OCR: Save the OCR result to a text file

In This Topic

OCR result can be saved to a text file as formatted text (OcrPage.GetFormattedText method) or not formatted text (OcrPage.GetText method).

Here is C#/VB.NET code that shows how to save OCR result to a text file as formatted text:

string imageFilePath = @"D:\TestImage.png";
// create the OCR engine
using (Vintasoft.Imaging.Ocr.Tesseract.TesseractOcr tesseractOcr = new Vintasoft.Imaging.Ocr.Tesseract.TesseractOcr())
{
    // specify that OCR engine will recognize English text
    Vintasoft.Imaging.Ocr.OcrLanguage language = Vintasoft.Imaging.Ocr.OcrLanguage.English;
    // create the OCR engine settings
    Vintasoft.Imaging.Ocr.Tesseract.TesseractOcrSettings settings = 
        new Vintasoft.Imaging.Ocr.Tesseract.TesseractOcrSettings(language);
    // initialize the OCR engine
    tesseractOcr.Init(settings);

    // load an image
    using (Vintasoft.Imaging.VintasoftImage image = new Vintasoft.Imaging.VintasoftImage(imageFilePath))
    {
        // specify the image, where text must be recognized
        tesseractOcr.SetImage(image);

        // recognize text in the image
        Vintasoft.Imaging.Ocr.Results.OcrPage ocrResult = tesseractOcr.Recognize();

        // get the recognized text as formatted text
        string ocrResultAsFormattedContent = ocrResult.GetFormattedText();

        string textFilePath = System.IO.Path.Combine(
            System.IO.Path.GetDirectoryName(imageFilePath),
            System.IO.Path.GetFileNameWithoutExtension(imageFilePath) + ".txt");
        // save the formatted text in a file
        System.IO.File.WriteAllText(textFilePath, ocrResultAsFormattedContent, System.Text.Encoding.UTF8);

        // clear the image
        tesseractOcr.ClearImage();
    }
    // shutdown the OCR engine
    tesseractOcr.Shutdown();
}

VB.NET

Dim imageFilePath As String = "D:\TestImage.png"
' create the OCR engine
Using tesseractOcr As New Vintasoft.Imaging.Ocr.Tesseract.TesseractOcr()
    ' specify that OCR engine will recognize English text
    Dim language As Vintasoft.Imaging.Ocr.OcrLanguage = Vintasoft.Imaging.Ocr.OcrLanguage.English
    ' create the OCR engine settings
    Dim settings As New Vintasoft.Imaging.Ocr.Tesseract.TesseractOcrSettings(language)
    ' initialize the OCR engine
    tesseractOcr.Init(settings)

    ' load an image
    Using image As New Vintasoft.Imaging.VintasoftImage(imageFilePath)
        ' specify the image, where text must be recognized
        tesseractOcr.SetImage(image)

        ' recognize text in the image
        Dim ocrResult As Vintasoft.Imaging.Ocr.Results.OcrPage = tesseractOcr.Recognize()

        ' get the recognized text as formatted text
        Dim ocrResultAsFormattedContent As String = ocrResult.GetFormattedText()

        Dim textFilePath As String = System.IO.Path.Combine(System.IO.Path.GetDirectoryName(imageFilePath), System.IO.Path.GetFileNameWithoutExtension(imageFilePath) & ".txt")
        ' save the formatted text in a file
        System.IO.File.WriteAllText(textFilePath, ocrResultAsFormattedContent, System.Text.Encoding.UTF8)

        ' clear the image
        tesseractOcr.ClearImage()
    End Using
    ' shutdown the OCR engine
    tesseractOcr.Shutdown()
End Using

Send Feedback