Code Examples:

Sample: C# Project

using PDFOCRCOM;

namespace CSharp_COM_Test

{

    public partial class Form1 : Form

    {

        public Form1()

        {

            InitializeComponent();

        }

        private void button1_Click(object sender, EventArgs e)

        {

            PDFOCRCOMClass pdfocr = new PDFOCRCOMClass();

            long ret = pdfocr.com_PDFOCRCmd(
                  "-ocr 1 \"D:\\temp\\test.pdf\" \"D:\\temp\\2_out.pdf\""

             );

        }

    }

}

 

Sample: VB.NET Project

 

Private Sub OCRPDFButton_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles OCRPDFButton.Click

        Dim strOptions As String

        Dim strInFile As String

        Dim strOutFile As String

        Dim strLogMsg As String

 

        strInFile = Application.StartupPath() & "\test1.pdf"

        strOutFile = Application.StartupPath() & "\test1_vb_net_ocred.pdf"

        strOptions = "-pidpi 300"

 

        Dim nPageCount As Integer = Image2PDFOCR_GetPageCount(strInFile)

        strLogMsg = """" & strInFile & """ file contains """ & Str(nPageCount)

        & """ pages."

        MsgBox(strLogMsg)

 

        Dim hOCRTextSDK As Integer =

           Image2PDFOCR_GetTextHandle(strInFile, strOptions)

        If hOCRTextSDK <> 0 Then

            Dim nOCRedPageCount As Integer =

                Image2PDFOCR_GetOCRedPageCount(hOCRTextSDK)

            For page = 0 To nOCRedPageCount - 1

                Dim nWordCount As Integer = Image2PDFOCR_GetWordCountOnPage(

                    hOCRTextSDK, page)

                For nWordIndex = 0 To nWordCount - 1

                    Dim nWord As TEXTPOSITION

                    nWord.init()

                    Image2PDFOCR_GetWordInfoByIndex(hOCRTextSDK, page,

                       nWordIndex, nWord.x, nWord.y, nWord.width,

                       nWord.height, nWord.text(0))

                    Dim enc As New System.Text.UTF8Encoding()

                    Dim strWord As String = enc.GetString(nWord.text)

                    Image2PDFOCR_SetWordInfoByIndex(hOCRTextSDK, page,

                       nWordIndex, nWord.x, nWord.y, nWord.width,

                       nWord.height, strWord)

                Next nWordIndex

            Next page

 

            Dim nDataBufLen As Integer = 0

            Dim nRet As Integer = Image2PDFOCR_CreatePDFInMemory(

            hOCRTextSDK, strOptions, 0, nDataBufLen)

            If nRet = 0 And nDataBufLen > 0 Then

                Dim vecFileData() As Byte = Nothing

                ReDim vecFileData(nDataBufLen)

                nRet = Image2PDFOCR_ReadPDFFromMemory(

                       hOCRTextSDK, vecFileData(0), nDataBufLen)

 

                Dim oFileStream As System.IO.FileStream

                oFileStream = New System.IO.FileStream(strOutFile,

                System.IO.FileMode.Create)

                oFileStream.Write(vecFileData, 0, vecFileData.Length)

                oFileStream.Close()

            End If

            Image2PDFOCR_FreeTextHandle(hOCRTextSDK)

        End If

    End Sub

End Class

 

For details on how to use this .NET package, please download the trial version of VeryPDF Image to PDF OCR SDK for .NET package.

For full version of this .NET package, please buy VeryPDF Image to PDF OCR SDK for .NET here.