VintaSoft Tech Community

Code: Select all

public static void RecognizeNonTextPdfPages(OcrEngine ocrEngine, string inPdfFilename, string outPdfFilename)
{
    OcrEngineManager engineManager = new OcrEngineManager(ocrEngine);
    OcrEngineSettings ocrSettings = new OcrEngineSettings(OcrLanguage.English);

    PdfRenderingSettings renderingSettings = new PdfRenderingSettings();
    renderingSettings.Resolution = new Resolution(300, 300);

    // open source PDF document
    using (PdfDocument document = new PdfDocument(inPdfFilename))
    {
        // create PDF document builder
        PdfDocumentBuilder builder = new PdfDocumentBuilder(document);
        builder.Font = PdfDocumentBuilder.CreateGlyphLessFont(document);
        builder.PageCreationMode = PdfPageCreationMode.ImageOverText;

        // for each page in source PDF document
        for (int i = 0; i < document.Pages.Count; i++)
        {
            // get PDF page
            PdfPage page = document.Pages[i];
            // if page does not have text
            if (page.TextRegion.IsEmpty)
            {
                // render image of PDF page
                using (VintasoftImage image = page.Render(renderingSettings, null, null))
                {
                    // recognize text in rendered image
                    OcrPage ocrPage = engineManager.Recognize(image, ocrSettings);
                    // if page has text
                    if (ocrPage != null && !string.IsNullOrEmpty(ocrPage.GetText()))
                        // set OCR page as a background for PDF page
                        builder.SetAsBackground(i, ocrPage);
                }
            }
        }

        // save PDF document to a new file
        document.Pack(outPdfFilename);
    }
}