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 9,701–9,800 of 14,752
Beyond Keypoints: Novel Techniques for Content-Based Image Matching and Retrieval
Sluzek, A. S., Yang, D.-D., & Paradowski, M. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-13208-7_69 · Cited by 2
Feature-based Image Comparison and Its Application in Wireless Visual Sensor Networks
Bai, Y. (2011) · Cited by 2
Real time multisensor Laplacian fusion on FPGA
Agrawal, K., & Chowdhury, S. R. (2015) · International Symposium on VLSI Design and Test (VDAT) · doi:10.1109/isvdat.2015.7208087 · Cited by 2
Robust image region descriptor using local derivative ordinal binary pattern
Shang, J., Chen, C., Pei, X., et al. (2015) · Journal of Electronic Imaging · doi:10.1117/1.jei.24.3.033009 · Cited by 2
Building Visual Maps with a Team of Mobile Robots
Ballesta, M. J., Gil, A., Reinoso, Ó., & Pay, L. (2011) · InTech eBooks · doi:10.5772/13122 · Cited by 2
Dealing with Data Association in Visual SLAM
Gil, A., Reinoso, Ó., Ballesta, M., & Ube, D. (2008) · InTech eBooks · doi:10.5772/6146 · Cited by 3
“Recently, a method called Speeded Up Robust Features (SURF) was presented (Bay et al., 2006).”
MethodQuasi-dense matching of selenograph based on image waves
Yang, S. Y., Li, X., Xie, J., et al. (2012) · Cited by 2
Smooth localization independent of GPS using coarse height maps
Wei, C., Wu, T. T., & Fu, H. (2015) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2015.7162620 · Cited by 2
Towards Accurate and Efficient Image Quality Assessment with Interest Points
Zhang, X., Wang, S., Ma, S., et al. (2015) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2015.58 · Cited by 2
A practical classifier for photographs and non-photographic images based on local visual features
Terayama, K., & Hioki, H. (2015) · doi:10.1109/mva.2015.7153192 · Cited by 2
“We derive visual features of BoVW with SIFT [13] and SURF [14] features.”
MethodComputer vision-based approach for rite decryption in old societies
Barros, J. M. D., Habed, A., Demonceaux, C., & Mansouri, A. (2015) · Machine Vision Applications · doi:10.1109/mva.2015.7153108 · Cited by 2
Evaluation of Aligning Methods for Landmark-Based Maps in Visual SLAM
Ballesta, M., Reinoso, Ó., Gil, A., Payá, L., & Juli, M. (2010) · InTech eBooks · doi:10.5772/9260 · Cited by 2
Improved SVD matching based on Delaunay triangulation and belief propagation
Dou, J., Qin, Q., Tu, Z., et al. (2015) · doi:10.1109/ccdc.2015.7162222 · Cited by 2
Surface reconstruction from endoscopic image sequence
Kumar, A., Wang, Y., Liu, K., et al. (2015) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-tw.2015.7216967 · Cited by 2
“Unique feature points on image frames were detected using the speeded-up robust feature (SURF) detection algorithm [1].”
MethodThe Cloud-Mobile Convergence Paradigm for Augmented Reality
Luo, X. (2011) · InTech eBooks · doi:10.5772/25690 · Cited by 2
“Representative ones among them include Harris Corners (Harris & Stephens, 1988), Shi and Tomasi (Shi & Tomasi, 1994), SIFT (Lowe, 2004), SURF (Bay et al., 2006), FERNS (Ozuysal et al.”
BackgroundEnhanced Rotational Feature Points Matching using Orientation Correction
Goh, K. M., Abu–Bakar, S. A. R., Mokji, M. M., & Sheikh, U. U. (2014) · ELCVIA Electronic Letters on Computer Vision and Image Analysis · doi:10.5565/rev/elcvia.554 · Cited by 2
State-of-the-art video coding approaches: A survey
Xu, M., Liang, Y., & Wang, Z. (2015) · IEEE International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) · doi:10.1109/icci-cc.2015.7259399 · Cited by 5
A User-Centric System for Home Movie Summarisation
Cooray, S. H., Lee, H., & O'Connor, N. E. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-17832-0_40 · Cited by 2
Mexican archaeological image retrieval based on object matching and a local descriptor
Cedillo-Hernández, M., Garcia-Ugalde, F. J., Cedillo-Hernández, A., et al. (2015) · International Conference on Computer Communication and Informatics (ICCCI) · doi:10.1109/iccci.2015.7218071 · Cited by 2
Fast Freehand Acquisition of 3D Objects and Their Visualization
Peters, G., Peters, Klaus, & haming (2010) · Journal of Communication and Computer · Cited by 2
Real time video processing and object detection on android smartphone
Chaudhari, S. B., & Patil, S. A. (2015) · International Conference on Electrical, Electronics, Signals, Communication and Optimization · doi:10.1109/eesco.2015.7254003 · Cited by 2
“On the similar concept new algorithms were born such as the Speeded-Up Feature Transform (SuRF)[8],Center Surrounded Extrema (CenSurE)[17], Good Features to Track (GFTT)[21], Maximally Stable Extremal Region Extractor (MSER)[19], and Oriented Binary Robust Independent Elementary Features (ORB)[16], and Features from A…”
MethodLow-Dimensional Local Self-Similarity Descriptor for Image Matching
Liu, J., & Zeng, G. (2011) · Lecture notes in electrical engineering · doi:10.1007/978-3-642-25646-2_39 · Cited by 2
Compressive image retrieval with modified images
Zhang, C., & Akashi, T. (2015) · Asian Control Conference (ASCC) · doi:10.1109/ascc.2015.7244465 · Cited by 2
A Spatial-Temporal-Scale Registration Approach for Video Copy Detection
Chen, S., Wang, T., Wang, J., Li, J., Zhang, Y., & Lu, H. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-89796-5_42 · Cited by 3
Efficient Development of User-Defined Image Recognition Systems
Moehrmann, J., & Heidemann, G. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37410-4_21 · Cited by 2
Palmprint retrieval based on match scores and decision-level fusion
Kavati, I., Prasad, M. V. N. K., & Bhagvati, C. (2015) · International Conference on Advances in Computing, Communications and Informatics (ICACCI) · doi:10.1109/icacci.2015.7275840 · Cited by 2
“Next, using the SURF features [7], [28] another set of representatives (i.”
MethodSingle Camera Motion Estimation: Modification of the 8-Point Method
Mirabdollah, M. H., & Mertsching, B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40852-6_14 · Cited by 2
A Study for the Self Similarity Smile Detection
Freire-Obregón, D., Antón, L., & Castrillón-Santana, M. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04391-8_13 · Cited by 2
“LAC descriptors are specially useful to describe points defined by a scale salient point detector (like DoG or SURF [2]).”
BackgroundMoving Object Detection and Tracking in Wide Area Motion Imagery
Santhaseelan, V., & Asari, V. K. (2013) · Augmented vision and reality · doi:10.1007/8612_2012_9 · Cited by 2
Evaluating Stacked Marginalised Denoising Autoencoders Within Domain Adaptation Methods
Chidlovskii, B., Csurka, G., & Clinchant, S. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24027-5_2 · Cited by 2
“2 Bag-of-visual (BOV) words [9] built on SURF features [2] on interest points.”
BackgroundA binarization technique using local edge information
Marukatat, S., Watcharabutsarakham, S., & Sinthupinyo, W. (2010) · Cited by 2
Vision-Based Fine-Grained Location Estimation
Liu, H., Mei, T., Li, H., et al. (2014) · Springer eBooks · doi:10.1007/978-3-319-09861-6_4 · Cited by 2
Person Tracking Based on a Hybrid Neural Probabilistic Model
Yan, W., Weber, C., & Wermter, S. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21738-8_47 · Cited by 2
“We extract here SURF features [1] for describing the image objects.”
MethodFast Adaptive Object Detection towards a Smart Environment by a Mobile Robot
Takano, S., Loshchilov, I., Meunier, D., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-319-03647-2_13 · Cited by 2
“Although it has become possible to run SIFT and SURF algorithm on an ordinary PC, it is still required to develop faster method for extracting local features for onboard root vision.”
Position Estimation of Multiple Light Sources for Augmented Reality
Liu, Y., Kwak, Y. S., & Jung, S. K. (2014) · Lecture notes in electrical engineering · doi:10.1007/978-3-662-45402-2_126 · Cited by 2
Analysis of Three Dimensional Object Reconstruction Method for Underwater Images
Gokhale, R., & Ramakanth Kumar, P. (2013) · Cited by 2
Pacheco-Gutiérrez, S., Stancu, A., Mustafa, M., et al. (2015) · International Conference on System Theory, Control and Computing (ICSTCC) · doi:10.1109/icstcc.2015.7321318 · Cited by 2
Performance Evaluation of Feature Point Descriptors in the Infrared Domain
Ricaurte, P., Chilán, C., Aguilera, C., et al. (2014) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004725305450550 · Cited by 2
Towards Exhaustive Pairwise Matching in Large Image Collections
Srijan, K., & Jawahar, C. V. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33863-2_22 · Cited by 2
“These visual words are used to quantize feature descriptors, such as SIFT [7], SURF [8] etc.”
MethodPhoto-Taking Point Recommendation with Nested Clustering
Kimura, K., Huang, H., & Kawagoe, K. (2012) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2012.20 · Cited by 2
“For realization of the second photo clustering, we do clustering with a set of features which are extracted from image data of photos using SURF (Speeded Up Robust Feature) method [15].”
MethodAchieving robust alignment for outdoor mixed reality using 3D range data
Inaba, M., Banno, A., Oishi, T., et al. (2012) · ACM Symposium on Virtual Reality Software and Technology (VRST) · doi:10.1145/2407336.2407348 · Cited by 2
Feature-Based GDLOH Deformable Registration for CT Lung Image
Yang, Y. H., & Xie, Y. Q. (2013) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.333-335.969 · Cited by 2
Makita, K., Nishida, J., Ishikawa, T., et al. (2013) · IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2013.6671801 · Cited by 2
“The techniques used for the detection of feature points are SURF (Speeded Up Robust Features) [2], ORB (Oriented FAST and Ro tated BRIEF) [3], and FREAK (Fast Retina Keypoint) [4].”
MethodThe Analysis of Similarity Measure Function in Image Matching Algorithms
Liu, H. L., Song, W. G., Na, P. Y., et al. (2013) · Advanced materials research · doi:10.4028/www.scientific.net/amr.842.649 · Cited by 2
Interest points based on maximization of distinctiveness
Oerlemans, A., & Lew, M. S. (2008) · doi:10.1145/1460096.1460130 · Cited by 2
“RELATED WORK Many interest point detectors are available [8-14], and depending on the application, different performance measures can be chosen.”
BackgroundA real-time 720p feature extraction core based on Semantic Kernels Binarized
Schaffner, M., Hager, P. A., Cavigelli, L., et al. (2013) · IFIP/IEEE International Conference on Very Large Scale Integration · doi:10.1109/vlsi-soc.2013.6673240 · Cited by 2
A computer vision approach to mining big solar data
Felix, S., & Csillaghy, A. (2014) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2014.7004401 · Cited by 2
Hamming embedding with fragile bits for image search
Zhuang, D., Zhang, D., Li, J., et al. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7026157 · Cited by 2
“Hamming distance based on logical exclusive-or (XOR) function is used because it ensures great performance in terms of speed and accuracy, thus this kind of similarity measure can significantly improve the performance in vision search applications over the Euclidean distance used in the floating-vector descriptors (su…”
BackgroundMethodInvariant Observer Design of a RGB-D Aided Inertial System for MAV in GPS-Denied Environments
Li, D., Li, Q., Cheng, N., Song, J., Wu, Q., & Tang, L. (2013) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2013.443 · Cited by 2
A novel framework for content-based video copy detection
Zhang, H., Zhao, Z., Cai, A., & Xie, X. (2010) · IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC) · doi:10.1109/icnidc.2010.5657881 · Cited by 2
“The SURF feature using a Hessian matrix-based measure as the detector is invariant to image scaling, translation, and rotation [11].”
Koyama, J., Makar, M. A., Araújo, A. D. M., et al. (2014) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2014.6890631 · Cited by 2
Song, D., Xu, Y., & Qin, N. (2009) · Journal of Real-Time Image Processing · doi:10.1007/s11554-009-0127-z · Cited by 2
“The two speed factor columns in the table indicate how many times CBIAA is faster than SURF and SIFT, respectively.”
MethodInfluentialThe estimation of a depth map using spatial continuity and edges
Bolecek, L., & Říčný, V. (2013) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2013.6614068 · Cited by 2
Li, B., Shang, K., & Zheng, Y. (2011) · IEEE International Conference on Communication Software and Networks · doi:10.1109/iccsn.2011.6014731 · Cited by 2
Information Gain Study for Visual Vocabulary Construction
Le, H. T., Gbèhounou, S., Urruty, T., et al. (2015) · ACM International Conference on Multimedia Retrieval (ICMR) · doi:10.1145/2671188.2749319 · Cited by 2
Efficient descriptor tree growing for fast action recognition
Ubalde, S., Goussies, N. A., & Mejail, M. E. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2013.05.007 · Cited by 2
“, 2008) use an extension of SURF features (Bay et al., 2006) to 3D.”
MethodInfluentialFeature detection and matching towards augmented reality applications on mobile devices
Gündoğdu, E., & Alatan, A. A. (2012) · 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video · doi:10.1109/3dtv.2012.6365432 · Cited by 2
““SURF:Speeded up robust features,”.”
BackgroundInfluentialREAL TIME DATA PROCESSING FOR OPTICAL REMOTE SENSING PAYLOADS
Wohlfeil, J., Börner, A., Buder, M., et al. (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-xxxix-b5-63-2012 · Cited by 2
Weighted least squares based improved SIFT matching algorithm
Zhu, W., Jiang, Y., Wang, M., & Lai, C.-H. (2012) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2012.6469982 · Cited by 2
Binary visual features for ROV motion estimation
Ferreira, F., Veruggio, G., Caccia, M., et al. (2013) · doi:10.1109/oceans-bergen.2013.6608116 · Cited by 2
“For instance, BRIEF can work well with a minimum of 256 descriptors that occupy 256 bits while popular floating point descriptors like SURF [4] require a minimum of 256 bytes, thus eight times bigger.”
MethodCLRF: Compressed Local Retinal Features for image description
Kannan, R., Ghinea, G., Kannaiyan, S., & Swaminathan, S. (2015) · International Conference on Advances in Pattern Recognition · doi:10.1109/icapr.2015.7050672 · Cited by 3
“The SURF [8] descriptor is proposed to fasten the feature matching to achieve a real time performance.”
MethodWhat We Can Learn From the Primate’s Visual System
Krüger, N., Zillich, M., Janssen, P., & Buch, A. G. (2015) · Künstliche Intell. · doi:10.1007/s13218-014-0345-9 · Cited by 2
Demirci, B., Arslan, O., Tunaboylu, N. S., & Altun, H. (2013) · International Conference on Technological Advances in Electrical, Electronics and Computer Engineering · doi:10.1109/taeece.2013.6557288 · Cited by 4
“The algorithm exhibits superior performance in many applications under different conditions [12,13].”
BackgroundYao, Y., & Li, C. (2013) · IAPR Asian Conference on Pattern Recognition (ACPR) · doi:10.1109/acpr.2013.153 · Cited by 2
“Then the Speeded Up Robust Features (SURF) [5] are extracted from adjacent frames to locate the same ROIs.”
MethodVisual people detection for safe Human-Robot Interaction
Martínez-Martín, E., & del Pobil, A. P. (2013) · IEEE RO-MAN · doi:10.1109/roman.2013.6628478 · Cited by 2
“Commonly used local features are colour [4], scale-invariant descriptors (SURF, SIFT) [5], [6], Histogram of Oriented Gradient (HOG) [1], Local Receptive Field 1Authors are with Robotic Intelligence Lab, Engineering and Computer Science Department, Universitat Jaume-I, Avda.”
BackgroundRatsamee, P., Mae, Y., Jinda-apiraksa, A., Machajdik, J., Ohara, K., Kojima, M., Sablatnig, R., & Arai, T. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6697110 · Cited by 3
“There are 4 similarity criteria: the number of Speeded Up Robust Features (SURF) [13] matching points, the average of the SURF matching error,the color histogram intersection, and the frame number distance.”
BackgroundInfluentialSubobject detection through spatial relationships on mobile phones
Brombach, B., Bruns, E., & Bimber, O. (2009) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/1502650.1502688 · Cited by 4
“An enhancement of SIFT, called SURF [3], is applied for classification.”
MethodEvaluation of distinctive color features from harris corner key points
Sirisha, B., & Sandhya, B. (2013) · IEEE International Advance Computing Conference · doi:10.1109/iadcc.2013.6514414 · Cited by 2
Straub, J. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2050171 · Cited by 2
Concurrent photo sequence organization
Presti, L. L., & Cascia, M. L. (2012) · Multimedia Tools and Applications · doi:10.1007/s11042-012-1079-z · Cited by 2
Effectiveness evaluation of view-based navigation for obstacle avoidance
Hagiwara, Y., Inamura, T., & Choi, Y. (2013) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.1109/iccas.2013.6704068 · Cited by 2
The matching of infrared markers for tracking objects using stereo pairs
Zeynalov, R. S., Yakubenko, A. A., & Konushin, A. (2013) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661813040196 · Cited by 2
Stereoscopic laparoscopy using depth information from 3D model
Kumar, A., Wang, Y., Wu, C.-J., et al. (2014) · doi:10.1109/isbb.2014.6820904 · Cited by 2
TelePort: Virtual touring of Dun-Huang with a mobile device
Chen, S.-C., Hsu, C.-W., Huang, D.-Y., et al. (2013) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2013.6618406 · Cited by 2
“To ensure the rotation and light invariance of the visual feature, we select the SURF [18] descriptor as the feature.”
MethodInfluentialXu, Z., Zhang, L., Xing, M., et al. (2014) · IET Image Processing · doi:10.1049/iet-ipr.2014.0632 · Cited by 2
Zhang, W., Zhang, X., Chen, Y., et al. (2013) · Computers & Geosciences · doi:10.1016/j.cageo.2013.05.013 · Cited by 2
Straub, J. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2050174 · Cited by 2
SIM - Smart Interactive Map with Pointing Gestures
Lê, H.-Â., Mac, K.-N. C., Pham, T.-A., et al. (2012) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc.2012.178 · Cited by 2
“• The scale- and rotate- invariant keypoints of each image is extracted using the SURF technique [12].”
MethodADAPTIVE HIERARCHICAL DENSE MATCHING OF MULTI-VIEW AIRBORNE OBLIQUE IMAGERY
Zhang, Z. C., Dai, C. G., Ji, S., et al. (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-3-w2-289-2015 · Cited by 2
Automatic registration of multi-source medium resolution satellite data
Barazzetti, L., Gianinetto, M., & Scaioni, M. (2014) · 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-7-23-2014 · Cited by 2
“The current implementation of the automatic extraction of multi-image correspondences is carried out with SURF operator (Bay et al., 2008).”
Method3D dense local point descriptors for mouse brain gene expression images
Le, Y. H., Kurkure, U., & Kakadiaris, I. A. (2014) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2014.03.006 · Cited by 4
[Paper] Semantic Concept Detection based on Spatial Pyramid Matching and Semi-supervised Learning
Kawai, Y., & Fujii, M. (2013) · ITE Transactions on Media Technology and Applications · doi:10.3169/mta.1.190 · Cited by 2
Cross domain boosting for information fusion in heterogeneous sensor-cyber sources
Zhang, Z., Zhang, Z., & Liu, S. (2015) · Signal Processing · doi:10.1016/j.sigpro.2015.04.002 · Cited by 2
On-line object segmentation through human-robot interaction
Kim, S., Kim, D. H., & Park, S.-K. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5651041 · Cited by 2
Robust visual odometry using stereo reconstruction error model
Pojar, D., Jeong, P., & Nedevschi, S. (2012) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp.2012.6356178 · Cited by 2
A feature compression scheme for large scale image retrieval systems
Khan, U. M., McCane, B., & Trotman, A. (2012) · doi:10.1145/2425836.2425929 · Cited by 2
“fast and competitive to SURF and U-SURF[1].”
MethodON-LINE INCREMENTAL 3D HUMAN BODY RECONSTRUCTION FOR HMI OR AR APPLICATIONS
Almeida, L., Vasconcelos, F., Barreto, J. P., et al. (2011) · Field Robotics · doi:10.1142/9789814374286_0041 · Cited by 2
Curvature Based Robust Descriptors
Mohideen, F., & Rodrigo, R. P. (2012) · British Machine Vision Conference (BMVC) · doi:10.5244/c.26.41 · Cited by 2
On filtering by means of generalized integral images: a review and applications
Haselhoff, A., & Kummert, A. (2010) · Multidimensional Systems and Signal Processing · doi:10.1007/s11045-010-0112-5 · Cited by 2
“This multi-scale analysis is applied in various methods in the context of edge, corner or blob detection to define interest points (Lindeberg 1998; Lowe 2004; Bay et al. 2006).”
MethodBouchahma, M., & Yan, W. (2012) · International Conference on Geoinformatics · doi:10.1109/geoinformatics.2012.6270334 · Cited by 2
Integral image computation on GPU
Chouchene, M., Sayadi, F. E., Atri, M., & Tourki, R. (2013) · International Multi-Conference on Systems, Signals & Devices (SSD) · doi:10.1109/ssd.2013.6564007 · Cited by 2
“In the SURF algorithm [5] [6], it accelerates the calculation first and second order of Gaussian derivative that uses the integral image.”
MethodA new affine-invariant image matching method based on SIFT
Wang, P., Chen, Q., Chen, H., et al. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2033014 · Cited by 2
“Bay, who proposed SURF algorithm [3] in 2006, replaced the complex Gaussian convolution with block filter and integral image in SIFT algorithm, which greatly improved the”
MethodA novel approach using T.H.E.S methodology for CBIR
Vasudevan, S. K., Priyadarsini, P. L. K., Gokul, M., et al. (2013) · doi:10.1109/icsipr.2013.6497781 · Cited by 2
Using Multi-descriptors for Khon Image Retrieval
Areeyapinan, J., Kanongchaiyos, P., & Kawewong, A. (2013) · International Conference on Culture and Computing · doi:10.1109/culturecomputing.2013.14 · Cited by 2
Image forgery detection for region duplication tampering
Kuo, T.-Y., Lo, Y.-C., & Huang, S.-N. (2013) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2013.6607452 · Cited by 2
“The sparse feature descriptors, such as the Scale Invariant Feature Transform (SIFT) [13] and the Speeded Up Robust Features (SURF) [15], are able to identify the keypoints with invariant property at different image scales, and create the spare feature descriptor vector based on the neighborhood of each keypoint.”
Method3D Scene Reconstruction for Aiding Unmanned Vehicle Navigation
Diskin, Y., & Asari, V. K. (2013) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2013.48 · Cited by 2
Robust tracking using visual cue integration for mobile mixed images
Chen, H.-T., & Tang, C. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.04.006 · Cited by 2
Self‐Similarity Based Corresponding‐Point Extraction from Weakly Textured Stereo Pairs
Mao, M., Hao, K., & Ding, Y. (2014) · Mathematical Problems in Engineering · doi:10.1155/2014/568034 · Cited by 2
A disparity range estimation technique for stereo-video streaming applications
Smirnov, S., Gotchev, A. P., & Hannuksela, M. M. (2013) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2013.6618287 · Cited by 2
Can Motion Segmentation Improve Patch-Based Object Recognition?
Ulges, A., & Breuel, T. M. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.745 · Cited by 3
“Features and Matching As a robust patch-based feature representation, SURF features [1] are chosen (other detectors and descriptors [9, 13] could be used equivalently).”
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.