Updates or deletes a word in the recognized words list.
Sub UpdateWord( _
ByVal words As IList(Of OcrWord), _
ByVal zoneIndex As Integer, _
ByVal wordIndex As Integer, _
ByVal newValue As String _
)
words
A list of OcrWord. In most cases, the same list obtained from IOcrZoneCharacters.GetWords.
zoneIndex
The 0-based zone index of the words.
wordIndex
The 0-based index of the word in words to update.
newValue
The value of the new word. Use null to delete the word.
You can use UpdateWord to modify the OCR recognition results by updating or deleting the words before optionally saving the results to the final output document. The C# and VB OCR Edit Demo uses this technique as well as the example below.
This example will recognize a document, then: capitalize all "the", delete all "a" and replaces all instance of "color" with "water".
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 OcrUpdateWordExample()
{
string tifFileName = Path.Combine(LEAD_VARS.ImagesDir, "Ocr1.tif");
string pdfFileName1 = Path.Combine(LEAD_VARS.ImagesDir, "Ocr1_Original.pdf");
string pdfFileName2 = Path.Combine(LEAD_VARS.ImagesDir, "Ocr1_Modified.pdf");
using (IOcrEngine ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.Advantage, false))
{
ocrEngine.Startup(null, null, null, LEAD_VARS.OcrAdvantageRuntimeDir);
using (IOcrDocument ocrDocument = ocrEngine.DocumentManager.CreateDocument())
{
// Recognize the TIFF file
IOcrPage ocrPage = ocrDocument.Pages.AddPage(tifFileName, null);
ocrPage.Recognize(null);
// Save the original recognition results to compare with the results
// we will modify
ocrDocument.Save(pdfFileName1, DocumentFormat.Pdf, null);
// Get the recognized words
IOcrPageCharacters pageCharacters = ocrPage.GetRecognizedCharacters();
foreach (IOcrZoneCharacters zoneCharacters in pageCharacters)
{
IList<OcrWord> words = zoneCharacters.GetWords(ocrPage.DpiX, ocrPage.DpiY, LogicalUnit.Pixel);
// Check for our words
// Note, we should not loop through words and change the collection. Remember, collections cannot
// be modified this way, instead, we have a helper method that returns the index of the word
// we are looking for then change the word. Repeat while no more words are found
int index;
// Capitalize all "the"
do
{
index = FindWord(words, "the", false);
if (index != -1)
{
// We have one, update it
pageCharacters.UpdateWord(words, zoneCharacters.ZoneIndex, index, "THE");
}
}
while (index != -1);
// Delete all "a"
do
{
index = FindWord(words, "a", true);
if (index != -1)
{
// We have one, update it
pageCharacters.UpdateWord(words, zoneCharacters.ZoneIndex, index, null);
}
}
while (index != -1);
// Replace all "color" with "water"
do
{
index = FindWord(words, "color", true);
if (index != -1)
{
// We have one, update it
pageCharacters.UpdateWord(words, zoneCharacters.ZoneIndex, index, "water");
}
}
while (index != -1);
}
// We are done, update the page recognized results
ocrPage.SetRecognizedCharacters(pageCharacters);
// Save this new results
ocrDocument.Save(pdfFileName2, DocumentFormat.Pdf, null);
}
}
}
private static int FindWord(IList<OcrWord> words, string value, bool ignoreCase)
{
if (words == null || words.Count == 0)
{
return -1;
}
for (int i = 0; i < words.Count; i++)
{
if (string.Compare(words[i].Value, value, ignoreCase) == 0)
{
// Found it
return i;
}
}
// Not found
return -1;
}
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 OcrUpdateWordExample()
Dim tifFileName As String = Path.Combine(LEAD_VARS.ImagesDir, "Ocr1.tif")
Dim pdfFileName1 As String = Path.Combine(LEAD_VARS.ImagesDir, "Ocr1_Original.pdf")
Dim pdfFileName2 As String = Path.Combine(LEAD_VARS.ImagesDir, "Ocr1_Modified.pdf")
Using ocrEngine As IOcrEngine = OcrEngineManager.CreateEngine(OcrEngineType.Advantage, False)
ocrEngine.Startup(Nothing, Nothing, Nothing, LEAD_VARS.OcrAdvantageRuntimeDir)
Using ocrDocument As IOcrDocument = ocrEngine.DocumentManager.CreateDocument()
' Recognize the TIFF file
Dim ocrPage As IOcrPage = ocrDocument.Pages.AddPage(tifFileName, Nothing)
ocrPage.Recognize(Nothing)
' Save the original recognition results to compare with the results
' we will modify
ocrDocument.Save(pdfFileName1, DocumentFormat.Pdf, Nothing)
' Get the recognized words
Dim pageCharacters As IOcrPageCharacters = ocrPage.GetRecognizedCharacters()
For Each zoneCharacters As IOcrZoneCharacters In pageCharacters
Dim words As IList(Of OcrWord) = zoneCharacters.GetWords(ocrPage.DpiX, ocrPage.DpiY, LogicalUnit.Pixel)
' Check for our words
' Note, we should not loop through words and change the collection. Remember, collections cannot
' be modified this way, instead, we have a helper method that returns the index of the word
' we are looking for then change the word. Repeat while no more words are found
Dim index As Integer
' Capitilize all "the"
Do
index = FindWord(words, "the", False)
If index <> -1 Then
' We have one, update it
pageCharacters.UpdateWord(words, zoneCharacters.ZoneIndex, index, "THE")
End If
Loop While index <> -1
' Delete all "a"
Do
index = FindWord(words, "a", True)
If index <> -1 Then
' We have one, update it
pageCharacters.UpdateWord(words, zoneCharacters.ZoneIndex, index, Nothing)
End If
Loop While index <> -1
' Replace all "color" with "water"
Do
index = FindWord(words, "color", True)
If index <> -1 Then
' We have one, update it
pageCharacters.UpdateWord(words, zoneCharacters.ZoneIndex, index, "water")
End If
Loop While index <> -1
Next
' We are done, update the page recognized results
ocrPage.SetRecognizedCharacters(pageCharacters)
' Save this new results
ocrDocument.Save(pdfFileName2, DocumentFormat.Pdf, Nothing)
End Using
End Using
End Sub
Private Shared Function FindWord(words As IList(Of OcrWord), value As String, ignoreCase As Boolean) As Integer
If words Is Nothing OrElse words.Count = 0 Then
Return -1
End If
For i As Integer = 0 To words.Count - 1
If String.Compare(words(i).Value, value, ignoreCase) = 0 Then
' Found it
Return i
End If
Next
' Not found
Return -1
End Function
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