Skip to main navigation Skip to search Skip to main content

SIFT-rank: Ordinal description for invariant feature correspondence

  • Brigham and Women’s Hospital

Research output: Contribution to Book/Report types › Contribution to conference proceedings › peer-review

50 Citations (Scopus)

Abstract

This paper investigates ordinal image description for invariant feature correspondence. Ordinal description is a meta-technique which considers image measurements in terms of their ranks in a sorted array, instead of the measurement values themselves. Rank-ordering normalizes descriptors in a manner invariant under monotonic deformations of the underlying image measurements, and therefore serves as a simple, non-parametric substitute for ad hoc scaling and thresholding techniques currently used. Ordinal description is particularly well-suited for invariant features, as the high dimensionality of state-of-the-art descriptors permits a large number of unique rank-orderings, and the computationally complex step of sorting is only required once after geometrical normalization. Correspondence trials based on a benchmark data set show that in general, rank-ordered SIFT (SIFT-Rank) descriptors outperform other state-of-the-art descriptors in terms of precisionrecall, including standard SIFT and GLOH.

Original languageEnglish
Title of host publication2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
PublisherIEEE Computer Society
Pages172-177
Number of pages6
ISBN (Print)9781424439935
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 - Miami, FL, United States
Duration: 20 Jun 2009 → 25 Jun 2009

Publication series

Name2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

Conference

Conference2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
Country/TerritoryUnited States
CityMiami, FL
Period20/06/09 → 25/06/09

Fingerprint

Dive into the research topics of 'SIFT-rank: Ordinal description for invariant feature correspondence'. These topics are generated from the title and abstract of the publication. Together, they form a unique fingerprint.

Cite this