The theory behind selection of the ``uniform error'' threshold which equalizes the probability of misclassification in an image containing two classes is presented. It is shown how this threshold can be estimated using local operations. Some examples and possible extensions are considered.
No takes yet. Share an insight, caveat, or question.
Dunn et al. (1984) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: