====== Example 3 - Performing a supervised classification ======

This example shows how to perform a supervised classifiation using InterIMAGE.







===== Database =====


{{interimage:examples:example3_data.zip|Example 3 - Database}}

This zip file contains:

  * tijuca.tif
















===== Step by step =====

  * Start InterIMAGE. Click on //File// -> //New Project// and fill the fields according to the following:
{{interimage:examples:example3_1.png|New Project}}
  * Check the //Default Image// checkbox and click the //Add// button. Click OK.
  * Create a semantic net like this one:
(Class names shouldn't contain blank spaces or special characters)
{{interimage:examples:example3_22.png|Semantic net}}
  * Select the //Image// tab and click the Add button. Set its //Keyname// to //composed// and click the //Composition// button.
{{interimage:examples:example3_3.png|Image layer}} -> {{interimage:examples:example3_4.png|}}
  * In the dialog that appears set the color composition according to the image below:
{{interimage:examples:example3_5.png|Color Composition dialog}}
  * Close the dialog. Click //Save//. Another image layer is added and you should see something like this:
{{interimage:examples:example3_62.png|Image layer added}}
  * Save the project. Select the //Scene// node and click the //Samples Editor// button.
{{interimage:examples:example3_7.png|Open Samples Editor}}
  * Maximize the window that appears. Select the //TA_Baatz_Segmenter// operator. Set its parameters according to the following:
{{interimage:examples:example3_8.png|Selecting the operator}} -> {{interimage:examples:example3_9.png|Setting the operator parameters}}
  * Click the //Segment// button. Once the segmentation is finished, make sure the //Buildings// class is selected and click the //Collect Samples// button.
{{interimage:examples:example3_10.png|Collect samples}}
  * Now, click on some objects that belong to the //Buildings// class (To deselect an object just click it again).
{{interimage:examples:example3_11.png|Collecting samples}}
  * When you are done, repeat the process to the other two classes. Setting the //Background Image// to the other composition created previously can be helpful here.
  * After, click the //Collect Samples// again, deselecting it.
  * Click the //Export// button. In the window that appears click the //Class// button. Select //All// and click OK.
{{interimage:examples:example3_12.png|Export Shapefile}} -> {{interimage:examples:example3_13.png|Insert Class}}
  * Click the //Expression// button. Set the fields according to the image below:
{{interimage:examples:example3_14.png|Insert Expression}}
  * After, create another three expressions. Your decision rule should look like this:
{{interimage:examples:example3_15.png|Decision Rule}}
  * Click OK. Set the file name to samples.shp and Click //Save//.
  * Save the project. Once the project is saved click on //File// → //Edit Project//. Fill the fields according to the following:
{{interimage:examples:example3_16.png|Edit Project dialog}}
  * Click the //Add// button and then click OK.
  * Associate the //TA_C45_Classifier// top-down operator to the //Buildings// node. Set the operator parameters according to the image below. Make sure the //TopDown Multi-class// checkbox is checked.
{{interimage:examples:example3_17.png|Selecting the operator}} -> {{interimage:examples:example3_182.png|Setting its parameters}}
  * Save the project and execute the interpretation.
  * You can improve your classification collecting more samples for the classes that presented more confusion and repeating the process.