Iso Cluster Unsupervised Classification (Spatial Analyst)

Summary

Performs unsupervised classification on a series of input raster bands using the Iso Cluster and Maximum Likelihood Classification tools.

Learn more about how the Interactive Supervised Classification tool works

Usage

• This tool combines the functionalities of the Iso Cluster and Maximum Likelihood Classification tools. It outputs a classified raster. It optionally outputs a signature file.

• The resulting signature file from this tool can be used as the input for another classification tool, such as Maximum Likelihood Classification, for greater control over the classification parameters.

• The minimum valid value for the number of classes is two. There is no maximum number of clusters. In general, more clusters require more iterations.

• To provide the sufficient statistics necessary to generate a signature file for a future classification, each cluster should contain enough cells to accurately represent the cluster. The value entered for the minimum class size should be approximately 10 times larger than the number of layers in the input raster bands.

• The value entered for the sample interval indicates one cell out of every n-by-n block of cells is used in the cluster calculations.

• You shouldn't merge or remove classes or change any of the statistics of the ASCII signature file.

• Generally, the more cells contained in the extent of the intersection of the input bands, the larger the values for minimum class size and sample interval should be specified. Values entered for the sample interval should be small enough that the smallest desirable categories existing in the input data will be appropriately sampled.

• The class ID values on the output signature file start at one and sequentially increase to the number of input classes. The assignment of the class numbers is arbitrary.

• The output signature file's name must have a .gsg extension.

• Better results will be obtained if all input bands have the same data ranges. If the bands have vastly different data ranges, the data ranges can be transformed to the same range using Map Algebra to perform the equation.

   where:
     Z is the output raster with new data ranges.
     X is the input raster.
     oldmin is the minimum value of the input raster.
     oldmax is the maximum value of the input raster.
     newmin is the desired minimum value for the output raster.
     newmax is the desired maximum value for the output raster.

• If the input is a layer created from a multiband raster with more than three bands, the operation will consider all the bands associated with the source dataset, not just the three bands that were loaded (symbolized) by the layer.

• There are several ways you can specify a subset of bands from a multiband raster to use as input into the tool.

  • If using the tool dialog box, navigate to the multiband raster using the browse button next to Input raster bands, open the raster, and select the desired bands.
  • If the multiband raster is a layer in the Table of Contents, you can use the Make Raster Layer tool create a new multiband layer containing only the desired bands.
  • You can also create a new dataset that contains only the desired bands with Composite Bands and use the resulting dataset as input to the tool.
  • In Python, the desired bands can be directly specified in the tool parameter as a list.

Syntax

IsoClusterUnsupervisedClassification (Input_raster_bands, Number_of_classes, {Minimum_class_size}, {Sample_interval}, {Output_signature_file})

Parameter	Explanation	Data Type
Input_raster_bands [in_raster_band,...]	The input raster bands.	Raster Layer
Number_of_classes number_of_classes	Number of classes into which to group the cells.	Long
Minimum_class_size minimum_class_size (Optional)	Minimum number of cells in a valid class. The default is 20.	Long
Sample_interval sample_interval (Optional)	The interval to be used for sampling. The default is 10.	Long
Output_signature_file out_signature_file (Optional)	The output signature file. A .gsg extension must be specified.	File

Return Value

Name	Explanation	Data Type
Output_classified_raster	The output classified raster.	Raster

Code Sample

IsoClusterUnsupervisedClassification example 1 (Python window)

This example performs an unsupervised classification classifying the input bands into 5 classes and outputs a classified raster.

import arcpy
from arcpy import env
from arcpy.sa import *
env.workspace = "C:/sapyexamples/data"
outUnsupervised = IsoClusterUnsupervisedClassification("redlands", 5, 20, 50)
outUnsupervised.save("c:/temp/unsup01")

IsoClusterUnsupervisedClassification example 2 (stand-alone script)

This example performs an unsupervised classification classifying the input bands into 5 classes and outputs a classified raster.

# Name: IsoClusterUnsupervisedClassification_Ex_02.py
# Description: Uses an isodata clustering algorithm to determine the 
#    characteristics of the natural groupings of cells in multidimensional 
#    attribute space and stores the results in an output ASCII signature file.
# Requirements: Spatial Analyst Extension

# Import system modules
import arcpy
from arcpy import env
from arcpy.sa import *

# Set environment settings
env.workspace = "C:/sapyexamples/data"

# Set local variables
inRaster = "redlands"
classes = 5
minMembers = 50
sampInterval = 15

# Check out the ArcGIS Spatial Analyst extension license
arcpy.CheckOutExtension("Spatial")

# Execute IsoCluster
outUnsupervised = IsoClusterUnsupervisedClassification(inRaster, classes, minMembers, sampInterval)
outUnsupervised.save("c:/temp/outunsup01.tif")

Environments

Cell Size, Current Workspace, Output Coordinate System, Scratch Workspace

Licensing Information

ArcGIS for Desktop Basic: Requires Spatial Analyst

ArcGIS for Desktop Standard: Requires Spatial Analyst

ArcGIS for Desktop Advanced: Requires Spatial Analyst