Speichern von durchsuchbaren PDFs in C#35; mit IronOCR

using IronOcr;

// Create the OCR engine: defaults to English with balanced speed and accuracy
IronTesseract ocrTesseract = new IronTesseract();

// Required: without this flag the text overlay layer is not built, and SaveAsSearchablePdf produces a plain image PDF
ocrTesseract.Configuration.RenderSearchablePdf = true;

// Wrap the TIFF in OcrImageInput: handles DPI detection and page layout automatically
using var imageInput = new OcrImageInput("Potter.tiff");
// Run OCR; returns a result containing the recognized text and spatial layout data
OcrResult ocrResult = ocrTesseract.Read(imageInput);

// Write the output: the original scanned image is preserved with an invisible text layer on top
ocrResult.SaveAsSearchablePdf("searchablePdf.pdf");

Imports IronOcr

' Create the OCR engine: defaults to English with balanced speed and accuracy
Dim ocrTesseract As New IronTesseract()

' Required: without this flag the text overlay layer is not built, and SaveAsSearchablePdf produces a plain image PDF
ocrTesseract.Configuration.RenderSearchablePdf = True

' Wrap the TIFF in OcrImageInput: handles DPI detection and page layout automatically
Using imageInput As New OcrImageInput("Potter.tiff")
    ' Run OCR; returns a result containing the recognized text and spatial layout data
    Dim ocrResult As OcrResult = ocrTesseract.Read(imageInput)

    ' Write the output: the original scanned image is preserved with an invisible text layer on top
    ocrResult.SaveAsSearchablePdf("searchablePdf.pdf")
End Using

using IronOcr;

// Create OCR engine: filters are applied at the OcrInput level, so no configuration changes are needed here
var ocr = new IronTesseract();
var ocrInput = new OcrInput();

// Load the scanned PDF as the OCR source
ocrInput.LoadPdf("invoice.pdf");

// Convert to grayscale: removes color noise that can reduce OCR accuracy on color-printed documents
ocrInput.ToGrayScale();
// Run OCR on the preprocessed input
OcrResult result = ocr.Read(ocrInput);

// Write the searchable PDF; true = embed the grayscale-filtered image rather than the original color scan
result.SaveAsSearchablePdf("outputGrayscale.pdf", true);

Imports IronOcr

' Create OCR engine: filters are applied at the OcrInput level, so no configuration changes are needed here
Dim ocr As New IronTesseract()
Dim ocrInput As New OcrInput()

' Load the scanned PDF as the OCR source
ocrInput.LoadPdf("invoice.pdf")

' Convert to grayscale: removes color noise that can reduce OCR accuracy on color-printed documents
ocrInput.ToGrayScale()
' Run OCR on the preprocessed input
Dim result As OcrResult = ocr.Read(ocrInput)

' Write the searchable PDF; True = embed the grayscale-filtered image rather than the original color scan
result.SaveAsSearchablePdf("outputGrayscale.pdf", True)

result.SaveAsSearchablePdf("output.pdf", false, "Fonts/LiberationSerif-Regular.ttf");

result.SaveAsSearchablePdf("output.pdf", False, "Fonts/LiberationSerif-Regular.ttf")

result.SaveAsSearchablePdf("output.pdf", false, "Fonts/LiberationSerif-Regular.ttf", "MyFont");

result.SaveAsSearchablePdf("output.pdf", False, "Fonts/LiberationSerif-Regular.ttf", "MyFont")

using IronOcr;
using System.Threading.Tasks;
using System.Collections.Concurrent;

public class BatchPdfProcessor
{
    private readonly IronTesseract _ocr;

    public BatchPdfProcessor()
    {
        _ocr = new IronTesseract
        {
            Configuration = 
            {
                RenderSearchablePdf = true,
                // Configure for optimal performance
                Language = OcrLanguage.English
            }
        };
    }

    public async Task ProcessBatchAsync(string[] filePaths)
    {
        var results = new ConcurrentBag<(string source, string output)>();

        await Parallel.ForEachAsync(filePaths, async (filePath, ct) =>
        {
            using var input = new OcrImageInput(filePath);
            var result = _ocr.Read(input);

            string outputPath = Path.ChangeExtension(filePath, ".searchable.pdf");
            result.SaveAsSearchablePdf(outputPath);

            results.Add((filePath, outputPath));
        });

        Console.WriteLine($"Processed {results.Count} files");
    }
}

Imports IronOcr
Imports System.Threading.Tasks
Imports System.Collections.Concurrent

Public Class BatchPdfProcessor
    Private ReadOnly _ocr As IronTesseract

    Public Sub New()
        _ocr = New IronTesseract With {
            .Configuration = New OcrConfiguration With {
                .RenderSearchablePdf = True,
                ' Configure for optimal performance
                .Language = OcrLanguage.English
            }
        }
    End Sub

    Public Async Function ProcessBatchAsync(filePaths As String()) As Task
        Dim results As New ConcurrentBag(Of (source As String, output As String))()

        Await Task.Run(Sub()
                           Parallel.ForEach(filePaths, Sub(filePath)
                                                           Using input As New OcrImageInput(filePath)
                                                               Dim result = _ocr.Read(input)

                                                               Dim outputPath As String = Path.ChangeExtension(filePath, ".searchable.pdf")
                                                               result.SaveAsSearchablePdf(outputPath)

                                                               results.Add((filePath, outputPath))
                                                           End Using
                                                       End Sub)
                       End Sub)

        Console.WriteLine($"Processed {results.Count} files")
    End Function
End Class

var advancedOcr = new IronTesseract
{
    Configuration = 
    {
        RenderSearchablePdf = true,
        TesseractVariables = new Dictionary<string, object>
        {
            { "preserve_interword_spaces", 1 },
            { "tessedit_char_whitelist", "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz" }
        },
        PageSegmentationMode = TesseractPageSegmentationMode.SingleColumn
    },
    Language = OcrLanguage.EnglishBest
};

Imports IronOcr

Dim advancedOcr As New IronTesseract With {
    .Configuration = New TesseractConfiguration With {
        .RenderSearchablePdf = True,
        .TesseractVariables = New Dictionary(Of String, Object) From {
            {"preserve_interword_spaces", 1},
            {"tessedit_char_whitelist", "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"}
        },
        .PageSegmentationMode = TesseractPageSegmentationMode.SingleColumn
    },
    .Language = OcrLanguage.EnglishBest
}