GdPicture.NET.14~GdPicture14.GdPictureOCR_methods - GetCharacterWordIndex Method (GdPictureOCR)

Visual Basic
C#
Delphi
JScript
Managed Extensions for C++
C++/CLI

'Declaration

 

Public Function GetCharacterWordIndex( _

   ByVal OCRResultID As String, _

   ByVal CharacterIdx As Integer _

) As Integer

public int GetCharacterWordIndex( 

   string OCRResultID,

   int CharacterIdx

)

public function GetCharacterWordIndex( 

    OCRResultID: String;

    CharacterIdx: Integer

): Integer;

public function GetCharacterWordIndex( 

   OCRResultID : String,

   CharacterIdx : int

) : int;

public: int GetCharacterWordIndex( 

   string* OCRResultID,

   int CharacterIdx

)

public:

int GetCharacterWordIndex( 

   String^ OCRResultID,

   int CharacterIdx

)

Parameters

OCRResultID: The unique result identifier of the executed OCR process obtained by the RunOCR method.
CharacterIdx: The 0-based index of the character within the specified OCR result. It must be a value between 0 and GetCharacterCount(OCRResultID) - 1.

Return Value

The index of the word, which involves the required character. Please always use the GetStat method to determine if this method has been successful.

It is recommend to use the GetStat method to identify the specific reason for the method's failure, if any.

How to determine, which character belongs to which word in the OCR result.

VB.NET
C#

Dim caption As String = "Example: GetCharacterWordIndex"

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

        'Set up the OCR parameters.

        gdpictureOCR.ResourcesFolder = "C:\Path\To\GdPicture.NET 14\Redist\OCR"

        gdpictureOCR.AddLanguage(OCRLanguage.English)

        gdpictureOCR.OCRMode = OCRMode.FavorAccuracy

        'Set up the OCR context and the character list.

        gdpictureOCR.Context = OCRContext.OCRContextDocument

        gdpictureOCR.CharacterSet = "@"

        'Run the OCR process to recognize the character.

        Dim resID As String = gdpictureOCR.RunOCR()

        If gdpictureOCR.GetStat() = GdPictureStatus.OK Then

            Dim wordCount As Integer = gdpictureOCR.GetWordCount(resID)

            If gdpictureOCR.GetStat() = GdPictureStatus.OK Then

                Dim message As String = "The number of all recognized words: " + wordCount.ToString() + vbCrLf

                Dim charCount As Integer = gdpictureOCR.GetCharacterCount(resID)

                If gdpictureOCR.GetStat() = GdPictureStatus.OK Then

                    message = message + "The number of all recognized characters: " + charCount.ToString() + vbCrLf

                    For i As Integer = 0 To charCount - 1

                        message = message + "The character nr." + i.ToString() + " is included in the word nr." +

                                            gdpictureOCR.GetCharacterWordIndex(resID, i).ToString() + "." + vbCrLf

                    Next

                    MessageBox.Show(message, caption)

                    'Continue with analyzing the result ...

                Else

                    MessageBox.Show("The GetCharacterCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString(), caption)

                End If

            Else

                MessageBox.Show("The GetWordCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString(), caption)

            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: GetCharacterWordIndex";

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.

    {

        //Set up the OCR parameters.

        gdpictureOCR.ResourcesFolder = "C:\\Path\\To\\GdPicture.NET 14\\Redist\\OCR";

        gdpictureOCR.AddLanguage(OCRLanguage.English);

        gdpictureOCR.OCRMode = OCRMode.FavorAccuracy;

        //Set up the OCR context and the character list.

        gdpictureOCR.Context = OCRContext.OCRContextDocument;

        gdpictureOCR.CharacterSet = "@";

        //Run the OCR process to recognize the character.

        string resID = gdpictureOCR.RunOCR();

        if (gdpictureOCR.GetStat() == GdPictureStatus.OK)

        {

            int wordCount = gdpictureOCR.GetWordCount(resID);

            if (gdpictureOCR.GetStat() == GdPictureStatus.OK)

            {

                string message = "The number of all recognized words: " + wordCount.ToString() + "\n";

                int charCount = gdpictureOCR.GetCharacterCount(resID);

                if (gdpictureOCR.GetStat() == GdPictureStatus.OK)

                {

                    message = message + "The number of all recognized characters: " + charCount.ToString() + "\n";

                    for (int i = 0; i < charCount; i++)

                    {

                        message = message + "The character nr." + i.ToString() + " is included in the word nr." +

                                            gdpictureOCR.GetCharacterWordIndex(resID, i).ToString() + ".\n";

                    }

                    MessageBox.Show(message, caption);

                    //Continue with analyzing the result ...

                }

                else

                    MessageBox.Show("The GetCharacterCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString(), caption);

            }

            else

                MessageBox.Show("The GetWordCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString(), caption);

        }

        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();

How to determine, which character belongs to which word in the OCR result. Dim caption As String = "Example: GetCharacterWordIndex" 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 'Set up the OCR parameters. gdpictureOCR.ResourcesFolder = "C:\Path\To\GdPicture.NET 14\Redist\OCR" gdpictureOCR.AddLanguage(OCRLanguage.English) gdpictureOCR.OCRMode = OCRMode.FavorAccuracy 'Set up the OCR context and the character list. gdpictureOCR.Context = OCRContext.OCRContextDocument gdpictureOCR.CharacterSet = "@" 'Run the OCR process to recognize the character. Dim resID As String = gdpictureOCR.RunOCR() If gdpictureOCR.GetStat() = GdPictureStatus.OK Then Dim wordCount As Integer = gdpictureOCR.GetWordCount(resID) If gdpictureOCR.GetStat() = GdPictureStatus.OK Then Dim message As String = "The number of all recognized words: " + wordCount.ToString() + vbCrLf Dim charCount As Integer = gdpictureOCR.GetCharacterCount(resID) If gdpictureOCR.GetStat() = GdPictureStatus.OK Then message = message + "The number of all recognized characters: " + charCount.ToString() + vbCrLf For i As Integer = 0 To charCount - 1 message = message + "The character nr." + i.ToString() + " is included in the word nr." + gdpictureOCR.GetCharacterWordIndex(resID, i).ToString() + "." + vbCrLf Next MessageBox.Show(message, caption) 'Continue with analyzing the result ... Else MessageBox.Show("The GetCharacterCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString(), caption) End If Else MessageBox.Show("The GetWordCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString(), caption) 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: GetCharacterWordIndex"; 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. { //Set up the OCR parameters. gdpictureOCR.ResourcesFolder = "C:\\Path\\To\\GdPicture.NET 14\\Redist\\OCR"; gdpictureOCR.AddLanguage(OCRLanguage.English); gdpictureOCR.OCRMode = OCRMode.FavorAccuracy; //Set up the OCR context and the character list. gdpictureOCR.Context = OCRContext.OCRContextDocument; gdpictureOCR.CharacterSet = "@"; //Run the OCR process to recognize the character. string resID = gdpictureOCR.RunOCR(); if (gdpictureOCR.GetStat() == GdPictureStatus.OK) { int wordCount = gdpictureOCR.GetWordCount(resID); if (gdpictureOCR.GetStat() == GdPictureStatus.OK) { string message = "The number of all recognized words: " + wordCount.ToString() + "\n"; int charCount = gdpictureOCR.GetCharacterCount(resID); if (gdpictureOCR.GetStat() == GdPictureStatus.OK) { message = message + "The number of all recognized characters: " + charCount.ToString() + "\n"; for (int i = 0; i < charCount; i++) { message = message + "The character nr." + i.ToString() + " is included in the word nr." + gdpictureOCR.GetCharacterWordIndex(resID, i).ToString() + ".\n"; } MessageBox.Show(message, caption); //Continue with analyzing the result ... } else MessageBox.Show("The GetCharacterCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString(), caption); } else MessageBox.Show("The GetWordCount() method has failed with the status: " + gdpictureOCR.GetStat().ToString(), caption); } 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();

Reference

GdPictureOCR Class
GdPictureOCR Members
RunOCR Method
GetStat Method
GetStat Method
GetCharacterCount Method
GetWordCount Method
GetWordFirstCharacterIndex Method
RunOCR Method