The DOI matches its Crossref record; 52 of the 52 references it cites were found in a registry or an index.
A performance evaluation of local descriptors
Open accessAbstract
In this paper, we compare the performance of descriptors computed for local interest regions, as, for example, extracted by the Harris-Affine detector [Mikolajczyk, K and Schmid, C, 2004]. Many different descriptors have been proposed in the literature. It is unclear which descriptors are more appropriate and how their performance depends on the interest region detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the detector. Our evaluation uses as criterion recall with respect to precision and is carried out for different image transformations. We compare shape context [Belongie, S, et al., April 2002], steerable filters [Freeman, W and Adelson, E, Setp. 1991], PCA-SIFT [Ke, Y and Sukthankar, R, 2004], differential invariants [Koenderink, J and van Doorn, A, 1987], spin images [Lazebnik, S, et al., 2003], SIFT [Lowe, D. G., 1999], complex filters [Schaffalitzky, F and Zisserman, A, 2002], moment invariants [Van Gool, L, et al., 1996], and cross-correlation for different types of interest regions. We also propose an extension of the SIFT descriptor and show that it outperforms the original method. Furthermore, we observe that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best. Moments and steerable filters show the best performance among the low dimensional descriptors.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“In the same paper [8], the authors have proposed a variant of SIFT, called GLOH, which proved to be even more distinctive with the same number of dimensions. However, GLOH is computationally more expensive.”
From SURF: Speeded Up Robust Features (2006) · cites this paper as [8]
In the citing paper
“It combines various sources of information, such as vision, language, depth data, lidar, and speech, to enhance the capability of scene semantic understanding [35,36,37].”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [35]
In the citing paper
“By studying the existing detectors and from published comparisons [15, 8], we can conclude that (1) Hessian-based detectors are more stable and repeatable than their Harris-based counterparts.”
From SURF: Speeded Up Robust Features (2006) · cites this paper as [8]
In the citing paper
“Using the determinant of the Hessian matrix rather than its trace (the Laplacian) seems advantageous, as it fires less on elongated, ill-localised structures.”
From SURF: Speeded Up Robust Features (2006) · cites this paper as [8]
In the citing paper
“This PCA-SIFT yields a 36dimensional 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.”
From SURF: Speeded Up Robust Features (2006) · cites this paper as [8]
In the citing paper
“Also, (2) approximations like the DoG can bring speed at a low cost in terms of lost accuracy.”
From SURF: Speeded Up Robust Features (2006) · cites this paper as [8]
In the citing paper
“Handcrafted local invariant features gained tremendous popularity, starting from the Scale Invariant Feature Transform (SIFT) feature (Lowe 1999), and the progress on various visual recognition tasks was based substantially on the use of local descriptors (Mikolajczyk and Schmid 2005) such as Haarlike features (Viola and Jones 2001), SIFT (Lowe 2004), Shape Contexts (Belongie et al. 2002), Hist”
From Deep Learning for Generic Object Detection: A Survey (2020) · cites this paper as Mikolajczyk and Schmid 2005
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
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
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
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
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
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
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
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
Габор, Д. (1946) · Journal of the IEE · Cited by 5,036
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 3,760
Flagged first, then by citations
Research works printed but not linked: 4
- Gouet, Evaluation de Détecteurs de Points d’Intér ${\rm \hat e}$ t pour la Couleur, 257
- Kadir, An Affine Invariant Method for Selecting Salient Regions in Images, 345
- Lazebnik, Sparse Texture Representation Using Affine-Invariant Neighborhoods, 319
- Schaffalitzky, Multi-View Matching for Unordered Image Sets, 414
Cited by
Sorted by citations
Items 1,001–1,006 of 1,006
Roy–Chowdhury, A. K., & Bi, S. (2012) · Synthesis lectures on computer vision · doi:10.2200/s00400ed1v01y201201cov004 · Cited by 46
Attention Weighted Local Descriptors
Wang, C., Xu, R., Lu, K., Xu, S., Meng, W., Zhang, Y., Fan, B., & Zhang, X. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3266728 · Cited by 36
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
Illumination invariant feature point matching for high-resolution planetary remote sensing images
Wu, B., Zeng, H., & Hu, H. (2018) · Planetary and Space Science · doi:10.1016/j.pss.2018.01.007 · Cited by 20
Counteracting the contemporaneous proliferation of digital forgeries and fake news
FERREIRA, A., CARVALHO, T., ANDALÓ, F., & ROCHA, A. (2019) · Anais da Academia Brasileira de Ciências · doi:10.1590/0001-3765201820180149 · Cited by 11
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
Metadata
- Authors
- Mikolajczyk, K., & Schmid, C.
- Affiliations
- University of Oxford (GB)
- Institut national de recherche en sciences et technologies du numérique (FR)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2005-10
- Volume
- 27
- Issue
- 10
- Pages
- 1615-1630
- ISSN
- 0162-8828 (ISSN-L)
- OpenAlex
- W2177274842
- Semantic Scholar
- 69401bfdafab7cde00bb8e5b2f6c28e9d72d8cfb
- Cited by
- 6,723
- References
- 52
- Citations by year
- 2026: 44 · 2025: 98 · 2024: 99 · 2023: 144 · 2022: 192 · 2021: 220 · 2020: 203 · 2019: 252 · 2018: 308 · 2017: 393 · 2016: 468 · 2015: 502 · 2014: 534 · 2013: 580 · 2012: 496
- FWCI
- 288.51
- Type
- journal article
- Language
- en
- Open access
- green
- inria.hal.science
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (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, PCA-SIFT, shape context, steerable filters, spin images, moment invariants, differential invariants, complex filters, cross correlation function, descriptor robustness, image transformation
- MeSH terms
- Algorithms, Artificial Intelligence, Computer Simulation, Data Interpretation, Statistical, Image Enhancement, Image Interpretation, Computer-Assisted, Pattern Recognition, Automated, Software, Software Validation, Models, Statistical, Information Storage and Retrieval
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
