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 7,701–7,800 of 14,752
Hierarchical clustering relevance feedback for content-based image retrieval
Mironică, I., Ionescu, B. E., & Vertan, C. (2012) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2012.6269811 · Cited by 4
AH-SIFT: Augmented Histogram based SIFT descriptor
Tang, H., & Tang, F. (2012) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2012.6467370 · Cited by 4
“The original SIFT is computationally heavy, so SURF [8] is proposed to reduce the computation while minimizing the performance loss.”
MethodGu, I. Y., & Zulfiqar, H. (2011) · InTech eBooks · doi:10.5772/14839 · Cited by 4
“IEEE int’l conf CVPR. [Bay et al.,06] Bay H., Tuytelaars T. & Gool L.V.(2006), "SURF: Speeded Up Robust Features", in proc.”
BackgroundMethodAugmented Reality System for Accelerometer Equipped Mobile Devices
Skoczewski, M., & Maekawa, H. (2010) · IEEE/ACIS International Conference on Computer and Information Science (ICIS) · doi:10.1109/icis.2010.140 · Cited by 4
Real-time scale-adaptive compressive tracking using two classification stages
Naglah, A. M., ElDesouky, A., & Elhelw, M. (2015) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2015.7418794 · Cited by 4
“A proposed future work is to combine both the compressive sensing and detection techniques in order to obtain scale updating, as an example to use SURF features [15] and FLANN matcher [17].”
MethodResearch and Analysis of Key Technologies in Image Mosaic
Gong, Y., Xie, H., & Yu, L. (2013) · International Journal of Signal Processing Image Processing and Pattern Recognition · doi:10.14257/ijsip.2013.6.5.21 · Cited by 4
“In 2006, Herbert Bay [3, 4] proposed Speed up Robust Features (SURF), which is a fast and robust features match algorithm.”
BackgroundImplicit Shape Models for 3D Shape Classification with a Continuous Voting Space
Seib, V., Link, N., & Paulus, D. W. R. (2015) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0005290700330043 · Cited by 4
Automatic projection positioning based on surface suitability
Funk, M., Kosch, T., Wolf, K., et al. (2016) · ACM International Symposium on Pervasive Displays (PerDis) · doi:10.1145/2914920.2915014 · Cited by 4
“A SURF detector defines interest points [1] indicating unique points in the image.”
BackgroundMethodA panoramic stitching vision performance improvement technique for Minimally Invasive Surgery
Kim, T. D., & Cheng, C.-H. (2016) · International Symposium on Next-Generation Electronics · doi:10.1109/isne.2016.7543381 · Cited by 4
“The proposed techniques are applied in comparison with other algorithms, such as SIFT, SURF, ORB… to accelerate video stitching.”
MethodInfluentialArchival and Retrieval of Lost Objects using Multi-feature Image Matching in Mobile Applications
Ghazal, M. A. (2016) · International Journal of Computing and Digital Systems · doi:10.12785/ijcds/050107 · Cited by 4
“The algorithm approximates the second order derivatives of the Gaussians using box filters in order to avoid discretion and cropping [12].”
BackgroundMethodInfluentialNight-time indoor relocalization using depth image with Convolutional Neural Networks
Li, R., Liu, Q., Gui, J., Gu, D., & Hu, H. (2016) · International Conference on Automation and Computing (ICAC) · doi:10.1109/iconac.2016.7604929 · Cited by 4
“[15] presented FAB-MAP using SURF features [16] to implement large scale relocalization, but SURF feature computation is too cost to run in real-time.”
MethodAdvanced feature based digital video stabilization
Spampinato, G., Bruna, A. R., Guarneri, I., et al. (2016) · IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin) · doi:10.1109/icce-berlin.2016.7684716 · Cited by 4
“To reduce the heavy computational burden, SURF features [6] have been introduced, achieving results [7] similar to Scale-Invariant Feature Transform (SIFT).”
MethodCascading Training for Relaxation CNN on Handwritten Character Recognition
Chen, L., Wang, S., Fan, W., Sun, J., & Naoi, S. (2016) · International Conference on Frontiers in Handwriting Recognition · doi:10.1109/icfhr.2016.0041 · Cited by 4
Research and implementation of 3D SLAM algorithm based on Kinect depth sensor
Li, C., Wei, H., & Lan, T. (2016) · International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) · doi:10.1109/cisp-bmei.2016.7852872 · Cited by 4
“Common feature point detection method Harris corner detection, SIFT[4], SURF[5], ORB[6], etc. SIFT feature is the local feature of image, which is invariant to rotation, scaling and brightness change.”
MethodModel-Based Real-Time Non-Rigid Tracking
Bronte, S., Bergasa, L. M., Pizarro, D., & Barea, R. (2017) · Sensors · doi:10.3390/s17102342 · Cited by 4
Deeply Learned Pore-Scale Facial Features
Wang, X., Liang, Y., Zeng, X., Li, D., & Jia, W. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-69923-3_15 · Cited by 4
Enhancing viewability for first-person videos based on a human perception model
Ma, B., & Reibman, A. R. (2017) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2017.8122223 · Cited by 4
Image matching using GPT correlation associated with simplified HOG patterns
Zhang, S., Wakahara, T., & Yamashita, Y. (2017) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2017.8310122 · Cited by 4
“Comparative experiments using the well-known Graffiti dataset [12] demonstrate the superiority of the proposed method in matching ability over the conventional feature-based techniques: a combination of the SURF feature descriptor [3], key point matching by k -NN, and RANSAC [4].”
MethodInfluentialVehicle Detection and Tracking Based on GMM and Enhanced Camshift Algorithm
Zhong, K. (2018) · Journal of Electrical and Electronic Engineering · doi:10.11648/j.jeee.20180602.11 · Cited by 4
“Considering the dynamic of vehicle, motion-based algorithms are given in [9-11].”
BackgroundGajalakshmi, P., & Sharmila, T. S. (2017) · IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI) · doi:10.1109/icpcsi.2017.8391780 · Cited by 4
“The feature vectors of SURF descriptors of corresponding images from the class labels is trained with set of dichotomizes id as shown in figure 2.”
MethodInfluentialHypersonic Pitching Control Model Development
Stern, N., Buttsworth, D. R., Birch, B., et al. (2018) · doi:10.2514/6.2018-5267 · Cited by 4
Farag, R., Saad, M., Emara, H., et al. (2018) · Proceedings of the Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon.2018.8592716 · Cited by 4
“SURF is performed in three steps.”
BackgroundMethodInfluentialLow-dimensional superpixel descriptor and its application in visual correspondence estimation
Ду, С., & Ikenaga, T. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7248-6 · Cited by 4
“[5] proposed a speeded up robust feature (SURF) by using integral images as keypoint detector and Haar wavelet response as feature descriptor.”
MethodInfluentialZhang, S., Cheng, S., & Radkowski, R. (2019) · IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct) · doi:10.1109/ismar-adjunct.2019.00-39 · Cited by 5
“Feature descriptor-based methods for RGB [19], [3] and RGB-D data [5], [20] constitute the next plausible solution.”
MethodA Fast Method for Large-Scale Scene Data Acquisition and 3D Reconstruction
Li, Y., Xie, Y., Wang, X., et al. (2019) · IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct) · doi:10.1109/ismar-adjunct.2019.00-20 · Cited by 4
Vision-based Indoor Positioning Method By Joint Using 2D Images and 3D Point Cloud Map
Ma, L., Jiang, H., Qin, D., & Tan, X. (2020) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc48107.2020.9148325 · Cited by 5
“The 3D point cloud map consists of 3D global coordinate of SURF point extracted from RGB image, which can be represented as a set of 3D points The transform matrix T is a 4th order square matrix, which is composed of a rotation matrix R and a translation matrix t from the local camera coordinate system that relates to…”
MethodInfluentialGeng, Q., Liu, W., & Dai, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3026212 · Cited by 4
Real-to-Synthetic Feature Transform for Illumination Invariant Camera Localization
Shoman, S., Mashita, T., Plopski, A., Ratsamee, P., & Uranishi, Y. (2020) · IEEE Computer Graphics and Applications · doi:10.1109/mcg.2020.3041617 · Cited by 5
An Overview of Control Strategy and Trajectory Planning of Visual Servoing
Wang, T., Wang, W., & Wei, F. (2020) · Communications in computer and information science · doi:10.1007/978-981-33-6378-6_27 · Cited by 4
Deduplication of Advertisement Assets Using Deep Learning Ensembles
Chakiat, A., Oli, N., & Modi, V. K. (2020) · International Conference on Machine Learning and Applications · doi:10.1109/icmla51294.2020.00145 · Cited by 5
3DTDesc: learning local features using 2D and 3D cues
Xing, X., Cai, Y., Lü, T., Yang, Y., & Wen, D. (2021) · Machine Vision and Applications · doi:10.1007/s00138-021-01176-8 · Cited by 3
Tomită, M.-A., Zaffar, M., Ferrarini, B., Milford, M. J., McDonald-Maier, K. D., & Ehsan, S. (2022) · IEEE Access · doi:10.1109/access.2022.3196389 · Cited by 6
Unconstrained Vision Guided UAV Based Safe Helicopter Landing
Sikdar, A., Sahu, A., Sen, D., Mahajan, R., & Chowdhury, A. S. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412966 · Cited by 4
Beyond ITQ: Efficient binary multi-view subspace learning for instance retrieval
Wu, Z., Li, J., Xu, J., & Yang, W. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103234 · Cited by 4
Visual Odometry for Absolute Position Estimation using Template Matching on Known Environment
Lee, C., Kim, D., Hur, S., et al. (2021) · International Conference on Ubiquitous Robots (UR) · doi:10.1109/ur52253.2021.9494655 · Cited by 4
Performance Comparison of Feature Generation Algorithms for Mosaic Photoacoustic Microscopy
Le, T. D., Kwon, S. Y., & Lee, C. (2021) · Photonics · doi:10.3390/photonics8090352 · Cited by 4
Accurate Silhouette Vectorization by Affine Scale-Space
He, Y., Kang, S. H., & Morel, J. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506518 · Cited by 4
Niyishaka, P., & Bhagvati, C. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11642-0 · Cited by 5
“Most common scale-rotation invariant features include SIFT [19], SURF [5], AKAZE [2], ORB [8], and BRISK [16].”
BackgroundOsorio, J. A. C., Osorio, J. A. C., & Robayo, C. D. L. (2021) · Revista Facultad de Ingeniería Universidad de Antioquia · doi:10.17533/udea.redin.20211165 · Cited by 4
“Another recognized feature extractor is the Speeded Up Robust Features (SURF), which detects interest points and descriptors [8, 9].”
Ren, H., Li, C., Zhang, X., Ding, C., Man, C., & Yu, H. (2021) · WRC Symposium on Advanced Robotics and Automation (WRC SARA) · doi:10.1109/wrcsara53879.2021.9612673 · Cited by 4
Hough-RANSAC: A Fast and Robust Method for Rejecting Mismatches
Gao, H., Xie, J., Hu, Y., et al. (2014) · Communications in computer and information science · doi:10.1007/978-3-662-45646-0_37 · Cited by 4
Classification of Crop and Weed from Digital Images: A Review
Kamath, R., Balachandra, M., & Prabhu, S. (2021) · IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER) · doi:10.1109/discover52564.2021.9663729 · Cited by 4
A robust and imperceptible watermarking method for 3D DIBR images
Etoom, W., & Al‐Haj, A. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12553-4 · Cited by 4
Attention Guided Invariance Selection for Local Feature Descriptors
Li, J., Li, G., & Li, T. H. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746419 · Cited by 4
Small-area Fingerprint Recognition Based on Improved ORB Algorithm in Embedded Environment
Xiao, J., Liu, J., & Liu, H. (2022) · EAI Endorsed Transactions on Internet of Things · doi:10.4108/eetiot.v7i27.297 · Cited by 4
High‐Precision Motion Compensation for LiDAR Based on LiDAR Odometry
Qin, P., Zhang, C., Ma, X., & Shi, Z. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/5866868 · Cited by 5
Harris Hawks Optimization Method based on Convolutional Neural Network for Face Recognition Systems
Ahmed, S., Frikha, M., Hussein, T. D. H., & Rahebi, J. (2022) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/hora55278.2022.9799955 · Cited by 4
Rectified Neighborhood Construction for Robust Feature Matching With Heavy Outliers
Liu, Y., Zhao, B. N., & Zhao, S. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3181754 · Cited by 4
“…matches, several meth-ods have been proposed, such as classical scale-invariant feature transform (SIFT) [6], speeded up robust features (SURF) [7], oriented FAST and rotated BRIEF (ORB) [8], deep learning-based learned-invariant feature transform (LIFT) [9], and SuperPoint (self-supervised…”
BackgroundLiu, P., & Li, Y. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3193182 · Cited by 4
Identification of herbarium specimens: a case study with Piperaceae Giseke family
Kajihara, A. Y., Bertolini, D. S., & Schwerz, A. L. (2022) · International Conference on Systems, Signals and Image Processing · doi:10.1109/iwssip55020.2022.9854444 · Cited by 4
A Light Field FDL-HCGH Feature in Scale-Disparity Space
Zhang, M., Jin, H., Xiao, Z., et al. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3202099 · Cited by 4
“Classic 2D image feature detection methods include Harris [1], SIFT [2], SURF [3], FAST [4], ORB [5], LBP [6], PCA-SIFT [7], GLOH [8], etc.”
Machine Learning based Detection of Alzheimer’s disease in MRI images
M.Rajendiran, D. K. P. S. K. (2022) · Journal of Pharmaceutical Negative Results · doi:10.47750/pnr.2022.13.s08.196 · Cited by 4
Reinforcement learning-based image exposure reconstruction for homography estimation
Lin, Y., Wu, F., & Zhao, J. (2022) · Applied Intelligence · doi:10.1007/s10489-022-04287-5 · Cited by 4
Detecting Tool Keypoints with Synthetic Training Data
Vanherle, B., Put, J., Michiels, N., & Reeth, F. V. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-19650-8_10 · Cited by 4
On approaches of investigating multi-layered medical images for implicit features
Hasanov, J. (2022) · IEEE International Conference on Application of Information and Communication Technologies (AICT) · doi:10.1109/aict55583.2022.10013622 · Cited by 4
“Symbolic and rule-based object detection algorithms like SIFT [9], SURF [10] and ORB [11] use feature detectors and descriptors to encode the images, which are preserved during the variations like size change, rotation, and affine transformations.”
MethodFast calibration stitching algorithm for underwater camera
Wang, Z., Tang, Z., Huang, J., et al. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14533-8 · Cited by 4
Improving Learning-based Camera Pose Estimation for Image-based Augmented Reality Applications
Cai, E., Rossi, R. A., & Xiao, C. (2023) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3544549.3585756 · Cited by 4
Lin, B.-H., Shivanna, V. M., Chen, J.-S., et al. (2023) · Sensors · doi:10.3390/s23125560 · Cited by 4
Shan, X., & Zhang, J. (2023) · Remote Sensing · doi:10.3390/rs15112820 · Cited by 4
Improved polar complex exponential transform for robust local image description
Yang, Z., Yang, L., Chen, G., & Yap, P. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109786 · Cited by 5
Classification of firing pin impressions using HOG‐SVM
Wen, Z., Curran, J. M., Harbison, S., et al. (2023) · Journal of Forensic Sciences · doi:10.1111/1556-4029.15377 · Cited by 4
Real-Time Wheel Detection and Rim Classification in Automotive Production
Staněk, R., Kerepecký, T., Novozámský, A., Šroubek, F., Zitová, B., & Flusser, J. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10223161 · Cited by 9
Overview on Interest Point Detection Over 40 Year’s Development: A Review
Zhou, G., Li, H., & Gao, E. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3318756 · Cited by 3
Covariant Peak Constraint for Accurate Keypoint Detection and Keypoint-Specific Descriptor Learning
Fu, Y., Zhang, P., Tang, F., & Wu, Y. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3333211 · Cited by 5
A Lightweight and Accurate Method for Detecting Traffic Flow in Real Time
Du, Z., Jin, Y. A., Ma, H., & Liu, P. (2023) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2023.p1086 · Cited by 5
Efficient Dynamic Correspondence Network
He, J., Zhang, T., Zhang, Z., Yu, T., & Zhang, Y. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3334594 · Cited by 20
Taranco, R., Arnau, J.-M., & González, A. M. (2023) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3613424.3614261 · Cited by 7
AttentionPose: Attention-driven end-to-end model for precise 6D pose estimation
Rasheed, M. A., Farhan, R. N., & Jasim, W. M. (2023) · Journal of Intelligent Systems · doi:10.1515/jisys-2023-0153 · Cited by 4
Ma, S., Li, X., Liu, K., et al. (2024) · Entropy · doi:10.3390/e26010061 · Cited by 4
“In addition, there is an improved SIFT-based accelerated robustness feature algorithm (SURF), which has a faster speed and is more suitable for real-time applications [6].”
BackgroundPlanarTrack: A Large-scale Challenging Benchmark for Planar Object Tracking
Liu, X., Liu, X., Yi, Z., Zhou, X., Le, T. H., Zhang, L., Huang, Y., Yang, Q. K., & Fan, H. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01870 · Cited by 5
LocoNeRF: A NeRF-Based Approach for Local Structure from Motion for Precise Localization
Nenashev, A., Kurenkov, M., Potapov, A., et al. (2023) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53992.2023.10394246 · Cited by 4
Towards Real-Time 3D Terrain Reconstruction from Aerial Imagery
Wang, Q. (2024) · Geographies · doi:10.3390/geographies4010005 · Cited by 4
Cross Fusion of Point Cloud and Learned Image for Loop Closure Detection
Yue, H., Cao, D., Liu, Z., Wang, T., & Chen, W. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3362681 · Cited by 4
Two-Stage Deep Learning Technology Based Iris Recognition Methodology for Biometric Authorization
Hsiao, C.-S., Chang, C., & Fan, C. (2024) · Journal of Advances in Information Technology · doi:10.12720/jait.15.2.212-218 · Cited by 4
“The workflow of most traditional iris recognition systems [3–12] can be split into the following steps: iris localization, segmentation, normalization, feature enhancement, feature extraction, and identification.”
MethodA Comparative Study of Copy-Move Forgery Detection Techniques
Lauwers, B., Κarampidis, K., Tampouratzis, M. G., Vasilakis, M., Papadourakis, G. M., & Mastorakis, N. E. (2023) · International Conference on Applied Mathematics & Computer Science (ICAMCS) · doi:10.1109/icamcs59110.2023.00027 · Cited by 4
Zarif, S., Morad, E., Amin, K., et al. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.046185 · Cited by 4
Jin, C., Zheng, A., Wu, Z., & Tong, C. (2024) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-024-08892-z · Cited by 5
“However, conventional manual feature design meth-ods [7–9] are often only effective for a specific scene and lack the required robustness, which limits their applicability in practical scenarios, especially for remote sensing applications.”
A high-resolution hyperspectral imaging system for retina imaging
Tran, M. H., Bryarly, M. D., Pruitt, K. T., et al. (2024) · doi:10.1117/12.3001647 · Cited by 4
“We registered the grayscale, high resolution images and the hyperspectral images using the SURF registration method [16].”
MethodA two‐stage substation equipment classification method based on dual‐scale attention
Yao, Y., Wang, X., Zhou, G., & Wang, Q. (2024) · IET Image Processing · doi:10.1049/ipr2.13091 · Cited by 7
Efficient Image Retrieval Using Hierarchical K-Means Clustering
Park, D., & Hwang, Y. (2024) · Sensors · doi:10.3390/s24082401 · Cited by 7
“Another well-known algorithm, SURF [26], improves the slow detection speed of SIFT by varying the size of the filter instead of the image pyramid.”
MethodSpatiotemporal Feature Enhancement Network for Blur Robust Underwater Object Detection
Zhou, H., Qi, L., Huang, H. Y., Yang, X., & Yang, J. (2024) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2024.3386664 · Cited by 8
“At an early stage, traditional object detection methods, such as scale invariant feature transform (SIFT) [7], speeded up robust feature (SURF) [8], and histogram of oriented (HOG) [9], which adopted handcrafted descriptors to extract shape or appearance features, were used to detect underwater…”
MethodSpeeding Up the AV1 Global Warped Motion Compensation
Kolodziejski, W., Domanski, R., & Agostini, L. V. (2024) · IEEE Latin America Symposium on Circuits and Systems (LASCAS) · doi:10.1109/lascas60203.2024.10506160 · Cited by 4
“On the other hand, solutions BEBLID [30], and SURF [31] presented an inferior inliers rate, when compared to the standard implementation.”
ResultRobust Feature Matching via Graph Neighborhood Motion Consensus
Huang, J., Li, H., Gong, Y., Fan, F., Ma, Y., Du, Q., & Ma, J. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3398266 · Cited by 5
Ling, X., Liu, J., Duan, Z., et al. (2024) · Remote Sensing · doi:10.3390/rs16111873 · Cited by 4
Asmara, R. A., Anugrah, M., Wibowo, D. W., et al. (2024) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v13i4.6895 · Cited by 6
Advancing Crowd Object Detection: A Review of YOLO, CNN, and Vision Transformers Hybrid Approach
Ali, M. A. M. (2024) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2024.63293 · Cited by 4
A Novel Multiple Camera RGB-D Calibration Approach Using Simulated Annealing
Taghipour‐Gorjikolaie, M., Volino, M., Rusbridge, C., et al. (2024) · IEEE Access · doi:10.1109/access.2024.3424412 · Cited by 4
“The most popular approaches are based on extracted features from an RGB image such as SIFT [24], SURF [25], and FAST [26].”
MethodZhang, B., Xian, Y., & Ma, X. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109477 · Cited by 5
“For example, fast appearance-based mapping (FAB-MAP) [8] extracted SURF point features from query images and clustered them into visual words using k-means in low-dimensional space.”
InfluentialImage retrieval based on auto-encoder and clustering with centroid update
Bel, K. N. S., & Sam, I. S. (2024) · The Computer Journal · doi:10.1093/comjnl/bxae067 · Cited by 4
Awasthi, D., Khare, P., & Srivastava, V. K. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19889-z · Cited by 4
“SURF features are computationally more efficient as well as invariant to blur, scale, rotation, noise, Illumination, and warping [9].”
InfluentialTQU-SLAM Benchmark Feature-based Dataset for Building Monocular VO
Le, V.-H., Do, H.-S., Phan, V.-N., & Te, T.-H. (2024) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.7611 · Cited by 5
“ Experiments were carried out on the TQU-SLAM benchmark dataset for estimating VO based on PySLAM [21, 26] with extracted features, such as ORB [22], ORB2 [23], SIFT [10], SURF [11], BRISK [13], AKAZE [24], KAZE[24] , or features extracted from a DL model such as VGG [25].”
MethodImproved Unsupervised Stitching Algorithm for Multiple Environments SuperUDIS
Wu, H., Bao, C., Hao, Q., Cao, J., & Zhang, L. (2024) · Sensors · doi:10.3390/s24165352 · Cited by 6
“The classic methods include Moravec corner detection [5], Harris corner detection [6], SIFT [7,8], SURF [9,10], BRIEF [11], ORB [12–14], BRISK [15] and KAZE [16–18].”
MethodWang, Y., Zhang, J., Wei, R., Gao, W., & Wang, Y. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681431 · Cited by 28
“Early methods [2, 43] based on handcrafted features [3, 25] face challenges due to the large viewpoint and appearance differences between queries and references.”
HS-Surf: A Novel High-Frequency Surface Shell Radiance Field to Improve Large-Scale Scene Rendering
Qin, J., Luo, F., Cao, T., et al. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681436 · Cited by 4
Deep Learning-Based Real-Time Engine Part Inspection With Collaborative Robot Application
Ardiç, O., & Çetinel, G. (2024) · IEEE Access · doi:10.1109/access.2024.3489714 · Cited by 5
“Feature extraction steps can be carried out using known machine learning or deep learning methods [15], [16], [17], [18].”
Enhancing Image Feature Matching Detection: ORB and HDBSCAN algorithm integration
Goel, A., Mishra, P., & Bhatia, R. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10724016 · Cited by 4
SRPose: Two-View Relative Pose Estimation with Sparse Keypoints
Rui, Y., Zhang, Y., Pan, Z., Zhu, J., Wang, C., & Jia, B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73010-8_6 · Cited by 10
Liu, H., Zhao, X., Liu, Q., & Chen, W. (2024) · Sensors · doi:10.3390/s24227373 · Cited by 7
“Moreover, Bay et al. developed the SURF [8] algorithm, which constructs a Hessian matrix for key point localization, significantly reducing computation and increasing detection speed.”
OneBEV: Using One Panoramic Image for Bird’s-Eye-View Semantic Mapping
Wei, J., Zheng, J., Liu, R., Hu, J., Zhang, J., & Stiefelhagen, R. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0972-7_22 · Cited by 19
Real-Scene 3D Urban Elements Modeling for Digital Twin City Construction
Li, Y., Yang, J. J., Li, Y., Li, X. Q., Qin, Z., & Guan, Y. (2024) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot62235.2024.00031 · Cited by 4
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.