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 12,201–12,300 of 14,752
Vision and SLAM on a highly dynamic mobile two-wheeled robot
Suhm, P. (2013) · OPUS Publication Server of the University of Stuttgart (University of Stuttgart) · doi:10.18419/opus-3256
“Active feature search or guided matching, how it’s sometimes called, allows relinquishing processor burdening feature descriptors like SIFT or SURF.”
MethodA Model for the Omnidirectional Acquisition and Rendering of Stereoscopic Images for Human Viewing
Gurrieri, L. E., & Dubois, É. (2015) · 3D Research · doi:10.1007/s13319-015-0069-0
Vectorfaces for Illumination Invariant Human Face Recognition
Ganguly, S., Bhattacharjee, D., & Nasipuri, M. (2015) · International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN) · doi:10.1109/cicsyn.2015.33
Matching of infrared and visible images
Li, J., Sun, L., Zhang, S., et al. (2012) · International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) · doi:10.1109/fskd.2012.6234052
Match propagation starting from a single initial correspondence under wide baseline views
JianKang, D., Liu, K., & JieNing, W. (2013) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2013.6561549
Human skeletal tracking using colour MSERs
Natarajan, V. (2012) · doi:10.1145/2425836.2425935
Feature track summary visualization for sequential multi-view reconstruction
Recker, S., Hess-Flores, M., & Joy, K. I. (2013) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2013.6749337
“The SURF algorithm, inspired by SIFT, in contrast, uses only a 64 dimensional feature vector for descriptor purposes [3].”
BackgroundMethodInfluentialThe influence of image objective parameters on the probability of finding corresponding points
Bolecek, L., & Říčný, V. (2014) · International Conference Radioelektronika · doi:10.1109/radioelek.2014.6828422
“The second one is Speeded– Up-Robust-Features (SURF) [7].”
BackgroundInfluentialMonovision based automated navigation and object detection
Charan, S. G., Manjunath, M., Niranjana, S., et al. (2015) · doi:10.1109/race.2015.7097242
Development of Stationary User Interface Using Head-Tracking
Miyata, K., Kitazono, Y., Yang, S. Y., et al. (2011) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.103.711
On coding of images and SIFT feature descriptors
Reznik, Y. A. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.940742
“(6) Then, by considering exponential model for magnitudes, we arrive at the following model: ( ) ( ) , ! r e P r P r α λ α λ α α − = , (7)”
Improvement of Target Extraction and Dense Matching
Jiang, Z., Wang, Q., & Cui, Y. (2012) · Communications in computer and information science · doi:10.1007/978-3-642-34038-3_28
Match-time covariance for descriptors
Christiansen, E. M., Rabaud, V., Ziegler, A., et al. (2013) · British Machine Vision Conference (BMVC) · doi:10.5244/c.27.12
“SIFT [8], SURF [2], ORB [15], BRISK [6], and FREAK [1] all use ETC.”
MethodInfluentialFeature integration with random forests for real-time human activity recognition
Kataoka, H., Hashimoto, K., & Aoki, Y. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2181201 · Cited by 2
“Three feature types are flow (HOOF [3]), shape (extended version of CoHOG [4]) and keypoint (SURF [5] + Bag-of-features (BoF) [6]).”
BackgroundPropagation-based dynamic topology estimation framework for vision sensor networks
Choi, Y., Cho, Y., Cho, K., et al. (2010) · doi:10.1145/1900179.1900194
“[16] presented SURF (Speeded Up Robust Features), which is a scale and rotation invariant interest point detector and descriptor.”
MethodAn approach for automated scale invariant STM-scan matching using SIFT
Bistry, H., Wolter, B., Schütz, B., et al. (2010) · IEEE International Conference on Nanotechnology (IEEE-NANO) · doi:10.1109/nano.2010.5697729
Performance analysis of Bag-of-Features based content identification systems
Voloshynovskiy, S., Diephuis, M., & Holotyak, T. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854312
An Improved Rapid SURF Algorithm Based on Region of Interest
Liu, Y. J., Wan, R. Q., Wang, Z. R., et al. (2014) · Advanced materials research · doi:10.4028/www.scientific.net/amr.945-949.1861
Using visual segments and spatial layouts for unsupervised object co-segmentation
Sun, L., Liang, X., & Liu, M. (2013) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist.2013.6729691
“For the histogram of SURF features, we detect and extract SURF features across an entire dataset.”
MethodObject localization using adaptive feature selection
Hwang, S.-Y., Kim, J., & Lee, S. (2008) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.805840
Understanding architectural characteristics of multimedia retrieval workloads
Dai, C., Lv, C., Li, J., et al. (2013) · ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS) · doi:10.1145/2465529.2465541
Vishnukumar, G. N., & Guerra‐Filho, G. (2011) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/2141622.2141668
“The main advantage of SURF over SIFT is that it is significantly faster than the latter.”
MethodInfluentialJoseph, N. C., & Wilson, A. (2015) · doi:10.1145/2791405.2791516
Camera based cross devices manipulating with augmented reality
Li, T., Hu, W., Wu, J., et al. (2013) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2013.6618405
Low level saliency feature extraction method based on Hessian threshold
Du, M., Wang, J., Li, J., Cao, H., Cui, G., Fang, J., Lv, J., & Pu, J. (2013) · Chinese Automation Congress · doi:10.1109/cac.2013.6775796
Feature-Based Multi-sensor Images Alignment and Enhancement
Ju, M.-H., Kim, S., & Kang, H.-B. (2012) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2012.45
“In our experiments, we use a Hessian Detector using Integral Images [8], which gives the location and scale of the detected features.”
MethodInfluentialHierarchical loop detection for mobile outdoor robots
Lang, D., Winkens, C., Häselich, M., & Paulus, D. W. R. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.908277
Accelerated Compression Algorithm Based on Factoring Repeated Content
Tang, Y., & Zhu, X. H. (2013) · Advanced materials research · doi:10.4028/www.scientific.net/amr.760-762.1972
“The Gray Split Rotate (GSR) [8] descriptor is related to classic descriptors, such as SIFT [4] and SURF [9] .”
MethodCreative Transformations of Personal Photographs
Wu, Y., Seshadrinathan, K., Sun, W. M., Choubassi, M. E., Ratcliff, J., & Kozintsev, I. V. (2012) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2012.87
“State-of-the-art candidates for visual feature extraction and descriptor generation include SIFT [9] and SURF [10].”
Park, J.-Y., & Ahn, H. C. (2013) · Journal of the Korea Society of Computer and Information · doi:10.9708/jksci.2013.18.10.039
“SURF기반에서특징점추출은적분영상과근사화한헤이 시안 검출기를 사용하는 고속 헤이시안 검출기(Fast Hessian Detector)를 사용한다[13, 15].”
InfluentialA new algorithm for estimating 3D structure and robot motion using visual tracking and IMU/compass
Wang, K., Liu, Y., & Li, L. (2012) · World Congress on Intelligent Control and Automation · doi:10.1109/wcica.2012.6359414
“Moreover, one camera is installed along ordinate axis of the robot for side view, and SURF (Speeded Up Robust Features [22]) feature is adopted for feature tracking, as illustrated in Fig.”
BackgroundMethodSelf-similarity based interest points extraction for weak texture
Mao, M., Hao, K., & Ding, Y. (2014) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2014.6895767
Nonlinear Optimization Method for Multiple Image Registration
Ahn, Y.-K., & Hong, J. (2012) · Journal of Broadcast Engineering · doi:10.5909/jbe.2012.17.4.634
“따라서 SIFT([9])나 SURF([10]) 같은 특징점을 많이 검출해내는 특징점”
Compact rotation invariant image descriptors by spectral trimming
Taquet, M., Jacques, L., Macq, B. M. M., et al. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6115878
“Alternatively, SURF [9] records Haar wavelet responses in subregions of the neighborhood.”
BackgroundMethodA toolchain for capturing and rendering stereo and multi-view datasets
Klose, F., Lipski, C., Ruhl, K., et al. (2011) · International Conference on D Imaging · doi:10.1109/ic3d.2011.6584392
Duo-graph: An efficient and robust method for large-scale mapping for visual-guided robots
Zhang, H., Hou, Z., Li, N., et al. (2012) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2012.6485179
“In the frontend of our local SLAM, SURF [16] will be extracted from each frame, and in the backend, graph opti-”
MethodA new local feature descriptor: Covariant support region
Yawei, L., Li, J., & Xiaohong, Z. (2009) · doi:10.1109/icicisys.2009.5357667
“SURF or Speeded Up Robust Features haves been proposed by Bay et al [6, 7], and it is a scale-invariant feature descriptor based on the Hessian-matrix.”
MethodVisual image search improved with geometric consistency
Özkan, S., Esen, E., & Akar, G. B. (2013) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2013.6531343
Saliency map estimation by constructing graphs of possible eye-tracking paths
Szalai, S., Szirányi, T., & Vidnyánszky, Z. (2012) · IEEE International Conference on Cognitive Infocommunications · doi:10.1109/coginfocom.2012.6421969
“For instance, for white threshold Ti = 128 (50 % saliency), the identity rates are: iSIFT = 95.45 %, iSURF = 97.12 %, iORB = 96.65 %; for Ti = 192 (75 % saliency): iSIFT = 98.46 %, iSURF = 98.88 %, iORB = 98.94 % (for the best k in the same descriptor).”
BackgroundInfluentialA fast and automatic fusion algorithm for unregistered multi-exposure image sequence
Liu, Y., & Yu, F. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2060036
An Iterative Combination Scheme for multimodal visual feature detection
Guerra‐Filho, G. (2012) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2012.6466806
RELATIVE POSE ESTIMATION USING IMAGE FEATURE TRIPLETS
Chuang, T., Rottensteiner, F., & Heipke, C. (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-w2-39-2015
Two-dimensional local ternary patterns using synchronized images for outdoor place categorization
Jung, H., Kurazume, R., Iwashita, Y., & Mozos, Ó. M. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7026158
“A natural scene is recognized as a semantic label of an image by extracting features, such as GIST[4], SIFT[5], SURF[6] and PLISS[7].”
Street searching service framework for navigation
Lee, S., Je, S., Lee, K., et al. (2013) · doi:10.1109/fcv.2013.6485487
A Fast Orthoimage Mosaic Method for Application of Grid
Li, Z. G., Wang, B., Zhang, Y. S., et al. (2012) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.151.685
“SIFT and SURF is the representative arithmetic operators of the image matching based on scale-invariant feature [1] .”
BackgroundSpeeding up mobile multimedia applications
Gao, J. (2010) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1873951.1874322
“In a previous work we implemented the SURF algorithm [1] on a mobile device.”
MethodTopic level sampling towards optimized locality sensitive vocabulary coding
Chen, J., Duan, L., Li, B., et al. (2011) · International Conference on Information, Communications & Signal Processing (ICICS) · doi:10.1109/icics.2011.6174287
Online discriminative tracker with selective feature update
Liong, V. E., Kim, J.-J., & Lee, J.-J. (2012) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie.2012.6237320
A novel method for redundant feature rejection in correspondence problem
Ranjan, R., Gupta, S., & Venkatesh, K. S. (2014) · doi:10.1109/ncc.2014.6811368
A local shape descriptor for mobile linedrawing retrieval
Xuan, Y., Duan, L., & Huang, T. (2013) · Visual Communications and Image Processing · doi:10.1109/vcip.2013.6706378
Object recognition based on inhibition-of-return control using particle filter
Tamura, Y., & Lim, H. (2014) · Joint International Conference on Soft Computing and Intelligent Systems and International Symposium on Advanced Intelligent Systems (SCIS&ISIS) · doi:10.1109/scis-isis.2014.7044808
Fast Remote Sensing Image Registration Algorithm Using Spatial Masks
Mousa, A., & Gao, X. (2014) · IEEE International Conference on Computer and Information Technology (CIT) · doi:10.1109/cit.2014.30
Simultaneous localization and mapping using adaptive appearance based loop-closing detection
Majdik, A. L., Lupea, D., Lazea, G., & Vajta, L. (2012) · IEEE International Conference on Automation, Quality and Testing, Robotics (AQTR) · doi:10.1109/aqtr.2012.6237755
Keyword based Keyframe Extraction in Online Video Collections
Ardizzone, E., Cascia, M. L., & Mazzola, G. (2015) · International Conference on Pattern Recognition Applications and Methods · doi:10.5220/0005190001700177
“the clip the SURF (Bay et al. 2006) points and descriptors, and compute the matches between two consecutive frames, by considering the minimum Euclidean distance between descriptors.”
MethodInfluentialA sparse representation-based approach for video copy detection
Li, J., Sun, C., & Zhang, B. (2011) · Frontiers of Electrical and Electronic Engineering in China · doi:10.1007/s11460-011-0171-x
“With Hessian-based detector, SURF [14] is another scale-invariant and robust local descriptor with similar performance compared with SIFT and similar speed compared with Harris descriptor.”
MethodOutdoor scenes identification on mobile device by integrating vision and inertial sensors
Gui, Z., Wang, Y., Liu, Y., et al. (2013) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc.2013.6583794
Plötz, T., Richarz, J., & Fink, G. A. (2008) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661808030097
An application framework for implicit sentiment human-centered tagging using attributed affect
Apostolakis, K. C., & Daras, P. (2013) · International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) · doi:10.1109/wiamis.2013.6616145
“With an emphasis on balance between accuracy and speed, obtaining image region descriptors in the first step of the BoW pipeline is achieved through Speeded Up Robust Feature (SURF) descriptors [9].”
MethodFast Feature-Based Template Matching, Based on Efficient Keypoint Extraction
Tavakol, A., & Soltanian, M. R. K. (2011) · Advanced materials research · doi:10.4028/www.scientific.net/amr.341-342.798
Watanabe, T., Kobayashi, S., Koshizuka, N., et al. (2013) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce.2013.6664937
Object Detection by Admissible Region Search
Chen, X., An, S., Liu, W., et al. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25832-9_53
“In these approaches, we first train a classifier as a quality function based on the extracted features of training images such as SIFT[1], SURF[5] and so on, next we apply the quality function to all possible subimages within an image and find out the one with maximum value.”
MethodEvaluation on the Impact of Image Quality on Image Retrieval
Wen, J. A., Zhou, W., Hong, R., et al. (2014) · doi:10.1145/2632856.2632911
“On the one hand, adopting compression of image patches devotes to descriptor compression [1, 11, 10, 3].”
MethodCV-SIFT Algorithm for Image Detection
Cui, Y., & Lei, Y. (2013) · Advances in intelligent systems research/Advances in Intelligent Systems Research · doi:10.2991/3ca-13.2013.71
ROBUST PERSON TRACKING WITH MULTIPLE NON-OVERLAPPING CAMERAS IN AN OUTDOOR ENVIRONMENT
Hellwig, S., & Treutner, N. (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-b5-339-2012
Local query on satellite images based on interest points
Bahroun, S., Gharbi, H., & Zagrouba, E. (2014) · doi:10.1109/igarss.2014.6947494
“The parameters of the three algorithms are the same settings according to the original paper [6] [1] [4].”
MethodInfluentialAn online visual loop closure detection method for indoor robotic navigation
Erhan, C., Sarıyanidi, E., Şencan, O., et al. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2082532
“sgn(a PQ nm) sgn(b PQ nm) (5)”
BackgroundImproving Computational Efficiency of 3D Point Cloud Reconstruction from Image Sequences
Chang, C.-H., & Kehtarnavaz, N. (2013) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2013.101
Video auto stitching in multicamera surveillance system
He, B., Zhao, G. L., Liu, Q., et al. (2012) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.920157
“For the extraction of the SURF descriptor [8], the first step consists of constructing a square region centered around the interest point, and oriented along the selected orientation.”
BackgroundMethodFast Tracking of Moving Target Combining SURF and Cluster Analysis
Li, Y., Yu, J. J., Fu, Y. G., et al. (2013) · Key engineering materials · doi:10.4028/www.scientific.net/kem.552.542
Nestle: Interest point extraction via nested circles
Gündoğdu, E., & Alatan, A. A. (2012) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2012.6204540
“Bütün algoritmalar için yaklaşık bulunan nokta sayısı 1000 civarındadır.”
Transformation-invariant image descriptors for change monitoring based on multi-modality imagery
Palenichka, R. M., Doyon, F., Lakhssassi, A., et al. (2013) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2013.6723487
Efficient initialization schemes for real-time 3D camera tracking using image sequences
Ababsa, F., Zendjebil, I., Didier, J.-Y., et al. (2011) · International Conference on Intelligent Systems Design and Applications (ISDA) · doi:10.1109/isda.2011.6121745
“We propose to use the SURF descriptors [6] in order to extract a stable set of natural key points which are invariant to image scaling and rotation, and partially invariant to changes in illumination and view point.”
MethodMotion Dense Sampling for Video Classification
Aihara, K., & Aoki, T. (2013) · International Conference on IT Convergence and Security (ICITCS) · doi:10.1109/icitcs.2013.6717859
Accurate matching method of multimodal image based on phase congruency and local mutual information
Zhao, C., Zhao, H., & Zhao, G. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2070198
“The proposed method is significant better than the SURF method, the CR of the former is almost the 3 times of the latter.”
BackgroundMethodInfluentialPoint correspondence by matching scaled invariants
Qu, J., Gong, L., Huang, C., & Fang, R. (2012) · International Conference on Audio, Language and Image Processing · doi:10.1109/icalip.2012.6376594
“SURF [20] was applied to both images to detect feature points.”
MethodThe use of computer vision technologies to augment human monitoring of secure computing facilities
Potgieter, M., & van Niekerk, J. (2012) · Information Security for South Africa · doi:10.1109/issa.2012.6320450
Omnidirectional object duplicate detection
Vajda, P., Ivanov, I., Goldmann, L., et al. (2011) · doi:10.1109/dsp-spe.2011.5739235
Marker-based tangible interfaces for 3D reconstruction
Jung, K., Park, J.-I., & Choi, B.-U. (2013) · International Conference on Consumer Electronics · doi:10.1109/icce.2013.6486967
“[4] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool, "SURF: Speeded Up Robust Features," Proceedings of the ninth European Conference on Computer Vision, pp.”
BackgroundMethodDecision Model Based on Semantic Similarity in Internet Information Recognition
Han, J. R., & Ma, J. (2014) · Journal of Multimedia · doi:10.4304/jmm.9.1.74-82
“On the internet, the description is mainly in the form of facts, has the branch of true and false, do not include emotional and degree of description [2-3].”
BackgroundStudy on a Rapid Real-Time Feature Extraction Algorithm
Xu, B., Li, X. N., & Xue, W. N. (2013) · Advanced materials research · doi:10.4028/www.scientific.net/amr.709.575
Research of Vehicle Recognition Method under SURF Feature and Bayesian Model
Tang, Z., Ying-Xia, X., & Jian, C. (2013) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid.2013.70
Robust irregular region matching based on inner product and exterior product
Liu, H., & Wang, Z. (2010) · doi:10.1109/icinfa.2010.5512191
A Fast Feature Matching Algorithm Based on Multi Scale Spatial Segmentation Technology
Li, S. R., Huang, Y., & Hu, Z. J. (2014) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.490-491.1217
Halftone Feature Based Classification of Commercial White Print Paper Using BP-MLP
Mandal, D., Chatterjee, A., & Tudu, B. (2014) · doi:10.1109/eait.2014.12
A new symmetry detection approach in IC layouts
Attwa, H. A., Khalil, M. I., & Abbas, H. M. (2012) · International Conference on Computer Engineering & Systems (ICCES) · doi:10.1109/icces.2012.6408502
“The most famous ones are SIFT [3] and Speeded Up Robust Features (SURF) [5].”
BackgroundInfluentialAn efficient volumetric matching algorithm based on MSVs and 3DSURF
Chen, P., Li, M., & Li, X. S. (2013) · International Conference on Computer Science & Education (ICCSE) · doi:10.1109/iccse.2013.6554065
Research on Saliency Prior Based Image Processing Algorithm
Yin, Z., & Zhang, H. (2014) · Journal of Multimedia · doi:10.4304/jmm.9.2.294-301
Real-Time Tracking by a Quadrotor for Arbitrary Objects Defined Online
Reyes, S., Rángel, J., Zavala, J., et al. (2013) · IFAC Proceedings Volumes · doi:10.3182/20131120-3-fr-4045.00060
Words-of-interest selection based on temporal motion coherence for video retrieval
Wang, L., Song, D., & Elyan, E. (2011) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2009916.2010117
“, using the Speed Up Robust Feature algorithm (SURF) [4].”
InfluentialA Low-Cost 3D Local Mapping and Localization Method
Li, L., Tao, R., & Jin, G. D. (2014) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.556-562.4089
“In this process two-step feature matching method is proposed to applied, firstly SURF algorithm [5] is applied to accomplish feature detection, description and rough matching , then The point clouds will be utilized to create the dense 3D structures of the environment by the ICP algorithm [6] .”
MethodMishimagi, K., Toda, M., & Kawashima, T. (2012) · International Journal of Intelligent Systems and Applications · doi:10.5815/ijisa.2012.07.05
Targeted surveillance system for highly maneuverable objects using fuzzy Kalman filter
Rohilla, R., Dehiya, V., & Kapoor, R. (2014) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciinfs.2014.7036634
“Another method of target detection is using SURF features [1] which give scale and rotation invariant interest point descriptors for the target.”
MethodA New Layout Method Allowing the Overlapped Configuration of Photos
Xiaobing, C. (2012) · Physics Procedia · doi:10.1016/j.phpro.2012.02.324
MET: media-embedded target for connecting paper to digital media
Liu, Q., Girgensohn, A., Wilcox, L. D., Shipman, F. M., III, & Dunnigan, T. (2014) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-014-0059-7
A New Ergonomic Interface System for the Disabled Person
Heo, H., Lee, J.-W., Lee, W.-O., et al. (2011) · Journal of the Ergonomics Society of Korea · doi:10.5143/jesk.2011.30.1.229
A Robust Instance-based Video Search Method by Re-ranking for Multiple Visual Codebooks
Wang, W., & Zhao, Z. (2012) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis.2012.44
“For features like SIFT, CSIFT and SURF, we chose Gaussian normalization to make the values varies in range [-1,1] and the others are normalized to [0,1].”
MethodInfluentialMultiple PiPs detection in unbounded video stream
Cui, C., Zhao, Y., Wei, S., et al. (2013) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2013.6618449
“For the local feature representation such as SIFT- and SURF-based schemes [4] [5], lots of local features are extracted from the whole frame, and embedding video can be separately represented by their local features.”
MethodXu, M., & Sun, Y. L. (2012) · International Conference on Biomedical Engineering and Informatics (BMEI) · doi:10.1109/bmei.2012.6513145
Chen, Y., & la Torre, F. D. (2011) · doi:10.1109/fg.2011.5771387
“SIFT and its extensions [24], [19], [25], [6], [23] have been successfully applied to many problems.”
A New Shape Adaptation Scheme to Affine Invariant Detector
Liu, C. (2010) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2010.12.016
“To further accelerate the detection, Bay et al. [9] provided an efficient implementation of ( ) by applying the integral image for the computation of image derivatives.”
Method
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.