SAGA-GIS Module Library Documentation (v2.3.0)

Module ISODATA Clustering for Grids

This tool executes the Isodata unsupervised classification - clustering algorithm. Isodata stands for Iterative Self-Organizing Data Analysis Techniques. This is a more sophisticated algorithm which allows the number of clusters to be automatically adjusted during the iteration by merging similar clusters and splitting clusters with large standard deviations.
The tool is based on Christos Iosifidis' Isodata implementation:
isodata.c

Further references:
Memarsadeghi, N., Mount, D. M., Netanyahu, N. S., Le Moigne, J. (2007): A Fast Implementation of the ISODATA Clustering Algorithm. International Journal of Computational Geometry and Applications, 17, 71-103. online

A Fast Implementation of the ISODATA Clustering Algorithm

Parameters

 NameTypeIdentifierDescriptionConstraints
InputFeaturesGrid list (input)FEATURES--
OutputClustersGrid (output)CLUSTER--
StatisticsTable (output)STATISTICS--
OptionsGrid systemGrid systemPARAMETERS_GRID_SYSTEMGrid system-
NormalizeBooleanNORMALIZE-Default: 0
Maximum Number of IterationsIntegerITERATIONS-Minimum: 3
Default: 20
Initial Number of ClustersIntegerCLUSTER_INI-Minimum: 0
Default: 5
Maximum Number of ClustersIntegerCLUSTER_MAX-Minimum: 3
Default: 16
Minimum Number of Samples in a ClusterIntegerSAMPLES_MIN-Minimum: 2
Default: 5
Update Colors from FeaturesBooleanRGB_COLORSUse the first three features in list to obtain blue, green, red components for class colour in look-up table.Default: 1

Command-line

Usage: saga_cmd imagery_classification 7 [-FEATURES <str>] [-CLUSTER <str>] [-STATISTICS <str>] [-NORMALIZE <str>] [-ITERATIONS <num>] [-CLUSTER_INI <num>] [-CLUSTER_MAX <num>] [-SAMPLES_MIN <num>]
  -FEATURES:<str>   	Features
	Grid list (input)
  -CLUSTER:<str>    	Clusters
	Grid (output)
  -STATISTICS:<str> 	Statistics
	Table (output)
  -NORMALIZE:<str>  	Normalize
	Boolean
	Default: 0
  -ITERATIONS:<num> 	Maximum Number of Iterations
	Integer
	Minimum: 3
	Default: 20
  -CLUSTER_INI:<num>	Initial Number of Clusters
	Integer
	Minimum: 0
	Default: 5
  -CLUSTER_MAX:<num>	Maximum Number of Clusters
	Integer
	Minimum: 3
	Default: 16
  -SAMPLES_MIN:<num>	Minimum Number of Samples in a Cluster
	Integer
	Minimum: 2
	Default: 5