DocumentCode
3078791
Title
Numerical stability of nystrom extension for image segmentation
Author
Izquierdo, Ebroul ; Guerra-Ones, Valia
Author_Institution
Dept. of Electron. Eng., London Univ.
fYear
2004
fDate
Sept. 29 2004-Oct. 1 2004
Firstpage
609
Lastpage
614
Abstract
A stability analysis of the approximate solution for spectral partitioning in image segmentation based on the Nystrom extension is presented. Algorithmic modifications are introduced to improve the stability of the original technique reported in (C. Fowlkes et al., 2004). The proposed improvement includes a criterion for the selection of the initial sample and more stable estimations of inverse matrices. The proposed algorithm is validated by several computer experiments
Keywords
image segmentation; matrix inversion; numerical stability; Nystrom extension; image segmentation; inverse matrices; numerical stability; spectral partitioning; stability analysis; Active contours; Bayesian methods; Eigenvalues and eigenfunctions; Image processing; Image segmentation; Motion estimation; Numerical stability; Partitioning algorithms; Pixel; Sparse matrices;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning for Signal Processing, 2004. Proceedings of the 2004 14th IEEE Signal Processing Society Workshop
Conference_Location
Sao Luis
ISSN
1551-2541
Print_ISBN
0-7803-8608-4
Type
conf
DOI
10.1109/MLSP.2004.1423024
Filename
1423024
Link To Document