics
Dore, A., Soto, M., & Regazzoni, C. S. (2010) · IEEE Signal Processing Magazine · doi:10.1109/msp.2010.937395 · Cited by 56
Shapira, D., Avidan, S., & Hel-Or, Y. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738468 · Cited by 50
Adaptive spatial pooling for image classification
Liu, Y., Zhang, Y., Zhang, X.-Y., & Liu, C. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.01.030 · Cited by 53
3D terrain reconstruction of construction sites using a stereo camera
Sung, C.-H., & Kim, P. Y. (2016) · Automation in Construction · doi:10.1016/j.autcon.2015.12.022 · Cited by 56
Augmented-Reality Survey: from Concept to Application
Kim, S. K., Kang, S.-J., Choi, Y.-J., Choi, M., & Hong, M. (2017) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2017.02.019 · Cited by 70
“The representative feature descriptors include SIFT [32], SURF [33], BRIEF [34], ORB [35], and FERNs[36].”
MethodAn application of pre-trained CNN for image classification
Abdullah, & Hasan, M. S. (2017) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccitechn.2017.8281779 · Cited by 53
Sensors, SLAM and Long-term Autonomy: A Review
Zaffar, M., Ehsan, S., Stolkin, R., & Maier, K. M. (2018) · NASA/ESA Conference on Adaptive Hardware and Systems (AHS) · doi:10.1109/ahs.2018.8541483 · Cited by 72
Fine-Grained Grocery Product Recognition by One-Shot Learning
Geng, W., Han, F., Lin, J., Zhu, L., Bai, J., Wang, S., He, L., Xiao, Q., & Lai, Z. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240522 · Cited by 62
Feature-Level Domain AdaptationPreprint
Kouw, W. M., Krijthe, J. H., Loog, M., & van der Maaten, L. J. P. (2015) · Journal of Machine Learning Research · doi:10.5555/2946645.3053453 · Cited by 65
Prototyping a Social Media Flooding Photo Screening System Based on Deep Learning
Ning, H., Li, Z., Hodgson, M. E., & Wang, C. (2020) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi9020104 · Cited by 48
A multimodal computational pipeline for 3D histology of the human brain
Mancini, M., Casamitjana, A., Peter, L., Robinson, E., Crampsie, S., Thomas, D. L., Holton, J. L., Jaunmuktane, Z., & Iglesias, J. E. (2020) · Scientific Reports · doi:10.1038/s41598-020-69163-z · Cited by 52
“The microtome reference is registered to the block reference to propagate the 236 location of the cassette corners as follows: (i) we compute salient points and SURF features [64] 237 on both images, and discard those outside the checkerboard in the microtome reference; (ii) 238 we match the salient points; (iii) we u…”
Xia, Z., Wang, X., Wang, C., Ma, B., Wang, M., & Shi, Y.-Q. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106568 · Cited by 51
Graph-Based Thermal–Inertial SLAM With Probabilistic Neural Networks
Saputra, M. R. U., Lu, C. X., de Gusmão, P. P. B., Wang, B., Markham, A., & Trigoni, N. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3120036 · Cited by 62
Inverted Index Compression for Scalable Image Matching
Chen, D. M., Tsai, S. S., Chandrasekhar, V., et al. (2010) · DCC · doi:10.1109/dcc.2010.53 · Cited by 49
RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous DrivingPreprint
Li, P., Zhao, H., Liu, P., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.03343 · Cited by 49
“The SIFT, SUFT and other traditional keypoint detection methods [26, 1]computed an image pyramid to solve the scaleinvariant problem.”
BackgroundMethodA robust hashing algorithm based on SURF for video copy detection
Yang, G., Chen, N., & Jiang, Q. (2012) · Computers & Security · doi:10.1016/j.cose.2011.11.004 · Cited by 48
Feature Combination and the kNN Framework in Object Classification
Hou, J., Gao, H., Xia, Q., & Qi, N. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2461552 · Cited by 51
Pose-invariant face recognition using facial landmarks and Weber local descriptor
Zhang, Z., Wang, L., Zhu, Q., Chen, S.-K., & Chen, Y. (2015) · Knowledge-Based Systems · doi:10.1016/j.knosys.2015.04.003 · Cited by 50
Shape Reconstruction Using Volume Sweeping and Learned Photoconsistency
Leroy, V., Franco, J.-S., & Boyer, E. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01240-3_48 · Cited by 63
“For broader geometric and photometric resilience, various features based on scale-invariant gradient characterizations [23, 2, 26] have been designed, some specialized for the dense matching required for the MVS problem [36].”
BackgroundA case for using rotation invariant features in state of the art feature matchers
Bökman, G., & Kahl, F. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00559 · Cited by 81
Hybrid CLAHE-CNN Deep Neural Networks for Classifying Lung Diseases from X-ray Acquisitions
Hussein, F., Mughaid, A. S., AlZu’bi, S. M. F., El-Salhi, S., Abuhaija, B., Abualigah, L., & Gandomi, A. H. (2022) · Electronics · doi:10.3390/electronics11193075 · Cited by 57
A systematic literature review on long‐term localization and mapping for mobile robots
Sousa, R. B., Sobreira, H., & Moreira, A. P. (2023) · Journal of Field Robotics · doi:10.1002/rob.22170 · Cited by 68
FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network
Wang, X., Liu, Z., Hu, Y., Xi, W., Yu, W., & Zou, 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/cvpr52729.2023.00737 · Cited by 64
“A lot of descriptors have been developed, including hand-crafted methods such as ORB [34], SURF [4], and SIFT [24], as well as more advanced learning-based methods such as SuperPoint [10].”
MethodORB feature based web pornographic image recognition
Li, Z., Geng, Z., Zhang, J., & Li, X. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.06.055 · Cited by 55
“Therefore, a variety of fast local feature extraction algorithms have been proposed, such as Speeded Up Robust Features(SURF)[16], Oriented FAST ([17])and Rotated BRIEF [18] (ORB) etc.”
MethodImage-based indoor positioning system
Kawaji, H., Hatada, K., Yamasaki, T., & Aizawa, K. (2010) · doi:10.1145/1878039.1878041 · Cited by 48
Coherent bag-of audio words model for efficient large-scale video copy detection
Liu, Y., Zhao, W., Ngo, C., Xu, C., & Lu, H. (2010) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1816041.1816057 · Cited by 49
“Most frame-level approaches extract local interest point descriptor as visual feature, which is more discriminative than global feature and has achieved significant result [6][7].”
BackgroundImproving Sparse 3D Models for Man-Made Environments Using Line-Based 3D Reconstruction
Hofer, M., Maurer, M., & Bischof, H. (2014) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2014.14 · Cited by 47
“Most of these Structure-from-Motion (SfM) approaches are based on detecting and matching distinctive keypoints over several images, by using invariant descriptors such as SIFT [18] or SURF [3].”
BackgroundTowards ubiquitous indoor localization service leveraging environmental physical features
Yang, T., Gao, R., Bian, K., Ye, F., Wang, T., Wang, Y., & Li, X. (2014) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2014.6847924 · Cited by 51
Spatio-temporal feature-based keyframe detection from video shots using spectral clustering
Vázquez-Martín, R., & Bandera, A. J. (2012) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.12.009 · Cited by 47
SURFing the point clouds: Selective 3D spatial pyramids for category-level object recognition
Redondo-Cabrera, C., López-Sastre, R. J., Acevedo-Rodríguez, F. J., & Maldonado-Bascón, 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.2012.6248087 · Cited by 48
3D Scene Reconstruction for Robotic Bridge Inspection
Lattanzi, D., & Miller, G. R. (2014) · Journal of Infrastructure Systems · doi:10.1061/(asce)is.1943-555x.0000229 · Cited by 48
Fast Computation of Rotation-Invariant Image Features by an Approximate Radial Gradient Transform
Gabriel Takacs, A., Chandrasekhar, V., Tsai, S. S., Chen, D., Grzeszczuk, R., & Girod, B. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2230011 · Cited by 48
New hybrid vision-based control approach for automated guided vehicles
Miljković, Z., Vuković, N. L., Mitić, M., & Babić, B. (2012) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-012-4321-y · Cited by 48
“It relies on usage of simple camera and well-known algorithms for extraction of image features [3, 48].”
BackgroundMethodWeighted Component Hashing of Binary Aggregated Descriptors for Fast Visual Search
Duan, L., Lin, J., Wang, Z., Huang, T., & Gao, W. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2419973 · Cited by 49
A realistic benchmark for visual indoor place recognition
Pronobis, A., Caputo, B., Jensfelt, P., & Christensen, H. I. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2009.07.025 · Cited by 55
Two Novel Detector-Descriptor Based Approaches for Face Recognition Using SIFT and SURF
Vinay, A., Hebbar, D., Shekhar, V. S., Murthy, K. N. B., & Natarajan, S. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.10.070 · Cited by 62
A fast and efficient image retrieval system based on color and texture features
Singh, C., & Kaur, K. P. (2016) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2016.10.002 · Cited by 52
HNIP: Compact Deep Invariant Representations for Video Matching, Localization, and Retrieval
Lin, J., Duan, L., Wang, S., Bai, Y., Lou, Y., Chandrasekhar, V., Huang, T., Kot, A. C., & Gao, W. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2713410 · Cited by 48
Product Recognition in Store Shelves as a Sub-Graph Isomorphism Problem
Tonioni, A., & Stefano, L. D. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68560-1_61 · Cited by 57
Automated Point Cloud Registration Using Visual and Planar Features for Construction Environments
Kim, P., Chen, J., & Cho, Y. K. (2017) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000720 · Cited by 48
Learning domain-shared group-sparse representation for unsupervised domain adaptation
Yang, B., Ma, A. J., & Yuen, P. C. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.04.027 · Cited by 50
Action recognition using spatial-optical data organization and sequential learning framework
Yuan, Y., Zhao, Y., & Wang, Q. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.06.071 · Cited by 48
Hidden Object Detection and Recognition in Passive Terahertz and Mid-wavelength Infrared
Kowalski, M. (2019) · Journal of Infrared Millimeter and Terahertz Waves · doi:10.1007/s10762-019-00628-7 · Cited by 49
Roadmap to High Throughput Phenotyping for Plant Breeding
Kim, J. Y. (2020) · Journal of Biosystems Engineering · doi:10.1007/s42853-020-00043-0 · Cited by 46
“…et al. 2009; Fattal et al. 2002; Levin et al. 2004) and image features such as scale invariant feature transform (SIFT) (Lowe 2004; Reddy and Chatterji 1996; Yang and Guo 2008), speeded up robust features (SURF) (Bay et al. 2006), and principal component analysis (PCA) (Ke and Sukthankar 2004).”
Influential3D‐Printed Microrobots with Integrated Structural Color for Identification and Tracking
Koepele, C. A., Guix, M., Bi, C., Adam, G., & Cappelleri, D. J. (2020) · Advanced Intelligent Systems · doi:10.1002/aisy.201900147 · Cited by 49
Learning Camera Localization via Dense Scene Matching
Tang, S., Tang, C., Huang, R., Zhu, S., & Tan, P. (2021) · 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/cvpr46437.2021.00187 · Cited by 70
Chen, Q., Yang, H., Mars, J., & Tang, L. (2016) · ACM SIGPLAN Notices · doi:10.1145/2954679.2872368 · Cited by 49
High resolution visual terrain classification for outdoor robots
Khan, Y. N., Komma, P., & Zell, A. (2011) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2011.6130362 · Cited by 56
Incremental spectral clustering and seasons: Appearance-based localization in outdoor environments
Valgren, C., & Lilienthal, A. J. (2008) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2008.4543477 · Cited by 48
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.