ByteScout Text Recognition SDK – PowerShell – Auto Corrections

ByteScout Text Recognition SDK – PowerShell – Auto Corrections

AutoCorrections.ps1

# Add reference to ByteScout.TextRecognition.dll assembly
Add-Type -Path "c:\Program Files\ByteScout Text Recognition SDK\net40\ByteScout.TextRecognition.dll"

$InputDocument = "..\..\bad-quality.png"
$OutputDocument = ".\result.txt"

# Create and activate TextRecognizer instance
$textRecognizer = New-Object ByteScout.TextRecognition.TextRecognizer
$textRecognizer.RegistrationName = "demo"
$textRecognizer.RegistrationKey = "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) # regular expression (regex) replacement


    # Recognize text from all pages and save it to file
    $textRecognizer.SaveText($OutputDocument)

    # Open the result file in default associated application (for demo purposes)
    & $OutputDocument
}
catch {
    # Display exception
    Write-Host $_.Exception.Message
}

$textRecognizer.Dispose()

run.bat

@echo off

powershell -NoProfile -ExecutionPolicy Bypass -Command "& .\AutoCorrections.ps1"
echo Script finished with errorlevel=%errorlevel%

pause

  Click here to get your Free Trial version of the SDK