Workshop on Bioimaging II / PDEs, Mon, 19 Nov, 2007
Speaker: Yunmei Chen
Abstract
Parametric and nonparametric region based active contour models have been widely used in image segmentation and showed promising results. However, since these models are driven by intensity probability density functions (pdf), intensity inhomogeneity and higher level of noise are always challenging problems that need to be addressed.
In this paper we present a novel local nonparametric method for simultaneous image segmentation and adaptive smoothing. We treat the recovered image intensity at each point as a random variable, whose realizations are the intensities of the observed image at a neighborhood of this point.
The neighborhood size varies from point to point depending on image gradients. A nonparametric pdf estimation is applied to the recovered image to get likelihood estimations for both object and background. Then, the simultaneous smoothing and segmentation is achieved by minimizing the negative log-likelihood estimations together with total length of the region boundaries. By the choice of the local neighborhoods the smoothing does not across the boundaries and is less at the locations where image gradient is large to preserve features. The proposed model is implemented using its level set formulation. The experimental results on synthetic data, human MRI, FLAIR MRI brain images, and echocardiographic images indicate the advantages of the proposed model in dealing with higher level noise and intensity inhomogeneity. The existence of a solution to the proposed model is also discussed.
URL: www.ricam.oeaw.ac.at/specsem/ssqbm/participants/abstracts/index.php
This page was made with 100% valid HTML & CSS - Send comments to Webmaster
Today's date and time is 04/27/24 - 00:54 CEST and this file (/specsem/ssqbm/participants/abstracts/index.php) was last modified on 12/18/12 - 11:01 CEST