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 11,501–11,600 of 14,752
Soft assignment vs hard assignment coding for bag of visual words
Chougrad, H., Zouaki, H., & Alheyane, O. (2015) · International Conference on Intelligent Systems: Theories and Applications · doi:10.1109/sita.2015.7358422 · Cited by 2
“Also, we need to deal with other factors, such as the viewpoint invariance as well as the robustness to scale, rotation and intensity changes [6, 7].”
BackgroundKeypoint Detection in RGB-D Images Using Binary Patterns
Romero-González, C., Martínez-Gómez, J., García-Varea, I., & Rodríguez-Ruiz, L. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-27149-1_53 · Cited by 1
Three Dimensional Panorama Visualization for Endoscopic Video
Kumar, A., Wang, Y., Liu, K., et al. (2015) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-319-19452-3_11 · Cited by 1
Estimation of Multiple View Relations Considering Evolutionary Approaches
Cuevas, E., Zaldívar, D., & Pérez‐Cisneros, M. (2015) · Intelligent systems reference library · doi:10.1007/978-3-319-26462-2_6 · Cited by 1
Automated identification of objects based on normalized cross-correlation and genetic algorithm
Rusu, M., & Zbancioc, M. D. (2015) · E-Health and Bioengineering Conference (EHB) · doi:10.1109/ehb.2015.7391457 · Cited by 1
“Are known matching methods based on interest points such as: Harris[6], Harris-Affine [7], LoG [8], DoG, Fast [9], Fast-hessian [10], SIFT [11], ASIFT [12] etc.”
MethodA Simple View-Based Software Architecture for an Autonomous Robot Navigation System
Ayala-Raggi, S. E., González, P. D. J., Sánchez-Urrieta, S., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-20801-5_31 · Cited by 1
“On the other hand, SURF, an acronym of Speeded Up Robust Features, was proposed in [13].”
MethodOn global transform preservation by region based interest points for image registration
Kashyap, M., & Bhattacharya, M. (2015) · doi:10.1109/icrcicn.2015.7434210 · Cited by 1
Bag-of-word based brand recognition using Markov clustering algorithm for codebook generation
Benezeth, Y., Bertaux, A., & Manceau, A. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351417 · Cited by 1
“While there are other detectors and descriptors (such as MSER [14] or SURF [2] to name a few), SIFT has been extensively compared with other descriptors and it has been demonstrated that it performs very well in image matching task [15].”
BackgroundWHY THE HORIZON IS IMPORTANT FOR AIRBORNE SENSE AND AVOID APPLICATIONS
Minwalla, C., & Ellis, K. (2015) · 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-xl-1-w4-123-2015 · Cited by 1
“The SURF algorithm also failed for the March Headon 2 dataset.”
MethodInfluentialImprovement of palmprint coding techniques with feature descriptors
Bingöl, Ö., & Ekіncі, M. (2015) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2015.7130368 · Cited by 1
The Performance Evaluation of a Novel Methodology of Fixational Eye Movements Detection
Li, J., & Zhang, X. (2013) · International Journal of Bioscience Biochemistry and Bioinformatics · doi:10.7763/ijbbb.2013.v3.209 · Cited by 1
A Method Using Auxiliary Direction to Improve SURF Recall
Zhang, L., & Yue, X. (2015) · International Journal of Hybrid Information Technology · doi:10.14257/ijhit.2015.8.11.04 · Cited by 1
An Image Automatic Matching Method Based on FAST Corner and LBP Descriptor
Zhang, Y. (2013) · Journal of Information and Computational Science · doi:10.12733/jics20101843 · Cited by 1
Video Shot segmentation algorithm based on SURF
Pan, S., Sun, S., Yang, L., et al. (2015) · International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE) · doi:10.2991/icmmcce-15.2015.357 · Cited by 1
An Implementation of the Real-time Image Stitching Algorithm Based on ROI
Kwak, J.-C. (2015) · Journal of IKEEE · doi:10.7471/ikeee.2015.19.4.460 · Cited by 1
nun, N. V. A., & Jareonpon, C. (2015) · International Conference on Intelligent Systems and Image Processing (ICISIP) · doi:10.12792/icisip2015.022 · Cited by 1
Multi-camera based Images through Feature Points Algorithm for HDR Panorama
Yeong, J.-H. (2015) · International journal of advanced smart convergence · doi:10.7236/ijasc.2015.4.2.6 · Cited by 1
“Image synthesis extracts the feature points of images using SURF algorithm and calculates their local invariant features.”
BackgroundA Fast and Power-Efficient Memory-Centric Architecture for Affine Computation
Yin, S., Ouyang, P., Liu, L., et al. (2016) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2016.2530168 · Cited by 1
“F EATURE detection is very important in computer vision applications [1].”
BackgroundClassification of Feature Points Required for Multi-Frame Based Building Recognition
Park, S.-Y., An, H.-E., Lee, G.-C., et al. (2016) · 한국통신학회논문지 · doi:10.7840/kics.2016.41.3.317 · Cited by 1
A Comparative Analysis of Object Recognition System Using SIFT, SURF and FAST Algorithms
Rajesh, G., Kaushik, R., & Jangra, R. (2016) · IJITR · Cited by 1
Object Detection in a Cluttered Scene Using SURF for Computer Assisted Histopathology
Abbas, A., Zehra, T., & Li, F. (2016) · doi:10.2991/icemie-16.2016.56 · Cited by 1
A comparison of the animal recognition between the real objects and the modeled 3D objects
Matúška, S., Hudec, R., Hlubík, J., et al. (2016) · International Conference Radioelektronika · doi:10.1109/radioelek.2016.7477414 · Cited by 1
Sawicki, Ł., Kubacki, A., & Owczarek, P. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-29357-8_29 · Cited by 1
Robust Content-Based Image Hash Functions Using Nested Lattice Codes
Nguyen, T., Hernandez, R. A. P., & Kurkoski, B. M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-31960-5_33 · Cited by 1
“First, the input signal is pre-processed to real feature vectors using signal processing techniques such as singular value decomposition (SVD), speeded up robust features (SURF), scale invariant feature transform(SIFT), Fourier transform and other signal processing operations.”
MethodInfluentialMulti-view distributed coding and selection of local binary features
Monteiro, N., Brites, C., Pereira, F. M. B., et al. (2016) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2016.7552995 · Cited by 1
Apparel coordination based on contour and dominant colours matching
Hamdy, A., Kareem, N., & Nagaty, K. (2016) · 2016 SAI Computing Conference (SAI) · doi:10.1109/sai.2016.7556012 · Cited by 1
“One of ORB’s prominent features is its remarkable efficiency in comparison to SIFT [18] and SURF (Speeded Up Robust Features) [19].”
Robust scene matching method based on sparse representation
Yang, S., Xiao, B. J., Yan, L., et al. (2016) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2016.7553967 · Cited by 1
Automatic Target Recognition from Inverse Synthetic Aperture Radar Images
Kondaveeti, H. K., & Vatsavayi, V. K. (2016) · Advances in wireless technologies and telecommunication book series · doi:10.4018/978-1-5225-0773-4.ch017 · Cited by 1
Optimization and Tracking of Vehicle Stable Features Using Vision Sensor in Outdoor Scenario
Flat No. 301, B. 2., & Sharma, K. (2016) · International Journal of Modern Education and Computer Science · doi:10.5815/ijmecs.2016.08.05 · Cited by 1
BF-ASIFT-2DPCA and ABF-ASIFT-2DPCA for Face Recognition
Vinay, A., Mathias, J. R., Fathepur, A. M., et al. (2016) · Procedia Technology · doi:10.1016/j.protcy.2016.08.126 · Cited by 1
Embedding graceful deception system in visual navigation for elderly health care
Huang, Y.-P., & Chen, G.-X. (2013) · doi:10.1109/cacs.2013.6734128 · Cited by 1
“Performance from three different methods, SIFT [6]-[7], SURF [8] and corner detection, are compared for feature evaluation.”
MethodInfluentialSparse representations of clustered video shots for action recognition
Ding, Y., & Lu, H. (2013) · International Conference on Computer Science and Network Technology (ICCSNT) · doi:10.1109/iccsnt.2013.6967162 · Cited by 1
An Aerial Video Stabilization Method Based on SURF Feature
Wu, H., & He, S.-Y. (2016) · ITM Web of Conferences · doi:10.1051/itmconf/20160705004 · Cited by 1
3D motion estimation via optimized feature point selection
Shen, Q., Dai, Y., Kong, F., et al. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.07.069 · Cited by 1
Enhancement system of nighttime infrared video image and visible video image
Wang, Y., & Piao, Y. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2256456 · Cited by 1
“Second, most images registration now are using sift algorithm([1]), surf algorithm([3]), mutual information registration algorithm([4]), based on B-spline registration algorithm([5]) and based MSER registration algorithm([6]) in the world.”
MethodVisual‐based and object‐conscious image retrieval by block reallocation into object region
Mochizuki, T., Kawai, Y., Sano, M., et al. (2016) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.22325 · Cited by 1
Video-Rate Panorama for Free-Viewpoint TV
Aziz, M. U., & Boulanger, P. (2016) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2016.16 · Cited by 1
Moving object detection by using GPS assisted image registration method
Gökçe, B., & Sonugür, G. (2016) · Pamukkale University Journal of Engineering Sciences · doi:10.5505/pajes.2016.68915 · Cited by 1
Kawabata, Y., Mizuchi, Y., Kim, Y., et al. (2016) · Lecture notes in electrical engineering · doi:10.1007/978-3-319-50904-4_30 · Cited by 1
Segmentation, Classification, and High Resolution of Image by Machine Learning.
Nagata, T. (2016) · PubMed · doi:10.11323/jjmp.36.1_23 · Cited by 1
Affine-Invariant Geometric Constraints-Based High Accuracy Simultaneous Localization and Mapping
Hua, G., & Tan, X. (2017) · Journal of Sensors · doi:10.1155/2017/1969351 · Cited by 1
“Almost all appearance-based SLAMs are pure bag-ofwords approaches that extract SIFT [1] or SURF [2] descriptors from images and then match descriptors by brute force method or NNDR [3] and so forth to calculate likelihood between two locations.”
MethodA scale-invariant keypoint detector in log-polar space
Tao, T., & Zhang, Y. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2267122 · Cited by 1
“The derived results are also compared with those from the SIFT method [7] and its fast version, the SURF method [8].”
MethodResultRobust alignment for UAV images based on adaptive adjustment
Xia, M., Yao, J., Xie, R., et al. (2016) · doi:10.1109/prrs.2016.7867017 · Cited by 1
A Survey of Feature Based Image Registration Algorithms: Performance Evaluation of SIFT Algorithm
Choksi, A., & Sevak, M. M. (2016) · Cited by 1
Brandtberg, T. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899933 · Cited by 1
“Another descriptor is the Speeded-up Robust Features Method (SURF) [2] in which the analysis is conducted in scale-space using the maxima of Hessians.”
MethodA bag of relevant regions for visual place recognition in challenging environments
Maldonado-Ramírez, A., Torres-Méndez, L. A., & Castelán, M. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899826 · Cited by 1
“In Figure 2, a comparison for the type of relevant regions detected by our visual attention algorithm, the STAR [16] and SURF [17] feature detectors is shown.”
MethodInfluentialMoreira, L. A. S., Justel, C. M., & Rosa, P. F. F. (2017) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit.2017.7915461 · Cited by 1
“B.1, with the use of SIFT and SURF descriptors.”
MethodInfluentialCumulative Color Naming for Accurate and Robust Image Retrieval
Shi, X., Guo, Z., Zhang, D., et al. (2016) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv.2016.35 · Cited by 1
Part-based deep representation for product tagging and search
Chen, K. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2280300 · Cited by 1
“In [1, 2, 4] the local descriptors (e.g., SIFT [5] and SURF [6]) are extracted and further quantized into visual words or hash bits for efficient matching.”
MethodKohyama, S., Ota, S., JINDAI, M., et al. (2015) · Transactions of the Institute of Systems Control and Information Engineers · doi:10.5687/iscie.28.249 · Cited by 1
Approximating Weighted Hamming Distance by Probabilistic Selection for Multiple Hash Tables
Tsai, C.-Y., Kuo, Y.-H., & Hsu, W. H. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16354-3_14 · Cited by 1
Face Match for Family Reunification: Real-World Face Image Retrieval
Borovikov, E., Vajda, S., & Gill, M. (2017) · International Journal of Computer Vision and Image Processing · doi:10.4018/ijcvip.2017040102 · Cited by 1
A robust feature descriptor based on multiple gradient-related features
Sun, Z., Zhou, F., & Liao, Q. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952388 · Cited by 2
Keypoints-based background model and foreground pedestrian extraction for future smart cameras
Hamdoun, O., & Moutarde, F. (2009) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 1
A Robust Method for Multimodal Image Registration Based on Vector Field Consensus
Wang, X., Liu, X., Chen, Y., & Zhou, Z. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-63315-2_12 · Cited by 3
Metric structure from motion by indoor localization using Wi-Fi channel state information
Ohara, K., Hayashi, T., Maekawa, T., et al. (2017) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2017.8015842 · Cited by 1
“First, image features such as SIFT features [1] or SURF features [2] are computed at multiple points in each image.”
Dark channel based illumination invariant feature detection
Sun, P., & Lau, H. Y. K. (2017) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2017.8023662 · Cited by 2
Face Recognition Using the Novel Fuzzy-GIST Mechanism
Vinay, A., Gagana, B., Shekhar, V. S., Shekar, V. S., Murthy, K. N. B., & Natarajan, S. (2017) · Lecture notes in networks and systems · doi:10.1007/978-981-10-5146-3_36 · Cited by 1
Towards Real-time Motion Estimation in High-Definition Video Based on Points of Interest
Pulc, P., & Holeňa, M. (2017) · Annals of Computer Science and Information Systems · doi:10.15439/2017f417 · Cited by 1
“In the following sections, we will consider only the use of ORB, for several reasons: According to both [18] and our experiments [19], ORB provides the same or even better results on approximately registered features than SIFT and SURF.”
BackgroundMethodInfluentialHuman-Assisted Learning of Object Models through Active Object Exploration
Rasch, R., & König, M. (2017) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3125739.3132601 · Cited by 1
“In this paper, we presented a human-assisted autonomous method for active object learning, consisting of three steps: manipulating the object to record images from several points of view, segmenting robot and object parts, calculating and filter SURF features of the different views.”
MethodInfluentialMeasuring level of cuteness of baby images: a supervised learning scheme
Makula, P., Kumar, A., & Mukherjee, S. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5257-x · Cited by 2
Local dominant orientation feature histograms (LDOFH) for face recognition
Cui, X., Zhou, P., & Yang, W. (2017) · Applied Informatics · doi:10.1186/s40535-017-0043-4 · Cited by 1
“2011), LTP (Tan and Triggs 2010), scaleinvariant feature transform (SIFT) (Lowe 2004), speeded-up robust features (SURF) (Bay et al.”
Bimodal codebooks based adult video detection
Liu, Y., Ouyang, J., & Liu, J. (2017) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2017.8309191 · Cited by 1
“SURF [16] visualwords and ROI based visual codebook are respectively applied for adult image detection [17, 18].”
MethodOn-board detection and matching of remotely sensing imagery
Huang, J., Zhou, G., & Zhang, R. (2017) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2017.8127761 · Cited by 1
The Development of the Virtual Studio System Using Hybrid Sensor
Kato, D., Muto, K., & Mitsumine, H. (2017) · The Journal of The Institute of Image Information and Television Engineers · doi:10.3169/itej.72.j13 · Cited by 1
Nonuniform fragmented piece reconstruction method using a texture-based patch-matching algorithm
Shih, H.-C., & Lu, J.-L. (2017) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce.2017.8229461 · Cited by 1
Γ-stochastic neighbour embedding for feed-forward data visualization
Rice, I. (2017) · Information Visualization · doi:10.1177/1473871617715212 · Cited by 1
Motion intention optimization for multirotor robust video stabilization
Aguilar, W. G., Ángulo, C., & Pardo, J. A. (2017) · CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies · doi:10.1109/chilecon.2017.8229689 · Cited by 1
“SIFT [10] (Scale Invariant Feature Transform) and SURF (Speed Up Robust Feature) [11] are the most widely used algorithms for detection, description, and almost computer vision problems [12].”
MethodCommon dictionary and domain-specific dictionary based cross-domain image classification
Zhang, K., Yuan, M., Xiong, Y., & Qu, L. (2017) · Chinese Automation Congress · doi:10.1109/cac.2017.8243257 · Cited by 1
“But before this, we need to extract the features using SURF descriptors from each domain [32].”
MethodA Research on Fast Face Feature Points Detection on Smart Mobile Devices
Li, X., Zhang, X., & Wang, H. (2018) · Wireless Communications and Mobile Computing · doi:10.1155/2018/9729014 · Cited by 1
Borovikov, E., Vajda, S., Bonifant, M. C., & Gill, M. (2018) · Procedia Computer Science · doi:10.1016/j.procs.2018.01.017 · Cited by 1
Analytical Study of Animal Biometrics: A Technical Survey
Kumar, S., Singh, S. K., Singh, R., & Singh, A. K. (2017) · Springer eBooks · doi:10.1007/978-981-10-7956-6_2 · Cited by 2
Robust active vision industrial CAD parts recognition system
Jain, T., Meenu, N. A., & Sardana, H. K. (2018) · International Journal of Intelligent Machines and Robotics · doi:10.1504/ijimr.2018.10011942 · Cited by 1
“The speeded-up robust features (SURF) (Bay et al., 2006) and scale invariant feature transform (SIFT) (Li and Ma, 2009) descriptors extracts a specific object in an occluded objects image or to detect exact matching between two images.”
BackgroundDesigning Efficient Parallel Processing in 3D Standard-Chip Stacking System with Standard Bus
Ohkawa, T., Ootsu, K., Yokota, T., Kikuchi, K., & Aoyagi, M. (2017) · IEEE International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) · doi:10.1109/mcsoc.2017.27 · Cited by 1
Study on the traditional pattern retrieval method of minorities in Gansu province
Zheng, G., Wang, B., Sun, Y., et al. (2018) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/322/5/052049 · Cited by 1
“SURF algorithm is a robust image recognition and description algorithm, first published in 2006 in the ECCV conference [1] .”
MethodStatistical evaluation of corner detectors: does the statistical test have an effect?
Anjum, F., Kanwal, N., Clark, A. F., et al. (2018) · IET Computer Vision · doi:10.1049/iet-cvi.2017.0256 · Cited by 1
ROBUST FEATURE MATCHING IN TERRESTRIAL IMAGE SEQUENCES
Abbas, A., & Ghuffar, S. (2018) · 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-3-3-2018 · Cited by 1
“…and descriptors, which provide region of interest, edges or corners (Remondino, n.d.) the most common of them are Speeded Up Robust Features (SURF) (Bay et al., 2006), Scale Invariant Feature Transform (SIFT) (Lowe, 2004), Features from Accelerated Segment Test (FAST) (Rosten and Drummond, 2005)…”
BackgroundMethodInfluentialResearch on the Algorithm for Solving the Indoor Vision Positioning Model of Mobile Robot
Zhou, G., Shen, B., & Yan, J. (2018) · International Conference on Mathematics, Modelling, Simulation and Algorithms (MMSA) · doi:10.2991/mmsa-18.2018.4 · Cited by 1
“INITIALIZATION POSITION CALCULATION The purpose of initialization location calculation is to calculate the motion platform position and posture of each image frame, and use it as the initial position of position and gesture to estimate the initial value for the subsequent adjustment adjustment model[2-4].”
MethodA MATCHING METHOD TO REDUCE THE INFLUENCE OF SAR GEOMETRIC DEFORMATION
Gao, C., & Xue, G. (2018) · 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-3-355-2018 · Cited by 1
Mathematical aspects of transit photometry for small UAV detection in video
DelMarco, S. P., & Webb, H. F. (2018) · doi:10.1117/12.2303889 · Cited by 1
Selecting Salient Features from Facial Components for Face Recognition
Gumede, A., Viriri, S., & Gwetu, M. V. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-92753-4_6 · Cited by 1
Robust and efficient techniques for texture-less object recognition
Chan, J., Kemao, Q., & Lee, J. A. (2018) · International Workshop on Advanced Image Technology (IWAIT) · doi:10.1109/iwait.2018.8369789 · Cited by 1
“Recognition of objects with low-textures has been a longstanding issue in the field of object recognition that often renders widely popular algorithms such as SIFT [1], SURF [2] and ORB [3] ineffective.”
MethodKeyword Clustering for Comparing Documents in Different Languages
Tae, J., & Shin, D.-J. (2015) · International Journal of Machine Learning and Computing · doi:10.7763/ijmlc.2015.v5.520 · Cited by 1
Automatic Image Classification for Web Content Filtering: New Dataset Evaluation
Fralenko, V. P., Suvorov, R. E., & Tikhomirov, I. A. (2018) · Studies in fuzziness and soft computing · doi:10.1007/978-3-319-75408-6_27 · Cited by 2
“They are extracted using some sub-algorithm (like SIFT [10] or SURF [11]).”
MethodEpiX: A 3D Measurement Tool for Heritage, Archeology, and Aerial Photogrammetry
Yao, S., Yu, H., Aliakbarpour, H., et al. (2018) · Springer eBooks · doi:10.1007/978-981-10-7221-5_3 · Cited by 1
Sliding window bag-of-visual-words for low computational power robotics scene matching
Ginn, D., Mendes, A. S., Chalup, S. K., et al. (2018) · International Conference on Control, Automation and Robotics (ICCAR) · doi:10.1109/iccar.2018.8384650 · Cited by 1
“One primary hindrance however has been that the methods used to extract the features from images for BOVW, such as SIFT [3] and SURF [4], are computationally expensive.”
MethodInfluentialLiu, L., Zhu, W., Yin, S., & Wei, S. (2018) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2018.2846634 · Cited by 1
“In general, at least one order of magnitude speedup can be achieved for the floating point local features, such as SIFT [5] and SURF [6].”
Towards Efficient Mobile Augmented Reality in Indoor Environments
Alahmadi, M. D., & Yang, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-94361-9_9 · Cited by 1
SIFT localisation accuracy on interpolated speckle images
Wang, V. C., & Hayes, M. (2017) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2017.8402510 · Cited by 1
Generation of Stereoscopic Image Sequences from Monocular Videos Using Epipolar Geometry
Goyal, V., & Schonfeld, D. (2018) · Electronic Imaging · doi:10.2352/issn.2470-1173.2018.2.vipc-265 · Cited by 1
Detection of copy move forgery technique based on SIFT and SURF
Aydın, Y., Muzaffer, G., & Ulutaş, G. (2018) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2018.8404609 · Cited by 1
“Hızlandırılmış Dayanıklı Öznitelikler (Speed up Robust Feature, SURF) algoritması, bir görüntüde döndürme, ölçekleme ve ötelemeden bağımsız, yerel özellik noktalarının belirlenmesi için 2006 yılında Herbert Bay tarafından geliştirilen algoritmadır [12].”
Design of video aerial target detection and tracking system based on AM5728
Li, L., Zhao, G., & Xu, S. (2018) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2018.8408277 · Cited by 1
Copy move forgery detection with using FAST key points and SIFT description vectors
Mumcu, A., & Savran, I. (2018) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2018.8404363 · Cited by 1
“KAYNAKLAR [1] Manu, V. and B.M. Mehtre, Detection of copy-move forgery in images using segmentation and SURF, in Advances in Signal Processing and Intelligent Recognition Systems.”
InfluentialTime image sequence self-encoding statistics to improve visual odometer
Zeng, C., & Yu, H. (2018) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/170/2/022019 · Cited by 1
“This paper studies the extraction processes such as SIFT[2], SURF[3], ORB[4], etc., and finds out the influence of algorithm related parameters on feature extraction.”
MethodGarain, J., Mishra, S. R., Kumar, R. K., et al. (2018) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-018-3501-y · Cited by 1
“SIFT [39] and SURF [40] points are used in this work as facial features.”
MethodFeature Extraction and Representation
Gong, S., Liu, C., Ji, Y., et al. (2018) · Modeling and optimization in science and technologies · doi:10.1007/978-3-319-77223-3_4 · Cited by 1
Content Based Image Retrieval Using Local Feature Descriptors on Hadoop for Indoor Navigation
Gaber, H., Marey, M. A. E.-R., Amin, S. E.-S., et al. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-99010-1_56 · Cited by 1
Toward semantic loop closure in simultaneous localization and mapping systems
Zhang, Y.-C., Huang, C., Yang, C.-Y., & Chen, Y.-H. (2018) · Current Developments in Lens Design and Optical Engineering · doi:10.1117/12.2320035 · Cited by 1
Word Sign Recognition of Invariant Images Based on SURF with Laplacian Eigenmaps
Narayanan, A., Sharmila, T. S., & Gajalakshmi, P. (2018) · International Conference on Computer, Communication and Signal Processing (ICCCSP) · doi:10.1109/icccsp.2018.8452825 · Cited by 1
“SURF [12] represents the collection of feature vector by creating integral images on the given grey scale which calculates the sum of pixels over upright rectangular regions.”
BackgroundMethodCommon Crucial Feature for Crowdsourcing Based Mobile Visual Location Recognition
Wang, H., Zhao, D. Y., Ma, H., et al. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451477 · Cited by 1
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.