GRalgo-GRalgo: Growing Region algorithm

In bozenne/MRIaggr: Management, Display, and Processing of Medical Imaging Data

Description

Perform the Growing Region algorithm proposed by (Revol et al., 1997). For internal use.

Usage

GRalgo(contrast, W, seed, sigma_max, range, breaks, step, operator, iter_max, 
         keep.lower, keep.upper, history.sigma, history.step, history.front)

Arguments

contrast	the contrast value of each observation. numeric vector.
W	the neighbourhood matrix. dgCMatrix.
seed	the index of the initial seeds or a binary indicator of the initial seeds. positive integer vector or logical vector.
sigma_max	the maximum admissible value for the variability of the group contrast. positive numeric.
range	the range of acceptable contrast values for the growing region group. numeric vector of size 2.
breaks	the break points to use to categorize the contrast distribution. numeric vector.
step	the step between two consecutive breaks. numeric.
iter_max	the maximum number of iterations for the expansion of the growing region. postive integer.
operator	should the median absolute deviation be used to estimte the variability of the group contrast ("mad") or the standard deviation ("sd").
keep.lower	should removing observations with high intensity of the region be forbidden ? logical.
keep.upper	should removing observations with low intensity of the region be forbidden ? logical.
history.sigma	should the values of sigma be recorded ? logical.
history.step	should the number of observations included in the GR set be recorded ? logical.
history.front	should the propagation front of the GR set be recorded ? logical.

References

Chantal Revol and Michel Jourlin. A new minimum varance region growing algorithm for image segmentation. Pattern Recognition Letters, 18(3):249-258,1997.

bozenne/MRIaggr documentation built on May 13, 2019, 1:39 a.m.