17.6 1:N Matching Implementation
Double click menu item “NeuralNet/Matching/1:N (Key vs Source)” and enter:
private void menuItem116_Click(object sender, System.EventArgs e)
{
this.mainMenuToAPI.neuralNet_Matching_1N
( textBox1.Text , gui.imageAbsoultePath, dataDir + "c1.txt" );
}
Here, mainMenuToAPI is an object, which will implement all functions. As we discussed earlier, the main form simply links menu items to functions in the mainMenuToAPI object. The implementation is:
public bool neuralNet_Matching_1N
( string key, string [] imageAbsoultePath, string c1_txt)
{
bool b = false;
if ( imageAbsoultePath == null )
{
f.richTextBox1.Text =
"Search Image Source Fail!\nPlease specify search source!\n" ;
return false;
}
try
{
script.results_1N =
script.neuralNetFilter.findMatch1N ( imageAbsoultePath ) ;
}
catch (Exception e)
{
appendText ( "NeuralFilter 1:N Matching fails:\n"
+ e.ToString () + "\n");
return false;
}
if ( script.results_1N == null )
{
appendText ( "NeuralNet 1:N Matching fails!\n" );
return false;
}
return true;
}
The following code simply makes sure search source exists:
if ( imageAbsoultePath == null )
{
f.richTextBox1.Text =
"Search Image Source Fail!\nPlease specify search source!\n" ;
return false;
}
The next section of code makes a 1:N Match:
try
{
script.results_1N =
script.neuralNetFilter.findMatch1N ( imageAbsoultePath ) ;
}
catch (Exception e)
{
appendText ( "NeuralFilter 1:N Matching fails:\n"
+ e.ToString () + "\n");
return false;
}
Remember, the neural net is already trained with the key image at this point.
Copyright (c) 2006 - 2007 Attrasoft. All rights reserved.