This document is archived and information here might be outdated.  Recommended version.


IMultivariateOp.MLClassify Method (ArcObjects .NET 10.4 SDK)
ArcObjects namespaces > SpatialAnalyst > ESRI.ArcGIS.SpatialAnalyst > Interfaces > IM > IMultivariateOp Interface > IMultivariateOp.MLClassify Method (ArcObjects .NET 10.4 SDK)
ArcObjects Library Reference (SpatialAnalyst)  

IMultivariateOp.MLClassify Method

Performs a maximum-likelihood classification on a raster band collection.

[Visual Basic .NET]
Public Function MLClassify ( _
    ByVal rasterBands As IGeoDataset, _
    ByVal signatureFile As String, _
    [ByVal createConfidenceOutput As Boolean], _
    [ByVal aPrioriWeighting As esriGeoAnalysisAPrioriEnum], _
    [ByVal aPrioriFile As Object], _
    [ByVal rejectFraction As Object] _
) As IGeoDataset

[C#]
public IGeoDataset MLClassify (
    IGeoDataset rasterBands,
    string signatureFile,
    bool createConfidenceOutput,
    esriGeoAnalysisAPrioriEnum aPrioriWeighting,
    object aPrioriFile,
    object rejectFraction
);
[C#]

Optional Values

createConfidenceOutput   Supply false as a default value.
aPrioriWeighting   Supply esriGeoAnalysisAPrioriEqual as a default value.
aPrioriFile   To indicate that this parameter is undefined, pass in Type.Missing.
rejectFraction   To indicate that this parameter is undefined, pass in Type.Missing. 
[C++]
HRESULT MLClassify(
  IGeoDataset* rasterBands,
  BSTR signatureFile,
  VARIANT_BOOL createConfidenceOutput,
  esriGeoAnalysisAPrioriEnum aPrioriWeighting,
  VARIANT aPrioriFile,
  VARIANT rejectFraction,
  IGeoDataset** classifiedDataset
);

[C++]

Parameters
rasterBands [in]

  rasterBands is a parameter of type IGeoDataset
signatureFile [in]
  signatureFile is a parameter of type BSTR
createConfidenceOutput [in, optional, defaultvalue(VARIANT_FALSE)]
  createConfidenceOutput is a parameter of type VARIANT_BOOL
aPrioriWeighting [in, optional, defaultvalue(1)]

  aPrioriWeighting is a parameter of type esriGeoAnalysisAPrioriEnum
aPrioriFile [optional]
  aPrioriFile is a parameter of type VARIANT

  To indicate this parameter is undefined pass in a VARIANT with type VT_ERROR and scode value of DISP_E_PARAMNOTFOUND.
rejectFraction [optional]
  rejectFraction is a parameter of type VARIANT

  To indicate this parameter is undefined pass in a VARIANT with type VT_ERROR and scode value of DISP_E_PARAMNOTFOUND.
classifiedDataset [out, retval]

  classifiedDataset is a parameter of type IGeoDataset

Product Availability

Available with ArcGIS Engine, ArcGIS Desktop, and ArcGIS Server. Requires Spatial Analyst Extension.

Remarks

rasterBands

name of a multiband Raster to perform the classification

signatureFile

name of the signature file whose class signatures are used by the maximum-likelihood classifier when performing the classification of the rasterBands

createConfidenceOutput

an optional output Raster showing the certainty of the classification in 14 levels of confidence with the lowest values representing the highest reliability

If the Boolean is set to True, the output Raster will be created.

APrioriWeighting

an esriGeoAnalysisAPrioriEnum specifying the type of a priori probabilities, or weights, for the classes represented in the aPriorFile

The enumeration types are:

esriGeoAnalysisEqual all classes will have the same a priori probability

esriGeoAnalysisSample a priori probabilities will be proportional to the number of cells in each class relative to the total number of cells sampled in all classes in the signature file

esriGeoAnalysisAPrioriFile a priori probabilities will be assigned to each class from an aPrioriFile ASCII file

[aPrioriFile]

a file containing user-defined a priori probabilities for the classes

[rejectFraction]

the portion of cells that will remain unclassified due to the lowest possibility of correct assignment

The most common reject fraction is 0.0, indicating every cell will be classified. The 14 valid entries are 0.0, 0.005, 0.01, 0.025, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.975, 0.99, 0.995.

 

See Also

IMultivariateOp Interface