GetTextLineParagraphIndex Method (GdPictureOCR)
In This Topic
Returns the index of the paragraph, which incorporates the specified text line, that is a part of a specified OCR result.
Syntax
'Declaration
Public Function GetTextLineParagraphIndex( _
ByVal As String, _
ByVal As Integer _
) As Integer
public int GetTextLineParagraphIndex(
string ,
int
)
public function GetTextLineParagraphIndex(
: String;
: Integer
): Integer;
public function GetTextLineParagraphIndex(
: String,
: int
) : int;
public: int GetTextLineParagraphIndex(
string* ,
int
)
public:
int GetTextLineParagraphIndex(
String^ ,
int
)
Parameters
- OCRResultID
- The unique result identifier of the executed OCR process obtained by the GdPictureOCR.RunOCR method.
- TextLineIdx
- The 0-based index of the text line within the specified OCR result. It must be a value between 0 and GdPictureOCR.GetTextLineCount(OCRResultID) - 1.
Return Value
The index of the paragraph, which involves the required text line. Please always use the
GdPictureOCR.GetStat method to determine if this method has been successful.
Example
How to determine, which text line belongs to which paragraph in the OCR result.
Dim caption As String = "Example: GetTextLineParagraphIndex"
Dim gdpictureOCR As GdPictureOCR = New GdPictureOCR()
Dim gdpicturePDF As GdPicturePDF = New GdPicturePDF()
'Load the PDF document.
If gdpicturePDF.LoadFromFile("input.pdf", False) = GdPictureStatus.OK Then
'Select the first page.
gdpicturePDF.SelectPage(1)
'Render this page to a 200 DPI image.
Dim image As Integer = gdpicturePDF.RenderPageToGdPictureImage(200, True)
'Setting up the image is mandatory.
If (gdpicturePDF.GetStat() = GdPictureStatus.OK) AndAlso
(gdpictureOCR.SetImage(image) = GdPictureStatus.OK) Then
Dim message As String = ""
'Set up the OCR parameters.
gdpictureOCR.ResourcesFolder = "C:\Path\To\GdPicture.NET 14\Redist\OCR"
gdpictureOCR.AddLanguage(OCRLanguage.English)
'Set up the OCR context and the character list.
gdpictureOCR.Context = OCRContext.OCRContextSingleBlock
gdpictureOCR.CharacterSet = ""
'Run the OCR process.
Dim resID As String = gdpictureOCR.RunOCR()
If gdpictureOCR.GetStat() = GdPictureStatus.OK Then
Dim paragraphCount As Integer = gdpictureOCR.GetParagraphCount(resID)
If gdpictureOCR.GetStat() = GdPictureStatus.OK Then
message = message + "The number of all recognized paragraphs: " + paragraphCount.ToString() + vbCrLf
Dim linesCount As Integer = gdpictureOCR.GetTextLineCount(resID)
If gdpictureOCR.GetStat() = GdPictureStatus.OK Then
message = message + "The number of all recognized text lines: " + linesCount.ToString() + vbCrLf
For i As Integer = 0 To linesCount - 1
message = message + "The line nr." + i.ToString() + " is included in the paragraph nr." +
gdpictureOCR.GetTextLineParagraphIndex(resID, i).ToString() + "." + vbCrLf
Next
MessageBox.Show(message, caption)
'Continue with analyzing the result ...
Else
MessageBox.Show("The GetTextLineCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString())
End If
Else
MessageBox.Show("The GetParagraphCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString())
End If
Else
MessageBox.Show("The error occurred when running the OCR. Status: " + gdpictureOCR.GetStat().ToString(), caption)
End If
'Release the image.
GdPictureDocumentUtilities.DisposeImage(image)
Else
MessageBox.Show("The error occurred when creating or setting up the image. Status: " + gdpicturePDF.GetStat().ToString() + "/" + gdpictureOCR.GetStat().ToString(), caption)
End If
'Close the document.
gdpicturePDF.CloseDocument()
Else
MessageBox.Show("The file can't be loaded. Status: " + gdpicturePDF.GetStat().ToString(), caption)
End If
'Release resources.
gdpictureOCR.ReleaseOCRResults()
gdpictureOCR.Dispose()
gdpicturePDF.Dispose()
string caption = "Example: GetTextLineParagraphIndex";
GdPictureOCR gdpictureOCR = new GdPictureOCR();
GdPicturePDF gdpicturePDF = new GdPicturePDF();
//Load the PDF document.
if (gdpicturePDF.LoadFromFile("input.pdf", false) == GdPictureStatus.OK)
{
//Select the first page.
gdpicturePDF.SelectPage(1);
//Render this page to a 200 DPI image.
int image = gdpicturePDF.RenderPageToGdPictureImage(200, true);
if ((gdpicturePDF.GetStat() == GdPictureStatus.OK) &&
(gdpictureOCR.SetImage(image) == GdPictureStatus.OK)) //Setting up the image is mandatory.
{
string message = "";
//Set up the OCR parameters.
gdpictureOCR.ResourcesFolder = "C:\\Path\\To\\GdPicture.NET 14\\Redist\\OCR";
gdpictureOCR.AddLanguage(OCRLanguage.English);
//Set up the OCR context and the character list.
gdpictureOCR.Context = OCRContext.OCRContextSingleBlock;
gdpictureOCR.CharacterSet = "";
//Run the OCR process.
string resID = gdpictureOCR.RunOCR();
if (gdpictureOCR.GetStat() == GdPictureStatus.OK)
{
int paragraphCount = gdpictureOCR.GetParagraphCount(resID);
if (gdpictureOCR.GetStat() == GdPictureStatus.OK)
{
message = message + "The number of all recognized paragraphs: " + paragraphCount.ToString() + "\n";
int linesCount = gdpictureOCR.GetTextLineCount(resID);
if (gdpictureOCR.GetStat() == GdPictureStatus.OK)
{
message = message + "The number of all recognized text lines: " + linesCount.ToString() + "\n";
for (int i = 0; i < linesCount; i++)
{
message = message + "The line nr." + i.ToString() + " is included in the paragraph nr." +
gdpictureOCR.GetTextLineParagraphIndex(resID, i).ToString() + ".\n";
}
MessageBox.Show(message, caption);
//Continue with analyzing the result ...
}
else
MessageBox.Show("The GetTextLineCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString());
}
else
MessageBox.Show("The GetParagraphCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString());
}
else
MessageBox.Show("The error occurred when running the OCR. Status: " + gdpictureOCR.GetStat().ToString(), caption);
//Release the image.
GdPictureDocumentUtilities.DisposeImage(image);
}
else
MessageBox.Show("The error occurred when creating or setting up the image. Status: " + gdpicturePDF.GetStat().ToString() + "/" + gdpictureOCR.GetStat().ToString(), caption);
//Close the document.
gdpicturePDF.CloseDocument();
}
else
MessageBox.Show("The file can't be loaded. Status: " + gdpicturePDF.GetStat().ToString(), caption);
//Release resources.
gdpictureOCR.ReleaseOCRResults();
gdpictureOCR.Dispose();
gdpicturePDF.Dispose();
Example
How to determine, which text line belongs to which paragraph in the OCR result.
Dim caption As String = "Example: GetTextLineParagraphIndex"
Dim gdpictureOCR As GdPictureOCR = New GdPictureOCR()
Dim gdpicturePDF As GdPicturePDF = New GdPicturePDF()
'Load the PDF document.
If gdpicturePDF.LoadFromFile("input.pdf", False) = GdPictureStatus.OK Then
'Select the first page.
gdpicturePDF.SelectPage(1)
'Render this page to a 200 DPI image.
Dim image As Integer = gdpicturePDF.RenderPageToGdPictureImage(200, True)
'Setting up the image is mandatory.
If (gdpicturePDF.GetStat() = GdPictureStatus.OK) AndAlso
(gdpictureOCR.SetImage(image) = GdPictureStatus.OK) Then
Dim message As String = ""
'Set up the OCR parameters.
gdpictureOCR.ResourcesFolder = "C:\Path\To\GdPicture.NET 14\Redist\OCR"
gdpictureOCR.AddLanguage(OCRLanguage.English)
'Set up the OCR context and the character list.
gdpictureOCR.Context = OCRContext.OCRContextSingleBlock
gdpictureOCR.CharacterSet = ""
'Run the OCR process.
Dim resID As String = gdpictureOCR.RunOCR()
If gdpictureOCR.GetStat() = GdPictureStatus.OK Then
Dim paragraphCount As Integer = gdpictureOCR.GetParagraphCount(resID)
If gdpictureOCR.GetStat() = GdPictureStatus.OK Then
message = message + "The number of all recognized paragraphs: " + paragraphCount.ToString() + vbCrLf
Dim linesCount As Integer = gdpictureOCR.GetTextLineCount(resID)
If gdpictureOCR.GetStat() = GdPictureStatus.OK Then
message = message + "The number of all recognized text lines: " + linesCount.ToString() + vbCrLf
For i As Integer = 0 To linesCount - 1
message = message + "The line nr." + i.ToString() + " is included in the paragraph nr." +
gdpictureOCR.GetTextLineParagraphIndex(resID, i).ToString() + "." + vbCrLf
Next
MessageBox.Show(message, caption)
'Continue with analyzing the result ...
Else
MessageBox.Show("The GetTextLineCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString())
End If
Else
MessageBox.Show("The GetParagraphCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString())
End If
Else
MessageBox.Show("The error occurred when running the OCR. Status: " + gdpictureOCR.GetStat().ToString(), caption)
End If
'Release the image.
GdPictureDocumentUtilities.DisposeImage(image)
Else
MessageBox.Show("The error occurred when creating or setting up the image. Status: " + gdpicturePDF.GetStat().ToString() + "/" + gdpictureOCR.GetStat().ToString(), caption)
End If
'Close the document.
gdpicturePDF.CloseDocument()
Else
MessageBox.Show("The file can't be loaded. Status: " + gdpicturePDF.GetStat().ToString(), caption)
End If
'Release resources.
gdpictureOCR.ReleaseOCRResults()
gdpictureOCR.Dispose()
gdpicturePDF.Dispose()
string caption = "Example: GetTextLineParagraphIndex";
GdPictureOCR gdpictureOCR = new GdPictureOCR();
GdPicturePDF gdpicturePDF = new GdPicturePDF();
//Load the PDF document.
if (gdpicturePDF.LoadFromFile("input.pdf", false) == GdPictureStatus.OK)
{
//Select the first page.
gdpicturePDF.SelectPage(1);
//Render this page to a 200 DPI image.
int image = gdpicturePDF.RenderPageToGdPictureImage(200, true);
if ((gdpicturePDF.GetStat() == GdPictureStatus.OK) &&
(gdpictureOCR.SetImage(image) == GdPictureStatus.OK)) //Setting up the image is mandatory.
{
string message = "";
//Set up the OCR parameters.
gdpictureOCR.ResourcesFolder = "C:\\Path\\To\\GdPicture.NET 14\\Redist\\OCR";
gdpictureOCR.AddLanguage(OCRLanguage.English);
//Set up the OCR context and the character list.
gdpictureOCR.Context = OCRContext.OCRContextSingleBlock;
gdpictureOCR.CharacterSet = "";
//Run the OCR process.
string resID = gdpictureOCR.RunOCR();
if (gdpictureOCR.GetStat() == GdPictureStatus.OK)
{
int paragraphCount = gdpictureOCR.GetParagraphCount(resID);
if (gdpictureOCR.GetStat() == GdPictureStatus.OK)
{
message = message + "The number of all recognized paragraphs: " + paragraphCount.ToString() + "\n";
int linesCount = gdpictureOCR.GetTextLineCount(resID);
if (gdpictureOCR.GetStat() == GdPictureStatus.OK)
{
message = message + "The number of all recognized text lines: " + linesCount.ToString() + "\n";
for (int i = 0; i < linesCount; i++)
{
message = message + "The line nr." + i.ToString() + " is included in the paragraph nr." +
gdpictureOCR.GetTextLineParagraphIndex(resID, i).ToString() + ".\n";
}
MessageBox.Show(message, caption);
//Continue with analyzing the result ...
}
else
MessageBox.Show("The GetTextLineCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString());
}
else
MessageBox.Show("The GetParagraphCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString());
}
else
MessageBox.Show("The error occurred when running the OCR. Status: " + gdpictureOCR.GetStat().ToString(), caption);
//Release the image.
GdPictureDocumentUtilities.DisposeImage(image);
}
else
MessageBox.Show("The error occurred when creating or setting up the image. Status: " + gdpicturePDF.GetStat().ToString() + "/" + gdpictureOCR.GetStat().ToString(), caption);
//Close the document.
gdpicturePDF.CloseDocument();
}
else
MessageBox.Show("The file can't be loaded. Status: " + gdpicturePDF.GetStat().ToString(), caption);
//Release resources.
gdpictureOCR.ReleaseOCRResults();
gdpictureOCR.Dispose();
gdpicturePDF.Dispose();
See Also