Parametric estimation of multi-dimensional affine transformations in the presence of noise: A linear solution

Rami Hagege, Joseph M. Francos

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

We consider the general framework of planar object registration and recognition based on a set of known templates. While the set of templates Is known, the tremendous set of possible affine transformations that may relate the template and the observed signature, makes any detection and recognition problem Ill-defined unless this variability Is taken Into account. Given a noisy observation on one of the known objects, subject to an unknown affine transformation of It, our goal Is to estimate the deformation that transforms some prechosen representation of this object (template) Into the current observation. We propose a method that employs a set of non-linear operators to replace the original high dimensional and non-linear problem by an equivalent linear least-squares problem, expressed In terms of the unknown affine transformation parameters. The proposed solution Is unique and Is applicable to any affine transformation regardless of the magnitude of the deformation.

Original languageEnglish
Title of host publication2005 IEEE/SP 13th Workshop on Statistical Signal Processing - Book of Abstracts
PublisherInstitute of Electrical and Electronics Engineers
Pages55-58
Number of pages4
ISBN (Print)0780394046, 9780780394049
DOIs
StatePublished - 1 Jan 2005
Event2005 IEEE/SP 13th Workshop on Statistical Signal Processing - Bordeaux, France
Duration: 17 Jul 200520 Jul 2005

Publication series

NameIEEE Workshop on Statistical Signal Processing Proceedings
Volume2005

Conference

Conference2005 IEEE/SP 13th Workshop on Statistical Signal Processing
Country/TerritoryFrance
CityBordeaux
Period17/07/0520/07/05

ASJC Scopus subject areas

  • Signal Processing

Fingerprint

Dive into the research topics of 'Parametric estimation of multi-dimensional affine transformations in the presence of noise: A linear solution'. Together they form a unique fingerprint.

Cite this