Title :
3-D contextual Bayesian classifiers
Author_Institution :
Dept. of Math. Modelling, Tech. Univ. Denmark, Lyngby, Denmark
fDate :
3/1/2000 12:00:00 AM
Abstract :
We extend a series of multivariate Bayesian two-dimensional (2-D) contextual classifiers to three-dimensional (3-D) by specifying a simultaneous Gaussian distribution for the feature vectors as well as a prior distribution of the class variables of a pixel and its six nearest 3-D neighbors
Keywords :
Bayes methods; Gaussian distribution; image classification; white noise; 3D contextual Bayesian classifiers; Gaussian distribution; class variables; feature vectors; image classification; multivariate Bayesian contextual classifiers; nearest 3D neighbors; prior distribution; Bayesian methods; Brain modeling; Frequency; Gaussian distribution; Image segmentation; Magnetic resonance; Nearest neighbor searches; Pixel; Testing; Two dimensional displays;
Journal_Title :
Image Processing, IEEE Transactions on
