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 7,401–7,500 of 14,752
Fake Identity Attributes Detection Based on Analysis of Natural and Human Behaviors
Zhang, Y., Hu, R., Li, D., & Wang, X. (2020) · IEEE Access · doi:10.1109/access.2020.2987966 · Cited by 6
“SURF [30] descriptor is applied for fingerprint, first SURF is utilized to extract features with training data, then the same feature is extracted and calculated matching scores with known features with FLANN, and the result is acquired by the rank of scores [31].”
MethodLiu, C., & Fuhrmann, S. (2020) · Transactions in GIS · doi:10.1111/tgis.12630 · Cited by 5
“The colorfulness metric M was calculated as below (in RGB color space): It should be noted that there exist more complicated and robust descriptors of image, such as SIFT (Lowe, 2004), SURF (Bay, Tuytelaars, & Van Gool, 2006), and WLD (Chen et al., 2009).”
MethodGautier, F., Sitepu, E., Blay, C. L., et al. (2020) · Acta Astronautica · doi:10.1016/j.actaastro.2020.06.003 · Cited by 5
“This region of interest was then scanned to find features using the Speeded Up Robust Features (SURF) method [25].”
MethodMatch or No Match: Keypoint Filtering based on Matching Probability
Papadaki, A. I., & Hänsch, R. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00515 · Cited by 7
“In the context of obtaining faster and more reliable matches, several approaches have been developed for reducing image pairs [13], improving descriptors [5, 24, 17, 26, 3, 36, 14, 27, 11, 1] and filtering matches [22, 6, 2, 32, 21] - most notably the work in [18] which casts the matching itself as classification task…”
Object Detection in Traffic Scenarios - A Comparison of Traditional and Deep Learning Approaches
Erabati, G. K., Gonçalves, N., & Araújo, H. J. (2020) · doi:10.5121/csit.2020.100918 · Cited by 5
Zhao, X., Gao, Z. Y., Sun, W., et al. (2020) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-3-2020-201-2020 · Cited by 5
Boosting Feature Matching Accuracy With Pairwise Affine Estimation
Dai, J., Jin, S., Zhang, J., & Nguyen, T. Q. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3013384 · Cited by 8
Red Green Blue Depth Image Classification Using Pre-Trained Deep Convolutional Neural Network
Kumar, N., Kaur, N., & Gupta, D. P. (2020) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661820030153 · Cited by 6
“Many of techniques available before the existence of CNN technique were mainly dependent on the descriptor based approaches such as SIFT (Scale Invariant Feature Transform) [3], SURF (Speeded Up Robust Features) [4], and HOG (Histogram of Oriented Gradients) [20].”
MethodAn Image-Based Real-Time Georeferencing Scheme for a UAV Based on a New Angular Parametrization
Khoramshahi, E., de Oliveira, R. A., Koivumäki, N., et al. (2020) · Remote Sensing · doi:10.3390/rs12193185 · Cited by 5
Detection of Fiber Defects Using Keypoints and Deep Learning
Siegmund, D., Fu, B., José-García, A., Salahuddin, A., & Kuijper, A. (2020) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001421500166 · Cited by 6
Recent Approaches for Image Colorization
Pierre, F., & Aujol, J. (2023) · Springer eBooks · doi:10.1007/978-3-030-98661-2_55 · Cited by 5
Abate, D. (2020) · Journal of Cultural Heritage · doi:10.1016/j.culher.2020.09.015 · Cited by 5
Yusefi, A., Durdu, A., & Sungur, C. (2020) · European Journal of Science and Technology · doi:10.31590/ejosat.819735 · Cited by 6
A revisited visual-based geolocalization framework for forensic investigation support tools
Yokota, R., Hawai, Y., Tsuchiya, K., Imoto, D., Hirabayashi, M., Akiba, N., Kakuda, H., Tanabe, K., Honma, M., & Kurosawa, K. (2020) · Forensic Science International Digital Investigation · doi:10.1016/j.fsidi.2020.301088 · Cited by 5
HelipadCat: Categorised Helipad Image Dataset and Detection Method
Bitoun, J., & WINKLER, S. S. (2020) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon50793.2020.9293911 · Cited by 5
Automatic Classification of Bridge Component based on Deep Learning
Lee, J. H. (2020) · doi:10.12652/ksce.2020.40.2.0239 · Cited by 5
“(Viola and Jones, 2001; Lowe, 2004; Dalal and Triggs, 2005; Bay et al., 2006 (Krizhevsky et al., 2012).”
An Improved ORB Algorithm Based on Optimized Feature Point Extraction
Sun, H., Wang, P., Zhang, D. L., et al. (2020) · IEEE International Conference on Automation, Electronics and Electrical Engineering (AUTEEE) · doi:10.1109/auteee50969.2020.9315683 · Cited by 5
Anomaly Detection of Trackside Equipment based on Semi-Supervised and Multi-Domain Learning
Guo, X., Wei, X., Guo, M., Wei, X., Gao, L., & Xing, W. (2020) · International Conference on Signal Processing · doi:10.1109/icsp48669.2020.9320922 · Cited by 9
“Subsequently, along with the idea of [8], Herbert et al. [9] present a novel scale-invariant and rotation-invariant interest point detector and descriptor, called Speeded Up Robust Features (SURF).”
BackgroundStreet View Image Retrieval with Average Pooling Features
Chu, T., Chen, Y., Huang, L., Tan, H., Cao, J., & Xu, Z. (2020) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss39084.2020.9323667 · Cited by 5
“Most of the current approaches are based on handcrafted features [1-3], such as SIFT [4], SURF [5] and so on, that are difficult to express complex street view image content and distinguish different street view.”
MethodAutonomous Tracking by an Adaptable Scaled KCF Algorithm
Tseng, D.-C., Chen, C.-H., & Chen, Y. (2021) · International Journal of Machine Learning and Computing · doi:10.18178/ijmlc.2021.11.1.1013 · Cited by 5
A Biometric System Design using Finger Knuckle Biological Trait
Singh, B. K., Kumar, R., & Kishore, R. R. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10987-w · Cited by 5
“…descriptor are available such as Local Binary Pattern (LBP) [34], Scale Invariant Feature Transform (SIFT) [28], Speed Up Robust Feature (SURF) [5], BRIEF [6], Binary Robust Invariant Scalable Key-points (BRISK) [27], Oriented fast Rotated BRIEF (ORB) [39], Maximally stable extremal regions…”
MethodLatest Developments of Gesture Recognition for Human–Robot Collaboration
Liu, H., & Wang, L. (2021) · Springer eBooks · doi:10.1007/978-3-030-69178-3_2 · Cited by 7
Staroletov, S. M., Laptev, M., & Nekrasov, D. V. (2021) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661821020152 · Cited by 5
“Using such a method, it is possible to obtain an accuracy higher than the methods of the SURF class [5] in an acceptable time, which is applicable to the analysis of images from servers of road compute appliance systems in the background process or upon given requests.”
MethodGeometric Calculus Applications to Medical Imaging: Status and Perspectives
Franchini, S., & Vitabile, S. (2021) · SEMA SIMAI Springer series · doi:10.1007/978-3-030-74486-1_3 · Cited by 5
Vehicle behavior analysis using reconstructed 3D parameters for road safety
Wang, X., Xu, J., Song, Y., et al. (2021) · Safety Science · doi:10.1016/j.ssci.2021.105419 · Cited by 5
Point2CN: Progressive two-view correspondence learning via information fusion
Liu, X., Xiao, G., Li, Z., & Chen, R. (2021) · Signal Processing · doi:10.1016/j.sigpro.2021.108304 · Cited by 4
Pose Tracking of Moving Sensor using Monocular Camera and IMU Sensor
Jung, S., Park, S.-H., & Lee, K.-T. (2021) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2021.08.017 · Cited by 5
“Local detector such as SIFT (Scale-Invariant Feature Transform) [7] and SURF (Speeded-Up Robust Feature) [8] are invariant to the rotation and illumination change [9].”
MethodPlanning on topological map using omnidirectional images and spherical CNNs*
Taniguchi, A., Sasaki, F., Muroi, M., & YAMASHINA, R. (2021) · Advanced Robotics · doi:10.1080/01691864.2021.1997641 · Cited by 5
“Besides, whereas traditional vSLAM [3–5] often uses bag-of-visual-words with handcrafted local features such as SIFT [6], SURF [7], and ORB [8], it is challenging CONTACT Asuto Taniguchi asuto.taniguchi@jp.ricoh.com ∗ Portions of this work were previously presented at the 26th Robotics Symposia…”
MethodHeterogeneous image retrieval based on structural information
Weng, H., Liu, J., & Luo, B. (2021) · Signal Image and Video Processing · doi:10.1007/s11760-021-02061-7 · Cited by 5
“Since SIFT was not efficient enough, SURF [4] improved SIFT using integral images for image convolutions and Fast-Hessian detector for feature point detection.”
MethodConvolution-Based Encoding of Depth Images for Transfer Learning in RGB-D Scene Classification
Gopalapillai, R., Gupta, D., Zakariah, M., & Alotaibi, Y. A. (2021) · Sensors · doi:10.3390/s21237950 · Cited by 6
Loop Closure Detection in RGB-D SLAM by Utilizing Siamese ConvNet Features
Xu, G., Xiang, L., Zhang, X., Xing, G., & Pan, F. (2021) · Applied Sciences · doi:10.3390/app12010062 · Cited by 5
A Hybrid Deep Learning Framework Approach for the Detection of Different Varieties of Grain Types
Nijhawan, R., Ashish, M., Ahuja, A., & Yadav, N. (2021) · International Conference on System Modeling & Advancement in Research Trends (SMART) · doi:10.1109/smart52563.2021.9676325 · Cited by 7
VR/AR Input Devices and Tracking
Grimm, P., Broll, W., Herold, R., et al. (2022) · Springer eBooks · doi:10.1007/978-3-030-79062-2_4 · Cited by 5
Vein pattern recognition based on RGB images using Monte Carlo simulation and ridge tracking
Tang, C., Zhang, Y., Han, L., & Chen, X. (2022) · Journal of Forensic Sciences · doi:10.1111/1556-4029.15002 · Cited by 5
A hybrid structural feature extraction-based intelligent predictive approach for image registration
Hazra, J., Chowdhury, A. R., Dasgupta, K., et al. (2022) · Innovations in Systems and Software Engineering · doi:10.1007/s11334-022-00436-8 · Cited by 5
“…techniques like FAST (Features from accelerated segment test) [24], SIFT (Scale-Invariant Feature Transform) [25], SURF (Speeded-Up Robust Features) [26], DAISY [27], ORB (Oriented FAST and Rotated BRIEF) [28], KAZE [29,30] took into account the SURF features-based image registration approach.”
Research Review of Object Detection Algorithms in Vehicle Detection
An, H., Liu, K., Liang, Z., Qin, M., Huang, Y., & Guo, Z. (2022) · IEEE International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA) · doi:10.1109/eebda53927.2022.9744735 · Cited by 5
“…traverse a given image, and select candidate regions on the image to be detected; Feature extraction: extract features from candidate regions by manually designing filter features, often using histogram of directional gradients (HOG)[16], Speeded up robust features (SURF)[17] and other methods.”
MethodChekanov, M., Shipitko, O., & Skoryukina, N. (2022) · IEEE Access · doi:10.1109/access.2022.3159650 · Cited by 6
“SURF (Speeded-Up Robust Features), described in [9], was designed based on SIFT.”
BackgroundMethodHua, G., & Hasegawa, O. (2015) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2015.p0011 · Cited by 5
Keypoint-based copy-move forgery detection in digital images: a survey
Bensaad, A., Loukhaoukha, K., & Sadoudi, S. (2022) · International Conference on Image and Signal Processing and their Applications (ISPA) · doi:10.1109/ispa54004.2022.9786359 · Cited by 6
Multiple Detection Model Fusion Framework for Printed Circuit Board Defect Detection
Wu, X., Zhang, Q., Wang, J., Yao, J., & Guo, Y. (2022) · Journal of Shanghai Jiaotong University (Science) · doi:10.1007/s12204-022-2471-0 · Cited by 5
Loop Closure Detection Based on Residual Network and Capsule Network for Mobile Robot
Zhang, X., Zheng, L., Tan, Z., & Li, S. (2022) · Sensors · doi:10.3390/s22197137 · Cited by 6
“It extracts artificial features such as the scale-invariant feature transform algorithm (SIFT) [11], the speed up robust features algorithm (SURF) [12], and oriented FAST and rotated BRIEF (ORB) [13].”
MethodNonlinear and Dotted Defect Detection with CNN for Multi-Vision-Based Mask Inspection
Woo, J., & Lee, H. (2022) · Sensors · doi:10.3390/s22228945 · Cited by 5
“…patterns (LBP) [4,5], you only look once (YOLO) [6,7], single-shot multibox detector (SSD) [8], RetinaNet [9], scale invariant feature transform (SIFT) [10–12], speeded up robust features (SURF) [13,14], artificial neural networks (ANN) [15–17], and convolutional neural network (CNN) [18–22].”
BackgroundWu, C., Chen, L. F., & Wu, S. (2022) · Machines · doi:10.3390/machines10121107 · Cited by 6
Hanson, N., Keleştemur, T., Berman, J., Ritzenhoff, D., & Padır, T. (2022) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers56178.2022.9955133 · Cited by 5
“The image is converted to grayscale to aid in the generation of image keypoints and descriptors, which are selected using the SURF algorithm [15].”
MethodSIFT and RANSAC-Based Image Mosaic Algorithm for Image Compression
Lungisani, B. A., Lebekwe, C. K., & Zungeru, A. M. (2022) · International Conference on Smart Applications, Communications and Networking (SmartNets) · doi:10.1109/smartnets55823.2022.9994026 · Cited by 5
Methodological Research on Image Registration Based on Human Brain Tissue In Vivo
Nan, J., Su, J., & Zhang, J. (2023) · Electronics · doi:10.3390/electronics12030738 · Cited by 5
Local Property of Depth Information in 3D Images and Its Application in Feature Matching
Yang, E., Chen, F., Wang, M., Cheng, H., & Liu, R. (2023) · Mathematics · doi:10.3390/math11051154 · Cited by 6
Violence Detection Enhancement in Video Sequences Based on Pre-trained Deep Models
Elkhashab, Y. R., & El-Behaidy, W. H. (2023) · النشرة المعلوماتية في الحاسبات والمعلومات · doi:10.21608/fcihib.2023.153245.1075 · Cited by 5
“It is an efficient and fast alternative to SIFT [22] or SURF [23] algorithms, used to extract features in a comparison between costs and matching performance.”
MethodResearch on Road Object Detection Algorithm Based on Improved YOLOX
Wu, Y., Yang, T., & Tang, Y. (2023) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice58320.2023.10105761 · Cited by 5
He, Z., Chao, Y., Wu, M., Hu, Y., & Zhao, X. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3271105 · Cited by 7
Nedjah, N., Cardoso, A. D. V., Tavares, Y. M., Mourelle, L. D. M., Gupta, B. B., & Arya, V. (2023) · Sensors · doi:10.3390/s23135881 · Cited by 6
“Some examples of algorithms based on features include Scale Invariant Feature Transform (SIFT) [30], invariant point detector [31], and Speeded-Up Robust Features (SURF) [32].”
MethodMulti-scale Local Implicit Keypoint Descriptor for Keypoint Matching
Lee, J., Park, E., & Yoo, S. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00654 · Cited by 5
“Learned Local Descriptors Recently, hand-crafted key-point detectors and descriptors [2,15,24,25] have been out-performed by deep learning-based models by a large margin in several vision tasks.”
BackgroundFlyTracker: Motion Tracking and Obstacle Detection for Drones Using Event Cameras
Wu, Y., Xu, J., Li, D., Xie, Y., Cao, H., Li, F., & Yang, Z. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10228976 · Cited by 9
Adaptive Reordering Sampler with Neurally Guided MAGSAC
Wei, T., Matas, J., & Baráth, D. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01665 · Cited by 14
“In addition to the feature orientation, the SIFT [30] and SURF [13] detectors return a uniform scaling parameter.”
MethodLow-Cost MEMS IMU Calibration Using Deep Learning and Visual-Inertial Odometry
Hosseini, H., & Atashgah, M. A. A. (2023) · RSI International Conference on Robotics and Mechatronics (ICRoM) · doi:10.1109/icrom60803.2023.10412527 · Cited by 5
Assuring Safety of Vision-Based Swarm Formation Control
Hsieh, C., Koh, Y., Li, Y., & Mitra, S. (2024) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc60939.2024.10644491 · Cited by 14
“Any of the various feature detection algorithms like SIFT [20], SURF [21], and ORB [22] can be used for this step.”
MethodQuasi-regular Facade Structure Extraction
Han, T., Liu, C., Tai, C. L., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37447-0_42 · Cited by 5
Who Shot the Picture and When?
Kanojia, G., Malireddi, S. R., Gullapally, S. C., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14364-4_42 · Cited by 5
Олегович, Ч. В., & Savchenko, A. (2014) · Communications in computer and information science · doi:10.1007/978-3-319-12580-0_5 · Cited by 5
Different Orderings and Visual Sequence Alignment Algorithms for Image Classification
Drozda, P., Sopyła, K., & Górecki, P. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-07173-2_59 · Cited by 5
“To the authors knowledge, in the group of leading descriptors we can distinguish MSER[8], SIFT[18], SURF[2] and ASIFT[19,26].”
MethodRobust Image Feature Point Matching Based on Structural Distance
Hu, M., Liu, Y., & Fan, Y. (2015) · Communications in computer and information science · doi:10.1007/978-3-662-47791-5_17 · Cited by 5
Co-registration of Satellite Images Based on Invariant Local Features
Tahoun, M., Shabayek, A. E. R., Reulke, R., et al. (2014) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-11310-4_56 · Cited by 5
Android Based Electronic Travel Aid System for Blind People
Diamantatos, P., & Kavallieratou, E. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-44654-6_58 · Cited by 5
“Various detectors were tried, offered by opencv library for this task, like SURF [10]: a robust local feature detector that is based on sums of 2D Haar wavelet responses, ORB [11]: a very fast binary descriptor based on BRIEF, and GFTT [12]: a detector that finds the most prominent corners in the…”
A Panoramic Image Registration Algorithm Based on SURF
Liang, Y., Li, Q., Lin, Z., et al. (2012) · Lecture notes in electrical engineering · doi:10.1007/978-3-642-25792-6_71 · Cited by 5
Dimensionality reduction for histogram features: A distance-adaptive approach
Cui, M., Cui, J., & Li, H. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.03.123 · Cited by 5
Egocentric Activity Recognition using Histograms of Oriented Pairwise Relations
Chapman, M., Behera, A., Cohn, A. G., & Hogg, D. (2014) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004655100220030 · Cited by 6
Automatic road network extraction from UAV image in mountain area
Cao, Y., & Yan, L. (2012) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2012.6469671 · Cited by 5
ROV vision-based motion estimation: a comparison study
Ferreira, F., Veruggio, G., Caccia, M., & Bruzzone, G. (2012) · IFAC Proceedings Volumes · doi:10.3182/20120905-3-hr-2030.00105 · Cited by 5
SURF-Based Multi-scale Resolution Histogram for Insect Recognition
Huang, S., Li, X., Zhou, M., et al. (2009) · doi:10.1109/aici.2009.415 · Cited by 5
A learning based approach for tremor detection from videos
Roy, K., Rao, G. S. V. R. K., & Anouncia, S. M. (2013) · IEEE Conference on Open Systems · doi:10.1109/icos.2013.6735051 · Cited by 5
Extrinsic Recalibration in Camera Networks
Hermans, C., Dumont, M., & Bekaert, P. (2007) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2007.31 · Cited by 5
Object pose estimation for grasping based on robust center point detection
Song, K., & Chang, C. (2011) · Cited by 5
Markerless vision-based augmented reality for enhanced project visualization
Bosché, F., Tingdahl, D., Carozza, L., et al. (2012) · Gerontechnology · doi:10.4017/gt.2012.11.02.138.00 · Cited by 5
Self-citationFast and Robust Keypoint Detection in Unstructured 3-D Point Clouds
Garstka, J., & Peters, G. (2015) · International Conference on Informatics in Control, Automation and Robotics (ICINCO) · doi:10.5220/0005569501310140 · Cited by 5
A Novel Method for Banknote RecognitionSystem
Bhavani, R., & Karthikeyan, A. (2014) · International Journal of Innovative Research in Science Engineering and Technology · Cited by 5
SVM classification of moving objects tracked by Kalman filter and Hungarian method.
Szücs, G., Papp, D., & Lovas, D. (2015) · CLEF (Working Notes) · Cited by 6
Multimodal image stitching algorithm for weed control applications in organic farming
Holtorf, T., Knoll, F. J., & Hussmann, S. H. (2016) · 2016 SAI Computing Conference (SAI) · doi:10.1109/sai.2016.7556003 · Cited by 5
Detection and extraction of pantograph region from bank cheque images
Ali, A., & Pal, R. (2016) · International Conference on Signal Processing and Integrated Networks (SPIN) · doi:10.1109/spin.2016.7566746 · Cited by 5
Versatile and Economical Acquisition Setup for Dorsa Palm Vein Authentication
Poornima, S., Nasreen, F., Prakash, A. D. S., et al. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.04.041 · Cited by 5
Visual Target Detection and Tracking in UAV EO/IR Videos by Moving Background Subtraction
Tufano, F., Angelino, C. V., & Cicala, L. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48680-2_48 · Cited by 5
Rat Brain Registration Using Improved Speeded Up Robust Features
Hsu, W., & Lee, Y.-C. (2017) · Journal of Medical and Biological Engineering · doi:10.1007/s40846-016-0204-2 · Cited by 5
“Concerning feature descriptors, a variety of invariant descriptors have been proposed [16–18].”
BackgroundMethodThermal vision human classification and localization using bag of visual word
Malpani, S., Asha, C. S., & Narasimhadhan, A. V. (2016) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon.2016.7848627 · Cited by 5
ACCELERATING FPGA-SURF FEATURE DETECTION MODULE BY MEMORY ACCESS REDUCTION
Idris, M. Y. I., Warif, N. B. A., Arof, H., Noor, N. M., Wahab, A. W. A., & Razak, Z. (2019) · Malaysian Journal of Computer Science · doi:10.22452/mjcs.vol32no1.4 · Cited by 5
“Herbert Bay [27] proposed approximation to the Laplacian of Gaussians by using box filter representations of the respective kernels based on SIFT.”
BackgroundMethodInfluentialNear Duplicate Product Image Detection Based on Binary Hashing
An, S., Huang, Z., Chen, Y., & Weng, D. (2017) · International Conference on Deep Learning Technologies (ICDLT) · doi:10.1145/3094243.3094260 · Cited by 6
“Commonly used local features are SIFT [8] and SURF [9].”
BINK: Biological binary keypoint descriptor
Saleiro, M., Terzić, K., Rodrigues, J. M. F., & du Buf, J. M. H. (2017) · Biosystems · doi:10.1016/j.biosystems.2017.10.007 · Cited by 5
“Although there were already some floating-point descriptors like SIFT and SURF that can yield high matching rates, the need for better and faster descriptors for real-time applications and embedded devices with low computational power led to the development of binary descriptors, which are usually much faster to compu…”
BackgroundInfluentialA Hybrid Model: DGnet-SVM for the Classification of Pulmonary Nodules
Xu, Y., Zhang, G., Yuan, L., Luo, Y., & Lu, J. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70093-9_78 · Cited by 5
Multiple Scale Canonical Correlation Analysis Networks for Two-View Object Recognition
Yang, X., & Liu, W. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70087-8_35 · Cited by 5
Angelats, E., & Navarro, J. A. (2017) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlii-2-w8-9-2017 · Cited by 5
Translation and rotation invariant video stabilization for real time applications
Sultan, B., Ahmed, J., Jalil, A., et al. (2017) · IEEE International Conference on Signal and Image Processing Applications (ICSIPA) · doi:10.1109/icsipa.2017.8120659 · Cited by 5
Menon, H. P. (2017) · International Conference on Advances in Computing, Communications and Informatics (ICACCI) · doi:10.1109/icacci.2017.8125938 · Cited by 5
Visual place recognition with CNNs: From global to partial
Xin, Z., Cui, X., Zhang, J., Yang, Y., & Wang, Y. (2017) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2017.8310121 · Cited by 6
“Local features such as SIFT [17], SURF [4] and ORB [23] are widely used as visual words in bag-of-words models.”
MethodDetection and registration of vessels for longitudinal 3D retinal OCT images using SURF
Pan, L., Guan, L., Shi, F., Chen, X., Zhu, W., & Nie, B. (2018) · SPIE Medical Imaging: Biomedical Applications in Molecular, Structural, and Functional Imaging · doi:10.1117/12.2292970 · Cited by 5
Face description using electric virtual binary pattern (EVBP): application to face recognition
Dahmouni, A., Moutaouakil, K. E., & Satori, K. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5932-6 · Cited by 5
Sundararajan, S. K., Gomathi, B. S., & Priya, D. S. (2017) · International Conference on Technological Advancements in Power and Energy (TAP Energy) · doi:10.1109/tapenergy.2017.8397235 · Cited by 5
“In this paper the author motivated to increase the accuracy in terms of image retrieval using local descriptors (SIFT [6, 13], SURF [7, 12]) based BOW model.”
MethodRobust Fingerprinting Method for Webtoon Identification in Large-Scale Databases
Kim, D., Lee, S., Jadhav, S., Kwon, H.-J., & Lee, S. (2018) · IEEE Access · doi:10.1109/access.2018.2845540 · Cited by 6
“The former includes template matching and hierarchical symmetric difference (HSD), and the latter includes texture-based features (SIFT, SURF, MSER) and a hashing function tested for identification accuracy, processing speed, and so on.”
MethodInfluentialEffective Descriptors based Face Recognition Technique for Robotic Surveillance Systems
Vinay, A., Deshpande, A. R., Pranathi, B. S., et al. (2018) · Procedia Computer Science · doi:10.1016/j.procs.2018.07.080 · Cited by 5
Visual Inertial Odometry with Pentafocal Geometric Constraints
Kim, P., Lim, H., & Kim, H. J. (2018) · International Journal of Control Automation and Systems · doi:10.1007/s12555-017-0200-5 · Cited by 5
“We detect the feature points for updating the filter state vector, and track them with SURF [28] within only five consecutive image sequences.”
MethodA Feature Averaging Method for Kinship Verification
Yadav, N., Goyal, A., & Meenpal, T. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-0617-4_38 · Cited by 5
Enhanced Visual Loop Closing for Laser-Based SLAM
Zhu, Z., Yang, S., & Dai, H. (2018) · IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) · doi:10.1109/asap.2018.8445128 · Cited by 5
“However, the length of SURF features has to be reconsidered as the inconformity of the tracking and loop detection features.”
MethodMultispectral Image Analysis for Patient Tissue Tracking During Complex Interventions
Manni, F., Mamprin, M., Zinger, S., et al. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451263 · Cited by 5
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.