Cited by 3,237Advanced Image and Video Retrieval TechniquesImage Retrieval and Classification TechniquesComputer Science and Engineering

PCA-SIFT: a more distinctive representation for local image descriptors

Yan Ke, Sukthankar, R.·2004·Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.

Abstract

Stable local feature detection and representation is a fundamental component of many image registration and object recognition algorithms. Mikolajczyk and Schmid (June 2003) recently evaluated a variety of approaches and identified the SIFT [D. G. Lowe, 1999] algorithm as being the most resistant to common image deformations. This paper examines (and improves upon) the local image descriptor used by SIFT. Like SIFT, our descriptors encode the salient aspects of the image gradient in the feature point's neighborhood; however, instead of using SIFT's smoothed weighted histograms, we apply principal components analysis (PCA) to the normalized gradient patch. Our experiments demonstrate that the PCA-based local descriptors are more distinctive, more robust to image deformations, and more compact than the standard SIFT representation. We also present results showing that using these descriptors in an image retrieval application results in increased accuracy and faster matching.

Integrity signals

Registry

Crossref · 10.1109/cvpr.2004.1315206

Cites

18 of 18 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Cites

Flagged first, then by citations

1 of the 19 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Authors
Ke, Y., & Sukthankar, R.
Affiliations
  • Carnegie Mellon University (US)
  • Intel (United States) (US)
Venue
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
Publisher
IEEE
Published
2004-11-12
Volume
2
Pages
506-513
ISSN
1063-6919 (ISSN-L)
OpenAlex
W2145072179
Cited by
3,237
References
19
Citations by year
2026: 8 · 2025: 36 · 2024: 50 · 2023: 72 · 2022: 84 · 2021: 129 · 2020: 113 · 2019: 159 · 2018: 156 · 2017: 229 · 2016: 223 · 2015: 261 · 2014: 265 · 2013: 254 · 2012: 217
FWCI
53.08
Type
conference paper
Language
en
Open access
closed
Locations
IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
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 › Artificial Intelligence › Computer Science and Engineering
Keywords
PCA-SIFT, local image descriptors, SIFT, principal component analysis, local feature detection, image registration, object recognition, image retrieval, feature matching

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