DimensionalityReduction
Brief Description
Perform Dimension reduction of the input image.Tags
Dimensionality Reduction,Image FilteringLong Description
Performs dimensionality reduction on input image. PCA,NA-PCA,MAF,ICA methods are available. It is also possible to compute the inverse transform to reconstruct the image. It is also possible to optionnaly export the transformation matrix to a text file.Parameters
- [param] -in <string> The input image to apply dimensionality reduction.. Mandatory: True. Default Value: ""
- [param] -out <string> output image. Components are ordered by decreasing eigenvalues.. Mandatory: True. Default Value: ""
- [param] -rescale <string> . Mandatory: False. Default Value: "0"
- [param] -outinv <string> reconstruct output image.. Mandatory: False. Default Value: ""
- [param] -nbcomp <int32> Number of relevant components kept. By default all components are kept.. Mandatory: False. Default Value: "0"
- [param] -normalize <boolean> center AND reduce data before Dimensionality reduction.. Mandatory: False. Default Value: "True"
- [param] -outmatrix <string> Filename to store the transformation matrix (csv format). Mandatory: False. Default Value: ""
- [param] -inxml <string> Load otb application from xml file. Mandatory: False. Default Value: ""
- [param] -outxml <string> Save otb application to xml file. Mandatory: False. Default Value: ""
[choice] -method Selection of the reduction dimension method. pca,napca,maf,ica. Mandatory: True. Default Value: "pca"- [group] -pca
- [group] -napca
- [param] -method.napca.radiusx <int32> . Mandatory: True. Default Value: "1"
- [param] -method.napca.radiusy <int32> . Mandatory: True. Default Value: "1"
- [group] -maf
- [group] -ica
- [param] -method.ica.iter <int32> . Mandatory: False. Default Value: "20"
- [param] -method.ica.mu <float> . Mandatory: False. Default Value: "1"
Limitations
This application does not provide the inverse transform and the transformation matrix export for the MAF.Authors
OTB-TeamSee Also
"Kernel maximum autocorrelation factor and minimum noise fraction transformations," IEEE Transactions on Image Processing, vol. 20, no. 3, pp. 612-624, (2011)Example of use
in: cupriteSubHsi.tif
out: FilterOutput.tif
method: pca