Pages Property

Summary

Allows you to add, remove or update image (raster) pages in the OCR document.

Syntax

Objective-C

C++/CLI

Java

Python

public IOcrPageCollection Pages { get; }

@property (nonatomic, strong, readonly) LTOcrPageCollection *pages

public OcrPageCollection getPages()

property IOcrPageCollection^ Pages { 
   IOcrPageCollection^ get(); 
}

Pages # get  (IOcrDocument)

Property Value

The IOcrPageCollection object that allow you to add, remove or update image (raster) pages in the OCR document.

Remarks

Pages is a standard .NET collection of IOcrPage objects. Through this member you can add, remove or update image (raster) pages to the OCR document. These pages can be image files on disk, memory or even in a remote URL.

In memory-based IOcrDocument, the IOcrPageCollection holds the pages. The user can recognize any or all of the pages at any time and pages can be added or removed at will.

In file-based IOcrDocument, the IOcrPageCollection is a store-only view of the pages. when page is added, a snap shot of the current recognition data is saved into the document. This data cannot be modified any more and the page is no longer needed. The user must recognize the pages before they are added to the document and pages can only be added but not removed. In this mode, you can only use IOcrPageCollection.Add and IOcrPageCollection.Count. No other method or property is supported.

Any file format supported by LEADTOOLS (TIFF, JPEG, BMP, etc) can be loaded into the OCR document. Once the image is loaded into the document, use the various IOcrPage methods to zone the page (or pages) in preparation to be recognized and saved as a document.

You can also convert to and from any of the pages added to the OCR document to a LEADTOOLS RasterImage for use with other LEADTOOLS for .NET assemblies such as TWAIN scanning, image processing, MRC, etc.

For more information refer to IOcrPageCollection and IOcrPage.

Example

Java

using Leadtools; 
using Leadtools.Codecs; 
using Leadtools.Ocr; 
using Leadtools.Document.Writer; 
using Leadtools.Forms.Common; 
using Leadtools.ImageProcessing.Core; 
 
public void PageCollectionExamples() 
{ 
   // For this example, we need a multi-page TIF file. 
   // Create a muti-page TIF from Ocr1.tif, Ocr2.tif, Ocr3.tif and Ocr4.tif 
   string tifFileName = Path.Combine(LEAD_VARS.ImagesDir, "Ocr.tif"); 
   if (File.Exists(tifFileName)) 
      File.Delete(tifFileName); 
 
   using (RasterCodecs codecs = new RasterCodecs()) 
   { 
      for (int i = 0; i < 4; i++) 
      { 
         string pageFileName = Path.Combine(LEAD_VARS.ImagesDir, string.Format("Ocr{0}.tif", i + 1)); 
         using (RasterImage image = codecs.Load(pageFileName)) 
            codecs.Save(image, tifFileName, RasterImageFormat.CcittGroup4, 1, 1, 1, -1, CodecsSavePageMode.Append); 
      } 
   } 
 
   string pdfFileName = Path.Combine(LEAD_VARS.ImagesDir, "Ocr.pdf"); 
 
   // Create an instance of the engine 
   using (IOcrEngine ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD)) 
   { 
      // Start the engine using default parameters 
      ocrEngine.Startup(null, null, null, LEAD_VARS.OcrLEADRuntimeDir); 
 
      // Create an OCR document 
      using (IOcrDocument ocrDocument = ocrEngine.DocumentManager.CreateDocument()) 
      { 
         // Load all the pages of the multi-page tif file we created into the form 
         ocrDocument.Pages.AddPages(tifFileName, 1, -1, null); 
         Console.WriteLine("{0} pages added to the document", ocrDocument.Pages.Count); 
 
         // Auto-zone 
         ocrDocument.Pages.AutoZone(null); 
 
         // Recognize 
         ocrDocument.Pages.Recognize(null); 
 
         // Save 
         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(); 
   } 
} 
 
static class LEAD_VARS 
{ 
   public const string ImagesDir = @"C:\LEADTOOLS23\Resources\Images"; 
   public const string OcrLEADRuntimeDir = @"C:\LEADTOOLS23\Bin\Common\OcrLEADRuntime"; 
}

 
import java.io.File; 
import java.io.IOException; 
import java.net.URI; 
import java.net.URISyntaxException; 
 
import org.junit.*; 
import org.junit.runner.JUnitCore; 
import org.junit.runner.Result; 
import org.junit.runner.notification.Failure; 
import static org.junit.Assert.*; 
 
import leadtools.*; 
import leadtools.codecs.*; 
import leadtools.document.writer.DocumentFormat; 
import leadtools.imageprocessing.core.DeskewCommand; 
import leadtools.imageprocessing.core.DeskewCommandFlags; 
import leadtools.ocr.OcrDocument; 
import leadtools.ocr.OcrEngine; 
import leadtools.ocr.OcrEngineManager; 
import leadtools.ocr.OcrEngineType; 
 
 
public void IOcrPageCollectionsPageCollectionExamples() { 
   final String LEAD_VARS_IMAGES_DIR = "C:\\LEADTOOLS23\\Resources\\Images"; 
   final String LEAD_VARS_OCR_LEAD_RUNTIME_DIR = "C:\\LEADTOOLS23\\Bin\\Common\\OcrLEADRuntime"; 
 
   // For this example, we need a multi-page TIF file. 
   // Create a muti-page TIF from Ocr1.tif, Ocr2.tif, Ocr3.tif and Ocr4.tif 
   var tifFileName = combine(LEAD_VARS_IMAGES_DIR, "Ocr.tif"); 
   var file = new File(tifFileName); 
   if (file.exists()) 
      file.delete(); 
 
   RasterCodecs codecs = new RasterCodecs(); 
   for (var i = 0; i < 4; i++) { 
      var pageFileName = combine(LEAD_VARS_IMAGES_DIR, "Ocr" + (i + 1) + ".tif"); 
      var image = codecs.load(pageFileName); 
      codecs.save(image, tifFileName, RasterImageFormat.CCITT_GROUP4, 1, 1, 1, -1, CodecsSavePageMode.APPEND); 
   } 
   codecs = null; 
 
   var pdfFileName = combine(LEAD_VARS_IMAGES_DIR, "Ocr.pdf"); 
 
   codecs = new RasterCodecs(); 
   // Create an instance of the engine 
   OcrEngine ocrEngine = OcrEngineManager.createEngine(OcrEngineType.LEAD); 
 
   // Start the engine using default parameters 
   ocrEngine.startup(codecs, null, null, LEAD_VARS_OCR_LEAD_RUNTIME_DIR); 
   assertTrue("Engine unsuccessfully started", ocrEngine.isStarted()); 
 
   // Create an OCR document 
   OcrDocument ocrDocument = ocrEngine.getDocumentManager().createDocument(); 
 
   // Load all the pages of the multi-page tif file we created into the form 
   ocrDocument.getPages().addPages(codecs.load(tifFileName), 1, -1, null); 
   System.out.println(ocrDocument.getPages().size() + " pages added to the document"); 
 
   // Auto-zone 
   ocrDocument.getPages().autoZone(null); 
 
   // Recognize 
   ocrDocument.getPages().recognize(null); 
 
   // Save 
   ocrDocument.save(pdfFileName, DocumentFormat.PDF, null); 
   assertTrue("File unsuccessfully saved", (new File(tifFileName)).exists()); 
 
   // Shutdown the engine 
   // Note: calling Dispose will also automatically shutdown the engine if it has 
   // been started 
   ocrEngine.shutdown(); 
}