ISODATA stands for "Iterative Self-Organiz
ing Data Analysis
Technique." It is
iterative in that it repeatedly performs an en
tire classification (outputting a thematic raster
layer) and recalculates statistics. "Self-Organi
zing" refers to the way in which it locates
the clusters that are inherent in the data.
The ISODATA clustering method uses the
minimum spectral distance formula to
form clusters. It begins with either arbi
trary cluster means or means of an existing
signature set, and each time the clustering repeats, the means of these clusters are shifted.
The new cluster means are used for the next iteration.
The ISODATA utility repeats the cl
ustering of the image until either:
1.
A maximum number of iterations
has been performed, or
2.
A maximum percentage of unchanged pi
xels has been reached between two
iterations.