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 3,301–3,400 of 14,752
Local polynomial space–time descriptors for action classification
Kihl, O., Picard, D., & Gosselin, P.-H. (2014) · Machine Vision and Applications · doi:10.1007/s00138-014-0652-z · Cited by 21
Cesana, M., Redondi, A. E. C., Tiglao, N. M. C., Grilo, A., Barceló-Ordinas, J. M., Alaei, M., & Todorova, P. (2012) · Next Generation Internet Networks (NGI) · doi:10.1109/ngi.2012.6252168 · Cited by 20
“However, practical implementations of feature extraction schemes on visual sensors has not been studied in detail yet: a working system has been presented in [20], where the features detection / extraction algorithm is based on SURF and takes about 10/20 seconds to be completed.”
BackgroundInfluentialCoverage quality and smoothness criteria for online view selection in a multi-camera network
Mavrinac, A., Chen, X., & Tan, Y. (2014) · ACM Transactions on Sensor Networks · doi:10.1145/2530373 · Cited by 20
Large scale image retrieval with visual groups
Dai, L., Sun, X., Wu, F., et al. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738532 · Cited by 20
“The local features such as SIFT [10] or SURF [11] are usually of different scales and overlapped with each other.”
Background6 DoF SLAM using a ToF camera: The challenge of a continuously growing number of landmarks
Hochdorfer, S., & Schlegel, C. B. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5651229 · Cited by 20
How was your day? Online visual workspace summaries using incremental clustering in topic space
Paul, R., Rus, D. L., & Newman, P. M. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6224762 · Cited by 20
“A visual vocabulary [13] of approximately 11 k visual words was generated by clustering SURF features [2] extracted from this data set.”
MethodA hybrid method for object identification and event detection in video
Kumar, K. P., & Parameswaran, L. (2013) · National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) · doi:10.1109/ncvpripg.2013.6776223 · Cited by 20
Cooperative Estimation of Averaged 3-D Moving Target Poses via Networked Visual Motion Observer
Hatanaka, T., & Fujita, M. (2012) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2012.2215732 · Cited by 20
“We assume that each target object has feature points and each camera can extract them from the vision data by using some techniques like [36].”
MethodPlanetary rover localization within orbital maps
Nefian, A., Bouyssounouse, X., Edwards, L., Kim, T., Hand, E., Rhizor, J., Deans, M., Bebis, G. N., & Fong, T. W. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025326 · Cited by 23
“The stereo visual odometry system starts with the detection of SURF keypoints [20].”
MethodImage Retrieval of First-Person Vision for Pedestrian Navigation in Urban Area
Kameda, Y., & Ohta, Y. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.1140 · Cited by 20
“As we have to deal with various interfering objects like other pedestrians, bicycles, and vehicles, we choose locality based operator SURF [5] for image features.”
3D mobile augmented reality in urban scenes
Gabriel Takacs, A., Choubassi, M. E., Wu, Y., & Kozintsev, I. V. (2011) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2011.6012101 · Cited by 22
Vision-based mobile robot's SLAM and navigation in crowded environments
Morioka, H., Yi, S., & Hasegawa, O. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094847 · Cited by 31
“We extract a 3D-PIRF from speeded-up robust features (SURF) [21], which is an image feature point and rotation invariant similar to SIFT, this attribute is suitable for omnidirectional camera, but with a faster calculation speed.”
MethodDIRD is an illumination robust descriptor
Lategahn, H., Beck, J., & Stiller, C. (2014) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2014.6856421 · Cited by 20
OBJECT RECOGNITION BASED ON BAG OF FEATURES AND A NEW LOCAL PATTERN DESCRIPTOR
Ferraz, C. T., PEREIRA, O., ROSA, M. V., & Gonzaga, A. (2014) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001414550106 · Cited by 20
Guiding a robotic gripper by visual feedback for object manipulation tasks
Kouskouridas, R., Amanatiadis, A. A., & Gasteratos, A. C. (2011) · IEEE International Conference on Mechatronics (ICM) · doi:10.1109/icmech.2011.5971325 · Cited by 20
“, implements both a detector and a descriptor) object recognition framework such as SIFT [35] and SUR F [36].”
MethodTracking-by-synthesis using point features and pyramidal blurring
Simon, G. (2011) · 2011 10th IEEE International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2011.6092373 · Cited by 28
“It would therefore be very useful to be able to use FAST or Harris in tracking-by-synthesis, providing that the performance of these detectors is similar to that of SURF in term of repeatability across view synthesis.”
BackgroundMethodInfluentialOn-line visual vocabularies for robot navigation and mapping
Nicosevici, T., & García, R. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354392 · Cited by 20
“In computer vision, these applications became possible with the introduction of affine invariant features [20][17][4].”
BackgroundMethodInfluentialChurchill, W., & Newman, P. M. (2012) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2012.6338716 · Cited by 20
“mance similar to Speeded Up Robust Features (SURF) [9].”
MethodAutomatic Movie Posters Classification into Genres
Ivašić-Kos, M., Pobar, M., & Ipšić, I. (2014) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-09879-1_32 · Cited by 20
Elnemr, H. A. (2016) · Journal of Computer Science · doi:10.3844/jcssp.2016.213.222 · Cited by 21
“SURF was first introduced in (Bay et al ., 2008) as an innovative interest point detector and descriptor that is scale and rotation invariant, as well as its computation, is considerably very fast.”
BackgroundMethodClassification of amyloid status using machine learning with histograms of oriented 3D gradients
Cattell, L., Platsch, G., Pfeiffer, R., Declerck, J. M., Schnabel, J. A., & Hutton, C. (2016) · NeuroImage Clinical · doi:10.1016/j.nicl.2016.05.004 · Cited by 24
“E Moreover, unlike SIFT and Speeded Up Robust Features (SURF) (Bay et al., 2006), HOG operates on a dense grid of cells rather than individual points of interest.”
Efficient Feature Coding Based on Auto-encoder Network for Image Classification
Xie, G.-S., Zhang, X.-Y., & Liu, C. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16865-4_41 · Cited by 19
Intelligent Vehicle Recognition based on Wireless Sensor Network
Nabeel, M. M., & El-Kader, S. M. A. (2013) · Cited by 20
Low-level feature extraction (including edge detection)
Nixon, M. S., & Aguado, A. S. (2012) · Elsevier eBooks · doi:10.1016/b978-0-12-396549-3.00004-5 · Cited by 20
Robust Plane-Based Calibration of Multiple Non-Overlapping Cameras
Zhu, C., Zhou, Z., Xing, Z., et al. (2016) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.73 · Cited by 20
Zhang, Y. H., Jin, X., & Wang, Z. (2016) · Memetic Computing · doi:10.1007/s12293-016-0219-9 · Cited by 20
“The equations are expressed as follows: )) 2 (2) Based on the framework of the SIFT, extended algorithms (e.g. SURF [11], MSERs and PCA-SIFT [12]) with improved performance have been proposed in the literature.”
MethodVisual Object Detection Using Cascades of Binary and One-Class Classifiers
Çevıkalp, H., & Triggs, B. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-016-0986-2 · Cited by 23
QR Code Recognition based on Principal Components Analysis Method
Tribak, H., & Zaz, Y. (2017) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2017.080433 · Cited by 20
On-Board Detection and Matching of Feature Points
Huang, J., & Zhou, G. (2017) · Remote Sensing · doi:10.3390/rs9060601 · Cited by 20
“SURF Detector The SURF detector firstly proposed by Bay [28] performs a multi-scale characteristic.”
MethodKeypoint Based Authentication And Localization Of Copy-Move Forgery In Digital Image
Sadeghi, S., Jalab, H. A., Wong, K., Uliyan, D. M., & Dadkhah, S. (2017) · Malaysian Journal of Computer Science · doi:10.22452/mjcs.vol30no2.4 · Cited by 20
“Later in 2006, Bay et al. [32] proposed SURF, which used integral images for image convolutions and a Fast-Hessian detector.”
MethodMultispectral Periocular Classification With Multimodal Compact Multi-Linear Pooling
Algashaam, F. M. A., Nguyen, K., Alkanhal, M. I., Chandran, V., Boles, W., & Banks, J. (2017) · IEEE Access · doi:10.1109/access.2017.2731118 · Cited by 19
“…of Gradient (HOG) and Local Binary Pattern (LBP) are extracted from the whole image or region of interest (ROI), the key-point features are extracted from a set of discrete points using such approaches as Scale Invariant Feature Transform (SIFT) [30] and Speeded Up Robust Features (SURF) [31].”
MethodA review of feature detection and match algorithms for localization and mapping
Li, S. (2017) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/231/1/012003 · Cited by 29
Mapping and determining the center of mass of a rotating object using a moving observer
Setterfield, T. P., Miller, D. W., Leonard, J. J., & Saenz‐Otero, A. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364917749024 · Cited by 19
“This is because extended SURF-128 feature descriptors are used in the ISS case, whereas the standard SURF feature descriptors are used in the simulated case; while providing improved feature matching, the extended descriptor is more computationally expensive to extract and match (Bay et al. (2006)).”
MethodScene Video Text Tracking With Graph Matching
Pei, W.-Y., Yang, C. H., Meng, L., Hou, J.-B., Tian, S., & Yin, X.-C. (2018) · IEEE Access · doi:10.1109/access.2018.2797181 · Cited by 18
Camera relative pose estimation for visual servoing using quaternions
Fathian, K., Jin, J., Wee, S.-G., Lee, D. H., Kim, Y., & Gans, N. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.05.014 · Cited by 19
Art painting detection and identification based on deep learning and image local features
Hong, Y., & Kim, J. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6387-5 · Cited by 23
Humanoid navigation using a visual memory with obstacle avoidance
Delfin, J., Becerra, H. M., & Arechavaleta, G. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.08.010 · Cited by 21
A sharing multi-view feature selection method via Alternating Direction Method of Multipliers
Lin, Q., Xue, Y., Wen, J., et al. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.12.043 · Cited by 20
SC-IQA: Shift compensation based image quality assessment for DIBR-synthesized views
Tian, S., Zhang, L., Morin, L., & Déforges, O. (2018) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip.2018.8698654 · Cited by 19
Single image defocus estimation by modified gaussian function
Hassan, H., Bashir, A. K., Abbasi, R., Ahmad, W., & Luo, B. (2019) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.3611 · Cited by 19
Transfer Neural Trees: Semi-Supervised Heterogeneous Domain Adaptation and Beyond
Chen, W.-Y., Hsu, T.-M. H., Tsai, Y.-H. H., Chen⋆, M.-S., & Wang, Y.-C. F. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2912126 · Cited by 21
Maiwald, F. (2019) · 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-w13-87-2019 · Cited by 20
Kazerouni, M. F., Saeed, N. T. M., & Kuhnert, K.-D. (2019) · SN Applied Sciences · doi:10.1007/s42452-019-0785-9 · Cited by 21
Event-driven stitching for tile-based live 360 video streaming
Chen, B., Yan, Z., Jin, H., et al. (2019) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/3304109.3306234 · Cited by 20
“The estimation involves feature extraction [1, 11], image matching, rough estimation based on homography and fine adjustment through bundle adjustment [19].”
MethodDriver hand localization and grasp analysis: A vision-based real-time approach
Siddharth, Rangesh, A., Ohn-Bar, E., & Trivedi, M. M. (2016) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2016.7795965 · Cited by 23
SIPs: Succinct Interest Points from Unsupervised Inlierness Probability Learning
Cieslewski, T., Derpanis, K. G., & Scaramuzza, D. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00072 · Cited by 20
Pricope, N. G., Mapes, K. L., Woodward, K. D., et al. (2019) · Drones · doi:10.3390/drones3030063 · Cited by 20
Region-based image registration for remote sensing imagery
Okorie, A. M., & Makrogiannis, S. K. (2019) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2019.102825 · Cited by 21
Deformable Surface Tracking by Graph Matching
Wang, T., Ling, H., Lang, C., Feng, S., & Hou, X. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00099 · Cited by 23
Minhas, A. A., Jabbar, S., Farhan, M., & Najam-ul-Islam, M. (2019) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-019-01554-1 · Cited by 20
A Joint Compression Scheme of Video Feature Descriptors and Visual Content
ZhangXiang, MaSiwei, WangShiqi, et al. (2017) · IEEE Transactions on Image Processing · Cited by 20
Robot perceptual adaptation to environment changes for long-term human teammate following
Siva, S., & Zhang, H. (2020) · The International Journal of Robotics Research · doi:10.1177/0278364919896625 · Cited by 21
“Feature extraction methods can be further categorized into local features (Bay et al., 2006; Calonder et al., 2010; Mikolajczyk and Schmid, 2001; Rublee et al., 2011) that describe the local information from different regions of interest, and global features (Arroyo et al., 2015; Dalal and Triggs,…”
MethodHerráez‐Aguilar, D., Madrazo, E., López‐Menéndez, H., Ramírez, M. R., Monroy, F., & Redondo-Muñóz, J. (2020) · Scientific Reports · doi:10.1038/s41598-020-63682-5 · Cited by 25
Nousias, S., Arvanitis, G., Lalos, A. S., Pavlidis, G. P., Koulamas, C., Kalogeras, A. P., & Μουστάκας, Κ. (2020) · IEEE Access · doi:10.1109/access.2020.3023167 · Cited by 20
“SfM has been signi(cid:28)cantly automated by the adoption of advanced feature extraction approaches such as SIFT [37] and SURF [38].”
MethodOn Aggregation of Unsupervised Deep Binary Descriptor With Weak Bits
Wu, G., Lin, Z., Ding, G., Ni, Q., & Han, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3025437 · Cited by 21
“Two classical feature descriptors: SIFT [1] and SURF [8] are widely used in vision recognition tasks like image retrieval and feature matching.”
MethodJanandi, R., & Cenggoro, T. W. (2020) · International Conference on Information Management and Technology (ICIMTech) · doi:10.1109/icimtech50083.2020.9211257 · Cited by 20
“It is also the method of preference for other computer vision tasks, as opposed to the traditional method that relies on feature extraction algorithm such as SIFT [6], SURF [7], PCA, and LDA.”
MethodSmart Self-Checkout Carts Based on Deep Learning for Shopping Activity Recognition
Chi, H.-C., Sarwar, M. A., Daraghmi, Y., Lin, K.-W., İk, T.-U., & Li, Y.-L. (2020) · Asia-Pacific Network Operations and Management Symposium (APNOMS) · doi:10.23919/apnoms50412.2020.9237053 · Cited by 23
“Traditional image recognition often utilizes the histogram of oriented gradients (HOG) [9], scale-invariant feature transform (SIFT) [10], speeded up robust features (SURF) [11] and other statistic functions to determine local image features.”
BackgroundQuantized Self-Supervised Local Feature for Real-Time Robot Indirect VSLAM
Li, S., Liu, S., Zhao, Q., & Xia, Q. (2021) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2021.3085326 · Cited by 24
A novel shape matching descriptor for real-time static hand gesture recognition
Lazarou, M., Li, B., & Stathaki, T. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103241 · Cited by 25
Learning by Stretching Deep Networks
Pandey, G. S., & Dukkipati, A. (2014) · Cited by 20
Visual summarization of image collections by fast RANSAC
Zhao, Y., Hong, R., & Jiang, J. (2015) · Neurocomputing · doi:10.1016/j.neucom.2014.09.095 · Cited by 21
Long-range stereo visual odometry for extended altitude flight of unmanned aerial vehicles
Warren, M., Corke, P., & Upcroft, B. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364915581194 · Cited by 22
Robust visual analysis for planogram compliance problem
Saran, A., Hassan, E., & Maurya, A. K. (2015) · doi:10.1109/mva.2015.7153257 · Cited by 20
OBJECT-BASED CHANGE DETECTION USING GEOREFERENCED UAV IMAGES
Shi, J., Wang, J., & Xu, Y. (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-1-c22-177-2011 · Cited by 20
Image Alignment for Tomography Reconstruction from Synchrotron X-Ray Microscopic Images
Cheng, C., Chien, C., Chen, H.-H., et al. (2014) · PLoS ONE · doi:10.1371/journal.pone.0084675 · Cited by 20
Wang, K., Huang, Z. F., & Zhong, Z. (2014) · Chinese Journal of Mechanical Engineering · doi:10.3901/cjme.2014.0707.118 · Cited by 20
SAR Image Matching Based on Speeded Up Robust Feature
Liu, R., & Wang, Y. (2009) · WRI Global Congress on Intelligent Systems · doi:10.1109/gcis.2009.297 · Cited by 20
Xu, L., Dai, Z., & Jia, J. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33709-3_28 · Cited by 22
Surgical Tools Recognition and Pupil Segmentation for Cataract Surgical Process Modeling
Bouget, D., Lalys, F., & Jannin, P. (2012) · Studies in health technology and informatics · doi:10.3233/978-1-61499-022-2-78 · Cited by 20
Tu, J., Sui, H., Feng, W., et al. (2016) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2016.2614298 · Cited by 20
“2) Quantitative Evaluation: In this experiment, we utilized two indices to describe the performance of the proposed method, precision and recall, and compared it with the Surf and Gabor descriptors.”
MethodInfluentialDigital image stabilization technique for fixed camera on small size drone
Mingkhwan, E., & Khawsuk, W. (2017) · Asian Conference on Defence Technology · doi:10.1109/acdt.2017.7886149 · Cited by 21
“The longest such vector lends its orientation to the interest point [13].”
BackgroundLEAST COST PATH ALGORITHM DESIGN FOR HIGHWAY ROUTE SELECTION
Sarı, F., & ŞEN, M. (2017) · International Journal of Engineering and Geosciences · doi:10.26833/ijeg.285770 · Cited by 22
Interactive Museum Guide: Accurate Retrieval of Object Descriptions
Fasel, B., & Gool, L. V. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-71545-0_14 · Cited by 20
“In this paper, we showthat thenew(SpeededUpRobustFeatures) algorithm [8] allows for similar recognition results when compared to SIFT while surpassing the latter with regard to speed substantially, while retaining its image description capabilities.”
MethodSelf-citationLocal descriptors for visual SLAM
Ballesta, M., Gil, A., Mozos, Ó. M., et al. (2007) · Lincoln Repository (University of Lincoln) · Cited by 20
Ma, J., Wang, Y., Fan, A., Xiao, G., & Chen, R. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3162115 · Cited by 23
Forward-looking sonar mosaicing for underwater environments
Hurtós, N. (2014) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 28
Chitrakar, P., Zhang, C., Warner, G., & Liao, X. (2016) · 2016 IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2016.0110 · Cited by 20
“SIFT and variants of SIFT [1-2] have been very popular for generating feature points for visual descriptions of objects-of-interest.”
Levy, J. J., Davis, M. J., Chacko, R. S., Davis, M. J., Fu, L. J., Goel, T., Pamal, A., Nafi, I., Angirekula, A., Suvarna, A., et al. (2024) · npj Precision Oncology · doi:10.1038/s41698-023-00477-7 · Cited by 20
“Feature Matching: Is accomplished with image matching (e.g., SIFT, SURF, ORB, deep feature matching 86,87 ), which can fi nd correspondent features across different viewpoints.”
Identifying Re-identification Challenges: Past, Current and Future Trends
Qian, Y., Barthélemy, J., Karuppiah, E. K., & Perez, P. (2024) · SN Computer Science · doi:10.1007/s42979-024-03271-9 · Cited by 30
“Several methods for feature extraction include: the scale-invariant feature transform (SIFT) [91], the Local Binary Pattern (LBP) [104], the Histogram of Oriented Gradient (HOG) [28], and the Speed Up Robust Features (SURF) [7].”
An Ensemble Approach to Image Matching Using Contextual Features
Morago, B., Bui, G. T. T., & Duan, Y. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2456498 · Cited by 19
Improved coding for image feature location information
Tsai, S. S., Chen, D. M., Gabriel Takacs, A., Chandrasekhar, V., Makar, M. A., Grzeszczuk, R., & Girod, B. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.935619 · Cited by 18
Towards Mobile Document Image Retrieval for Digital Library
Duan, L., Ji, R., Chen, Z., et al. (2014) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2013.2293063 · Cited by 19
Automated real-time video surveillance algorithms for SoC implementation: A survey
Salahat, E. N., Saleh, H. H., Mohammad, B. S., et al. (2013) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs.2013.6815354 · Cited by 19
“However, detection and extraction are computationally demanding and therefore can’t be used in systems with limited computational power [11].”
BackgroundGuan, T., Fan, Y., Duan, L., & Yu, J. (2014) · PLoS ONE · doi:10.1371/journal.pone.0098806 · Cited by 19
“We extract SURF features from each database panorama.”
MethodA unified framework for local visual descriptors evaluation
Kihl, O., Picard, D., & Gosselin, P.-H. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.11.013 · Cited by 21
“The SURF [7] descriptor has been developed as a faster alternative to SIFT.”
BackgroundMethodInfluentialCharacterization of 3-D Volumetric Probabilistic Scenes for Object Recognition
Restrepo, M. I., Mayer, B. A., Ulusoy, A. O., & Mundy, J. L. (2012) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2012.2201693 · Cited by 21
A new sketch-based 3D model retrieval approach by using global and local features
Wang, F., Lin, L., & Tang, M. A. (2013) · Graphical Models · doi:10.1016/j.gmod.2013.11.002 · Cited by 19
Zhao, G., Chen, L., Chen, G., & Yuan, J. (2010) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1873951.1874180 · Cited by 19
“Herbert et al. [13] proposed SURF that approximates SIFT by using Haar wavelet response and integral images to compute the histogram bins.”
MethodVideo Processing Techniques for the Contactless Investigation of Large Oscillations
Civera, M., Fragonara, L. Z., & Surace, C. (2019) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1249/1/012004 · Cited by 19
Multimodal data fusion for object recognition
Knyaz, V. A. (2019) · doi:10.1117/12.2526067 · Cited by 23
Combining Satellite Images with Feature Indices for Improved Change Detection
Pérez, D., Lu, Y., Kwan, C., Shen, Y., Koperski, K., & Jiang, L. (2018) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon.2018.8796538 · Cited by 19
“First, SURF features [34] and SIFT features [35] are extracted from the two images.”
MethodA deep multimodal system for provenance filtering with universal forgery detection and localization
Jabeen, S., Khan, M. U. G., Iqbal, R., Mukherjee, M., & Lloret, J. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09623-w · Cited by 23
“The query images were compared for fast retrieval using SURF [9].”
MethodInfluentialLee, S., Yu, W., & Yang, C. (2021) · IET Image Processing · doi:10.1049/ipr2.12226 · Cited by 22
“Fundamen-tally, robust feature extraction algorithms are required to solve this problem, such as local binary pattern (LBP) [8], BRIEF [9], SIFT [10], and SURF [11], as these algorithms have different advantages in different scenarios.”
BackgroundMGG: Monocular Global Geolocation for Outdoor Long-Range Targets
Gao, F., Deng, F. Y., Li, L., Zhang, L., Zhu, J., & Yu, C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3093789 · Cited by 21
Forero, M. G., Mambuscay, C. L., Monroy, M. F., et al. (2021) · Plants · doi:10.3390/plants10091791 · Cited by 19
A Generative Feature-to-Image Robotic Vision Framework for 6D Pose Measurement of Metal Parts
He, Z., Wu, M., Zhao, X., Zhang, S., & Tan, J. (2021) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2021.3109344 · Cited by 25
DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Points
Kuang, Z., Li, J., He, M., Wang, T., & Zhao, Y. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956472 · Cited by 30
He, Z., Shen, C., Wang, Q., Zhao, X., & Jiang, H. (2022) · Remote Sensing · doi:10.3390/rs14030706 · Cited by 19
Image Classification Approaches for Segregation of Plastic Waste Based on Resin Identification Code
Agarwal, S., Gudi, R. D., & Saxena, P. (2022) · Transactions of Indian National Academy of Engineering · doi:10.1007/s41403-022-00324-4 · Cited by 21
“Traditional image classification methods such as scale-invariant feature transform (SIFT) (Lowe et al. 2004), speeded up robust features (SURF) (Bay et al. 2006), features from accelerated segment test (FAST) (Rosten and Drummond 2006), histogram of oriented gradients (HOG) (Dalal and Triggs 2005) and binary robust in…”
MethodKong, X., & Smyl, D. (2022) · Structures · doi:10.1016/j.istruc.2022.06.009 · Cited by 21
“10 (FAST) [66], Harris-Stephens [67], binary robust invariant scalable keypoints (BRISK) [68] and speeded up robust features (SURF) [69].”
Background
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.