In This Topic ▼

OCR Tutorial - Scanning to Searchable PDF

Take the following steps to create and run a program that shows how scan a document and convert it to a searchable PDF file.

Start Visual Studio
Choose File->New->Project from the menu.
In the New Project dialog box, choose either "Visual C# Projects" or "VB Projects" in the Projects Type List, and choose "Windows Application" or "Windows Forms Application" depending on your Visual Studio version from the Templates List.
Type the project name as "OcrTutorial3" in the Project Name field, and then choose OK. If desired, type a new location for your project or select a directory using the Browse button, and then choose OK.
In the "Solution Explorer" window, right-click on the "References" folder, and select "Add Reference..." from the context menu. In the "Add Reference" dialog box, select the ".NET" tab and browse to LEADTOOLS For .NET "<LEADTOOLS_INSTALLDIR>\Bin\DotNet4\Win32" folder and select the following DLLs:
- Leadtools.dll
- Leadtools.Codecs.dll
- Leadtools.Twain.dll
- Leadtools.ImageProcessing.Core.dll
- Leadtools.Forms.Common.dll
- Leadtools.Document.Writer.dll
- Leadtools.Ocr.dll
- Leadtools.Ocr.LEADEngine.dll
- Leadtools.Codecs.Bmp.dll
- Leadtools.Codecs.Cmp.dll
- Leadtools.Codecs.Tif.dll
- Leadtools.Codecs.Fax.dll
Note: The Leadtools.Codecs.*.dll references added are for the BMP, JPG, CMP, TIF and FAX image formats. Add any additional file format codec DLL if required in your application.

Drag and drop three buttons in Form1. Leave all the buttons names as the default "button1, button2 ...", then change the Text property of each button to the following:

Button	Text
button1	Change output directory
button2	Select the Scanner
button3	Scan and OCR

Switch to Form1 code view (Right-click Form1 in the solution explorer then select View Code) and add the following lines at the beginning of the file after any using or Imports section if there are any:

     
using Leadtools; 
using Leadtools.Twain; 
using Leadtools.ImageProcessing; 
using Leadtools.ImageProcessing.Core; 
using Leadtools.Forms.Common; 
using Leadtools.Document.Writer; 
using Leadtools.Ocr;

Imports Leadtools 
Imports Leadtools.Twain 
Imports Leadtools.ImageProcessing 
Imports Leadtools.ImageProcessing.Core 
Imports Leadtools.Forms.Common 
Imports Leadtools.Document.Writer 
Imports Leadtools.Ocr

Add the following private variables to the Form1 class:

// The OCR engine instance 
private IOcrEngine _ocrEngine; 
// OCR document instance 
private IOcrDocument _ocrDocument; 
// The Twain session 
private TwainSession _twainSession; 
// The output directory for saving PDF files 
private string _outputDirectory = @"C:\MyImages"; 
// The image processing commands we are going to use to clean the scanned image 
private List<RasterCommand> _imageProcessingCommands; 
private int _scanCount;

' The OCR engine instance 
Private _ocrEngine As IOcrEngine 
' OCR document instance 
Private _ocrDocument As IOcrDocument 
' The Twain session 
Private _twainSession As TwainSession 
' The output directory for saving PDF files 
Private _outputDirectory As String = "C:\MyImages" 
' The image processing commands we are going to use to clean the scanned image 
Private _imageProcessingCommands As List(Of RasterCommand) 
Private _scanCount As Integer

Override Form1OnLoad and add the following code:

protected override void OnLoad(EventArgs e) 
{ 
   // Initialize the OCR engine 
   _ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD, false); 
   // Startup the engine 
   _ocrEngine.Startup(null, null, null, @"C:\LEADTOOLS 20\Bin\Common\OcrLEADRuntime"); 
           
   // Initialize Twain scanning session 
   _twainSession = new TwainSession(); 
   _twainSession.Startup(this.Handle, "My Company", "My Product", "My Version", "My Application", TwainStartupFlags.None); 
           
   // Subscribe to the TwainSession.Acquire event to get the image 
   _twainSession.AcquirePage += new EventHandler<TwainAcquirePageEventArgs>(_twainSession_AcquirePage); 
           
   // Initialize the image processing commands we are going to use 
   // Add as many as you like, here we will add Deskew and Despeckle 
   _imageProcessingCommands = new List<RasterCommand>(); 
   _imageProcessingCommands.Add(new DeskewCommand()); 
   _imageProcessingCommands.Add(new DespeckleCommand()); 
           
   base.OnLoad(e); 
}

Protected Overrides Sub OnLoad(e As EventArgs) 
   ' Initialize the OCR engine 
   _ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD, False) 
   ' Startup the engine 
   _ocrEngine.Startup(Nothing, Nothing, Nothing, "C:\LEADTOOLS 20\Bin\Common\OcrLEADRuntime") 
           
   ' Initialize Twain scanning session 
   _twainSession = New TwainSession() 
   _twainSession.Startup(Me.Handle, "My Company", "My Product", "My Version", "My Application", TwainStartupFlags.None) 
           
   ' Subscribe to the TwainSession.Acquire event to get the image 
   AddHandler _twainSession.AcquirePage, AddressOf _twainSession_AcquirePage 
           
   ' Initialize the image processing commands we are going to use 
   ' Add as many as you like, here we will add Deskew and Despeckle 
   _imageProcessingCommands = New List(Of RasterCommand)() 
   _imageProcessingCommands.Add(New DeskewCommand()) 
   _imageProcessingCommands.Add(New DespeckleCommand()) 
           
   MyBase.OnLoad(e) 
End Sub

Override Form1OnFormClosed and add the following code:

protected override void OnFormClosed(FormClosedEventArgs e) 
{ 
   // Shutdown and dispose the OCR engine 
   _ocrEngine.Dispose(); 
           
   // And the twain session 
   _twainSession.Shutdown(); 
           
   base.OnFormClosed(e); 
}

Protected Overrides Sub OnFormClosed(e As FormClosedEventArgs) 
   ' Shutdown and dispose the OCR engine 
   _ocrEngine.Dispose() 
           
   ' And the twain session 
   _twainSession.Shutdown() 
           
   MyBase.OnFormClosed(e) 
End Sub

Add the following code for the button1 (Change output directory) Click handler:

private void button1_Click(object sender, EventArgs e) 
{ 
   // Change the output directory 
   using (FolderBrowserDialog dlg = new FolderBrowserDialog()) 
   { 
      dlg.SelectedPath = _outputDirectory; 
      dlg.ShowNewFolderButton = true; 
      if (dlg.ShowDialog(this) == DialogResult.OK) 
         _outputDirectory = System.IO.Path.GetFullPath(dlg.SelectedPath); 
   } 
}

Private Sub button1_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles button1.Click 
   ' Change the output directory 
   Using dlg As New FolderBrowserDialog() 
      dlg.SelectedPath = _outputDirectory 
      dlg.ShowNewFolderButton = True 
      If dlg.ShowDialog(Me) = DialogResult.OK Then 
         _outputDirectory = System.IO.Path.GetFullPath(dlg.SelectedPath) 
      End If 
   End Using 
End Sub

Add the following code for the button2 (Select the Scanner) Click handler:

private void button2_Click(object sender, EventArgs e) 
{ 
   // Select the scanner to use 
   _twainSession.SelectSource(null); 
}

Private Sub button2_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles button2.Click 
   ' Select the scanner to use 
   _twainSession.SelectSource(Nothing) 
End Sub

Add the following code for the button3 (Scan and Ocr) Click handler:

private void button3_Click(object sender, EventArgs e) 
{ 
   // Create the output directory if it does not exist 
   if(!System.IO.Directory.Exists(_outputDirectory)) 
      System.IO.Directory.CreateDirectory(_outputDirectory); 
           
   // Build the output PDF file name 
   string name = "Scanned" + _scanCount; 
   _scanCount++; 
   string pdfFileName = System.IO.Path.Combine(_outputDirectory, name + ".pdf"); 
           
   // Create a new file-based OCR document to add the scanned pages to 
   _ocrDocument = _ocrEngine.DocumentManager.CreateDocument(null, OcrCreateDocumentOptions.AutoDeleteFile); 
           
   // Scan the new page(s) 
   _twainSession.Acquire(TwainUserInterfaceFlags.Show); 
           
   // Save as PDF 
   _ocrDocument.Save(pdfFileName, DocumentFormat.Pdf, null); 
           
   // Delete the document 
   _ocrDocument.Dispose(); 
           
   // Show the result PDF file 
   System.Diagnostics.Process.Start(pdfFileName); 
}

Private Sub button3_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles button3.Click 
   ' Create the output directory if it does not exist 
   If Not System.IO.Directory.Exists(_outputDirectory) Then 
      System.IO.Directory.CreateDirectory(_outputDirectory) 
   End If 
           
   ' Build the output PDF file name 
   Dim name As String = "Scanned" + _scanCount 
   _scanCount = _scanCount + 1 
           
   Dim pdfFileName As String = System.IO.Path.Combine(_outputDirectory, name + ".pdf") 
           
   ' Create a new file-based OCR document to add the scanned pages to 
   _ocrDocument = _ocrEngine.DocumentManager.CreateDocument(Nothing, OcrCreateDocumentOptions.AutoDeleteFile) 
           
   ' Scan the new page(s) 
   _twainSession.Acquire(TwainUserInterfaceFlags.Show) 
           
   ' Save as PDF 
   _ocrDocument.Save(pdfFileName, DocumentFormat.Pdf, Nothing) 
           
   ' Delete the document 
   _ocrDocument.Dispose() 
           
   ' Show the result PDF file 
   System.Diagnostics.Process.Start(pdfFileName) 
End Sub

Finally add the following code for the Twain acquire handle:

private void _twainSession_AcquirePage(object sender, TwainAcquirePageEventArgs e) 
{ 
   // We have a page 
   RasterImage image = e.Image; 
           
   // First, run the image processing commands on it 
   foreach (RasterCommand command in _imageProcessingCommands) 
   { 
      command.Run(image); 
   } 
           
   // Create an OCR page for it 
   using (IOcrPage ocrPage = _ocrEngine.CreatePage(image, OcrImageSharingMode.AutoDispose)) 
   { 
      // Recognize it and add it to the document 
      ocrPage.Recognize(null); 
           
      _ocrDocument.Pages.Add(ocrPage); 
   } 
}

Private Sub _twainSession_AcquirePage(sender As Object, e As TwainAcquirePageEventArgs) 
   ' We have a page 
   Dim image As RasterImage = e.Image 
           
   ' First, run the image processing commands on it 
   For Each command As RasterCommand In _imageProcessingCommands 
      command.Run(image) 
   Next 
           
   ' Create an OCR page for it 
   Using ocrPage As IOcrPage = _ocrEngine.CreatePage(image, OcrImageSharingMode.AutoDispose) 
      ' Recognize it and add it to the document 
      ocrPage.Recognize(Nothing) 
           
      _ocrDocument.Pages.Add(ocrPage) 
   End Using 
End Sub