ByteScout Text Recognition SDK – VB.NET – Auto Corrections

ByteScout Text Recognition SDK – VB.NET – Auto Corrections

Module1.vb

Imports Bytescout.TextRecognition

Module Module1

    Sub Main()

        Dim inputDocument As String = ".\bad-quality.png"
        Dim outputDocument As String = ".\result.txt"

        ' Create and activate TextRecognizer instance
        Using textRecognizer As TextRecognizer = New TextRecognizer("demo", "demo")

            Try
                ' Load document (image or PDF)
                textRecognizer.LoadDocument(inputDocument)

                ' Set location of "tessdata" folder containing language data files
                textRecognizer.OCRLanguageDataFolder = "c:\Program Files\ByteScout Text Recognition SDK\tessdata\"

                ' Set OCR language.
                ' "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "tessdata" folder
                ' Find more language files at https://github.com/tesseract-ocr/tessdata/tree/3.04.00
                textRecognizer.OCRLanguage = "eng"


                ' Add error corrections that will be applied after the recognition.
                textRecognizer.Corrections.Add("Tut ", "Test ")
                textRecognizer.Corrections.Add("Recog\w{1,}on", "Recognition", True)

                
                ' Recognize text from all pages and save it to file
                textRecognizer.SaveText(outputDocument)

                ' Open the result file in default associated application (for demo purposes)
                Process.Start(outputDocument)

            Catch exception As Exception

                Console.WriteLine(exception)

            End Try

        End Using

    End Sub

End Module

  Click here to get your Free Trial version of the SDK