Take the following steps to create and run a program that shows how to add/delete and paint the zones in an OCR document. Remember, the purpose of the tutorials is to provide you with a quick and easy way to generate an OCR program.
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 "OcrTutorial1" 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:
Note: The Leadtools.Codecs.*.dll references added are for the BMP, JPG, CMP, TIF and FAX image file formats. Add any additional file format codec DLL if required in your application.
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.Codecs;
using Leadtools.Drawing;
using Leadtools.Controls;
using Leadtools.Forms;
using Leadtools.Forms.Ocr;
using Leadtools.Forms.DocumentWriters;
Imports Leadtools
Imports Leadtools.Codecs
Imports Leadtools.Drawing
Imports Leadtools.Controls
Imports Leadtools.Forms
Imports Leadtools.Forms.Ocr
Imports Leadtools.Forms.DocumentWriters
Add the following private variables to the Form1 class:
private ImageViewer _imageViewer;
private IOcrEngine _ocrEngine;
private IOcrPage _ocrPage;
Private _imageViewer As ImageViewer
Private _ocrEngine As IOcrEngine
Private _ocrPage As IOcrPage
Override Form1OnLoad
and add the following code:
protected override void OnLoad(EventArgs e)
{
// Add the image viewer to the form
_imageViewer = new ImageViewer();
_imageViewer.Dock = DockStyle.Fill;
Controls.Add(_imageViewer);
_imageViewer.BringToFront();
// Show images using their true size
_imageViewer.UseDpi = true;
// Add ability to pan/zoom with the mouse, but disable double click size mode support because we will use our own
ImageViewerPanZoomInteractiveMode panZoomMode = new ImageViewerPanZoomInteractiveMode();
panZoomMode.DoubleTapSizeMode = ControlSizeMode.None;
_imageViewer.InteractiveModes.Add(panZoomMode);
// Initialize the OCR engine
_ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.Advantage, false);
// Startup the engine
_ocrEngine.Startup(null, null, null, @"C:\LEADTOOLS 19\Bin\Common\OcrAdvantageRuntime");
// Create the OCR page from an image
string fileName = @"C:\Users\Public\Documents\LEADTOOLS Images\Ocr1.tif";
RasterImage rasterImage = _ocrEngine.RasterCodecsInstance.Load(fileName, 1);
_ocrPage = _ocrEngine.CreatePage(rasterImage, OcrImageSharingMode.AutoDispose);
// Auto-zone this page
_ocrPage.AutoZone(null);
// Add an extra zone, this is our user defined one
OcrZone zone = new OcrZone();
zone.Name = "Custom zone";
zone.ZoneType = OcrZoneType.Text;
zone.Bounds = new LogicalRectangle(10, 10, _ocrPage.Width - 20, 100, LogicalUnit.Pixel);
_ocrPage.Zones.Add(zone);
// Show this image in the viewer
_imageViewer.Image = _ocrPage.GetRasterImage();
Text = "Right click on any zone to remove it from the page, double click anywhere to save the result as a PDF file";
// Hook to the events we will use
_imageViewer.PostRender += _imageViewer_PostRender;
_imageViewer.MouseDown += _imageViewer_MouseDown;
_imageViewer.MouseDoubleClick += _imageViewer_MouseDoubleClick;
base.OnLoad(e);
}
Protected Overrides Sub OnLoad(e As EventArgs)
' Add the image viewer to the form
_imageViewer = New ImageViewer()
_imageViewer.Dock = DockStyle.Fill
Controls.Add(_imageViewer)
_imageViewer.BringToFront()
' Show images using their true size
_imageViewer.UseDpi = True
' Add ability to pan/zoom with the mouse, but disable double click size mode support because we will use our own
Dim panZoomMode As New ImageViewerPanZoomInteractiveMode()
panZoomMode.DoubleTapSizeMode = ControlSizeMode.None
_imageViewer.InteractiveModes.Add(panZoomMode)
' Initialize the OCR engine
_ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.Advantage, False)
' Startup the engine
_ocrEngine.Startup(Nothing, Nothing, Nothing, "C:\LEADTOOLS 19\Bin\Common\OcrAdvantageRuntime")
' Create the OCR page from an image
Dim fileName As String = "C:\Users\Public\Documents\LEADTOOLS Images\Ocr1.tif"
Dim rasterImage As RasterImage = _ocrEngine.RasterCodecsInstance.Load(fileName, 1)
_ocrPage = _ocrEngine.CreatePage(rasterImage, OcrImageSharingMode.AutoDispose)
' Auto-zone this page
_ocrPage.AutoZone(Nothing)
' Add an extra zone, this is our user defined one
Dim zone As New OcrZone()
zone.Name = "Custom zone"
zone.ZoneType = OcrZoneType.Text
zone.Bounds = New LogicalRectangle(10, 10, _ocrPage.Width - 20, 100, LogicalUnit.Pixel)
_ocrPage.Zones.Add(zone)
' Show this image in the viewer
_imageViewer.Image = _ocrPage.GetRasterImage()
Text = "Right click on any zone to remove it from the page, double click anywhere to save the result as a PDF file"
' Hook to the events we will use
AddHandler _imageViewer.PostRender, AddressOf _imageViewer_PostRender
AddHandler _imageViewer.MouseDown, AddressOf _imageViewer_MouseDown
AddHandler _imageViewer.MouseDoubleClick, AddressOf _imageViewer_MouseDoubleClick
MyBase.OnLoad(e)
End Sub
Override Form1OnFormClosed
and add the following code:
protected override void OnFormClosed(FormClosedEventArgs e)
{
// Destroy the page
_ocrPage.Dispose();
// And the engine
_ocrEngine.Dispose();
base.OnFormClosed(e);
}
Protected Overrides Sub OnFormClosed(e As FormClosedEventArgs)
' Destroy the page
_ocrPage.Dispose()
' And the engine
_ocrEngine.Dispose()
MyBase.OnFormClosed(e)
End Sub
Add the following code to handle the image viewer post render event. Draw our zones:
private void _imageViewer_PostRender(object sender, ImageViewerRenderEventArgs e)
{
// Draw the zones
foreach (OcrZone zone in _ocrPage.Zones)
{
// Get the zone boundary
LogicalRectangle zoneBounds = zone.Bounds;
// The zone bounds is a logical rectangle, it may be in units other than pixels. Convert to pixels
LeadRect bounds = zoneBounds.ToRectangle(_ocrPage.DpiX, _ocrPage.DpiY);
// Convert the bound to what we see in the viewer
// Note that this demo does not have rotation; otherwise, you need to use the four corner points
bounds = _imageViewer.ConvertRect(null, ImageViewerCoordinateType.Image, ImageViewerCoordinateType.Control, bounds);
// If this is our custom zone, draw its border a red pen, else use a blue pen
if(zone.Name == "Custom zone")
e.PaintEventArgs.Graphics.DrawRectangle(Pens.Red, bounds.X, bounds.Y, bounds.Width - 1, bounds.Height - 1);
else
e.PaintEventArgs.Graphics.DrawRectangle(Pens.Blue, bounds.X, bounds.Y, bounds.Width - 1, bounds.Height - 1);
}
}
Private Sub _imageViewer_PostRender(sender As Object, e As ImageViewerRenderEventArgs)
' Draw the zones
For Each zone As OcrZone In _ocrPage.Zones
' Get the zone boundary
Dim zoneBounds As LogicalRectangle = zone.Bounds
' The zone bounds is a logical rectangle, it may be in units other than pixels. Convert to pixels
Dim bounds As LeadRect = zoneBounds.ToRectangle(_ocrPage.DpiX, _ocrPage.DpiY)
' Convert the bound to what we see in the viewer
' Note that this demo does not have rotation; otherwise, you need to use the four corner points
bounds = _imageViewer.ConvertRect(Nothing, ImageViewerCoordinateType.Image, ImageViewerCoordinateType.Control, bounds)
' If this is our custom zone, draw its border a red pen, else use a blue pen
If zone.Name = "Custom zone" Then
e.PaintEventArgs.Graphics.DrawRectangle(Pens.Red, bounds.X, bounds.Y, bounds.Width - 1, bounds.Height - 1)
Else
e.PaintEventArgs.Graphics.DrawRectangle(Pens.Blue, bounds.X, bounds.Y, bounds.Width - 1, bounds.Height - 1)
End If
Next
End Sub
Add the following code to handle the viewer mouse down event. Delete zones:
private void _imageViewer_MouseDown(object sender, MouseEventArgs e)
{
// Check if this is a right button click
if (e.Button != MouseButtons.Right)
return;
// Convert the point from control to image coordinate
LeadPoint point = new LeadPoint(e.X, e.Y);
point = _imageViewer.ConvertPoint(null, ImageViewerCoordinateType.Control, ImageViewerCoordinateType.Image, point);
// Use the HitTestZone method to find the zone under the mouse button
int zoneIndex = _ocrPage.HitTestZone(new LogicalPoint(point.X, point.Y, LogicalUnit.Pixel));
if(zoneIndex != -1)
{
// Remove this zone
_ocrPage.Zones.RemoveAt(zoneIndex);
// Re-paint the viewer to show the zones left
_imageViewer.Invalidate();
_imageViewer.Update();
// If no zones are left, show a message
if(_ocrPage.Zones.Count == 0)
MessageBox.Show(this, "No zones left in the page, saving this document to PDF is disabled now");
}
}
Private Sub _imageViewer_MouseDown(sender As Object, e As MouseEventArgs)
' Check if this is a right button click
If e.Button <> MouseButtons.Right Then Return
' Convert the point from control to image coordinate
Dim point As New LeadPoint(e.X, e.Y)
point = _imageViewer.ConvertPoint(Nothing, ImageViewerCoordinateType.Control, ImageViewerCoordinateType.Image, point)
' Use the HitTestZone method to find the zone under the mouse button
Dim zoneIndex As Integer = _ocrPage.HitTestZone(New LogicalPoint(point.X, point.Y, LogicalUnit.Pixel))
If zoneIndex <> -1 Then
' Remove this zone
_ocrPage.Zones.RemoveAt(zoneIndex)
' Re-paint the viewer to show the zones left
_imageViewer.Invalidate()
_imageViewer.Update()
' If no zones are left, show a message
If _ocrPage.Zones.Count = 0 Then
MessageBox.Show(Me, "No zones left in the page, saving this document to PDF is disabled now")
End If
End If
End Sub
Finally add the following code to handle mouse double click. Save the document:
private void _imageViewer_MouseDoubleClick(object sender, MouseEventArgs e)
{
// Check if we have any zones in the page
if (_ocrPage.Zones.Count == 0)
{
MessageBox.Show(this, "No zones left in the page, saving this document to PDF is disabled");
return;
}
// Yes, recognize
string pdfFileName = @"C:\Users\Public\Documents\LEADTOOLS Images\Ocr1.pdf";
// Try to delete the file if it exists. Might be open by the external application from previous operation
if (System.IO.File.Exists(pdfFileName))
{
try
{
System.IO.File.Delete(pdfFileName);
}
catch
{
MessageBox.Show(this, "The file is probably opened in an external viewer. Close it and try again");
return;
}
}
_ocrPage.Recognize(null);
// Create a document
using (IOcrDocument ocrDocument = _ocrEngine.DocumentManager.CreateDocument(null, OcrCreateDocumentOptions.AutoDeleteFile))
{
// Add the page
ocrDocument.Pages.Add(_ocrPage);
// Save as PDF
ocrDocument.Save(pdfFileName, DocumentFormat.Pdf, null);
}
// Show the document
System.Diagnostics.Process.Start(pdfFileName);
}
Private Sub _imageViewer_MouseDoubleClick(sender As Object, e As MouseEventArgs)
' Check if we have any zones in the page
If _ocrPage.Zones.Count = 0 Then
MessageBox.Show(Me, "No zones left in the page, saving this document to PDF is disabled")
Return
End If
' Yes, recognize
Dim pdfFileName As String = "C:\Users\Public\Documents\LEADTOOLS Images\Ocr1.pdf"
' Try to delete the file if it exists. Might be open by the external application from previous operation
If System.IO.File.Exists(pdfFileName) Then
Try
System.IO.File.Delete(pdfFileName)
Catch
MessageBox.Show(Me, "The file is probably opened in an external viewer. Close it and try again")
Return
End Try
End If
_ocrPage.Recognize(Nothing)
' Create a document
Using ocrDocument As IOcrDocument = _ocrEngine.DocumentManager.CreateDocument(Nothing, OcrCreateDocumentOptions.AutoDeleteFile)
' Add the page
ocrDocument.Pages.Add(_ocrPage)
' Save as PDF
ocrDocument.Save(pdfFileName, DocumentFormat.Pdf, Nothing)
End Using
' Show the document
System.Diagnostics.Process.Start(pdfFileName)
End Sub
Save this project to use for testing other code samples.
OCR Tutorial - Working with Pages
OCR Tutorial - Recognizing Pages
OCR Tutorial - Working with Recognition Results
OCR Tutorial - Scanning to Searchable PDF
Getting Started (Guide to Example Programs)
Programming with LEADTOOLS .NET OCR
An Overview of OCR Recognition Modules
Creating an OCR Engine Instance
Starting and Shutting Down the OCR Engine
Multi-Threading with LEADTOOLS OCR
OCR Spell Language Dictionaries
Using OMR in LEADTOOLS .NET OCR