AddDib Method

Summary

Adds a page from a DIB (Device-independent bitmap) stored in unmanaged memory.

Syntax

C++/CLI

Python

public IOcrPage AddDib( 
   IntPtr dib, 
   OcrProgressCallback callback 
)

IOcrPage^ AddDib(  
   IntPtr dib, 
   OcrProgressCallback^ callback 
)

def AddDib(self,dib,callback):

Parameters

dib
An unmanaged pointer to the DIB (device-independent bitmap).

callback
Optional callback to show operation progress.

Return Value

The IOcrPage object that define the newly added page.

Remarks

This method will add a device independent bitmap (DIB) stored in an unmanaged memory pointer to the OCR document.

This method will add the page to the end of the collection if you already have pages in this IOcrPageCollection.

You can use the OcrProgressCallback to show the operation progress or to abort it. For more information and an example, refer to OcrProgressCallback.

The LEADTOOLS OCR engine supports pages of dots per inch (DPI) values of 150 and greater. If you try to add a page with a DPI of less than 150 then the engine might be able to recognize any data from this page.

Note: The value of the "Recognition.ShareOriginalImage" (only supported by the LEADTOOLS OCR Module - LEAD Engine) setting is not used when calling this method. The engine loads the image(s) and sets them in the pages internally. The original image reference can be obtained from the page using IOcrPage.GetRasterImage(OcrPageType.Original). Sharing the original image minimizes the memory used during OCR operations.

This member only works with memory-based documents and will throw an exception otherwise. For more information, refer to IOcrDocumentManager.CreateDocument and Programming with the LEADTOOLS .NET OCR.

Example

This example will add a raster image stored in an HTTP location to an OCR document

Java

using Leadtools; 
using Leadtools.Codecs; 
using Leadtools.Ocr; 
using Leadtools.Document.Writer; 
using Leadtools.Forms.Common; 
using Leadtools.ImageProcessing.Core; 
 
public void AddPageFromDibExample() 
{ 
   string tifFileName = Path.Combine(LEAD_VARS.ImagesDir, "Ocr1.tif"); 
   string bmpFileName = Path.Combine(LEAD_VARS.ImagesDir, "Ocr1.bmp"); 
   string pdfFileName = Path.Combine(LEAD_VARS.ImagesDir, "Ocr1.pdf"); 
 
   // Get a DIB 
   // In this example, we will save the TIF file as BMP, then load it without the BITMAPFILEHEADER structure 
   // The result is a valid Windows DIB 
 
   using (RasterCodecs codecs = new RasterCodecs()) 
      codecs.Convert(tifFileName, bmpFileName, RasterImageFormat.Bmp, 0, 0, 1, null); 
 
 
   // From MSDN 
   const int bitmapFileHeaderStructSize = 14; 
   IntPtr dib = IntPtr.Zero; 
 
   using (FileStream fs = File.OpenRead(bmpFileName)) 
   { 
      // Allocate the DIB 
      int dibSize = (int)fs.Length - bitmapFileHeaderStructSize; 
      dib = Marshal.AllocHGlobal(dibSize); 
      int dibOffset = 0; 
 
      // Now read it 
      fs.Seek(bitmapFileHeaderStructSize, SeekOrigin.Begin); 
 
      const int bufferSize = 1024 * 4; 
      byte[] buffer = new byte[bufferSize]; 
      int bytes = 0; 
      do 
      { 
         bytes = fs.Read(buffer, 0, bufferSize); 
         if (bytes > 0) 
         { 
            IntPtr dibPtr = new IntPtr(dib.ToInt64() + dibOffset); 
            Marshal.Copy(buffer, 0, dibPtr, bytes); 
            dibOffset += bytes; 
         } 
      } 
      while (bytes > 0); 
   } 
 
   // 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()) 
      { 
         // Add the image 
         ocrDocument.Pages.AddDib(dib, null); 
 
         // Free the DIB since we do not need it anymore 
         Marshal.FreeHGlobal(dib); 
 
         // 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; 
 
 
// Skipped - Jave is missing the AddDib method 
/* 
 *  * public void IOcrPageCollectionsAddPageFromDibExample() throws IOException { 
 * final String LEAD_VARS_IMAGES_DIR ="C:\\LEADTOOLS23\\Resources\\Images"; 
 * final String LEAD_VARS_OCR_LEAD_RUNTIME_DIR = 
 * "C:\\LEADTOOLS23\\Bin\\Common\\OcrLEADRuntime"; 
 * String tifFileName = combine(LEAD_VARS_IMAGES_DIR, "Ocr1.tif"); 
 * String bmpFileName = combine(LEAD_VARS_IMAGES_DIR, "Ocr1.bmp"); 
 * String pdfFileName = combine(LEAD_VARS_IMAGES_DIR, "Ocr1.pdf"); 
 *  
 * // Get a DIB 
 * // In this example, we will save the TIF file as BMP, then load it without 
 * the BITMAPFILEHEADER structure 
 * // The result is a valid Windows DIB 
 * RasterCodecs codecs = new RasterCodecs(); 
 * codecs.convert(tifFileName, bmpFileName, RasterImageFormat.BMP, 0, 0, 1, 
 * null); 
 *  
 * // From MSDN 
 * final int bitmapFileHeaderStructSize = 14; 
 * ILeadStream ls = LeadStreamFactory.create(bmpFileName); 
 * File inputFile = new File(bmpFileName); 
 *  
 * // Allocate the DIB 
 * int dibSize = (int)inputFile.length() - bitmapFileHeaderStructSize; 
 * System.out.println(dibSize); 
 * byte[] dib = new byte[dibSize]; 
 * int dibOffset = 0; 
 *  
 * // Now read it 
 * ls.openFile(bmpFileName, LeadStreamMode.OPEN, LeadStreamAccess.READ, 
 * LeadStreamShare.READ); 
 * ls.seek(LeadSeekOrigin.BEGIN, bitmapFileHeaderStructSize); 
 *  
 * final int bufferSize = 1024 * 4; 
 * byte[] buffer = new byte[bufferSize]; 
 * int bytes = 0; 
 * do { 
 * bytes = ls.read(buffer, bufferSize); 
 * System.out.println(bytes); 
 * if (bytes > 0) { 
 * byte[] dibPtr = new byte[dib.length + dibOffset]; 
 * for(int i = 0; i<bytes; i++){ 
 * dibPtr[i]=dib[i]; 
 * } 
 * dibOffset += bytes; 
 * } 
 * } 
 * while (bytes > 0); 
 * ls.close(); 
 *  
 * // Create an instance of the engine 
 * OcrEngine ocrEngine = OcrEngineManager.createEngine(OcrEngineType.LEAD); 
 *  
 * // Start the engine using default parameters 
 * ocrEngine.startup(null, null, null, LEAD_VARS_OCR_LEAD_RUNTIME_DIR); 
 * assertTrue("Engine unsuccessfully started", ocrEngine.isStarted()); 
 *  
 * // Create an OCR document 
 * OcrDocument ocrDocument = ocrEngine.getDocumentManager().createDocument(); 
 *  
 * // Add the image 
 * ILeadStream dibStream = LeadStreamFactory.create(dib); 
 * ocrDocument.getPages().addPage(dibStream, null); 
 *  
 * // Free the DIB since we do not need it anymore 
 * dib = null; 
 * dibStream.dispose(); 
 *  
 * // Recognize 
 * ocrDocument.getPages().recognize(null); 
 *  
 * // Save 
 * ocrDocument.save(pdfFileName, DocumentFormat.PDF, null); 
 * ocrDocument.dispose(); 
 *  
 * // Shutdown the engine 
 * // Note: calling Dispose will also automatically shutdown the engine if it 
 * has been started 
 * ocrEngine.dispose(); 
 * } 
 */