Eigendecomposition of Correlated Images Characterized by Three Parameters

Author

Saitwal, Kishor ; Maciejewski, Anthony A. ; Roberts, Rodney G.

Author_Institution

Dept. of Electr. & Comput. Eng., Colorado State Univ., Fort Collins, CO

fYear

0

fDate

0-0 0

Firstpage

203

Lastpage

207

Abstract

Most eigendecomposition algorithms operate on correlated images that are characterized by only one parameter. Hence they lack the required specifications of fully general 3D image data sets, in which the images need to be characterized by three parameters. In this paper, an extension of one of the fastest known eigendecomposition algorithms is successfully implemented to improve the computational efficiency of computing the eigendecomposition of such 3D image sets. This algorithm can be used in pattern recognition applications such as fully general 3D pose estimation of objects

Keywords

correlation methods; eigenvalues and eigenfunctions; image processing; computational efficiency; correlated image eigendecomposition; fully general 3D image data sets; fully general 3D pose estimation; pattern recognition applications; Active appearance model; Application software; Collaborative work; Computational efficiency; Computer vision; Contracts; Government; Image processing; Pattern recognition; Singular value decomposition;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Interpretation, 2006 IEEE Southwest Symposium on

Conference_Location

Denver, CO

Print_ISBN

1-4244-0069-4

Type

conf

DOI

10.1109/SSIAI.2006.1633751

Filename

1633751