A performance evaluation of local descriptors
Open accessAbstract
In this paper we compare the performance of interest point descriptors. Many different descriptors have been proposed in the literature. However, it is unclear which descriptors are more appropriate and how their performance depends on the interest point detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the point detector. Our evaluation uses as criterion detection rate with respect to false positive rate and is carried out for different image transformations. We compare SIFT descriptors (Lowe, 1999), steerable filters (Freeman and Adelson, 1991), differential invariants (Koenderink ad van Doorn, 1987), complex filters (Schaffalitzky and Zisserman, 2002), moment invariants (Van Gool et al., 1996) and cross-correlation for different types of interest points. In this evaluation, we observe that the ranking of the descriptors does not depend on the point detector and that SIFT descriptors perform best. Steerable filters come second ; they can be considered a good choice given the low dimensionality.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Distribution-based descriptors capture a substantial amount of information about spatial intensity patterns while being robust to small deformations or localisation errors.
“This can be explained by the fact that they capture a substantial amount of information about the spatial intensity patterns, while at the same time being robust to small deformations or localisation errors.”
From SURF: Speeded Up Robust Features (2006) · cites this paper as [7]
The SIFT descriptor outperforms other feature descriptors.
“The latter, introduced by Lowe [2], have been shown to outperform the others [7].”
From SURF: Speeded Up Robust Features (2006) · cites this paper as [7]
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 · see citing works
A Computational Approach to Edge Detection
Canny, J. (1986) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1986.4767851 · Cited by 30,004 · see citing works
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070 · see citing works
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 · see citing works
Multiresolution gray-scale and rotation invariant texture classification with local binary patterns
Ojala, T., Pietikainen, M., & Maenpaa, T. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1017623 · Cited by 15,398 · see citing works
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 · see citing works
Video Google: a text retrieval approach to object matching in videos
Sivic, & Zisserman (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238663 · Cited by 6,367 · see citing works
Shape matching and object recognition using shape contexts
Belongie, S., Malik, J., & Puzicha, J. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.993558 · Cited by 6,306 · see citing works
Габор, Д. (1946) · Journal of the IEE · Cited by 4,480 · see citing works
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 3,683 · see citing works
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 · see citing works
Self-citationPCA-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.2004.1315206 · Cited by 3,237 · see citing works
The design and use of steerable filters
Freeman, W. T., & Adelson, E. H. (1991) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.93808 · Cited by 2,937 · see citing works
Vetterli, M., & Kovačević, J. (1995) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 2,911 · see citing works
Feature detection with automatic scale selection
Lindeberg, T. (1998) · International Journal of Computer Vision · doi:10.1023/a:1008045108935 · Cited by 2,541 · see citing works
Object class recognition by unsupervised scale-invariant learning
Fergus, R., Perona, P., & Zisserman, A. (2003) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2003.1211479 · Cited by 2,030 · see citing works
Non-parametric local transforms for computing visual correspondence
Zabih, R., & Woodfill, J. (1994) · Lecture notes in computer science · doi:10.1007/bfb0028345 · Cited by 1,797 · see citing works
Evaluation of Interest Point Detectors
Schmid, C., Mohr, R., & Bauckhage, C. (2000) · International Journal of Computer Vision · doi:10.1023/a:1008199403446 · Cited by 1,484 · see citing works
Self-citationLocal grayvalue invariants for image retrieval
Schmid, C., & Mohr, R. (1997) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.589215 · Cited by 1,430 · see citing works
Self-citationFiltering for texture classification: a comparative study
Randen, T., & Husøy, J. H. (1999) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.761261 · Cited by 1,401 · see citing works
An Affine Invariant Interest Point Detector
Mikolajczyk, K., & Schmid, C. (2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-47969-4_9 · Cited by 1,325 · see citing works
Self-citationIndexing based on scale invariant interest points
Mikolajczyk, K., & Schmid, C. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937561 · Cited by 1,101 · see citing works
Self-citationBrown, & Lowe (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238630 · Cited by 934 · see citing works
Representation of local geometry in the visual system
Koenderink, J. J., & van Doorn, A. J. (1987) · Biological Cybernetics · doi:10.1007/bf00318371 · Cited by 720 · see citing works
Reliable feature matching across widely separated views
Baumberg, A. (2002) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2000.855899 · Cited by 629 · see citing works
Matching Widely Separated Views Based on Affine Invariant Regions
Tuytelaars, T., & Gool, L. V. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000020671.28016.e8 · Cited by 616 · see citing works
Multi-view Matching for Unordered Image Sets, or “How Do I Organize My Holiday Snaps?”
Schaffalitzky, F., & Zisserman, A. (2002) · Lecture notes in computer science · doi:10.1007/3-540-47969-4_28 · Cited by 532 · see citing works
Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions
Tuytelaars, T., & Gool, L. V. (2000) · British Machine Vision Conference (BMVC) · doi:10.5244/c.14.38 · Cited by 451 · see citing works
Selection of scale-invariant parts for object class recognition
Dorko, & Schmid, C. (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238407 · Cited by 282 · see citing works
Self-citationAffine / photometric invariants for planar intensity patterns
Gool, L. V., Moons, T., & Ungureanu, D. (1996) · Lecture notes in computer science · doi:10.1007/bfb0015574 · Cited by 269 · see citing works
Tony Lindeberg, C., & Gårding, J. (1997) · Image and Vision Computing · doi:10.1016/s0262-8856(97)01144-x · Cited by 269 · see citing works
Weak Hypotheses and Boosting for Generic Object Detection and Recognition
Opelt, A., Fussenegger, M., Pinz, A. J., & Auer, P. L. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24671-8_6 · Cited by 266 · see citing works
Interleaving Object Categorization and Segmentation
Leibe, B., & Schiele, B. (2006) · Lecture notes in computer science · doi:10.1007/11414353_10 · Cited by 225 · see citing works
Simultaneous Object Recognition and Segmentation by Image Exploration
Ferrari, V., Tuytelaars, T., & Gool, L. V. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24670-1_4 · Cited by 224 · see citing works
Global localization using distinctive visual features
Se, S., Lowe, D. G., & Little, J. J. (2003) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/irds.2002.1041393 · Cited by 180 · see citing works
Carneiro, G., & Jepson, A. D. (2002) · Lecture notes in computer science · doi:10.1007/3-540-47969-4_19 · Cited by 94 · see citing works
Empirical Evaluation Methods in Computer Vision
(2002) · Series in machine perception and artificial intelligence · doi:10.1142/9789812777423 · Cited by 77 · see citing works
Automated Scene Matching in Movies
Schaffalitzky, F., & Zisserman, A. (2002) · Lecture notes in computer science · doi:10.1007/3-540-45479-9_20 · Cited by 75 · see citing works
Robust Recognition of Scaled Shapes using Pairwise Geometric Histograms.
Ashbrook, A. P., Thacker, N. A., Rockett, P., & Brown, C. (1995) · British Machine Vision Conference (BMVC) · doi:10.5244/c.9.50 · Cited by 57 · see citing works
Empirical Evaluation Methods in Computer Vision
Christensen, H. I., & Phillips, P. J. (2002) · Series in machine perception and artificial intelligence · doi:10.1142/4965 · Cited by 54 · see citing works
General Intensity Transformations and Second Order Invariants
Florack, L. M. J., Romeny, B. M. T. H., Koenderink, J. J., & Viergever, M. A. (1992) · Series in machine perception and artificial intelligence · doi:10.1142/9789812797896_0003 · Cited by 43 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955 · see citing works
Speeded-Up Robust Features (SURF)
Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2007.09.014 · Cited by 13,557 · see citing works
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 · see citing works
Self-citationVideo Google: a text retrieval approach to object matching in videos
Sivic, & Zisserman (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238663 · Cited by 6,367 · see citing works
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 · see citing works
Self-citationPCA-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.2004.1315206 · Cited by 3,237 · see citing works
A comparison of affine region detectors
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., & Gool, L. V. (2005) · International Journal of Computer Vision · doi:10.1007/s11263-005-3848-x · Cited by 2,939 · see citing works
Self-citationRobust Object Recognition with Cortex-Like Mechanisms
Serre, T., Wolf, L., Bileschi, S., Riesenhuber, M., & Poggio, T. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.56 · Cited by 1,667 · see citing works
LDAHash: Improved Matching with Smaller Descriptors
Strecha, C., Bronstein, A. M., Bronstein, M. M., & Fua, P. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.103 · Cited by 605 · see citing works
Monocular model-based 3D tracking of rigid objects: a survey
Lepetit, V., & Fua, P. (2005) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000001 · Cited by 484 · see citing works
Unsupervised deep learning for optical flow estimation
Ren, Z., Yan, J., Ni, B., Liu, B., Yang, X., & Zha, H. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10723 · Cited by 296 · see citing works
Animal biometrics: quantifying and detecting phenotypic appearance
Kühl, H. S., & Burghardt, T. (2013) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2013.02.013 · Cited by 189 · see citing works
Robust video fingerprinting for content-based video identification
Lee, S., & Yoo, C. D. (2008) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2008.920739 · Cited by 183 · see citing works
MTLDesc: Looking Wider to Describe Better
Wang, C., Xu, R., Zhang, Y., Xu, S., Meng, W., Fan, B., & Zhang, X. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20138 · Cited by 33 · see citing works
A Performance comparison of feature detectors for planetary rover mapping and localization
Wan, W., Peng, M., Xing, Y., Wang, Y., Liu, Z., Di, K., Teng, B., Mao, X., Zhao, Q., Xin, X., et al. (2017) · The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences · doi:10.5194/isprs-archives-xlii-3-w1-149-2017 · Cited by 6 · see citing works
- Authors
- Mikolajczyk, K., & Schmid, C.
- Affiliations
- Centre National de la Recherche Scientifique (FR)
- Venue
- 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
- Publisher
- IEEE Comput. Soc
- Published
- 2003-11-20
- Volume
- 2
- Pages
- II-257-II-263
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2129116707
- Cited by
- 955
- References
- 41
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 6 · 2023: 14 · 2022: 21 · 2021: 17 · 2020: 20 · 2019: 31 · 2018: 40 · 2017: 42 · 2016: 41 · 2015: 50 · 2014: 45 · 2013: 47 · 2012: 50
- FWCI
- 55.37
- Type
- conference paper
- Language
- en
- Open access
- green
- inria.hal.science
- Licence
- other-oa
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- HAL (submittedVersion, other-oa)
- 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
- local descriptors, SIFT, steerable filters, differential invariants, complex filters, moment invariants, cross correlation function, detection rate, false positive rate, image transformation, descriptor robustness
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.
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
