Fast and Robust Fuzzy C-Means Algorithms for Automated Brain MR Image Segmentation

Fast and Robust Fuzzy C-Means Algorithms for Automated Brain MR Image Segmentation

László Szilágyi, Sándor Miklós Szilágyi, Zoltán Benyó
Copyright: © 2008 |Pages: 9
DOI: 10.4018/978-1-59904-889-5.ch073
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

By definition, image segmentation represents the partitioning of an image into nonoverlapping, consistent regions, which appear to be homogeneous with respect to some criteria concerning gray level intensity and/or texture. The fuzzy c-means (FCM) algorithm is one of the most widely used method for data clustering, and probably also for brain image segmentation (Bezdek & Pal., 1991). However, in this latter case, standard FCM is not efficient by itself, as it is unable to deal with that relevant property of images that neighbor pixels are strongly correlated. Ignoring this specificity leads to strong noise sensitivity and several other imaging artifacts.

Key Terms in this Chapter

Gaussian Noise: Noise having Gaussian distribution.

Data Clustering: Partitioning data sets into subsets whose elements share common or similar properties.

Salt-and-Pepper Noise or Impulse Noise: Scattered black and white pixels replacing actual value.

Median Filter: A non-linear filtering technique which replaces the intensity of each pixel with the median intensity value found in a symmetrical neighborhood containing an odd number of pixels. It is usually applied to reduce salt-and-pepper noise.

Low-Pass Filter or Averaging Filter: Linear smoothing operator that replaces the intensity of each pixel with a weighted average intensity of its neighbor pixels.

Image Segmentation: Partitioning images into regions which are homogeneous with respect to some criteria that concern color, intensity, or texture.

Complete Chapter List

Search this Book:
Reset