SOM Classification

Brief Description

SOM image classification.

Tags

Learning, Segmentation

Long Description

Unsupervised Self Organizing Map image classification.

Parameters

• InputImage (in): Input image to classify.

• OutputImage (out): Output classified image (each pixel contains the index of its corresponding vector in the SOM).

• ValidityMask (vm): Validity mask (only pixels corresponding to a mask value greater than 0 will be used for learning)

• TrainingProbability (tp): Probability for a sample to be selected in the training set

• TrainingSetSize (ts): Maximum training set size (in pixels)

• SOM Map (som): Output image containing the Self-Organizing Map

• SizeX (sx): X size of the SOM map

• SizeY (sy): Y size of the SOM map

• NeighborhoodX (nx): X size of the initial neighborhood in the SOM map

• NeighborhoodY (ny): Y size of the initial neighborhood in the SOM map

• NumberIteration (ni): Number of iterations for SOM learning

• BetaInit (bi): Initial learning coefficient

• BetaFinal (bf): Final learning coefficient

• InitialValue (iv): Maximum initial neuron weight

• Available RAM (Mb) (ram): Available memory for processing (in MB)

• set user defined seed (rand): Set specific seed. with integer value.

• Load otb application from xml file (inxml): Load otb application from xml file

• Save otb application to xml file (outxml): Save otb application to xml file

Limitations

None

Authors

OTB-Team

See also

Example of use

• Values for GUIs:

• in: QB_1_ortho.tif

• out: SOMClassification.tif

• tp: 1.0

• ts: 16384

• sx: 32

• sy: 32

• nx: 10

• ny: 10

• ni: 5

• bi: 1.0

• bf: 0.1

• iv: 0

• Command line to execute:

otbcli_SOMClassification -in QB_1_ortho.tif -out SOMClassification.tif -tp 1.0 -ts 16384 -sx 32 -sy 32 -nx 10 -ny 10 -ni 5 -bi 1.0 -bf 0.1 -iv 0