←Select platform

OcrEngineManager Class

Summary

Provides methods to create OCR engine instances.

Syntax
C#
VB
Objective-C
C++
Java
public static class OcrEngineManager 
Public MustInherit NotInheritable Class OcrEngineManager  
@interface LTOcrEngineManager : NSObject // STATIC CLASS 
public class OcrEngineManager 
public ref class OcrEngineManager abstract sealed  

Remarks

The OcrEngineManager class and its methods are your entry point to using the Leadtools.Ocr class library.

This class provides the methods you need to create an object of the IOcrEngine interface. Afterwards, you can use the properties and methods of this interface to perform your OCR tasks.

Based on the engine type passed to the CreateEngine methods, OcrEngineManager will load the OCR engine defined in one of the supporting assemblies and return an interface to IOcrEngine. Use this interface and its included types to start using the Leadtools.Ocr class library. For more information about the engine types, refer to OcrEngineType.

The CreateEngine method lets you create an instance of IOcrEngine, loading the corresponding Leadtools.Ocr.[EngineName].dll assembly using the .NET System.Reflection.Assembly.Load(string assemblyString) method. You cannot unload this assembly once it has been successfully loaded.

All LEADTOOLS OCR engines (LEAD, OmniPage, and Arabic) are now thread-safe and so the "THUNK" mechanism is no longer required. Consequently, the useThunkServer parameter of the CreateEngine method will be ignored at all times for all engines.

Example

This example shows how to OCR documents using multiple threads.

C#
VB
using Leadtools; 
using Leadtools.Ocr; 
using Leadtools.Document.Writer; 
 
public void MultiThreadedOcrExample() 
{ 
   // The image file names we are going to OCR and convert to PDF 
   string[] tifFileNames = 
   { 
      Path.Combine(LEAD_VARS.ImagesDir, "Ocr1.tif"), 
      Path.Combine(LEAD_VARS.ImagesDir, "Ocr2.tif"), 
      Path.Combine(LEAD_VARS.ImagesDir, "Ocr3.tif"), 
      Path.Combine(LEAD_VARS.ImagesDir, "Ocr4.tif") 
   }; 
 
   int threadCount = tifFileNames.Length; 
 
   // Create the thread 
   Thread[] threads = new Thread[threadCount]; 
   AutoResetEvent[] waitHandles = new AutoResetEvent[threadCount]; 
   for (int i = 0; i < threadCount; i++) 
   { 
      threads[i] = new Thread(new ParameterizedThreadStart(MyThreadProc)); 
      threads[i].Name = "OCR thread + " + i.ToString(); 
 
      waitHandles[i] = new AutoResetEvent(false); 
   } 
 
   Console.WriteLine("Starting the threads and waiting..."); 
 
   // Start the threads 
   for (int i = 0; i < threadCount; i++) 
   { 
      MyThreadData threadData = new MyThreadData(); 
      threadData.ImageFileName = tifFileNames[i]; 
      threadData.WaitHandle = waitHandles[i]; 
      threads[i].Start(threadData); 
   } 
 
   // Wait till all threads are done 
   WaitHandle.WaitAny(waitHandles); 
   Console.WriteLine("All threads finished"); 
} 
private struct MyThreadData 
{ 
   public string ImageFileName; 
   public AutoResetEvent WaitHandle; 
} 
 
private void MyThreadProc(object data) 
{ 
   // Grab the data 
   MyThreadData threadData = (MyThreadData)data; 
   string imageFileName = threadData.ImageFileName; 
 
   // Show a status message 
   Console.WriteLine("Begin: {0}", imageFileName); 
 
   // Create an instance of the OCR engine using. If you change the engine type from Advantage, 
   // then the last parameter indicates the use of the LEADTOOLS Thunk Server 
   using (IOcrEngine ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD, true)) 
   { 
      // Start the engine using default parameters 
      ocrEngine.Startup(null, null, null, LEAD_VARS.OcrLEADRuntimeDir); 
 
      // Get the PDf file name 
      string pdfFileName = Path.ChangeExtension(imageFileName, "pdf"); 
 
      // Create an OCR document 
      using (IOcrDocument ocrDocument = ocrEngine.DocumentManager.CreateDocument()) 
      { 
 
         // Add a page to the document 
         IOcrPage ocrPage = ocrDocument.Pages.AddPage(imageFileName, null); 
 
         // Recognize the page 
         // Note, Recognize can be called without calling AutoZone or manually adding zones. The engine will 
         // check and automatically auto-zones the page 
         ocrPage.Recognize(null); 
 
         // Save the document we have as PDF 
         ocrDocument.Save(pdfFileName, DocumentFormat.Pdf, null); 
      } 
 
      // Shutdown the engine 
      // Note: calling Dispose will also automatically shutdown the engine if it has been started 
      ocrEngine.Shutdown(); 
   } 
 
   Console.WriteLine("End: {0}", imageFileName); 
 
   // Singal the main thread 
   threadData.WaitHandle.Set(); 
} 
 
static class LEAD_VARS 
{ 
   public const string ImagesDir = @"C:\Users\Public\Documents\LEADTOOLS Images"; 
   public const string OcrLEADRuntimeDir = @"C:\LEADTOOLS 20\Bin\Common\OcrLEADRuntime"; 
} 
Imports Leadtools 
Imports Leadtools.Ocr 
Imports Leadtools.Document.Writer 
 
Private Structure MyThreadData 
   Public ImageFileName As String 
   Public WaitHandle As AutoResetEvent 
End Structure 
 
Public Sub MultiThreadedOcrExample() 
   ' The image file names we are going to OCR and convert to PDF 
   Dim tifFileNames As String() = { 
      Path.Combine(LEAD_VARS.ImagesDir, "Ocr1.tif"), 
      Path.Combine(LEAD_VARS.ImagesDir, "Ocr2.tif"), 
      Path.Combine(LEAD_VARS.ImagesDir, "Ocr3.tif"), 
      Path.Combine(LEAD_VARS.ImagesDir, "Ocr4.tif")} 
 
   Dim threadCount As Integer = tifFileNames.Length 
 
   ' Create the thread 
   Dim threads As Thread() = New Thread(threadCount - 1) {} 
   Dim waitHandles As AutoResetEvent() = New AutoResetEvent(threadCount - 1) {} 
   For i As Integer = 0 To threadCount - 1 
      threads(i) = New Thread(New ParameterizedThreadStart(AddressOf MyThreadProc)) 
      threads(i).Name = "OCR thread + " & i.ToString() 
 
      waitHandles(i) = New AutoResetEvent(False) 
   Next 
 
   Console.WriteLine("Starting the threads and waiting...") 
 
   ' Start the threads 
   For i As Integer = 0 To threadCount - 1 
      Dim threadData As New MyThreadData() 
      threadData.ImageFileName = tifFileNames(i) 
      threadData.WaitHandle = waitHandles(i) 
      threads(i).Start(threadData) 
   Next 
 
   ' Wait till all threads are done 
   WaitHandle.WaitAll(waitHandles) 
   Console.WriteLine("All threads finished") 
End Sub 
 
Private Sub MyThreadProc(data As Object) 
   ' Grab the data 
   Dim threadData As MyThreadData = CType(data, MyThreadData) 
   Dim imageFileName As String = threadData.ImageFileName 
 
   ' Show a status message 
   Console.WriteLine("Begin: {0}", imageFileName) 
 
   ' Create an instance of the OCR engine using. If you change the engine type from Advantage, 
   ' then the last parameter indicates the use of the LEADTOOLS Thunk Server 
   Using ocrEngine As IOcrEngine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD, True) 
      ' Start the engine using default parameters 
      ocrEngine.Startup(Nothing, Nothing, Nothing, LEAD_VARS.OcrLEADRuntimeDir) 
 
      ' Get the PDf file name 
      Dim pdfFileName As String = Path.ChangeExtension(imageFileName, "pdf") 
 
      ' Create an OCR document 
      Using ocrDocument As IOcrDocument = ocrEngine.DocumentManager.CreateDocument() 
 
         ' Add a page to the document 
         Dim ocrPage As IOcrPage = ocrDocument.Pages.AddPage(imageFileName, Nothing) 
 
         ' Recognize the page 
         ' Note, Recognize can be called without calling AutoZone or manually adding zones. The engine will 
         ' check and automatically auto-zones the page 
         ocrPage.Recognize(Nothing) 
 
         ' Save the document we have as PDF 
         ocrDocument.Save(pdfFileName, DocumentFormat.Pdf, Nothing) 
      End Using 
 
      ' Shutdown the engine 
      ' Note: calling Dispose will also automatically shutdown the engine if it has been started 
      ocrEngine.Shutdown() 
   End Using 
 
   Console.WriteLine("End: {0}", imageFileName) 
 
   ' Singal the main thread 
   threadData.WaitHandle.Set() 
End Sub 
 
Public NotInheritable Class LEAD_VARS 
   Public Const ImagesDir As String = "C:\Users\Public\Documents\LEADTOOLS Images" 
   Public Const OcrLEADRuntimeDir As String = "C:\LEADTOOLS 20\Bin\Common\OcrLEADRuntime" 
End Class 

Requirements

Target Platforms

Help Version 20.0.2020.4.2
Products | Support | Contact Us | Intellectual Property Notices
© 1991-2020 LEAD Technologies, Inc. All Rights Reserved.

Leadtools.Ocr Assembly