.. _SOMClassification: 

SOMClassification
=================





SOM image classification.

Description
-----------

Unsupervised Self Organizing Map image classification.



Parameters
----------

.. contents:: :local:

.. |br| raw:: html

   <br />

.. |em| raw:: html

   &emsp;

**InputImage** :code:`-in image` *Mandatory* |br|
Input image to classify.

**OutputImage** :code:`-out image [dtype]` *Mandatory* |br|
Output classified image (each pixel contains the index of its corresponding vector in the SOM).

**ValidityMask** :code:`-vm image` |br|
Validity mask (only pixels corresponding to a mask value greater than 0 will be used for learning)

**TrainingProbability** :code:`-tp float` *Default value: 1* |br|
Probability for a sample to be selected in the training set

**TrainingSetSize** :code:`-ts int` |br|
Maximum training set size (in pixels)

**SOM Map** :code:`-som image [dtype]` |br|
Output image containing the Self-Organizing Map

**SizeX** :code:`-sx int` *Default value: 32* |br|
X size of the SOM map

**SizeY** :code:`-sy int` *Default value: 32* |br|
Y size of the SOM map

**NeighborhoodX** :code:`-nx int` *Default value: 10* |br|
X size of the initial neighborhood in the SOM map

**NeighborhoodY** :code:`-ny int` *Default value: 10* |br|
Y size of the initial neighborhood in the SOM map

**NumberIteration** :code:`-ni int` *Default value: 5* |br|
Number of iterations for SOM learning

**BetaInit** :code:`-bi float` *Default value: 1* |br|
Initial learning coefficient

**BetaFinal** :code:`-bf float` *Default value: 0.1* |br|
Final learning coefficient

**InitialValue** :code:`-iv float` *Default value: 0* |br|
Maximum initial neuron weight

**Random seed** :code:`-rand int` |br|
Set a specific random seed with integer value.

**Available RAM (MB)** :code:`-ram int` *Default value: 256* |br|
Available memory for processing (in MB).



Examples
--------

From the command-line:

.. code-block:: bash

    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


From Python:

.. code-block:: python

	import otbApplication

	app = otbApplication.Registry.CreateApplication("SOMClassification")

	app.SetParameterString("in", "QB_1_ortho.tif")
	app.SetParameterString("out", "SOMClassification.tif")
	app.SetParameterFloat("tp", 1.0)
	app.SetParameterInt("ts", 16384)
	app.SetParameterInt("sx", 32)
	app.SetParameterInt("sy", 32)
	app.SetParameterInt("nx", 10)
	app.SetParameterInt("ny", 10)
	app.SetParameterInt("ni", 5)
	app.SetParameterFloat("bi", 1.0)
	app.SetParameterFloat("bf", 0.1)
	app.SetParameterFloat("iv", 0)

	app.ExecuteAndWriteOutput()