SIFT-Rank: Ordinal description for invariant feature correspondence

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...

Full description

Saved in:
Bibliographic Details
Published in2009 IEEE Conference on Computer Vision and Pattern Recognition pp. 172 - 177
Main Authors Toews, Matthew, Wells, William
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2009
Subjects
Application software
Biomedical imaging
Computer vision
Current measurement
Electrical resistance measurement
Hospitals
Image sensors
Lighting
Sorting
Time measurement
Online AccessGet full text

Cover

More Information
Summary: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 precision-recall, including standard SIFT and GLOH.
ISBN:1424439922
9781424439928
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2009.5206849