Share Email Print
cover

Proceedings Paper

Bayesian segmentation for damage image using MRF prior
Author(s): G. Li; F. G. Yuan; R. Haftka; N. H. Kim
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Image segmentation for quantifying damage based on Bayesian updating scheme is proposed for diagnosis and prognosis in structural health monitoring. This scheme enables taking into account the prior information of the state of the structures, such as spatial constraints and image smoothness. Bayes' law is employed to update the segmentation with the spatial constraint described as Markov Random Field and the current observed image acting as a likelihood function. Segmentation results demonstrate that the proposed algorithm holds promise of searching a crack area in the SHM image and focusing on the real damage area by eliminating the pseudo-shadow area. Thus more precise crack estimation can be obtained than the conventional K-means segmentation by shrinking the fuzzy tails which often exist on both sides of the crack tips.

Paper Details

Date Published: 30 March 2009
PDF: 12 pages
Proc. SPIE 7292, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2009, 72920J (30 March 2009); doi: 10.1117/12.816507
Show Author Affiliations
G. Li, North Carolina State Univ. (United States)
F. G. Yuan, North Carolina State Univ. (United States)
R. Haftka, Univ. of Florida (United States)
N. H. Kim, Univ. of Florida (United States)


Published in SPIE Proceedings Vol. 7292:
Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2009
Masayoshi Tomizuka, Editor(s)

© SPIE. Terms of Use
Back to Top