Is sift scale invariant?

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

61 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)115-136
Journal / PublicationInverse Problems and Imaging
Volume5
Issue number1
Publication statusPublished - Feb 2011
Externally publishedYes

Abstract

This note is devoted to a mathematical exploration of whether Lowe's Scale-Invariant Feature Transform (SIFT) [21], a very successful image matching method, is similarity invariant as claimed. It is proved that the method is scale invariant only if the initial image blurs are exactly guessed. Yet, even a large error on the initial blur is quickly attenuated by this multiscale method, when the scale of analysis increases. In consequence, its scale invariance is almost perfect. The mathematical arguments are given under the assumption that the Gaussian smoothing performed by SIFT gives an aliasing free sampling of the image evolution. The validity of this main assumption is confirmed by a rigorous experimental procedure, and by a mathematical proof. These results explain why SIFT outperforms all other image feature extraction methods when it comes to scale invariance. © 2011 American Institute of Mathematical Sciences.

Research Area(s)

  • Aliasing, Gaussian blur, Sampling theory, Scale invariance, Shannon interpolation, SIFT

Bibliographic Note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to lbscholars@cityu.edu.hk.

Citation Format(s)

Is sift scale invariant? / Morel, Jean-Michel; Yu, Guoshen.
In: Inverse Problems and Imaging, Vol. 5, No. 1, 02.2011, p. 115-136.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review