Umstellung von ABBYY FineReader auf IronOCR

// ABBYY: COM loader + license path validation + profile load — before a single pixel of OCR runs
var loader = new EngineLoader();
var engine = loader.GetEngineObject(
    @"C:\Program Files\ABBYY SDK\FineReader Engine\Bin",  // Breaks on every new machine
    @"C:\Program Files\ABBYY SDK\License"                 // Fails if .lic file is missing
);
engine.LoadPredefinedProfile("DocumentConversion_Accuracy");
var langParams = engine.CreateLanguageParams();
langParams.Languages.Add("English");

' ABBYY: COM loader + license path validation + profile load — before a single pixel of OCR runs
Dim loader As New EngineLoader()
Dim engine = loader.GetEngineObject(
    "C:\Program Files\ABBYY SDK\FineReader Engine\Bin",  ' Breaks on every new machine
    "C:\Program Files\ABBYY SDK\License"                 ' Fails if .lic file is missing
)
engine.LoadPredefinedProfile("DocumentConversion_Accuracy")
Dim langParams = engine.CreateLanguageParams()
langParams.Languages.Add("English")

// IronOCR: the entire initialization
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";
var ocr = new IronTesseract();

Imports IronOcr

' IronOCR: the entire initialization
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"
Dim ocr As New IronTesseract()

<Reference Include="FREngine">
  <HintPath>C:\Program Files\ABBYY SDK\FineReader Engine\Bin\FREngine.dll</HintPath>
</Reference>

// Before (ABBYY)
using FREngine;
using ABBYY.FineReader;

// After (IronOCR)
using IronOcr;

Imports IronOcr

IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE_KEY");

Imports System

IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE_KEY")

using FREngine;

public class DocumentOcrService : IHostedService, IDisposable
{
    private IEngine _engine;

    public Task StartAsync(CancellationToken cancellationToken)
    {
        // Step 1: Create loader — requires COM-Interoperabilität registration
        var loader = new EngineLoader();

        // Step 2: Load engine from SDK path — throws if license files are missing
        _engine = loader.GetEngineObject(
            @"C:\Program Files\ABBYY SDK\FineReader Engine\Bin",
            @"C:\Program Files\ABBYY SDK\License"
        );

        // Step 3: Load profile before any recognition work
        _engine.LoadPredefinedProfile("DocumentConversion_Accuracy");

        return Task.CompletedTask;
    }

    public string ProcessDocument(string imagePath)
    {
        // Document must be created and destroyed per call
        var document = _engine.CreateFRDocument();
        try
        {
            document.AddImageFile(imagePath, null, null);
            document.Process(null);
            return document.PlainText.Text;
        }
        finally
        {
            document.Close(); // Memory leaks if omitted
        }
    }

    public Task StopAsync(CancellationToken cancellationToken)
    {
        _engine = null; // COM cleanup
        return Task.CompletedTask;
    }

    public void Dispose() => _engine = null;
}

Imports FREngine
Imports System.Threading
Imports System.Threading.Tasks

Public Class DocumentOcrService
    Implements IHostedService, IDisposable

    Private _engine As IEngine

    Public Function StartAsync(cancellationToken As CancellationToken) As Task Implements IHostedService.StartAsync
        ' Step 1: Create loader — requires COM-Interoperabilität registration
        Dim loader As New EngineLoader()

        ' Step 2: Load engine from SDK path — throws if license files are missing
        _engine = loader.GetEngineObject(
            "C:\Program Files\ABBYY SDK\FineReader Engine\Bin",
            "C:\Program Files\ABBYY SDK\License"
        )

        ' Step 3: Load profile before any recognition work
        _engine.LoadPredefinedProfile("DocumentConversion_Accuracy")

        Return Task.CompletedTask
    End Function

    Public Function ProcessDocument(imagePath As String) As String
        ' Document must be created and destroyed per call
        Dim document = _engine.CreateFRDocument()
        Try
            document.AddImageFile(imagePath, Nothing, Nothing)
            document.Process(Nothing)
            Return document.PlainText.Text
        Finally
            document.Close() ' Memory leaks if omitted
        End Try
    End Function

    Public Function StopAsync(cancellationToken As CancellationToken) As Task Implements IHostedService.StopAsync
        _engine = Nothing ' COM cleanup
        Return Task.CompletedTask
    End Function

    Public Sub Dispose() Implements IDisposable.Dispose
        _engine = Nothing
    End Sub
End Class

using IronOcr;

public class DocumentOcrService
{
    //Neinstartup, no shutdown, no COM lifecycle
    // IronTesseract is stateless — create per call or reuse per thread

    public string ProcessDocument(string imagePath)
    {
        return new IronTesseract().Read(imagePath).Text;
    }
}

Imports IronOcr

Public Class DocumentOcrService
    'Neinstartup, no shutdown, no COM lifecycle
    ' IronTesseract is stateless — create per call or reuse per thread

    Public Function ProcessDocument(imagePath As String) As String
        Return New IronTesseract().Read(imagePath).Text
    End Function
End Class

using FREngine;

// Engine must already be initialized with sdkPath and licensePath
private void ConfigureLanguages(IEngine engine, string[] languageCodes)
{
    // Create language parameters object
    var langParams = engine.CreateLanguageParams();

    // Add each language — string names must match installed data file names
    // Missing data file causes runtime failure
    foreach (var lang in languageCodes)
    {
        langParams.Languages.Add(lang);  // e.g., "English", "French", "German"
    }

    // Language params are associated at the profile level, not per-document
    // Changing languages requires reloading profile or reinitializing engine
    engine.LoadPredefinedProfile("DocumentConversion_Accuracy");
}

public string RecognizeFrenchDocument(IEngine engine, string imagePath)
{
    var langParams = engine.CreateLanguageParams();
    langParams.Languages.Add("French");  // Requires FrenchLanguage data files at runtime path

    var document = engine.CreateFRDocument();
    try
    {
        document.AddImageFile(imagePath, null, null);
        document.Process(null);
        return document.PlainText.Text;
    }
    finally
    {
        document.Close();
    }
}

Imports FREngine

' Engine must already be initialized with sdkPath and licensePath
Private Sub ConfigureLanguages(engine As IEngine, languageCodes As String())
    ' Create language parameters object
    Dim langParams = engine.CreateLanguageParams()

    ' Add each language — string names must match installed data file names
    ' Missing data file causes runtime failure
    For Each lang In languageCodes
        langParams.Languages.Add(lang)  ' e.g., "English", "French", "German"
    Next

    ' Language params are associated at the profile level, not per-document
    ' Changing languages requires reloading profile or reinitializing engine
    engine.LoadPredefinedProfile("DocumentConversion_Accuracy")
End Sub

Public Function RecognizeFrenchDocument(engine As IEngine, imagePath As String) As String
    Dim langParams = engine.CreateLanguageParams()
    langParams.Languages.Add("French")  ' Requires FrenchLanguage data files at runtime path

    Dim document = engine.CreateFRDocument()
    Try
        document.AddImageFile(imagePath, Nothing, Nothing)
        document.Process(Nothing)
        Return document.PlainText.Text
    Finally
        document.Close()
    End Try
End Function

using IronOcr;

// Single language — install IronOcr.Languages.French via NuGet first
var ocr = new IronTesseract();
ocr.Language = OcrLanguage.French;
var result = ocr.Read("french-document.jpg");
Console.WriteLine(result.Text);

// Multiple simultaneous languages — operator overload, no data file management
var multiOcr = new IronTesseract();
multiOcr.Language = OcrLanguage.French + OcrLanguage.German + OcrLanguage.English;
var multiResult = multiOcr.Read("multilingual-contract.jpg");
Console.WriteLine(multiResult.Text);

Imports IronOcr

' Single language — install IronOcr.Languages.French via NuGet first
Dim ocr As New IronTesseract()
ocr.Language = OcrLanguage.French
Dim result = ocr.Read("french-document.jpg")
Console.WriteLine(result.Text)

' Multiple simultaneous languages — operator overload, no data file management
Dim multiOcr As New IronTesseract()
multiOcr.Language = OcrLanguage.French + OcrLanguage.German + OcrLanguage.English
Dim multiResult = multiOcr.Read("multilingual-contract.jpg")
Console.WriteLine(multiResult.Text)

using FREngine;

public string ProcessMultiFrameTiff(IEngine engine, string tiffPath)
{
    var document = engine.CreateFRDocument();

    try
    {
        // Must add each frame individually — no automatic multi-frame handling
        // Page count requires reading the TIFF metadata before processing
        var imageInfo = engine.CreateImageInfo();
        imageInfo.LoadImageFile(tiffPath);
        int frameCount = imageInfo.FrameCount;

        for (int i = 0; i < frameCount; i++)
        {
            // Each frame added with its frame index via image processing params
            var imgParams = engine.CreateImageProcessingParams();
            imgParams.FrameIndex = i;
            document.AddImageFile(tiffPath, imgParams, null);
        }

        document.Process(null);
        return document.PlainText.Text;
    }
    finally
    {
        document.Close();
    }
}

Imports FREngine

Public Function ProcessMultiFrameTiff(engine As IEngine, tiffPath As String) As String
    Dim document = engine.CreateFRDocument()

    Try
        ' Must add each frame individually — no automatic multi-frame handling
        ' Page count requires reading the TIFF metadata before processing
        Dim imageInfo = engine.CreateImageInfo()
        imageInfo.LoadImageFile(tiffPath)
        Dim frameCount As Integer = imageInfo.FrameCount

        For i As Integer = 0 To frameCount - 1
            ' Each frame added with its frame index via image processing params
            Dim imgParams = engine.CreateImageProcessingParams()
            imgParams.FrameIndex = i
            document.AddImageFile(tiffPath, imgParams, Nothing)
        Next

        document.Process(Nothing)
        Return document.PlainText.Text
    Finally
        document.Close()
    End Try
End Function

using IronOcr;

// LoadImageFrames handles multi-frame TIFF automatically
using var input = new OcrInput();
input.LoadImageFrames("scanned-batch.tiff");

var ocr = new IronTesseract();
var result = ocr.Read(input);

// Per-page results accessible directly
foreach (var page in result.Pages)
{
    Console.WriteLine($"Frame {page.PageNumber}: {page.Text.Length} characters");
    Console.WriteLine(page.Text);
}

Imports IronOcr

' LoadImageFrames handles multi-frame TIFF automatically
Using input As New OcrInput()
    input.LoadImageFrames("scanned-batch.tiff")

    Dim ocr As New IronTesseract()
    Dim result = ocr.Read(input)

    ' Per-page results accessible directly
    For Each page In result.Pages
        Console.WriteLine($"Frame {page.PageNumber}: {page.Text.Length} characters")
        Console.WriteLine(page.Text)
    Next
End Using

using FREngine;
using System.Collections.Concurrent;
using System.Threading;

public class AbbyyBatchProcessor
{
    // Pool required because engine is not safely concurrent
    private readonly SemaphoreSlim _engineLock = new SemaphoreSlim(1, 1);
    private IEngine _engine;

    public async Task<Dictionary<string, string>> ProcessBatchAsync(string[] imagePaths)
    {
        var results = new ConcurrentDictionary<string, string>();

        // Must serialize — one document at a time through single engine
        foreach (var imagePath in imagePaths)
        {
            await _engineLock.WaitAsync();
            try
            {
                var document = _engine.CreateFRDocument();
                try
                {
                    document.AddImageFile(imagePath, null, null);
                    document.Process(null);
                    results[imagePath] = document.PlainText.Text;
                }
                finally
                {
                    document.Close();
                }
            }
            finally
            {
                _engineLock.Release();
            }
        }

        return new Dictionary<string, string>(results);
    }
}

Imports FREngine
Imports System.Collections.Concurrent
Imports System.Threading

Public Class AbbyyBatchProcessor
    ' Pool required because engine is not safely concurrent
    Private ReadOnly _engineLock As New SemaphoreSlim(1, 1)
    Private _engine As IEngine

    Public Async Function ProcessBatchAsync(imagePaths As String()) As Task(Of Dictionary(Of String, String))
        Dim results As New ConcurrentDictionary(Of String, String)()

        ' Must serialize — one document at a time through single engine
        For Each imagePath In imagePaths
            Await _engineLock.WaitAsync()
            Try
                Dim document = _engine.CreateFRDocument()
                Try
                    document.AddImageFile(imagePath, Nothing, Nothing)
                    document.Process(Nothing)
                    results(imagePath) = document.PlainText.Text
                Finally
                    document.Close()
                End Try
            Finally
                _engineLock.Release()
            End Try
        Next

        Return New Dictionary(Of String, String)(results)
    End Function
End Class

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

public class OcrBatchProcessor
{
    public Dictionary<string, string> ProcessBatch(string[] imagePaths)
    {
        var results = new ConcurrentDictionary<string, string>();

        // IronTesseract is thread-safe — one instance per thread, fully parallel
        Parallel.ForEach(imagePaths, imagePath =>
        {
            var ocr = new IronTesseract();  // Each thread owns its instance
            var result = ocr.Read(imagePath);
            results[imagePath] = result.Text;
        });

        return new Dictionary<string, string>(results);
    }
}

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

Public Class OcrBatchProcessor
    Public Function ProcessBatch(imagePaths As String()) As Dictionary(Of String, String)
        Dim results = New ConcurrentDictionary(Of String, String)()

        ' IronTesseract is thread-safe — one instance per thread, fully parallel
        Parallel.ForEach(imagePaths, Sub(imagePath)
                                         Dim ocr = New IronTesseract() ' Each thread owns its instance
                                         Dim result = ocr.Read(imagePath)
                                         results(imagePath) = result.Text
                                     End Sub)

        Return New Dictionary(Of String, String)(results)
    End Function
End Class

using FREngine;

public class AbbyyExporter
{
    private IEngine _engine;

    public void ExportToMultipleFormats(string imagePath, string outputDir)
    {
        var document = _engine.CreateFRDocument();

        try
        {
            document.AddImageFile(imagePath, null, null);
            document.Process(null);

            string baseName = Path.GetFileNameWithoutExtension(imagePath);

            // Export as plain text
            document.Export(
                Path.Combine(outputDir, baseName + ".txt"),
                FileExportFormatEnum.FEF_TextUnicodeDefaults,
                null
            );

            // Export as searchable PDF (requires PDF export params)
            var pdfParams = _engine.CreatePDFExportParams();
            pdfParams.Scenario = PDFExportScenarioEnum.PDES_Balanced;
            pdfParams.UseOriginalPaperSize = true;
            document.Export(
                Path.Combine(outputDir, baseName + ".pdf"),
                FileExportFormatEnum.FEF_PDF,
                pdfParams
            );

            // Export as DOCX
            var docxParams = _engine.CreateDOCXExportParams();
            document.Export(
                Path.Combine(outputDir, baseName + ".docx"),
                FileExportFormatEnum.FEF_DOCX,
                docxParams
            );
        }
        finally
        {
            document.Close();
        }
    }
}

Imports FREngine

Public Class AbbyyExporter
    Private _engine As IEngine

    Public Sub ExportToMultipleFormats(imagePath As String, outputDir As String)
        Dim document = _engine.CreateFRDocument()

        Try
            document.AddImageFile(imagePath, Nothing, Nothing)
            document.Process(Nothing)

            Dim baseName As String = Path.GetFileNameWithoutExtension(imagePath)

            ' Export as plain text
            document.Export(
                Path.Combine(outputDir, baseName & ".txt"),
                FileExportFormatEnum.FEF_TextUnicodeDefaults,
                Nothing
            )

            ' Export as searchable PDF (requires PDF export params)
            Dim pdfParams = _engine.CreatePDFExportParams()
            pdfParams.Scenario = PDFExportScenarioEnum.PDES_Balanced
            pdfParams.UseOriginalPaperSize = True
            document.Export(
                Path.Combine(outputDir, baseName & ".pdf"),
                FileExportFormatEnum.FEF_PDF,
                pdfParams
            )

            ' Export as DOCX
            Dim docxParams = _engine.CreateDOCXExportParams()
            document.Export(
                Path.Combine(outputDir, baseName & ".docx"),
                FileExportFormatEnum.FEF_DOCX,
                docxParams
            )
        Finally
            document.Close()
        End Try
    End Sub
End Class

using IronOcr;

public class OcrExporter
{
    public void ExportToMultipleFormats(string imagePath, string outputDir)
    {
        var ocr = new IronTesseract();
        var result = ocr.Read(imagePath);
        string baseName = Path.GetFileNameWithoutExtension(imagePath);

        // Plain text — direct property access
        File.WriteAllText(
            Path.Combine(outputDir, baseName + ".txt"),
            result.Text
        );

        // Searchable PDF — one method call, no parameter objects
        result.SaveAsSearchablePdf(
            Path.Combine(outputDir, baseName + ".pdf")
        );

        // hOCR format — for document management systems
        result.SaveAsHocrFile(
            Path.Combine(outputDir, baseName + ".hocr")
        );
    }
}

Imports IronOcr
Imports System.IO

Public Class OcrExporter
    Public Sub ExportToMultipleFormats(imagePath As String, outputDir As String)
        Dim ocr As New IronTesseract()
        Dim result = ocr.Read(imagePath)
        Dim baseName As String = Path.GetFileNameWithoutExtension(imagePath)

        ' Plain text — direct property access
        File.WriteAllText(
            Path.Combine(outputDir, baseName & ".txt"),
            result.Text
        )

        ' Searchable PDF — one method call, no parameter objects
        result.SaveAsSearchablePdf(
            Path.Combine(outputDir, baseName & ".pdf")
        )

        ' hOCR format — for document management systems
        result.SaveAsHocrFile(
            Path.Combine(outputDir, baseName & ".hocr")
        )
    End Sub
End Class

// Before: explicit Close in finally
var document = _engine.CreateFRDocument();
try { document.Process(null); }
finally { document.Close(); }

// After: using pattern on OcrInput
using var input = new OcrInput();
input.LoadImage(imagePath);
var result = new IronTesseract().Read(input);

Option Strict On



' Before: explicit Close in finally
Dim document = _engine.CreateFRDocument()
Try
    document.Process(Nothing)
Finally
    document.Close()
End Try

' After: using pattern on OcrInput
Using input As New OcrInput()
    input.LoadImage(imagePath)
    Dim result = New IronTesseract().Read(input)
End Using

// Speed-optimized
var ocr = new IronTesseract();
//Neinpreprocessing — fastest path
var result = ocr.Read("clean-document.jpg");

// Accuracy-optimized for difficult inputs
var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("degraded-scan.jpg");
input.Deskew();
input.DeNoise();
input.Contrast();
input.Binarize();
var result = ocr.Read(input);

Imports IronTesseract

' Speed-optimized
Dim ocr As New IronTesseract()
' Neinpreprocessing — fastest path
Dim result = ocr.Read("clean-document.jpg")

' Accuracy-optimized for difficult inputs
Dim ocr As New IronTesseract()
Using input As New OcrInput()
    input.LoadImage("degraded-scan.jpg")
    input.Deskew()
    input.DeNoise()
    input.Contrast()
    input.Binarize()
    Dim result = ocr.Read(input)
End Using

# Remove these CI/CD steps after migration:
# - name: Copy ABBYY license files
#   run: |
#     cp $SECRETS_PATH/ABBYY.lic $DEPLOY_PATH/License/
#     cp $SECRETS_PATH/ABBYY.key $DEPLOY_PATH/License/

# Add this instead (environment variable injection):
# - name: Set IronOCR license
#   env:
#     IRONOCR_LICENSE_KEY: ${{secrets.IRONOCR_LICENSE}}

IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE_KEY")
    ?? throw new InvalidOperationException("IRONOCR_LICENSE_KEY not set");

Imports System

IronOcr.License.LicenseKey = If(Environment.GetEnvironmentVariable("IRONOCR_LICENSE_KEY"), Throw New InvalidOperationException("IRONOCR_LICENSE_KEY not set"))

// Remove all of this:
// private readonly SemaphoreSlim _engineLock = new SemaphoreSlim(1, 1);
// await _engineLock.WaitAsync();
// try { ... } finally { _engineLock.Release(); }

// Replace with:
Parallel.ForEach(documents, doc =>
{
    var ocr = new IronTesseract(); // One per thread — no lock needed
    results[doc.Id] = ocr.Read(doc.Path).Text;
});

Imports System.Threading.Tasks

Parallel.ForEach(documents, Sub(doc)
    Dim ocr = New IronTesseract() ' One per thread — no lock needed
    results(doc.Id) = ocr.Read(doc.Path).Text
End Sub)

// Remove:
// var imageInfo = engine.CreateImageInfo();
// imageInfo.LoadImageFile(tiffPath);
// for (int i = 0; i < imageInfo.FrameCount; i++) { document.AddImageFile(...) }

// Replace with:
using var input = new OcrInput();
input.LoadImageFrames("multi-page-scan.tiff");
var result = new IronTesseract().Read(input);
// result.Pages contains one entry per TIFF frame

Imports IronOcr

' Remove:
' Dim imageInfo = engine.CreateImageInfo()
' imageInfo.LoadImageFile(tiffPath)
' For i As Integer = 0 To imageInfo.FrameCount - 1
'     document.AddImageFile(...)
' Next

' Replace with:
Using input As New OcrInput()
    input.LoadImageFrames("multi-page-scan.tiff")
    Dim result = New IronTesseract().Read(input)
    ' result.Pages contains one entry per TIFF frame
End Using

//IronOCR to searchable PDF (closest equivalent)
var result = new IronTesseract().Read(inputPath);
result.SaveAsSearchablePdf(outputPath.Replace(".docx", ".pdf"));

// Or extract structured text for downstream DOCX generation
foreach (var paragraph in result.Paragraphs)
{
    Console.WriteLine(paragraph.Text);
    // Write to DOCX via Open XML SDK or similar
}

Imports IronOcr

' IronOCR to searchable PDF (closest equivalent)
Dim result = New IronTesseract().Read(inputPath)
result.SaveAsSearchablePdf(outputPath.Replace(".docx", ".pdf"))

' Or extract structured text for downstream DOCX generation
For Each paragraph In result.Paragraphs
    Console.WriteLine(paragraph.Text)
    ' Write to DOCX via Open XML SDK or similar
Next

# Find all files using ABBYY namespaces
grep -r "using FREngine" --include="*.cs" .
grep -r "using ABBYY" --include="*.cs" .

# Find engine lifecycle patterns
grep -r "EngineLoader\|GetEngineObject\|LoadPredefinedProfile" --include="*.cs" .

# Find document lifecycle patterns
grep -r "CreateFRDocument\|document\.Close\|AddImageFile\|document\.Process" --include="*.cs" .

# Find language configuration
grep -r "CreateLanguageParams\|langParams\.Languages" --include="*.cs" .

# Find export calls
grep -r "FileExportFormatEnum\|CreatePDFExportParams\|document\.Export" --include="*.cs" .

# Find license file references in CI/CD and deployment scripts
grep -r "ABBYY\.lic\|ABBYY\.key" .