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 10,801–10,900 of 14,752
OpenSURF performance in windows phone 7
Wijaya, R., Wuryandari, A. I., & Nugraha, H. C. (2012) · International Conference on System Engineering and Technology · doi:10.1109/icsengt.2012.6339334 · Cited by 1
“4 Detail of the Graffiti scene showing the size of window at different scales[3]”
BackgroundImproved binary feature matching through fusion of hamming distance and fragile bit weight
Zhuang, D., Zhang, D., Li, J., & Tian, Q. (2013) · doi:10.1145/2505483.2505492 · Cited by 1
“In image search applications, the mobile device usually need processing a large quantity of visual features, but the well-established features (such as SIFT [5] and SURF [6]) are all high-dimensional vectors that require a huge amount memory space to store.”
BackgroundMethodInfluentialOptimal operations for visual categorization
Cheng, Y., Qu, Y., Huang, J., Fang, T., Shen, L., & Xie, Y. (2010) · International Conference on Internet Multimedia Computing and Service · doi:10.1145/1937728.1937746 · Cited by 1
Generic object recognition with local features: From bags to subspaces
Raytchev, B., Kikutsugi, Y., Shigenaka, R., Tamaki, T., & Kaneda, K. (2013) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2013.6706938 · Cited by 1
“Typically, salient low-level features like SIFT [2], SURF [3] and HOG [4], to name a few (see [5] for a comprehensive survey), are automatically detected and extracted from both the training and test images, i.”
BackgroundZhao, D., Wang, J., Wan, J., et al. (2013) · International Conference on Computer Science and Electronics Engineering (ICCSEE) · doi:10.2991/iccsee.2013.243 · Cited by 1
“[3] H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool, “SURF: Speeded up robust features,” Proc.”
ResultTimestamp removal for panorama video surveillance
Cheng, J. T., Yu, X., Liao, S., et al. (2015) · International Conference on Internet Multimedia Computing and Service · doi:10.1145/2808492.2808544 · Cited by 1
A local appearance contextual descriptor for object matching
Xia, X., Zhang, S., & Liang, W. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5495303 · Cited by 1
An image matching method based on BoVW model for visual self-localization
Peng, H., Liu, S., Wang, J., et al. (2014) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2014.6896429 · Cited by 1
Optimal angular back-projection error for vehicle motion estimation using omnidirectional vision
Hoang, V.-D., Hernández, D. C., Seo, D.-W., & Jo, K.-H. (2014) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2014.6878154 · Cited by 2
“The projection rays of the image points are transformed to the points on the sphere by using the following function: 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 (1 )( ) 1 (1 )( ) ( ) 1 (1 )( ) u v u u v u v g m v u v u v u v”
MethodLocal image descriptor based on spectral embedding
Yan, P., Tang, J., Zhu, M. B., & Liang, D. (2014) · IET Computer Vision · doi:10.1049/iet-cvi.2014.0124 · Cited by 1
Multi-scale Ill-Structured Road Detection
Lin, Y., Geng, Y., Guo, Z., et al. (2014) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn.2014.241 · Cited by 1
GRoM — Generalized robust multichannel featur detector
Smirnov, P., Semenov, P., Lyakh, M., et al. (2011) · IEEE International Conference on Signal and Image Processing Applications (ICSIPA) · doi:10.1109/icsipa.2011.6144155 · Cited by 1
“The color image is converted to grayscale before SIFT or SURF image processing.”
BackgroundMethodInfluentialJoint distribution and steerable filter based fast local feature description algorithm
Zhang, L., Liu, C., Wang, Z., et al. (2010) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2010.5646928 · Cited by 1
“Reference [5] creates the codebook using the local features created by SIFT to annotate images.”
MethodImproving Matching Performance of SURF Using Color and Relative Position
Lee, K., Kim, D., Rho, S., et al. (2012) · The Journal of Advanced Navigation Technology · doi:10.12673/jkoni.2012.16.2.394 · Cited by 1
“사물의 특징 추출을 위 한 알고리즘으로 SIFT[6][7], PCA-SIFT[8], GLOH[9], LESH[10], SURF[11] 등이 있다 .”
Using GPUs to improve system performance in visual servo systems
Zang, C., & Hashimoto, K. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5650418 · Cited by 1
Rotated Object Recognition Based on Corner Feature Points for Mobile Augmented Reality Applications
Kim, D.-H., Jung, H.-S., Hong, C.-P., et al. (2013) · International Conference on IT Convergence and Security (ICITCS) · doi:10.1109/icitcs.2013.6717879 · Cited by 1
Position and Rotation Estimation for Mobile Robots in Outside of Recording Path Using Ego‐Motion
Hagiwara, Y., Shoji, T., & Imamura, H. (2014) · Electrical Engineering in Japan · doi:10.1002/eej.22562 · Cited by 1
Designing real-time multimedia applications on mobile devices
Gao, J. (2011) · doi:10.1145/2043106.2043109 · Cited by 1
Moving Object Detection Using SURF and Label Cluster Update in Active Camera
Jung, Y., Park, E.-S., Lee, H. H., et al. (2012) · Journal of Institute of Control Robotics and Systems · doi:10.5302/j.icros.2012.18.1.035 · Cited by 1
Geometric descriptor for bag of visual words-based place recognition
Stalbaum, J., & Song, J.-B. (2014) · International Conference on Ubiquitous Robots and Ambient Intelligence · doi:10.1109/urai.2014.7057391 · Cited by 1
“SURF descriptor extraction and FAB-MAP 2.0 include non-deterministic processes, which makes the results between trials inconsistent.”
MethodInfluentialKang, J., Bang, S. W., Atkeson, C. G., et al. (2011) · The Journal of Korea Robotics Society · doi:10.7746/jkros.2011.6.3.197 · Cited by 1
“3 Natural Features Extraction In recent research, the features named SIFT([14]) and SURF([15]) have been widely used because they are robustly detected and matched regardless of the scaling and rotation of the features in images.”
InfluentialInformation-theoretic database building and querying for mobile augmented reality applications
Baheti, P. K., Swaminathan, A., Chari, M., et al. (2011) · IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2011.6092369 · Cited by 1
An image retrieval framework for distributed datacenters
Yang, D., Liao, J., Qi, Q., et al. (2014) · Conference on Local Computer Networks · doi:10.1109/lcn.2014.6925803 · Cited by 1
“Recently, local features, SURF (Speed up Robust Feature) [4], have been studied, which are designed to handle object rotation, translation and scaling.”
BackgroundSOFT CLUSTERING BASED EXPOSITION TO MULTIPLE DICTIONARY BAG OF WORDS
Sujatha (2012) · Journal of Computer Science · doi:10.3844/jcssp.2012.2068.2074 · Cited by 1
“…description, local descriptors such as Haar descriptor (Viola and Jones, 2001), Scale-Invariant Feature Transform (SIFT) descriptor (Lowe, 2004), Histogram of Gradients (HOG) descriptor (Dalal and Triggs, 2005) and Speeded Up Robust Feature descriptor (SURF) (Bay et al ., 2006) are commonly used.”
MethodMULTI-SOURCE REMOTE SENSING IMAGES MATCHING BASED ON IMPROVED KAZE ALGORITHM
Wang, Z., Wang, H. B., Wang, G.-H., et al. (2013) · 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-w1-109-2013 · Cited by 1
Depth measurement based on pixel number variation and Speeded Up Robust Features
Hsu, C.-C. J., Huang, P.-T., Cai, Z.-H., et al. (2014) · IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin) · doi:10.1109/icce-berlin.2014.7034300 · Cited by 1
“Subsequently, mismatching points are removed by using the Identifying point correspondences by Correspondence Function (ICF) [5] algorithm so that desired reference points can be automatically selected.”
MethodInfluentialCopied video detection with MPEG-7 video signature and multiple direct-mapped cache
Murabayashi, N., & Yoshida, K. (2011) · International Conference on Hybrid Intelligent Systems (HIS) · doi:10.1109/his.2011.6122103 · Cited by 1
Robust scale-invariant feature extraction
Lou, L., & Kühnlenz, K. (2014) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2014.7064447 · Cited by 1
Image processing in airborne applications using multicore embedded computers
Sánchez, C. M., Nowotsch, J., Paulitsch, M., et al. (2013) · IEEE/AIAA Digital Avionics Systems Conference (DASC) · doi:10.1109/dasc.2013.6712535 · Cited by 1
An improved SURF algorithm based local image symmetry scoring scheme
Ma, L., Song, Z. P., & Zhu, G. (2014) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2014.7003789 · Cited by 1
Stereoscopic augmented reality with pseudo-realistic global illumination effects
de Sorbier, F., & Saitô, H. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2039280 · Cited by 1
Using advanced ML for improving surveillance accuracy
Meena, T. (2014) · doi:10.1109/impetus.2014.6775875 · Cited by 1
“The figures 7, 8 and 9 shows the output of the MKTL model along with no transfer and prior-feature model using rbf, polynomial and prbf kernel, repectively.”
BackgroundMethodEnhancing region-based object tracking with the SP-SIFT feature
Fajardo, F. N., Escudero-Viñolo, M., & Cano, J. B. (2014) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2014.6849848 · Cited by 1
“In the POI characterization scenario, due to a combination of reasonable performance and publicly available implementations, SIFT[14], Speeded Up Robust Features (SURF)[19] or DAISY [15] are some of the most popular POI description techniques.”
MethodAn Adaptive Particle Filter Based Method for Real Time Face Tracking
Chen, W.-M., Lin, Y.-L., & Hsieh, Y.-H. (2013) · Journal of Software Engineering and Applications · doi:10.4236/jsea.2013.65b001 · Cited by 1
PIR: A Domain Specific Language for Multimedia Information Retrieval
Huang, X., Zhao, T. Q., & Cao, Y. (2014) · International Journal of Multimedia Data Engineering and Management · doi:10.4018/ijmdem.2014070101 · Cited by 2
High-performance computing in image registration
Zanin, M., Fabio Remondino, A., & Mura, M. D. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.981177 · Cited by 1
Fast repurposing of high-resolution stereo video content for mobile use
Karaoglu, A., Lee, B. H., Boev, A., et al. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.924508 · Cited by 1
Construcción automática de ortofotomapas: una aproximación fotométrica
Prados, R., García, R., & Neumann, L. (2012) · Revista Iberoamericana de Automática e Informática Industrial RIAI · doi:10.1016/j.riai.2012.11.010 · Cited by 1
“SURF: Speeded Up Robust Fea- tures.”
BackgroundInfluentialTire mounting on a car using the real-time control architecture ARCADE
Nierhoff, T., Lou, L., Koropouli, V., et al. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386094 · Cited by 1
“The SURF [7] detector is employed to extract 2D multiscale features.”
MethodVisual Odometry and 3D Mapping in Indoor Environments
Wu, Q., Li, Q., & Cheng, N. (2013) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.336-338.348 · Cited by 1
Searching for People through Textual and Visual Attributes
Fabián, J., Pires, R., & Rocha, A. D. R. (2012) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2012.45 · Cited by 1
“1) Low-level Feature Extraction: For each face image in the database, extract the points of interest using SURF [2].”
BackgroundMethodInfluentialSymbolic feature detection for image understanding
Aslan, S., Akgül, C. B., & Sankur, B. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2040783 · Cited by 1
3D feature extraction from uncalibrated video clips
Donate, A., & Liu, X. (2010) · doi:10.1145/1877791.1877799 · Cited by 1
PERSPECTIVE-INVARIANT IMAGE MATCHING FRAMEWORK WITH BINARY FEATURE DESCRIPTOR AND APSO
Geng, L.-C., Su, S., Cao, D., & Li, S. (2014) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001414550118 · Cited by 2
Illumination-invariance and nonlocal means based super resolution
Wang, M., Liu, J., Bai, W., et al. (2013) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2013.6572068 · Cited by 1
Shiraishi, S., Feng, Y., & Uchida, S. (2013) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e96.d.1503 · Cited by 1
Stability analysis of a semiglobal algorithm for stereo vision in the soft-approach problem
Ponomarev, S. V. (2014) · Journal of Optical Technology · doi:10.1364/jot.81.000651 · Cited by 1
Essential keypoints to enhance visual object recognition with saliency-based metrics
Le, T.-N., Le, Y.-T., Tran, M., et al. (2014) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2014.7064289 · Cited by 1
“In this experiment, we use four common local features, including BRIEF, BRISK, SIFT, and SURF.”
MethodInfluentialChoi, J., Park, Y., Song, J.-B., et al. (2011) · Journal of the Korea Institute of Military Science and Technology · doi:10.9766/kimst.2011.14.2.271 · Cited by 1
“본 논문에서는 최근에 제안된 불변 특징 량으로 SURF(Speeded Up Robust Feature)([4]) 를 사용하였다.”
BackgroundInfluentialPatch based specular reflection removal for range images in hybrid 3-D endoscopy
Haase, S., Wasza, J., Safak, M., et al. (2014) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2014.6867920 · Cited by 1
“Our technique calculates SURF (Speeded Up Robust Features) in both images and detects corresponding points in both views [10].”
MethodAction recognition based on semantic feature description and cross classification
Zhao, Y., Wang, Q., & Yuan, Y. (2014) · doi:10.1109/chinasip.2014.6889319 · Cited by 1
Liu, Q., Liao, C., Wilcox, L. D., & Dunnigan, A. (2010) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/1891903.1891934 · Cited by 1
Object detection based on saliency map using reference image containing complex background
Tamura, Y., Masuta, H., Takanishi, A., et al. (2014) · World Automation Congress (WAC) · doi:10.1109/wac.2014.6936136 · Cited by 1
Fast Detection of Robust Features by Reducing the Number of Box Filtering in SURF
Park, H., Mitsumine, H., & Fujii, M. (2011) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e94.d.725 · Cited by 1
“In order to detect features in an image, SURF [2] computes the determinants (usually called Hessian) of the approximated Hessian matrix at different scales as follows.”
BackgroundMethod3D egomotion from stereo cameras using constrained search window and bundle adjustment
Chen, C., Zhang, J., Chen, T.-I., & Chen, C.-F. (2013) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2013.6727055 · Cited by 1
Color image retrieval based on spatio-chromatic multichannel Gaussian mixture modelling
Łuszczkiewicz-Piątek, M., & Bogdan Smolka, B. (2013) · International symposium on image and signal processing and analysis/ISPA ... · doi:10.1109/ispa.2013.6703727 · Cited by 1
“10: The Precision-Recall plots of the retrieval results performed on LIVE database obtained for various retrieval methods: proposed method (SC − GMM ), CEDD, FCTH, MPEG-7 SCD, Tamura histogram [38], SURF technique, [39].”
MethodA method for extraction of affective audio-visual facial clips from movies
Turan, C., Kansin, C., Zhalehpour, S., Aydin, Z., & Erdem, Ç. E. (2013) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2013.6531371 · Cited by 1
PIRF 3D: Online spatial and appearance based loop closure
Khan, S., Wollherr, D., & BUSS, M. J. (2012) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2012.6485181 · Cited by 1
Zhang, X., & Hirai, S. (2011) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2011.6181344 · Cited by 1
Moments-based stereo camera egomotion analysis and results for long-range trajectories
Rodriguez, D., Aouf, N., & Richardson, M. A. (2012) · The Imaging Science Journal · doi:10.1179/1743131x12y.0000000034 · Cited by 1
Extracting Corresponding Point Based on Texture Synthesis for Nearly Flat Textureless Object Surface
Mao, M., Hao, K., & Ding, Y. (2015) · Mathematical Problems in Engineering · doi:10.1155/2015/594956 · Cited by 1
“The first observation of the results from Table 1 is that SIFT detector which performs better than SURF, and HarrisAffine, but it is more sensitive to the change of texture than others; the standard deviations of the points’ numbers on the object detected by SIFT, SURF and HarrisAffine are 123.6, 72.6, and 27.9, respe…”
BackgroundMethodInfluentialImproving the efficiency and effectiveness of estimating the ego motion of a stereo camera
Li, X., Li, M., & Sun, L. (2012) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2012.6285699 · Cited by 1
“The corresponding feature [11]points must lie in a line, i.”
BackgroundActive view planing for human observation through a RGB-D camera
Du, J., & Sheng, W. (2013) · doi:10.1109/worv.2013.6521923 · Cited by 1
“Gradient-based features are used to identify the existence of humans such as HOG [11], SIFT [12], SURF [13], etc.”
MethodDetecting Building-Level Changes of a City Using Street Images and a 2D City Map
Tetsuka, D., & Okatani, T. (2015) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2015.53 · Cited by 1
Cognitive Semantic Model for Visual Object Recognition in Image
Tan, S. Y., & Lukose, D. (2012) · Communications in computer and information science · doi:10.1007/978-3-642-35286-7_10 · Cited by 2
Toward Part-Based Document Image Decoding
Song, W., Uchida, S., & Liwicki, M. (2012) · IAPR International Workshop on Document Analysis Systems (DAS) · doi:10.1109/das.2012.90 · Cited by 1
Tele-assistance system for the blinds using Video-call with remote scene construction
Maneesaeng, N., Punyabukkana, P., & Suchato, A. (2015) · International Conference on Informatics, Electronics & Vision (ICIEV) · doi:10.1109/iciev.2015.7333973 · Cited by 2
Augmented distinctive features for efficient image matching
Wang, Q., Guan, W., & You, S. O. (2011) · Proceedings · doi:10.1109/wacv.2011.5711478 · Cited by 1
Visualization of anatomical information in near-infrared imaging for robotic urological surgery
Savarimuthu, T. R., Minnillo, B. J., Taylor, R. H., et al. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979955 · Cited by 1
Comparative analysis on SIFT features in visible and infrared aerial imaging
Li, X., Aouf, N., & Richardson, M. A. (2014) · International Journal of Applied Pattern Recognition · doi:10.1504/ijapr.2014.065767 · Cited by 1
Product search framework with categorization and identification
Park, C., & Kweon, I. S. (2008) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.1109/iccas.2008.4694513 · Cited by 1
“Recently, a feature that aims to speed up the extraction time, named SURF[9] was presented.”
BackgroundChen, W.-Y., Chen, J., Su, Y.-C., et al. (2013) · International Conference on Consumer Electronics · doi:10.1109/icce.2013.6486826 · Cited by 1
Improved X-ray Edge Detection Based on Background Extraction Algorithm
Romanowski, J., Nowak, T., Najgebauer, P., et al. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-38610-7_29 · Cited by 1
Autonomous flight of small helicopter with real-time camera calibration
Matsukawa, T., Arai, S., & Hashimoto, K. (2010) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2010.5708332 · Cited by 1
“SIFT and SURF are often used to extract image features [2], [15].”
MethodTNO instance search at TRECVID 2010
Schavemaker, J. G. M., Doets, P. J., Raaijmakers, S., et al. (2011) · TNO Repository · Cited by 1
Graph matching based a probabilistic spectral method
Ren, Z., & Zhao, J. (2011) · International Conference on Natural Computation (ICNC) · doi:10.1109/icnc.2011.6022320 · Cited by 1
“The local feature descriptor used in our experiments is the Speeded Up Robust Features (SURF) descriptor [20], which is an improvement of the SIFT descriptor [16].”
MethodA New Homogenized Feature Based Multi-spectral Image Registration Method
Wu, C., Niu, H., & Liang, W. G. (2012) · Global Congress on Intelligent Systems · doi:10.1109/gcis.2012.76 · Cited by 1
Effect of Salient Features in Object Recognition
Ahmad, K., Ahmad, N., Haider, K., & Ikram, M. J. (2013) · International Journal of Computer Applications · doi:10.5120/9991-4839 · Cited by 1
“Introduced by Herbert Bay in [3], SURF is a robust image detector and descriptor which uses integral images [23].”
BackgroundMethod60.1: Invited Paper : 3D Model‐Based Camera Tracking Technology for Augmented Reality
Makita, K. (2014) · SID Symposium Digest of Technical Papers · doi:10.1002/j.2168-0159.2014.tb00230.x · Cited by 1
A probabilistic quality metric for camera placement in 3D reconstructions
Holec, E., & Papanikolopoulos, N. P. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980520 · Cited by 1
“SURF features were used to perform the localization and identification of the markers [2].”
MethodA stereoscopic content analysis system with visual discomfort-aware
Luo, A.-C., Huang, W., Chen, W., et al. (2012) · International Conference on D Imaging · doi:10.1109/ic3d.2012.6615131 · Cited by 1
Content based video copy detection with local descriptors
Ateş, T. K., Esen, E., Saracoğlu, A., et al. (2010) · IEEE Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2010.5654395 · Cited by 1
Building Regionally Spatial Appearance Model by Topological Color Histogram
Zhou, Y., Zheng, S., & Snoussi, H. (2011) · IEEE International Conference on Computational Science and Engineering (CSE) · doi:10.1109/cse.2011.23 · Cited by 1
Online self-supervised learning for dynamic object segmentation
Guizilini, V., & Ramos, F. T. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364914566514 · Cited by 1
“Any other similar method could be readily applied, both for speed purposes (Bay et al., 2006) or as a way to model different environment properties.”
Categorization in natural time-varying image sequences
Ko, T. H., Soatto, S., & Estrin, D. L. (2009) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2009.5204208 · Cited by 1
Hsieh, A.-C., Wu, Y., Tseng, S.-Y., et al. (2011) · Proceedings of the International Conference on Parallel Processing · doi:10.1109/icpp.2011.33 · Cited by 1
A framework based on the Affine Invariant Regions for improving unsupervised image segmentation
Mostajabi, M., & Gholampour, I. (2012) · International Conference on Information Science, Signal Processing and their Applications (ISSPA) · doi:10.1109/isspa.2012.6310541 · Cited by 1
“[12] have been used which is based on estimation of the Hessian matrix.”
BackgroundMethodInfluentialFast tracking of feature points in full-view image
Qin, X., & Li, S. (2011) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2011.5986232 · Cited by 1
Showroom introduction using mobile phone based on scene image recognition
Li, Y., Lim, J., Lim, K. L., et al. (2009) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2009.5202739 · Cited by 1
“[2] Herbert Bay, Tinne Tuytelaars, Luc Van Gool, "SURF: Speeded Up Robust Features", Proceedings of the ninth European Conference on Computer Vision, May 2006.”
MethodLiu, J., Johns, E., & Yang, G. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094669 · Cited by 1
Building service robot using U-Bot
Lu, L.-W., Baltes, J., Jhan, H.-C., et al. (2011) · World Congress on Intelligent Control and Automation · doi:10.1109/wcica.2011.5970688 · Cited by 1
An Application of Graph Commute Times to Image Indexing
Behmo, R., Paragios, N., & Prinet, V. (2008) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2008.4779392 · Cited by 1
Component Localization in Face Alignment
Qu, Y., Fang, T., Cheng, Y., et al. (2011) · International Journal of Advanced Computer Science and Applications · doi:10.14569/specialissue.2011.010109 · Cited by 1
Invariant Local Feature for Image Matching
Yuk-Man, W. (2006) · Cited by 1
Color restoration for objects of interest using robust image features
Chen, D. M., Chandrasekhar, V., Takacs, G., et al. (2008) · IEEE Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2008.4665136 · Cited by 1
Image based assistant localization in urban navigation
Zhu, H., Zhao, G., & Wang, J. (2009) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2009.5164309 · Cited by 1
“Not only detectors, but also descriptors are discussed in [9] In cost of calculation, SURF describes image faster than SIFT by 3 times and is good at handling serious blurring (Le. low resolution image).”
MethodInfluentialEigenmethod for Feature Matching of Pre- and Postevent Images Exploiting Adjacency
Manfredi, M., Aldrighi, M., & Dell’Acqua, F. (2010) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2010.2043111 · Cited by 1
“, a crossroad detector [19] or a building corner detector [22]; a good choice would probably be a method explicitly designed and intended for feature matching, like scale-invariant feature transform [20] and its successor speeded up robust features [21].”
MethodTraffic sign detection and recognition fusing feature descriptors
Erhan, C., Tazehkandi, A. A., Yalcin, H., et al. (2013) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2013.6531427 · Cited by 1
Matching corners using the informative arc
Kanwal, N., Bostancı, E., & Clark, A. F. (2014) · IET Computer Vision · doi:10.1049/iet-cvi.2013.0104 · Cited by 1
An Improved Offline Stable Point Filtering Method for Mobile Search Application
Wang, Y., Chen, K., Zhou, Y., Zheng, Q., & Guan, H. (2009) · International Conference on Information Engineering and Computer Science · doi:10.1109/iciecs.2009.5363273 · 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.