Training Image classification procedure in which the computer identifies inherent patterns in the spectral data and uses a clustering algorithm to order pixels into discrete classes.
Must cluster analysis algorithms are unsupervised, this means that the analyst does not impose any structure on to the classification, instead the classification 'emerges' from the data. Later, we may wish to investigate if the classification matches some other grouping criteria (e.g. gender or species).
classification Using a computer to automatically generate a thematic map from digital remotely sensed imagery by statistically clustering pixels on the basis of spectral similarity. The clusters may then be assigned labels (e.g. habitat names) using the operator's field knowledge.