Performs auto decomposition of the page to find the text and graphics zones using predefined parameters
public void AutoZone(
OcrProgressCallback callback
)
Sub AutoZone( _
ByVal callback As Leadtools.Forms.Ocr.OcrProgressCallback _
)
void AutoZone(
Leadtools.Forms.Ocr.OcrProgressCallback callback
)
- (BOOL)autoZone:(nullable LTOcrProgressHandler)progressHandlererror:(NSError **)error
public void autoZone(OcrProgressListener callback)
function Leadtools.Forms.Ocr.IOcrPage.AutoZone(
callback
)
void AutoZone(
Leadtools.Forms.Ocr.OcrProgressCallback^ callback
)
callback
Optional callback to show operation progress.
You can use the OcrProgressCallback to show the operation progress or to abort it. For more information and an example, refer to OcrProgressCallback.
The zones found by this method are added to the Zones collection of this page. Any previously added zones will be removed from Zones first.
This method finds the zone coordinates (OcrZone.Bounds which will always have units of LogicalUnit.Pixels) and type (OcrZone.ZoneType). The type of the zone determines its role in the page layout and can be classified into three different groups:
Note: If this IOcrPage is an empty page, in other words, when the OCR engine performs automatic page decomposing with the AutoZone method and could not find any zones in it, the Recognize method will fail with an exception. It is recommended you call AutoZone and then check if there is at least one zone found by the engine (using Zones.Count). If the count is zero, do not call Recognize.
If a recognition module is not able to recognize an object (i.e. character, or checkmark etc.), this object will be marked as a rejected one. It will become marked by a rejection symbol during conversion to the final output document. Note that IOcrDocumentManager.RejectionSymbol can be set to specify the rejection symbol used in the final document.
Note on AutoZone/Recognize and the page image: In certain cases, AutoZone and Recognize will perform image processing on the page that might result in the page being manipulated. For example, if you add a zone of type table, the engine might automatically deskew the page if required. This result in the image representation of the image to be different after AutoZone or Recognize is called. If your application has a requirement to view the image of the page, then call GetRasterImage after AutoZone or Recognize to get the latest version of the image representation of the page in case it has changed. The LEADTOOLS Main OCR C# and VB demos do exactly that.
This example will perform auto-zoning on an OCR page then displays information about the zones found.
using Leadtools;
using Leadtools.Codecs;
using Leadtools.Forms.Ocr;
using Leadtools.Forms;
using Leadtools.Forms.DocumentWriters;
using Leadtools.WinForms;
using Leadtools.Drawing;
using Leadtools.ImageProcessing;
using Leadtools.ImageProcessing.Color;
public void OcrAutoZoneExample()
{
// Create an image with some text in it
RasterImage image = new RasterImage(RasterMemoryFlags.Conventional, 320, 200, 24, RasterByteOrder.Bgr, RasterViewPerspective.TopLeft, null, IntPtr.Zero, 0);
Rectangle imageRect = new Rectangle(0, 0, image.ImageWidth, image.ImageHeight);
IntPtr hdc = RasterImagePainter.CreateLeadDC(image);
using (Graphics g = Graphics.FromHdc(hdc))
{
g.SmoothingMode = System.Drawing.Drawing2D.SmoothingMode.HighQuality;
g.FillRectangle(Brushes.White, imageRect);
using (Font f = new Font("Arial", 20, FontStyle.Regular))
g.DrawString("Normal line", f, Brushes.Black, 0, 0);
using (Font f = new Font("Courier New", 20, FontStyle.Regular))
g.DrawString("Monospaced line", f, Brushes.Black, 0, 80);
}
RasterImagePainter.DeleteLeadDC(hdc);
string zonesFileName = Path.Combine(LEAD_VARS.ImagesDir, "MyZones.xml");
// Create an instance of the engine
using (IOcrEngine ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.Advantage, false))
{
// Start the engine using default parameters
ocrEngine.Startup(null, null, null, LEAD_VARS.OcrAdvantageRuntimeDir);
// Create an OCR page
using (IOcrPage ocrPage = ocrEngine.CreatePage(image, OcrImageSharingMode.AutoDispose))
{
// Show the zones, there should be no zones yet
ShowZones("Right after the page was created", ocrPage);
// Perform default AutoZoning on the page
ocrPage.AutoZone(null);
// Show the zones, there should be two zones, one for each line
ShowZones("AutoZone with default parameters", ocrPage);
// Update the first zone manually
OcrZone ocrZone = ocrPage.Zones[0];
ocrZone.ZoneType = OcrZoneType.Text;
ocrPage.Zones[0] = ocrZone;
// Show the zones
ShowZones("After updating the type of the first zone", ocrPage);
// Save the zones to a file and then clear them
ocrPage.SaveZones(zonesFileName);
ocrPage.Zones.Clear();
// Show the zones, there should be no zones since we just cleared them
ShowZones("After calling save and clear", ocrPage);
// Re-load the zones
ocrPage.LoadZones(zonesFileName);
ShowZones("After re-loading the zones", ocrPage);
}
// Shutdown the engine
// Note: calling Dispose will also automatically shutdown the engine if it has been started
ocrEngine.Shutdown();
}
}
private void ShowZones(string message, IOcrPage ocrPage)
{
Console.WriteLine("Zones after {0}:", message);
foreach (OcrZone ocrZone in ocrPage.Zones)
{
int index = ocrPage.Zones.IndexOf(ocrZone);
Console.WriteLine("Zone index: {0}", index);
Console.WriteLine(" Id {0}", ocrZone.Id);
Console.WriteLine(" Bounds {0}", ocrZone.Bounds);
Console.WriteLine(" ZoneType {0}", ocrZone.ZoneType);
Console.WriteLine(" CharacterFilters: {0}", ocrZone.CharacterFilters);
Console.WriteLine("----------------------------------");
}
Console.WriteLine("Hit enter to continue");
//Console.ReadLine();
}
static class LEAD_VARS
{
public const string ImagesDir = @"C:\Users\Public\Documents\LEADTOOLS Images";
public const string OcrAdvantageRuntimeDir = @"C:\LEADTOOLS 19\Bin\Common\OcrAdvantageRuntime";
}
Imports Leadtools
Imports Leadtools.Codecs
Imports Leadtools.Forms.Ocr
Imports Leadtools.Forms
Imports Leadtools.Forms.DocumentWriters
Imports Leadtools.WinForms
Imports Leadtools.Drawing
Imports Leadtools.ImageProcessing
Imports Leadtools.ImageProcessing.Color
Public Sub OcrAutoZoneExample()
' Create an image with some text in it
Dim image As New RasterImage(RasterMemoryFlags.Conventional, 320, 200, 24, RasterByteOrder.Bgr, RasterViewPerspective.TopLeft,
Nothing, IntPtr.Zero, 0)
Dim imageRect As New Rectangle(0, 0, image.ImageWidth, image.ImageHeight)
Dim hdc As IntPtr = RasterImagePainter.CreateLeadDC(image)
Using g As Graphics = Graphics.FromHdc(hdc)
g.SmoothingMode = System.Drawing.Drawing2D.SmoothingMode.HighQuality
g.FillRectangle(Brushes.White, imageRect)
Using f As New Font("Arial", 20, FontStyle.Regular)
g.DrawString("Normal line", f, Brushes.Black, 0, 0)
End Using
Using f As New Font("Courier New", 20, FontStyle.Regular)
g.DrawString("Monospaced line", f, Brushes.Black, 0, 80)
End Using
End Using
RasterImagePainter.DeleteLeadDC(hdc)
Dim zonesFileName As String = Path.Combine(LEAD_VARS.ImagesDir, "MyZones.xml")
' Create an instance of the engine
Using ocrEngine As IOcrEngine = OcrEngineManager.CreateEngine(OcrEngineType.Advantage, False)
' Start the engine using default parameters
ocrEngine.Startup(Nothing, Nothing, Nothing, LEAD_VARS.OcrAdvantageRuntimeDir)
' Create an OCR page
Using ocrPage As IOcrPage = ocrEngine.CreatePage(image, OcrImageSharingMode.AutoDispose)
' Show the zones, there should be no zones yet
ShowZones("Right after the page was created", ocrPage)
' Perform default AutoZoning on the page
ocrPage.AutoZone(Nothing)
' Show the zones, there should be two zones, one for each line
ShowZones("AutoZone with default parameters", ocrPage)
' Update the first zone manually
Dim ocrZone As OcrZone = ocrPage.Zones(0)
ocrZone.ZoneType = OcrZoneType.Text
ocrPage.Zones(0) = ocrZone
' Show the zones
ShowZones("After updating the type of the first zone", ocrPage)
' Save the zones to a file and then clear them
ocrPage.SaveZones(zonesFileName)
ocrPage.Zones.Clear()
' Show the zones, there should be no zones since we just cleared them
ShowZones("After calling save and clear", ocrPage)
' Re-load the zones
ocrPage.LoadZones(zonesFileName)
ShowZones("After re-loading the zones", ocrPage)
End Using
' Shutdown the engine
' Note: calling Dispose will also automatically shutdown the engine if it has been started
ocrEngine.Shutdown()
End Using
End Sub
Private Sub ShowZones(message As String, ocrPage As IOcrPage)
Console.WriteLine("Zones after {0}:", message)
For Each ocrZone As OcrZone In ocrPage.Zones
Dim index As Integer = ocrPage.Zones.IndexOf(ocrZone)
Console.WriteLine("Zone index: {0}", index)
Console.WriteLine(" Id {0}", ocrZone.Id)
Console.WriteLine(" Bounds {0}", ocrZone.Bounds)
Console.WriteLine(" ZoneType {0}", ocrZone.ZoneType)
Console.WriteLine(" CharacterFilters: {0}", ocrZone.CharacterFilters)
Console.WriteLine("----------------------------------")
Next
Console.WriteLine("Hit enter to continue")
Console.ReadLine()
End Sub
Public NotInheritable Class LEAD_VARS
Public Const ImagesDir As String = "C:\Users\Public\Documents\LEADTOOLS Images"
Public Const OcrAdvantageRuntimeDir As String = "C:\LEADTOOLS 19\Bin\Common\OcrAdvantageRuntime"
End Class
Raster .NET | C API | C++ Class Library | JavaScript HTML5
Document .NET | C API | C++ Class Library | JavaScript HTML5
Medical .NET | C API | C++ Class Library | JavaScript HTML5
Medical Web Viewer .NET