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 1,001–1,100 of 14,752
Batik Classification using Deep Convolutional Network Transfer Learning
Gultom, Y., Arymurthy, A. M., & Masikome, R. J. (2018) · Jurnal Ilmu Komputer dan Informasi · doi:10.21609/jiki.v11i2.507 · Cited by 73
Toward Deep Transfer Learning in Industrial Internet of Things
Liu, X., Yu, W., Liang, F., GRIFFITH, D. W. T., & Golmie, N. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3062482 · Cited by 76
Wang, Q., Zhang, K., & Manjotho, A. A. (2022) · IEEE Access · doi:10.1109/access.2022.3164711 · Cited by 84
“(HOG) [5], Speeded Up Robust Feature (SURF) [6] and Scale-Invariant Feature Transform (SIFT) [7] as features to extract discriminative dependencies.”
BackgroundUnsupervised Homography Estimation with Coplanarity-Aware GAN
Hong, M., Lu, Y., Ye, N., Lin, C., Zhao, Q., & Liu, S. (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/cvpr52688.2022.01714 · Cited by 87
“Classic feature extraction methods include SIFT [22], SURF [2, 3], ORB [26], LPM [23], GMS [4], BEBLID [29] etc.”
Image dataset development for measuring construction equipment recognition performance
Tajeen, H., & Zhu, Z. (2014) · Automation in Construction · doi:10.1016/j.autcon.2014.07.006 · Cited by 79
Manweiler, J., Jain, P. K., & Choudhury, R. R. (2012) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/2307636.2307656 · Cited by 69
“First, SfM accepts multiple photos from the user, and on each photo, runs an algorithm known as a feature detector [1, 11, 15].”
MethodAccurate and robust localization of duplicated region in copy–move image forgery
Jaberi, M., Bebis, G. N., Hussain, M., & Muhammad, G. (2013) · Machine Vision and Applications · doi:10.1007/s00138-013-0522-0 · Cited by 69
“Speeded up robust features (SURF) [36] speeds-up computations using a fast approximation of the Hessian matrix and “integral images”.”
MethodHolt, J., Allen, J. I., Anderson, T. R., Brewin, R. J. W., Butenschön, M., Harle, J. D., Huse, G., Lehodey, P., Lindemann, C., Mémery, L., et al. (2014) · Progress In Oceanography · doi:10.1016/j.pocean.2014.04.024 · Cited by 78
Dynamic Feature Learning for Partial Face Recognition
He, L., Li, H., Zhang, Q., & Sun, Z. (2018) · 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.2018.00737 · Cited by 78
“[37] propose a Robust Point Set Matching (RPSM) method based on SIFT descriptor, SURF descriptor [2] and LBP [1] histogram for partial face matching.”
MethodImage annotation: Then and now
Bhagat, P. K., & Choudhary, P. (2018) · Image and Vision Computing · doi:10.1016/j.imavis.2018.09.017 · Cited by 72
Spatial Uncertainty Model for Visual Features Using a Kinect™ Sensor
Park, J., Shin, Y.-D., Bae, J., & Baeg, M.-H. (2012) · Sensors · doi:10.3390/s120708640 · Cited by 68
Sextant: Towards Ubiquitous Indoor Localization Service by Photo-Taking of the Environment
Gao, R., Yang, T., Ye, F., Luo, G., Bian, K., Wang, Y., Wang, T., & Li, X. (2015) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2015.2418205 · Cited by 68
Wang, R., Shi, Y., & Cao, W. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.11.001 · Cited by 68
Advances in Computer Vision: Proceedings of the 2019 Computer Vision Conference (CVC), Volume 1
O’Mahony, N., Campbell, S., Carvalho, A., Harapanahalli, S., Velasco-Hernandez, G., Krpálková, L., Riordan, D., & Walsh, J. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-17795-9 · Cited by 104
“Traditionally, from the perspective of signal processing, we know the operational connotations of CV algorithms such as SIFT and SURF methods, but DL leads such meaning nowhere, all you need is more data.”
InfluentialTemporal Context Aggregation for Video Retrieval with Contrastive Learning
Shao, J., Wen, X., Zhao, B., & Xue, X. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00331 · Cited by 91
Puniach, E., Gruszczyński, W., Ćwiąkała, P., & Matwij, W. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.02.006 · Cited by 75
Deep-seated features histogram: A novel image retrieval method
Liu, G., & Yang, J.-Y. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107926 · Cited by 73
From SLAM to Situational Awareness: Challenges and Survey
Bavle, H., Sánchez-López, J. L., Cimarelli, C., Tourani, A., & Voos, H. (2023) · Sensors · doi:10.3390/s23104849 · Cited by 108
Kidney Tumor Semantic Segmentation Using Deep Learning: A Survey of State-of-the-Art
Abdelrahman, A., & Viriri, S. (2022) · Journal of Imaging · doi:10.3390/jimaging8030055 · Cited by 81
Albattah, W., Masood, M., Javed, A., Nawaz, M., & Albahli, S. (2022) · Complex & Intelligent Systems · doi:10.1007/s40747-022-00847-x · Cited by 77
A Survey of 6DoF Object Pose Estimation Methods for Different Application Scenarios
Guan, J., Hao, Y., Wu, Q., Li, S., & Fang, Y. (2024) · Sensors · doi:10.3390/s24041076 · Cited by 115
XoFTR: Cross-modal Feature Matching Transformer
Tuzcuoğlu, Ö., Köksal, A., Sofu, B., Kalkan, S., & Alatan, A. A. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00431 · Cited by 154
“Following the success of [9, 12, 54, 61], handcrafted methods used to be popular before the rise of deep learning based techniques [25, 70, 84].”
MethodVision-Aided Inertial Navigation Based on Ground Plane Feature Detection
Panahandeh, G., & Jansson, M. (2013) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2013.2276404 · Cited by 72
“To get closer to real time, the speeded up robust features (SURF) [45], which is invariant to image scale, viewing angle, and viewing condition, has been used for extracting image feature descriptors.”
MethodInfluentialUSB: Ultrashort Binary Descriptor for Fast Visual Matching and Retrieval
Zhang, S. S., Tian, Q., Huang, Q., Gao, W., & Rui, Y. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2330794 · Cited by 73
Leveraging 3D City Models for Rotation Invariant Place-of-Interest Recognition
Baatz, G., Köser, K., Chen, D. M., Grzeszczuk, R., & Pollefeys, M. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-011-0458-7 · Cited by 69
kNN based image classification relying on local feature similarity
Amato, G. M., & Falchi, F. (2010) · doi:10.1145/1862344.1862360 · Cited by 68
Improved human detection and classification in thermal images
Wang, W., Zhang, J., & Shen, C. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5649946 · Cited by 79
“In the training phase, they used a combination of multiple cues to find interest points in the images and use SURF (Speed Up Robust Features) [6] as features to describe these points.”
MethodTowards simultaneous recognition, localization and mapping for hand-held and wearable cameras
Castle, R. O., Gawley, D. J., Klein, G., & Murray, D. W. (2007) · Proceedings 2007 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2007.364109 · Cited by 68
Doush, I. A., & AL-Btoush, S. (2016) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2016.06.003 · Cited by 68
“Although many alternative algorithms to SIFT have been designed, such as SURF (Bay et al., 2006), it is still used by several researchers (Lin and Zhao, 2008).”
Mobile augmented reality survey: a bottom-up approachPreprint
Huang, Z., Hui, P., Peylo, C., & Chatzopoulos, D. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1309.4413 · Cited by 90
Large-Area Photo-Mosaics Using Global Alignment and Navigation Data
Ferrer, J., Elibol, A., Delaunoy, O., Gracias, N., & Garcia, R. (2007) · OCEANS 2007 · doi:10.1109/oceans.2007.4449367 · Cited by 67
Object Learning Through Active Exploration
Ivaldi, S., Nguyen, S. M., Lyubova, N., Droniou, A., Padois, V., Filliat, D., Oudeyer, P., & Sigaud, O. (2014) · IEEE Transactions on Autonomous Mental Development · doi:10.1109/tamd.2013.2280614 · Cited by 79
Global visual localization in LiDAR-maps through shared 2D-3D embedding space
Cattaneo, D., Vaghi, M., Fontana, S., Ballardini, A. L., & Sorrenti, D. G. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196859 · Cited by 92
Swapped face detection using deep learning and subjective assessment
Ding, X., Raziei, Z., Larson, E. C., Olinick, E. V., Krueger, P., & Hahsler, M. (2020) · EURASIP Journal on Information Security · doi:10.1186/s13635-020-00109-8 · Cited by 71
“They used sped up robust features (SURF) [4] and Bag of Words (BoW) to create image features instead of using raw pixels.”
MethodBakour, K., & Ünver, H. M. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05195-w · Cited by 77
“[32] This algorithm was introduced as an alternative to the SIFT algorithm because the SIFT algorithm is fairly slow.”
MethodBurlingame, E. A., McDonnell, M., Schau, G. F., Thibault, G., Lanciault, C., Morgan, T. K., Johnson, B., Corless, C. L., Gray, J. W., & Chang, Y. H. (2020) · Scientific Reports · doi:10.1038/s41598-020-74500-3 · Cited by 74
P$$^{2}$$Net: Patch-Match and Plane-Regularization for Unsupervised Indoor Depth Estimation
Yu, Z., Jin, L., & Gao, S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58586-0_13 · Cited by 91
Chen, Z., Liu, X., Kojima, M., Huang, Q., & Arai, T. (2021) · Sensors · doi:10.3390/s21041536 · Cited by 84
A Comprehensive Study of 3-D Vision-Based Robot Manipulation
Cong, Y., Chen, R., Ma, B., Liu, H., Hou, D., & Yang, C. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3108165 · Cited by 99
Schmalstieg, D., Langlotz, T., & Billinghurst, M. (2010) · Springer eBooks · doi:10.1007/978-3-211-99178-7_2 · Cited by 68
Region Duplication Forgery Detection Technique Based on SURF and HAC
Mishra, P., Mishra, N., Sharma, S., & Patel, R. (2013) · The Scientific World JOURNAL · doi:10.1155/2013/267691 · Cited by 68
Region-Based Object Recognition by Color Segmentation Using a Simplified PCNN
Chen, Y.-L., Ma, Y., Kim, D. H., & Park, S.-K. (2014) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2014.2351418 · Cited by 70
Outsourceable two-party privacy-preserving biometric authentication
Hu, C., Elmehdwi, Y., Li, F., Bhattacharya, P., & Jiang, W. (2014) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/2590296.2590343 · Cited by 69
“Several types of local descriptors have been proposed in the literature [3, 28, 32, 42, 49].”
BackgroundMethodDistributed Sensor Perception via Sparse Representation
Yang, A. Y., Gastpar, M., Bajcsy, R., & Sastry, S. (2010) · Proceedings of the IEEE · doi:10.1109/jproc.2010.2040797 · Cited by 67
“In computer vision, a sparse representation can be defined to concisely quantize the 2-D appearance of an object in vector form, which is called a SIFT (scale-invariant feature transform) histogram [34], [35].”
BackgroundLearning spatially semantic representations for cognitive robot navigation
Kostavelis, I., & Gasteratos, A. C. (2013) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2013.07.008 · Cited by 66
A framework for analysis of linear ultrasound videos to detect fetal presentation and heartbeat
Maraci, M. A., Bridge, C. P., Napolitano, R., Papageorghiou, A., & Noble, J. A. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.01.003 · Cited by 65
Image recognition performance enhancements using image normalization
Koo, K.-M., & Cha, E.-Y. (2017) · Human-centric Computing and Information Sciences · doi:10.1186/s13673-017-0114-5 · Cited by 81
“For instance, features such as SIFT [1, 2], SURF [3], BRIEF [4], ORB [5], MSER [6, 7] or the image of the region (or object) estimated by a saliency map [8] or selective search [9] are learned and recognized using the convolutional neural networks (CNN).”
MethodOkayasu, K., Yoshida, K., Fuchida, M., & Nakamura, A. (2019) · Applied Sciences · doi:10.3390/app9183935 · Cited by 73
Neural networks for facial age estimation: a survey on recent advances
Punyani, P., Gupta, R., & Kumar, A. (2019) · Artificial Intelligence Review · doi:10.1007/s10462-019-09765-w · Cited by 71
“SURF descriptor consists of a few steps.”
MethodInfluentialDeepVO: A Deep Learning approach for Monocular Visual Odometry
Mohanty, V., Agrawal, S., Datta, S., Ghosh, A., Sharma, V. D., & Chakravarty, D. (2016) · arXiv · doi:10.48550/arxiv.1611.06069 · Cited by 67
“A standard Visual Odometry approach generally follows the following steps (for both monocular and stereo vision cases) [24] : 1) Image acquisition at two time instances 2) Image correction such as rectification and lens distortion removal 3) Feature detection in the two images (such as corners using SURF [2], ORB [35]…”
MethodReal-time indoor scene understanding using Bayesian filtering with motion cues
Tsai, G., Xu, C., Liu, J., & Kuipers, B. J. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126233 · Cited by 66
“Any method can be used but in this paper, we use KLT [20] tracking because it is more efficient than SIFT [15] and SURF [2], and it works well in our experiments.”
MethodEfficient region search for object detection
Vijayanarasimhan, S., & Grauman, K. L. (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.2011.5995545 · Cited by 73
Tissue Tracking and Registration for Image-Guided Surgery
Yip, M. C., Lowe, D., Salcudean, S., Rohling, R., & Nguan, C. (2012) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2012.2212718 · Cited by 73
“We follow the formulation of the BRIEF feature descriptor described in [6], choosing a feature vector length of bits and a patch size of , and we follow the original papers [20] and [3] for the implementations of SIFT and SURF respectively.”
MethodGeneral traffic sign recognition by feature matching
Ren, F., Huang, J., Jiang, R., et al. (2009) · doi:10.1109/ivcnz.2009.5378370 · Cited by 66
Mehmood, I., Ullah, A., Khan, M., Deng, D.-J., Meng, W.-Z., Al-turjman, F., Sajjad, M., & de Albuquerque, V. D. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2896151 · Cited by 58
A Discriminative Feature Learning Approach for Remote Sensing Image Retrieval
Xiong, W., Lv, Y., Cui, Y., Zhang, X., & Gu, X. (2019) · Remote Sensing · doi:10.3390/rs11030281 · Cited by 67
Convolutional Patch Representations for Image Retrieval: An Unsupervised Approach
Paulin, M., Mairal, J., Douze, M., Harchaoui, Z., Perronnin, F., & Schmid, C. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-016-0924-3 · Cited by 70
“Local descriptors that improve SIFT include SURF (Bay et al 2006), BRIEF (Calonder et al 2010) and LIOP (Wang et al 2011).”
Kraetzer, C., Makrushin, A., Neubert, T., Hildebrandt, M., & Dittmann, J. (2017) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/3082031.3083244 · Cited by 67
An Automatic Analog Instrument Reading System Using Computer Vision and Inspection Robot
Huang, J., Wang, J.-Z., Tan, Y., et al. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2967956 · Cited by 65
“By using SURF [25], it aims to reconstruct the pixel pointers in the actual scale region plane onto its relevant template image plane which represent the strict forward-looking scale region, so that the influence of the instrument deformation can be removed.”
MethodInfluentialMahmood, B., Han, S., & Lee, D. (2020) · Remote Sensing · doi:10.3390/rs12142302 · Cited by 84
“In the construction, various feature descriptors, such as scale-invariant feature transform (SIFT) [27] and speeded-up robust feature (SURF) [28], have been used for localization.”
BackgroundMethodInfluentialCosyPose: Consistent Multi-view Multi-object 6D Pose Estimation
Labbé, Y., Carpentier, J., Aubry, M., & Šivic, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58520-4_34 · Cited by 597
“The object pose estimation problem [15,16] has been approached either by estimating the pose from 2D-3D correspondences using local invariant features [3,13], or directly by estimating the object pose using template-matching [14].”
MethodResearch progress of zero-shot learning
Sun, X., Gu, J., & Sun, H. (2020) · Applied Intelligence · doi:10.1007/s10489-020-02075-7 · Cited by 78
“…[28] and Histogram of Oriented Gradient (HOG) [29]; texture information can be described by the gray-level cooccurrence matrix (GLCM) [30], autoregressive model (AR) [31] and local binary patterns (LBP) [32]; and shape information can be described by Hough [33], SIFT [34], SURF [35] and so on.”
BackgroundAssisting UAV Localization Via Deep Contextual Image Matching
Mughal, M. H., Khokhar, M. J., & Shahzad, M. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3054832 · Cited by 75
“…transforms (e.g., wavelet [6], Fourier [7], [8], annulus projection transformations [9]), or scale and rotation invariant feature descriptors (e.g., histogram of dominant gradients [10], SIFT [11], SURF [12], ORB [13], BRISK [14], adaptive radial ring code [15] etc.) have been proposed.”
BackgroundDeep Lucas-Kanade Homography for Multimodal Image Alignment
Zhao, Y., Huang, X., & Zhang, Z. (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/cvpr46437.2021.01569 · Cited by 72
Real-Time Dynamic SLAM Algorithm Based on Deep Learning
Su, P., Luo, S., & Huang, X. (2022) · IEEE Access · doi:10.1109/access.2022.3199350 · Cited by 78
Decoupling Makes Weakly Supervised Local Feature Better
Li, K., Wang, L., Liu, L., Ran, Q., Xu, K., & Guo, Y. (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/cvpr52688.2022.01538 · Cited by 86
“Sparse local feature [5,11,21,35,47], as one of the mainstream methods to find correspondences, has been widely applied in many areas, such as simultaneous localization and mapping (SLAM) [28, 51], structure from motion (SfM) [1,39], and visual localization [15,37,50].”
A Review of Homography Estimation: Advances and Challenges
Luo, Y., Wang, X., Liao, Y. Y., Fu, Q., Shu, C., Wu, Y., & He, Y. (2023) · Electronics · doi:10.3390/electronics12244977 · Cited by 94
“Refer.”
GPU Accelerating Speeded-Up Robust Features
Terriberry, T. B., & Helmsen, J. (2008) · Cited by 66
On Feature Matching and Image Registration for Two‐dimensional Forward‐scan Sonar Imaging
Aykin, M. D., & Negahdaripour, S. (2013) · Journal of Field Robotics · doi:10.1002/rob.21461 · Cited by 67
“For optical images, various feature matching algorithms have been devised that exploit the similarity in the feature appearance in the source and destination images; see, e.g., Lowe (1999) and Bay et al. (2006).”
MethodBiometrics inspired watermarking based on a fractional dual tree complex wavelet transform
Bhatnagar, G., & Wu, Q. M. J. (2012) · Future Generation Computer Systems · doi:10.1016/j.future.2012.05.021 · Cited by 65
Video search in concept subspace: a text-like paradigm
Li, X., Wang, D., Li, J., & Zhang, B. (2007) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1282280.1282366 · Cited by 72
“…a center region overlapping with the other four, where Color Moments Grid (CMG), 108 dim, localized color extracted from a 4 × 3 grid and represented by the • Keypoint Histogram Grid (KHG), 300 dim, localized SURF [5] keypoint histogram from a 3 × 2 grid and quantized into 50 bins for each region.”
MethodFeature point-based copy-move forgery detection: covering the non-textured areas
Yu, L., Han, Q., & Niu, X. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2362-y · Cited by 67
Real-time 6-DOF monocular visual SLAM in a large-scale environment
Lim, H., Lim, J., & Kim, H. J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907055 · Cited by 61
Spatio-temporal feature extraction and representation for RGB-D human action recognition
Luo, J., Wang, W., & Qi, H. (2014) · Pattern Recognition Letters · doi:10.1016/j.patrec.2014.03.024 · Cited by 62
Searching for objects driven by context
Alexe, B., Heess, N., Teh, Y. W., & Ferrari, V. (2012) · Edinburgh Research Explorer (University of Edinburgh) · Cited by 71
Hierarchical Dense Structure-from-Motion Reconstructions for Infrastructure Condition Assessment
Khaloo, A., & Lattanzi, D. (2016) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000616 · Cited by 70
Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics
Wiriyathammabhum, P., Summers-Stay, D. A., Fermuller, C. M., & Aloimonos, Y. (2016) · ACM Computing Surveys · doi:10.1145/3009906 · Cited by 86
“…are salient keypoints of an image extracted using techniques such as Scale-invariant feature transform (SIFT) [Lowe 2004] or speeded up robust features (SURF) [Bay et al. 2006] that can reliably find descriptors across images under difficulties like rotation, translation, or illumination changes.”
InfluentialState of the art in passive digital image forgery detection: copy-move image forgery
Sadeghi, S., Dadkhah, S., Jalab, H. A., Mazzola, G., & Uliyan, D. M. (2017) · Pattern Analysis and Applications · doi:10.1007/s10044-017-0678-8 · Cited by 65
“They used the same parameters as used in the original papers [12, 61].”
BackgroundMethodLiang, F., Qian, P., Su, K., Baydoun, A., Leisser, A., Hedent, S. V., Kuo, J., Zhao, K., Parikh, P. J., Lu, Y., et al. (2018) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2018.07.001 · Cited by 64
An evaluation of ROS-compatible stereo visual SLAM methods on a nVidia Jetson TX2
Giubilato, R., Chiodini, S., Pertile, M., & Debei, S. (2019) · Measurement · doi:10.1016/j.measurement.2019.03.038 · Cited by 68
Speeded-up, relaxed spatial matching
Tolias, G., & Avrithis, Y. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126427 · Cited by 63
Quaternion-Michelson Descriptor for Color Image Classification
Lan, R., & Zhou, Y. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2605922 · Cited by 64
“QLBP achieves a slight improvement compared with WLD. SURF does not work well in this data set, whose classification rate is much smaller than those of other methods.”
BackgroundInfluentialSample-to-sample correspondence for unsupervised domain adaptation
Das, D., & Lee, C. S. G. (2018) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2018.05.001 · Cited by 62
“The features used are the shallow SURF features [2] and deep-learning feature sets [13] – decaf6 and decaf7.”
MethodKaur, P., Singh, G., & Kaur, P. (2019) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2019.100239 · Cited by 64
Monocular Neural Image Based Rendering With Continuous View Control
Song, J., Chen, X., & Hilliges, O. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00419 · Cited by 76
Android malware detection based on image-based features and machine learning techniques
Ünver, H. M., & Bakour, K. (2020) · SN Applied Sciences · doi:10.1007/s42452-020-3132-2 · Cited by 69
“This algorithm is introduced by [38] as a fast algorithm that can be an alternative of SIFT algorithm.”
MethodA novel copy-move forgery detection algorithm via two-stage filtering
Yang, J., Liang, Z., Gan, Y., & Zhong, J. (2021) · Digital Signal Processing · doi:10.1016/j.dsp.2021.103032 · Cited by 74
Review of Image-Based 3D Reconstruction of Building for Automated Construction Progress Monitoring
Xue, J., Hou, X., & Zeng, Y. (2021) · Applied Sciences · doi:10.3390/app11177840 · Cited by 76
Application of MobileNetV2 to waste classification
Yong, L., Ma, L., Sun, D., & Du, L. (2023) · PLoS ONE · doi:10.1371/journal.pone.0282336 · Cited by 114
Artificial Intelligence-Powered Surface-Enhanced Raman Spectroscopy for Biomedical Applications
Bi, X., Ai, X., Wu, Z., Lin, L., Chen, Z., & Ye, J. (2025) · Analytical Chemistry · doi:10.1021/acs.analchem.4c06584 · Cited by 72
Escartin, J., García, R., Delaunoy, O., Ferrer, J., Gracias, N., Elibol, A., Cufí, X., Neumann, L., Fornari, D. J., Humphris, S. E., et al. (2008) · Geochemistry Geophysics Geosystems · doi:10.1029/2008gc002204 · Cited by 65
Live Texturing of Augmented Reality Characters from Colored Drawings
Magnenat, S., Groß, M. H., Sumner, R. W., Ngo, D. T., Zünd, F., Ryffel, M., Noris, G., Röthlin, G., Marra, A., Nitti, M., et al. (2015) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2015.2459871 · Cited by 73
Semi-supervised Laplacian Regularization of Kernel Canonical Correlation Analysis
Blaschko, M. B., Lampert, C. H., & Gretton, A. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87479-9_27 · Cited by 64
Globally exponentially stable observer for vision-based range estimation
Dani, A. P., Fischer, N., Kan, Z., & Dixon, W. E. (2011) · Mechatronics · doi:10.1016/j.mechatronics.2011.10.001 · Cited by 63
Maturana, D., Mery, D., & Soto, Á. (2009) · International Conference of the Chilean Computer Science Society (SCCC) · doi:10.1109/sccc.2009.21 · Cited by 78
“Another interesting avenue of research is to complement or replace the LBP 8,2 histogram descriptors with other local descriptors, such as SIFT [8], SURF [7] or one of the many LBP variations.”
BackgroundMethodWatanabe, T., Yamazaki, K., & Yokokohji, Y. (2017) · Advanced Robotics · doi:10.1080/01691864.2017.1365010 · Cited by 67
“We can find famous feature descriptors: e.g. SIFT [17], SURF [18], MSER [19], and HOG [20].”
MethodFracking Deep Convolutional Image Descriptors
Simo‐Serra, E., Trulls, E., Ferraz, L., Kokkinos, I., & Moreno-Noguer, F. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.6537 · Cited by 57
Liu, M., & Siegwart, R. (2013) · IEEE Transactions on Robotics · doi:10.1109/tro.2013.2272250 · Cited by 63
“Nevertheless, the state-of-the-art object detection meth-ods [11], [12] are usually computationally expensive.”
BackgroundMethodKomuravelli, R., Sinclair, M. D., Alsop, J., et al. (2015) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1145/2749469.2750374 · Cited by 63
Fast car detection using image strip features
Zheng, W., & Liang, L. (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.2009.5206642 · Cited by 65
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.