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 2,801–2,900 of 14,752
A Cooking Recipe Recommendation System with Visual Recognition of Food Ingredients
Yanai, ., Maruyama, T., & Kawano, Y. (2014) · International Journal of Interactive Mobile Technologies (iJIM) · doi:10.3991/ijim.v8i2.3623 · Cited by 24
Automatic human action recognition in a scene from visual inputs
Bouma, H., Hanckmann, P., Marck, J.-W., et al. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.918582 · Cited by 24
Object Detection Using FAST Corner Detector Based on Smartphone Platforms
Jeong, K., & Moon, H. (2011) · ACIS/JNU International Conference on Computers, Networks, Systems and Industrial Engineering · doi:10.1109/cnsi.2011.60 · Cited by 24
“For faster feature matching, SURF algorithms that have similar performance to SIFT while being much faster are used [2].”
MethodImproving SIFT-based Descriptors Stability to Rotations
Bellavia, F., Tegolo, D., & Trucco, E. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.845 · Cited by 30
Hindmarsh, S., Andreae, P. M., & Zhang, M. (2012) · doi:10.1145/2425836.2425855 · Cited by 24
“These algorithms have since been improved upon with methods which take these difficulties into consideration [2, 3, 9, 15].”
MethodNavigating a Portable Robotic Device by a 3D imaging sensor
Ye, C. (2010) · Proceedings of IEEE Sensors/Proceedings of IEEE Sensors ... · doi:10.1109/icsens.2010.5690750 · Cited by 24
“This may be achieved through the following efforts: (1) investigate other feature descriptors and adopt one with less computational cost such as the SURF (Speeded Up Robust Features) [15] for the VR-odometry; and (2) use spatial invariants between the detected features' 3D points (e.g., distances between the 3D points…”
Integrated Content and Context Analysis for Mobile Landmark Recognition
Chen, T., Yap, K., & Chau, L. (2011) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2011.2161413 · Cited by 24
ARIES: Enabling Visual Exploration and Organization of Art Image Collections
Crissaff, L., Ruby, L. W., Deutch, S., et al. (2017) · IEEE Computer Graphics and Applications · doi:10.1109/mcg.2017.377152546 · Cited by 24
Feature-Based Efficient Moving Object Detection for Low-Altitude Aerial Platforms
Loğoğlu, K. B., Lezki, H., Yucel, M. K., et al. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.248 · Cited by 24
“At each acquired frame, keypoints and corresponding descriptors (for our case; SURF [2]) are calculated.”
MethodMastcam image enhancement using estimated point spread functions
Kwan, C., Dao, M., Chou, B., Kwan, L.-Y. M., & Ayhan, B. (2017) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon.2017.8249023 · Cited by 24
Hierarchical information quadtree: efficient spatial temporal image search for multimedia stream
Zhang, C., Chen, R., Zhu, L., Liu, Y., Lin, Y., & Huang, F. L. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6284-y · Cited by 24
“Local feature representations such as the bag-of-visual-words (BoVW) models [28, 41, 42] applying local feature descriptors such as SIFT [20, 21, 45] and SURF [4, 46].”
MethodSuzuki, K., Hiroki, M. O. R. I., & Ogata, T. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2853651 · Cited by 23
Dynamic topology and relevance learning SOM-based algorithm for image clustering tasks
Medeiros, H. R., de Oliveira, F. D. B., Bassani, H. F., & Araujo, A. F. R. (2018) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2018.11.003 · Cited by 24
Detection of breast cancer mass using MSER detector and features matching
Hassan, S. A., Sayed, M. S., Abdalla, M. I., et al. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7358-1 · Cited by 24
“There are also some previous works that use SURF descriptor for feature extraction process in breast cancer detection and classification, such as Matos [13], Deshmukh [5] and Jasmin [9].”
MethodInfluentialJames, J. G., Agrawal, P., & Rajwade, A. V. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00793 · Cited by 34
“Our salient feature point detection combines four algorithms: (1) difference of Gaussians (DoG) used by SURF[6], (2) the FAST method [24], (3) the popular Harris corner method, and (4) the BRISK technique [17].”
MethodImage Feature Matching Based on Deep Learning
Liu, Y., Xu, X., & Li, F. (2018) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/compcomm.2018.8780936 · Cited by 24
“Based on the SIFT algorithm, Speed Up Robust Features (SURF) algorithm [2] is improved the calculation speed, but the robustness of its features is reduced, and the effect of large-scale image matching is generally satisfactory.”
MethodSearch and Rescue Under the Forest Canopy Using Multiple UAS
Tian, Y., Liu, K. Y., Ok, K., Tran, L., Allen, D., Roy, N., & How, J. P. (2020) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-33950-0_13 · Cited by 27
Wrist Vascular Biometric Recognition Using a Portable Contactless System
Garcia-Martin, R., & Sánchez-Reillo, R. (2020) · Sensors · doi:10.3390/s20051469 · Cited by 24
Gradient-Based Feature Extraction From Raw Bayer Pattern Images
Zhou, W., Zhang, L., Gao, S., & Lou, X. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3067166 · Cited by 33
Tiwari, S., Bhandari, R. B., & Raman, B. (2020) · ACM SIGCAS Conference on Computing and Sustainable Societies (COMPASS) · doi:10.1145/3378393.3402284 · Cited by 24
“Next, they use Bag of Words (BoW) model [11] with SURF (Speeded up robust features) [3] to extract features which are then trained using an SVM [45] classifier.”
MethodThe role of machine intelligence in photogrammetric 3D modeling – an overview and perspectives
Qin, R., & Gruen, A. (2020) · International Journal of Digital Earth · doi:10.1080/17538947.2020.1805037 · Cited by 39
Kanellakis, C., Fresk, E., Mansouri, S. S., Kominiak, D., & Nikolakopoulos, G. (2020) · IEEE Access · doi:10.1109/access.2020.3028195 · Cited by 40
A Survey on the Use of Computer Vision to Improve Software Engineering Tasks
Bajammal, M., Stocco, A., Mazinanian, D., & Mesbah, A. (2020) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2020.3032986 · Cited by 31
“Furthermore, scale-and transformation-invariant features (e.g., SURF– Speeded-Up Robust Features [101], Wavelets [102]), which are basically features aiming at analyzing image structure and content, were used to classify and detect GUI elements [8, 64, 73, 85].”
MethodSASSI — Super-Pixelated Adaptive Spatio-Spectral Imaging
Saragadam, V., DeZeeuw, M., Baraniuk, R. G., et al. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3075228 · Cited by 25
Accurate and Robust Teach and Repeat Navigation by Visual Place Recognition: A CNN Approach
Camara, L. G., Pivoňka, T., Jílek, M., et al. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341764 · Cited by 24
Abdullah, F., Ghadi, Y. Y., Gochoo, M., Jalal, A., & Kim, K. (2021) · Entropy · doi:10.3390/e23050628 · Cited by 27
GMSK-SLAM: a new RGB-D SLAM method with dynamic areas detection towards dynamic environments
Wei, H., Zhang, T., & Zhang, L. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11168-5 · Cited by 23
“The limitation of the classical feature matching algorithms (SIFT [21], SURF [3], Hamming Distance, Brute Force Matcher, FANN [24], ORB[13, 30]) is that the algorithm with strong robustness has low matching speed, while the algorithm with high matching speed has poor robustness.”
MethodDibs, H., Hasab, H. A., Jaber, H. S., et al. (2021) · Innovative Infrastructure Solutions · doi:10.1007/s41062-021-00598-7 · Cited by 24
“Therefore, this step has received considerable attention [1, 2].”
BackgroundMethodInfluentialPRISMA Spatial Resolution Enhancement by Fusion With Sentinel-2 Data
Acito, N., Diani, M., & Corsini, G. U. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3132135 · Cited by 24
Singh, N., Rathore, S. S., & Kumar, S. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13160-z · Cited by 28
“SURF descriptor is a rotation and scale-invariant scheme.”
InfluentialAutomatic freezing-tolerant rapeseed material recognition using UAV images and deep learning
Li, L., Li, L., Qiao, J., et al. (2022) · Plant Methods · doi:10.1186/s13007-022-00838-6 · Cited by 24
“In the traditional machine learning models, the SIFT [41] and SURF [42] are selected as the hand-crafted features.”
MethodFast image mosaicing using incremental bags of binary words
Garcia‐Fidalgo, E., Ortiz, A., Bonnin‐Pascual, F., & Joan P. Company (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487247 · Cited by 25
A novel zero-watermarking algorithm based on robust statistical features for natural images
Wang, X., Wen, M., Tan, X., et al. (2022) · The Visual Computer · doi:10.1007/s00371-022-02544-9 · Cited by 24
Yang, H., Liang, L., Carlone, L., & Toh, K.-C. (2022) · Mathematical Programming · doi:10.1007/s10107-022-01912-6 · Cited by 45
Hussein, F., Al-Ahmad, A., El-Salhi, S., Alshdaifat, E., & Al-Hami, M. A. (2022) · Data · doi:10.3390/data7090122 · Cited by 24
“• SURF: Speeded-Up Robust Features (SURF) is a detector–descriptor scheme used in the fields of computer vision and image analysis [27].”
MethodMulti-level Taxonomy Review for Sign Language Recognition: Emphasis on Indian Sign Language
Bahia, N. K., & Rani, R. (2022) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3530259 · Cited by 26
“Lesslifespan.”
Arabic Optical Character Recognition: A Review
Alghyaline, S. (2022) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2022.024555 · Cited by 32
Hou, K., Kong, D., Jiang, J., Zhuang, H., Huang, X., & Fang, Z. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3268850 · Cited by 26
Data Diversity in Convolutional Neural Network Based Ensemble Model for Diabetic Retinopathy
Inamullah, Hassan, S., Alrajeh, N. A., Mohammed, E. A., & Khan, S. (2023) · Biomimetics · doi:10.3390/biomimetics8020187 · Cited by 25
Robust Biometric System Using Palmprint for Personal Verification
Badrinath, G. S., & Gupta, P. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-01793-3_57 · Cited by 24
“The SURF [14] is recently emerged cutting edge methodology for pattern recognition, and has been used in general object recognition and for other machine vision applications [17], [18].”
BackgroundMethodContent Based Video Retrieval Using SURF Descriptor
Asha, S., & Sreeraj, M. (2013) · International Conference on Advances in Computing and Communications (ICACC) · doi:10.1109/icacc.2013.49 · Cited by 24
AUTOMATIC ORIENTATION OF IMAGE SEQUENCES IN CULTURAL HERITAGE
Pizzo, S. D., & Troisi, S. (2012) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsarchives-xxxviii-5-w16-293-2011 · Cited by 25
“…feature extraction classified as blob detectors or region detector consent to extract from a generic image specific features called keypoints and a vector of descriptors associated with them, which express the trend of the gradient in the surrounding area (Brown et. al, 2007; Bay et al., 2006)..”
BackgroundMethodVarfolomieiev, A. Y., & Lysenko, O. M. (2013) · Journal of Real-Time Image Processing · doi:10.1007/s11554-013-0354-1 · Cited by 24
da Silva, A. T., dos Santos, J. A., Falcão, A. X., Torres, R. D. S., & Magalhães, L. P. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.12.001 · Cited by 26
Schauwecker, K., Klette, R., & Zell, A. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385492 · Cited by 25
Towards Detecting Changes in Underwater Image Sequences
Delaunoy, O., Gracias, N., & García, R. (2008) · doi:10.1109/oceanskobe.2008.4531004 · Cited by 24
Mobile Landmark Search with 3D Models
Min, W., Xu, C., Xu, M. G., et al. (2014) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2014.2302744 · Cited by 24
“Meanwhile, local features such as Speeded Up Robust Feature (SURF) [33], MPEG-7 image signature, and Scale-Invariant Feature Transform (SIFT) feature [15] were devised to handle luminance and geometry variances.”
MethodKnuckle Biometrics Based on Texture Features
Choraś, M., & Kozik, R. (2010) · doi:10.1109/etchb.2010.5559285 · Cited by 24
A Fast Integral Image Computing Hardware Architecture With High Power and Area Efficiency
Ouyang, P., Yin, S.-Y., Zhang, Y., Liu, L.-B., & Wei, S.-J. (2015) · IEEE Transactions on Circuits and Systems - II - Express Briefs · doi:10.1109/tcsii.2014.2362651 · Cited by 22
“It can be used to compute the Haar-like feature in the Adaptive Boosting (AdaBoost)-based face detection [1], [2], speech detection, and human activity recognition [3], and can also be used to compute the Speeded Up Robust Features in the corresponding detection occasions [4].”
MethodLocal feature-based multi-object recognition scheme for surveillance
Kim, D., Rho, S., & Hwang, E. (2012) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2012.03.005 · Cited by 23
“(i) We calculate interest points for each image and then construct their local feature descriptors using SURF (Bay et al., 2006).”
BackgroundMethodInfluentialA Method Based on the Indirect Approach for Counting People in Crowded Scenes
Conte, D., Foggia, P., Percannella, G., et al. (2010) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2010.86 · Cited by 24
“Interest points are determined by using the SURF algorithm [3] and not the Harris corner detector as in the paper by Albiol et al.”
MethodYamazaki, K., & Inaba, M. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696739 · Cited by 24
“Although recently developed image features [8] [11] [13] provide highly reliable results for the purpose of object detection, these features cannot be used for clothing because there is an assumption that the transformations are limited only to solid objects.”
BackgroundPuerto-Souza, G. A., & Mariottini, G. L. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385979 · Cited by 23
“Several algorithms have been proposed to extract features (SIFT [17], SURF [21], ASIFT [22], etc.”
MethodLow-cost 3D scene reconstruction for response robots in real-time
Tran, J., Ufkes, A., Fiala, M. A., & Ferworn, A. (2011) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr.2011.6106780 · Cited by 22
“Several well-known feature detection algorithms and feature tracking/matching methods were examined, including SURF [19], Shi-Tomasi corners [20], and FAST corners [21, 22].”
MethodRoopalakshmi, R., & Reddy, G. R. M. (2012) · Signal Processing · doi:10.1016/j.sigpro.2012.06.004 · Cited by 27
Exact order based feature descriptor for illumination robust image matching
Kim, B., Yoo, H., & Sohn, K. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.04.015 · Cited by 24
“Bay et al. [11] proposed the SURF descriptor, which reduces the computation time signi fi cantly by employing an integral image.”
BackgroundFace detection and recognition with SURF for human-robot interaction
An, S., Ma, X., Song, R., & Li, Y. (2009) · IEEE International Conference on Automation and Logistics (ICAL) · doi:10.1109/ical.2009.5262624 · Cited by 23
Schaeferling, M., & Kiefer, G. (2010) · International Conference on ReConFigurable Computing and FPGAs (ReConFig) · doi:10.1109/reconfig.2010.11 · Cited by 25
HiPPAI: High Performance Portable Accelerator Interface for SoCs
Stillwell, P. M., Chadha, V., Tickoo, O., et al. (2009) · International Conference on High Performance Computing (HiPC) · doi:10.1109/hipc.2009.5433219 · Cited by 24
Intensity self similarity features for pedestrian detection in Far-Infrared images
Miron, A., Besbes, B., Rogozan, A., Aïnouz, S., & Bensrhair, A. (2012) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2012.6232227 · Cited by 26
Accelerating SURF detector on mobile devices
Yang, X. Y., & Cheng, K.-T. T. (2012) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2393347.2393427 · Cited by 24
“Over the past decades, several detectors [1, 2, 3, 4, 5, 16] have been developed.”
BackgroundDermoscopic interest point detector and descriptor
Zhou, H., Chen, M., & Rehg, J. M. (2009) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2009.5193307 · Cited by 26
Detecting Moving Objects Using a Camera on a Moving Platform
Lin, C.-C., & Wolf, M. C. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.121 · Cited by 24
“Feature points are found by SURF algorithm [6] in every frame.”
MethodShivakumar, B. L., & Baboo, S. S. (2011) · International Journal of Computer Applications · doi:10.5120/3283-4472 · Cited by 26
The Effect of Gamification on Emotions - The Potential of Facial Recognition in Work Environments
Korn, O., Boffo, S., & Schmidt, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-20901-2_46 · Cited by 29
“These key points were extracted from detected faces using the Speeded Up Robust Features algorithm (SURF) which is invariant towards scale and rotation [1].”
MethodKaul, H., Anders, M. A., Mathew, S. K., et al. (2016) · Digest of technical papers/Digest of technical papers - IEEE International Solid-State Circuits Conference · doi:10.1109/isscc.2016.7418006 · Cited by 24
“Energy-efficiency measurements also improve with algorithm-dependent SURF-128 [5] scale- and rotation-invariant feature vector matching for object recognition.”
BackgroundPayá, L., Reinoso, Ó., Berenguer, Y., et al. (2016) · Journal of Sensors · doi:10.1155/2016/1209507 · Cited by 24
Visual Odometry Drift Reduction Using SYBA Descriptor and Feature Transformation
Desai, A., & Lee, D.-J. (2016) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2015.2511453 · Cited by 24
Indoor navigation with smartphone-based visual SLAM and Bluetooth-connected wheel-robot
Kao, W., & Huy, B. Q. (2013) · International Automatic Control Conference · doi:10.1109/cacs.2013.6734167 · Cited by 23
“Other feature detection algorithms with lower computation cost such as SURF (Speeded Up Robust Features) [5] are also developed.”
MethodRobust Video Stabilization Using Particle Keypoint Update and l1-Optimized Camera Path
Jeon, S., Yoon, I., Jang, J., Yang, S., Kim, J., & Paik, J. (2017) · Sensors · doi:10.3390/s17020337 · Cited by 24
A PROMPT METHODOLOGY TO GEOREFERENCE COMPLEX HYPOGEA ENVIRONMENTS
Troisi, S., Baiocchi, V., Pizzo, S. D., et al. (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-w3-639-2017 · Cited by 24
Pharos: improving navigation instructions on smartwatches by including global landmarks
Wenig, N., Wenig, D., Ernst, S., Malaka, R., Hecht, B., & Schöning, J. (2017) · International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) · doi:10.1145/3098279.3098529 · Cited by 30
“We compared the most common image features used in object detection tasks in combination with machine learning on three di ff erent landmarks: With this training data we compared SIFT [31], SURF [3] and ORB [44] as image features in combination with a Support Vector Machine [5] and an approach using a convolutional neu…”
MethodInfluentialYu, H., Gao, F., Jiang, L., & Ma, S. (2017) · JMIR mhealth and uhealth · doi:10.2196/mhealth.8242 · Cited by 24
“An algorithm roughly estimates pairwise translation of FoVs by stitching each captured FoV with the last one through key point (KP) detection and matching with the speeded-up robust features (SURF) algorithm [26,27].”
MethodVisMerge: Light Adaptive Vision Augmentation via Spectral and Temporal Fusion of Non-visible Light
Orlosky, J., Kim, P., Kiyokawa, K., et al. (2017) · IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2017.19 · Cited by 24
Połap, D., Kęsik, K., Książek, K., et al. (2017) · Sensors · doi:10.3390/s17122803 · Cited by 24
Latest Developments in Reality-Based 3D Surveying and Modelling
Remondino, F., Georgopoulos, A., González‐Aguilera, D., & Agrafiotis, P. (2018) · MDPI eBooks · doi:10.3390/books978-3-03842-685-1 · Cited by 45
Optical-aided, autonomous and optimal space rendezvous with a non-cooperative target
Volpe, R., & Circi, C. (2019) · Acta Astronautica · doi:10.1016/j.actaastro.2019.01.020 · Cited by 25
Mobile Robot Navigation in Indoor Environments: Geometric, Topological, and Semantic Navigation
Barber, R., Crespo, J., Gómez, C., Hernámdez, A. C., & Galli, M. (2019) · IntechOpen eBooks · doi:10.5772/intechopen.79842 · Cited by 30
“Some techniques are based on local and global descriptors such as the works presented by Bay et al. [39] and Hernández et al. [40], or a combination of both of them (Hernandez-Lopez et al. [41]).”
MethodComposite Description Based on Salient Contours and Color Information for CBIR Tasks
Iakovidou, C., Anagnostopoulos, N., Lux, M., Christodoulou, K., Boutalis, Y. S., & Chatzichristofis, S. A. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2894281 · Cited by 25
“Additionally, experiments were conducted using the local-features descriptors SURF and SIFT with two aggregation methods VLAD (16 and 64) and BOVW + WS (512, 2048).”
MethodA Continuation Method for Graph Matching Based Feature Correspondence
Yang, X., Liu, Z., & Qiao, H. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2903483 · Cited by 24
“Other unary methods generally concentrate on designing a robust appearance descriptor around each feature point, such as the well-known SIFT [1], SURF [2], shape context [3] etc.”
MethodVisual Diver Recognition for Underwater Human-Robot Collaboration
Xia, Y., & Sattar, J. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794290 · Cited by 26
Point-Cloud-Based Place Recognition Using CNN Feature Extraction
Sun, T., Liu, M., Ye, H., & Yeung, D. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2937740 · Cited by 25
“Widely adopted local descriptors include scale-invariant feature transforms (SIFT) [15], speeded-up robust features (SURF) [27], binary robust independent elementary features (BRIEF) [28], binary robust invariant scalable keypoints (BRISK) [29], oriented FAST and rotated BRIEF (ORB) [30], local difference binary (LDB)…”
Park, S., & Carriquiry, A. (2020) · Statistical Analysis and Data Mining The ASA Data Science Journal · doi:10.1002/sam.11449 · Cited by 29
“We used Matlab to implement these steps and also for detecting the SURF (speeded-up robust features) [3].”
MethodDCT-Based Local Descriptor for Robust Matching and Feature Tracking in Wide Area Motion Imagery
Gao, K., Aliakbarpour, H., Seetharaman, G. S., & Palaniappan, K. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.3000762 · Cited by 24
Khan, M. A. (2021) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22564 · Cited by 25
Diffusion runs low on persistence fast
Chen, C., & Edelsbrunner, H. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126271 · Cited by 27
“The construction is popular for the extraction of local to global features [2, 17], which are useful for image registration, camera calibration, and object recognition [18], among other computer vision tasks.”
BackgroundImage Mosaicking from Uncooled Thermal IR Video Captured by a Small UAV
Wang, Y., Camargo, A., Fevig, R. A., Martel, F., & Schultz, R. R. (2008) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai.2008.4512310 · Cited by 24
“[6] Herbert Bay, Tinne Tuytelaars, Luc Van Gool, SURF: Speeded Up Robust Features.”
ResultInfluentialTV ad video categorization with probabilistic latent concept learning
Wang, J., Duan, L., Xu, L., Lu, H., & Jin, J. S. (2007) · Multimedia Information Retrieval · doi:10.1145/1290082.1290113 · Cited by 24
Vision-based control of the Manus using SIFT
Liefhebber, F., & Sijs, J. (2007) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr.2007.4428524 · Cited by 24
“Recently various new approaches of keypoint-detection [2],[3],[4] are developed.”
Cho, D.-M., Tsiotras, P., Zhang, G., & Holzinger, M. J. (2013) · AIAA Guidance, Navigation, and Control Conference and Exhibit · doi:10.2514/6.2013-5197 · Cited by 28
Exploit the Connectivity: Multi-Object Tracking with TrackletNetPreprint
Wang, G., Wang, Y., Zhang, H., Gu, R., & Hwang, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.07258 · Cited by 35
“Fundamental matrix F can be estimated by the RANSAC [6] algorithm with matched SURF points [1] between two consecutive frames.”
MethodVideo-based Human Action Recognition using Deep Learning: A ReviewPreprint
Pham, H., Khoudour, L., Crouzil, A., Zegers, P., & Velastín, S. A. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2208.03775 · Cited by 83
Material augmented semantic segmentation of point clouds for building elements
Liang, H., Yeoh, J. K. W., & Chua, D. K. H. (2024) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13198 · Cited by 25
“To accomplish this, this study employs the speeded-up robust features (SURF; Bay et al., 2006) to extract key features and descriptors from each image, as shown in Figure 3a. SURF is chosen over the scale-invariant feature transform (SIFT; Lowe, 2004) descriptor due to its faster processing time…”
POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference
Fan, Z., Pan, P., Wang, P., Jiang, Y., Xu, D., & Wang, Z. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00773 · Cited by 58
“SIFT [50], and SURF [51], or using learned features [52, 53, 54, 55, 56, 57].”
MethodCV-Cities: Advancing Cross-View Geo-Localization in Global Cities
Huang, G., Zhou, Y., Zhao, L., & Gan, W. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3502160 · Cited by 33
“For instance, Lin et al. [11] initially employed manual features, including HOG [12], Gist [13], and color histogram, for CVGL. Viswanathan [14] transformed ground query images into satellite images and matched them using manual features, such as SIFT [15], SURF [16], and FREAK [17].”
Kéchichian, R., Valette, S., Sdika, M., & Desvignes, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13972-2_19 · Cited by 22
Genetic programming as strategy for learning image descriptor operators
Pérez, C. B., & Gustavo Olague, A. (2013) · Intelligent Data Analysis · doi:10.3233/ida-130594 · Cited by 22
“Bay et al. [20] presented the SURF algorithm (Speed Up Robust Features) which was inspired from SIFT algorithm.”
InfluentialBerns, K., Kuhnert, K.-D., & Armbrust, C. (2011) · Künstliche Intell. · doi:10.1007/s13218-011-0100-4 · Cited by 27
“For these purposes, local features such as sift [62], surf [9] etc.”
BackgroundReal time static/dynamic obstacle detection for visually impaired persons
Țapu, R., Mocanu, B., & Zaharia, T. B. (2014) · International Conference on Consumer Electronics · doi:10.1109/icce.2014.6776055 · Cited by 23
On the Use of Optical Flow for Scene Change Detection and Description
Nourani‐Vatani, N., Borges, P. V. K., Roberts, J. M., & Srinivasan, M. V. (2013) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-013-9840-8 · Cited by 23
“Local descriptors such as the Scale Invariant Feature Transform (SIFT) [33] or the Speeded-Up Robust Features (SURF) [4] have demonstrated their value but their shortcomings have also been revealed.”
BackgroundMethodInfluential
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.