Migrating from XImage.OCR to IronOCR

<PackageReference Include="RasterEdge.XImage.OCR" Version="12.4.0" />
<PackageReference Include="XImage.OCR.Language.English" Version="12.4.0" />
<PackageReference Include="XImage.OCR.Language.German" Version="12.4.0" />
<PackageReference Include="XImage.OCR.Language.French" Version="12.4.0" />
<PackageReference Include="XImage.OCR.Language.Spanish" Version="12.4.0" />
<PackageReference Include="XImage.OCR.Language.Italian" Version="12.4.0" />
<PackageReference Include="XImage.OCR.Language.Portuguese" Version="12.4.0" />
<PackageReference Include="XImage.OCR.Language.ChineseSimplified" Version="12.4.0" />
<PackageReference Include="XImage.OCR.Language.Japanese" Version="12.4.0" />
<PackageReference Include="XImage.OCR.Language.Korean" Version="12.4.0" />
<PackageReference Include="XImage.OCR.Language.Arabic" Version="12.4.0" />

<PackageReference Include="IronOcr" Version="2024.x.x" />

dotnet remove package RasterEdge.XImage.OCR
dotnet remove package XImage.OCR.Language.English
dotnet remove package XImage.OCR.Language.German
dotnet remove package XImage.OCR.Language.French
# Repeat for every language pack in your project

// Before (XImage.OCR)
using RasterEdge.XImage.OCR;
using RasterEdge.Imaging.Basic;

// 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")

// Requires: RasterEdge.XImage.OCR + one XImage.OCR.Language.* package per language
// Language strings must exactly match installed package names or OCR fails at runtime

RasterEdge.XImage.OCR.License.LicenseManager.SetLicense("your-ximage-license-key");

var ocrHandler = new OCRHandler();

// String codes — typo "enh" instead of "eng" silently fails or throws at runtime
ocrHandler.Languages = new[] { "eng", "deu", "fra", "spa", "ita" };

// Process returns a plain string — no structure, no confidence
string extractedText = ocrHandler.Process("document.png");
Console.WriteLine(extractedText);

' Requires: RasterEdge.XImage.OCR + one XImage.OCR.Language.* package per language
' Language strings must exactly match installed package names or OCR fails at runtime

RasterEdge.XImage.OCR.License.LicenseManager.SetLicense("your-ximage-license-key")

Dim ocrHandler As New OCRHandler()

' String codes — typo "enh" instead of "eng" silently fails or throws at runtime
ocrHandler.Languages = New String() {"eng", "deu", "fra", "spa", "ita"}

' Process returns a plain string — no structure, no confidence
Dim extractedText As String = ocrHandler.Process("document.png")
Console.WriteLine(extractedText)

// Requires: IronOcr (single package — all languages included)
IronOcr.License.LicenseKey = "YOUR-IRONOCR-LICENSE-KEY";

var ocr = new IronTesseract();

// Type-safe enum — compiler catches typos, no runtime surprises
ocr.Language = OcrLanguage.English + OcrLanguage.German +
               OcrLanguage.French + OcrLanguage.Spanish + OcrLanguage.Italian;

using var input = new OcrInput();
input.LoadImage("document.png");

var result = ocr.Read(input);
Console.WriteLine(result.Text);
Console.WriteLine($"Confidence: {result.Confidence}%");

Imports IronOcr

' Requires: IronOcr (single package — all languages included)
IronOcr.License.LicenseKey = "YOUR-IRONOCR-LICENSE-KEY"

Dim ocr As New IronTesseract()

' Type-safe enum — compiler catches typos, no runtime surprises
ocr.Language = OcrLanguage.English Or OcrLanguage.German Or OcrLanguage.French Or OcrLanguage.Spanish Or OcrLanguage.Italian

Using input As New OcrInput()
    input.LoadImage("document.png")

    Dim result = ocr.Read(input)
    Console.WriteLine(result.Text)
    Console.WriteLine($"Confidence: {result.Confidence}%")
End Using

// XImage.OCR: different handling per image source type
var ocrHandler = new OCRHandler();
ocrHandler.Language = "eng";

// File path — works directly
string resultFromFile = ocrHandler.Process("invoice.jpg");

// Byte array — must write to temp file first, then process
byte[] imageBytes = File.ReadAllBytes("invoice.jpg");
string tempPath = Path.GetTempFileName() + ".jpg";
File.WriteAllBytes(tempPath, imageBytes);
try
{
    string resultFromBytes = ocrHandler.Process(tempPath);
    Console.WriteLine(resultFromBytes);
}
finally
{
    File.Delete(tempPath);    // Manual cleanup — easy to forget
}

// Multi-page TIFF — must split frames manually
// No built-in TIFF frame iteration in base XImage.OCR

Imports System.IO

' XImage.OCR: different handling per image source type
Dim ocrHandler As New OCRHandler()
ocrHandler.Language = "eng"

' File path — works directly
Dim resultFromFile As String = ocrHandler.Process("invoice.jpg")

' Byte array — must write to temp file first, then process
Dim imageBytes As Byte() = File.ReadAllBytes("invoice.jpg")
Dim tempPath As String = Path.GetTempFileName() & ".jpg"
File.WriteAllBytes(tempPath, imageBytes)
Try
    Dim resultFromBytes As String = ocrHandler.Process(tempPath)
    Console.WriteLine(resultFromBytes)
Finally
    File.Delete(tempPath)    ' Manual cleanup — easy to forget
End Try

' Multi-page TIFF — must split frames manually
' No built-in TIFF frame iteration in base XImage.OCR

// IronOCR: unified OcrInput accepts all source types identically
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

var ocr = new IronTesseract();

// File path
using (var input = new OcrInput())
{
    input.LoadImage("invoice.jpg");
    var result = ocr.Read(input);
    Console.WriteLine($"From file: {result.Text}");
}

// Byte array — no temp file needed
byte[] imageBytes = File.ReadAllBytes("invoice.jpg");
using (var input = new OcrInput())
{
    input.LoadImage(imageBytes);
    var result = ocr.Read(input);
    Console.WriteLine($"From bytes: {result.Text}");
}

// Multi-page TIFF — all frames processed in one call
using (var input = new OcrInput())
{
    input.LoadImageFrames("scanned-archive.tiff");
    var result = ocr.Read(input);
    Console.WriteLine($"TIFF pages: {result.Pages.Count}");
    foreach (var page in result.Pages)
        Console.WriteLine($"Page {page.PageNumber}: {page.Text}");
}

Imports IronOcr

' IronOCR: unified OcrInput accepts all source types identically
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

Dim ocr As New IronTesseract()

' File path
Using input As New OcrInput()
    input.LoadImage("invoice.jpg")
    Dim result = ocr.Read(input)
    Console.WriteLine($"From file: {result.Text}")
End Using

' Byte array — no temp file needed
Dim imageBytes As Byte() = File.ReadAllBytes("invoice.jpg")
Using input As New OcrInput()
    input.LoadImage(imageBytes)
    Dim result = ocr.Read(input)
    Console.WriteLine($"From bytes: {result.Text}")
End Using

' Multi-page TIFF — all frames processed in one call
Using input As New OcrInput()
    input.LoadImageFrames("scanned-archive.tiff")
    Dim result = ocr.Read(input)
    Console.WriteLine($"TIFF pages: {result.Pages.Count}")
    For Each page In result.Pages
        Console.WriteLine($"Page {page.PageNumber}: {page.Text}")
    Next
End Using

// XImage.OCR: plain text output only
// Searchable PDF requires purchasing the RasterEdge PDF SDK separately

var ocrHandler = new OCRHandler();
ocrHandler.Language = "eng";

string plainText = ocrHandler.Process("scanned-contract.jpg");

// To produce a searchable PDF from this text, you would need:
// 1. Purchase RasterEdge PDF SDK (separate commercial license)
// 2. Create a PDF document programmatically
// 3. Embed the extracted text as invisible text layer over the image
// 4. Manage the PDF document lifecycle manually
// No built-in path from OCR result to searchable PDF in XImage.OCR alone
Console.WriteLine(plainText);

' XImage.OCR: plain text output only
' Searchable PDF requires purchasing the RasterEdge PDF SDK separately

Dim ocrHandler As New OCRHandler()
ocrHandler.Language = "eng"

Dim plainText As String = ocrHandler.Process("scanned-contract.jpg")

' To produce a searchable PDF from this text, you would need:
' 1. Purchase RasterEdge PDF SDK (separate commercial license)
' 2. Create a PDF document programmatically
' 3. Embed the extracted text as invisible text layer over the image
' 4. Manage the PDF document lifecycle manually
' No built-in path from OCR result to searchable PDF in XImage.OCR alone
Console.WriteLine(plainText)

// IronOCR: plain text, searchable PDF, and structured data from one result
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

var ocr = new IronTesseract();

using var input = new OcrInput();
input.LoadImage("scanned-contract.jpg");

var result = ocr.Read(input);

// Plain text
Console.WriteLine(result.Text);

// Searchable PDF — no extra package required
result.SaveAsSearchablePdf("searchable-contract.pdf");

// Structured data: paragraphs with bounding box coordinates
foreach (var page in result.Pages)
{
    foreach (var paragraph in page.Paragraphs)
    {
        Console.WriteLine($"Paragraph at ({paragraph.X}, {paragraph.Y}): {paragraph.Text}");
    }
}

// Per-word confidence for quality gating
var lowConfidenceWords = result.Pages
    .SelectMany(p => p.Words)
    .Where(w => w.Confidence < 70)
    .ToList();

Console.WriteLine($"Words below 70% confidence: {lowConfidenceWords.Count}");

Imports IronOcr

' IronOCR: plain text, searchable PDF, and structured data from one result
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

Dim ocr As New IronTesseract()

Using input As New OcrInput()
    input.LoadImage("scanned-contract.jpg")

    Dim result = ocr.Read(input)

    ' Plain text
    Console.WriteLine(result.Text)

    ' Searchable PDF — no extra package required
    result.SaveAsSearchablePdf("searchable-contract.pdf")

    ' Structured data: paragraphs with bounding box coordinates
    For Each page In result.Pages
        For Each paragraph In page.Paragraphs
            Console.WriteLine($"Paragraph at ({paragraph.X}, {paragraph.Y}): {paragraph.Text}")
        Next
    Next

    ' Per-word confidence for quality gating
    Dim lowConfidenceWords = result.Pages _
        .SelectMany(Function(p) p.Words) _
        .Where(Function(w) w.Confidence < 70) _
        .ToList()

    Console.WriteLine($"Words below 70% confidence: {lowConfidenceWords.Count}")
End Using

// XImage.OCR: one handler per thread — memory multiplies with concurrency
// 4 threads processing English documents: 4 x ~100MB = ~400MB for OCR alone
// 4 threads processing 5 languages: 4 x ~250MB = ~1GB just for OCR handlers

var results = new ConcurrentDictionary<string, string>();
string[] documentPaths = Directory.GetFiles("./incoming", "*.png");

Parallel.ForEach(documentPaths,
    new ParallelOptions { MaxDegreeOfParallelism = 4 },
    documentPath =>
    {
        // Each thread must create and dispose its own handler
        var ocrHandler = new OCRHandler();
        ocrHandler.Language = "eng";

        try
        {
            string text = ocrHandler.Process(documentPath);
            results[documentPath] = text;
        }
        finally
        {
            // Manual disposal required — no using statement support shown
            ocrHandler.Dispose();
        }
    });

foreach (var kvp in results)
    Console.WriteLine($"{Path.GetFileName(kvp.Key)}: {kvp.Value.Length} chars");

Imports System.Collections.Concurrent
Imports System.IO
Imports System.Threading.Tasks

' XImage.OCR: one handler per thread — memory multiplies with concurrency
' 4 threads processing English documents: 4 x ~100MB = ~400MB for OCR alone
' 4 threads processing 5 languages: 4 x ~250MB = ~1GB just for OCR handlers

Dim results As New ConcurrentDictionary(Of String, String)()
Dim documentPaths As String() = Directory.GetFiles("./incoming", "*.png")

Parallel.ForEach(documentPaths,
    New ParallelOptions With {.MaxDegreeOfParallelism = 4},
    Sub(documentPath)
        ' Each thread must create and dispose its own handler
        Dim ocrHandler As New OCRHandler()
        ocrHandler.Language = "eng"

        Try
            Dim text As String = ocrHandler.Process(documentPath)
            results(documentPath) = text
        Finally
            ' Manual disposal required — no using statement support shown
            ocrHandler.Dispose()
        End Try
    End Sub)

For Each kvp In results
    Console.WriteLine($"{Path.GetFileName(kvp.Key)}: {kvp.Value.Length} chars")
Next

// IronOCR: single IronTesseract instance shared across all threads
// Memory stays flat regardless of thread count
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

var ocr = new IronTesseract();    // Create once outside the parallel loop
var results = new ConcurrentDictionary<string, string>();
string[] documentPaths = Directory.GetFiles("./incoming", "*.png");

Parallel.ForEach(documentPaths, documentPath =>
{
    // OcrInput is created per thread — IronTesseract instance is shared
    using var input = new OcrInput();
    input.LoadImage(documentPath);
    input.Deskew();     // Preprocessing runs per-document, not per-thread engine
    input.DeNoise();

    var result = ocr.Read(input);
    results[documentPath] = result.Text;
});

foreach (var kvp in results)
    Console.WriteLine($"{Path.GetFileName(kvp.Key)}: {kvp.Value.Length} chars");

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

' IronOCR: single IronTesseract instance shared across all threads
' Memory stays flat regardless of thread count
License.LicenseKey = "YOUR-LICENSE-KEY"

Dim ocr As New IronTesseract() ' Create once outside the parallel loop
Dim results As New ConcurrentDictionary(Of String, String)()
Dim documentPaths As String() = Directory.GetFiles("./incoming", "*.png")

Parallel.ForEach(documentPaths, Sub(documentPath)
                                    ' OcrInput is created per thread — IronTesseract instance is shared
                                    Using input As New OcrInput()
                                        input.LoadImage(documentPath)
                                        input.Deskew() ' Preprocessing runs per-document, not per-thread engine
                                        input.DeNoise()

                                        Dim result = ocr.Read(input)
                                        results(documentPath) = result.Text
                                    End Using
                                End Sub)

For Each kvp In results
    Console.WriteLine($"{Path.GetFileName(kvp.Key)}: {kvp.Value.Length} chars")
Next

// XImage.OCR: text only — barcodes require a separate library and second pass

var ocrHandler = new OCRHandler();
ocrHandler.Language = "eng";

// Pass 1: text extraction with XImage.OCR
string documentText = ocrHandler.Process("warehouse-label.png");
Console.WriteLine($"Text: {documentText}");

// Pass 2: barcode reading requires a completely separate library
// e.g., ZXing.Net, Dynamsoft Barcode Reader, or another commercial SDK
// - Additional NuGet package required
// - Additional license required
// - Additional code for result merging
// No combined text + barcode result object exists in XImage.OCR

' XImage.OCR: text only — barcodes require a separate library and second pass

Dim ocrHandler As New OCRHandler()
ocrHandler.Language = "eng"

' Pass 1: text extraction with XImage.OCR
Dim documentText As String = ocrHandler.Process("warehouse-label.png")
Console.WriteLine($"Text: {documentText}")

' Pass 2: barcode reading requires a completely separate library
' e.g., ZXing.Net, Dynamsoft Barcode Reader, or another commercial SDK
' - Additional NuGet package required
' - Additional license required
' - Additional code for result merging
' No combined text + barcode result object exists in XImage.OCR

// IronOCR: text and barcodes from a single Read() call
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

var ocr = new IronTesseract();
ocr.Configuration.ReadBarCodes = true;    // Enable barcode extraction

using var input = new OcrInput();
input.LoadImage("warehouse-label.png");

var result = ocr.Read(input);

// Text and barcodes in one result object
Console.WriteLine($"Document text:\n{result.Text}");

if (result.Barcodes.Any())
{
    Console.WriteLine($"\nBarcodes found: {result.Barcodes.Count}");
    foreach (var barcode in result.Barcodes)
        Console.WriteLine($"  [{barcode.BarcodeType}] {barcode.Value}");
}

Imports IronOcr

' IronOCR: text and barcodes from a single Read() call
License.LicenseKey = "YOUR-LICENSE-KEY"

Dim ocr As New IronTesseract()
ocr.Configuration.ReadBarCodes = True ' Enable barcode extraction

Using input As New OcrInput()
    input.LoadImage("warehouse-label.png")

    Dim result = ocr.Read(input)

    ' Text and barcodes in one result object
    Console.WriteLine($"Document text:{vbCrLf}{result.Text}")

    If result.Barcodes.Any() Then
        Console.WriteLine($"{vbCrLf}Barcodes found: {result.Barcodes.Count}")
        For Each barcode In result.Barcodes
            Console.WriteLine($"  [{barcode.BarcodeType}] {barcode.Value}")
        Next
    End If
End Using

// Before (XImage.OCR) — typos compile fine, fail at runtime
ocrHandler.Languages = new[] { "eng", "deu", "fra" };

// After (IronOCR) — typos are compile errors
ocr.Language = OcrLanguage.English + OcrLanguage.German + OcrLanguage.French;

// Before (XImage.OCR) — temp file required
string tempPath = Path.GetTempFileName() + ".png";
File.WriteAllBytes(tempPath, imageBytes);
try { text = ocrHandler.Process(tempPath); }
finally { File.Delete(tempPath); }

// After (IronOCR) — direct byte array loading, no disk I/O
using var input = new OcrInput();
input.LoadImage(imageBytes);
var result = ocr.Read(input);
string text = result.Text;

Imports System.IO
Imports IronOcr

' Before (XImage.OCR) — temp file required
Dim tempPath As String = Path.GetTempFileName() & ".png"
File.WriteAllBytes(tempPath, imageBytes)
Try
    text = ocrHandler.Process(tempPath)
Finally
    File.Delete(tempPath)
End Try

' After (IronOCR) — direct byte array loading, no disk I/O
Using input As New OcrInput()
    input.LoadImage(imageBytes)
    Dim result = ocr.Read(input)
    Dim text As String = result.Text
End Using

// Single instance — shared safely across all threads
var ocr = new IronTesseract();
ocr.Language = OcrLanguage.English + OcrLanguage.German +
               OcrLanguage.French + OcrLanguage.Spanish + OcrLanguage.Italian;

Parallel.ForEach(documentPaths, path =>
{
    using var input = new OcrInput();    // Per-document, lightweight
    input.LoadImage(path);
    var result = ocr.Read(input);        // Thread-safe call on shared instance
    ProcessResult(result.Text);
});

Imports IronOcr
Imports System.Threading.Tasks

' Single instance — shared safely across all threads
Dim ocr As New IronTesseract()
ocr.Language = OcrLanguage.English + OcrLanguage.German + OcrLanguage.French + OcrLanguage.Spanish + OcrLanguage.Italian

Parallel.ForEach(documentPaths, Sub(path)
    Using input As New OcrInput() ' Per-document, lightweight
        input.LoadImage(path)
        Dim result = ocr.Read(input) ' Thread-safe call on shared instance
        ProcessResult(result.Text)
    End Using
End Sub)

# In your CI pipeline — verify single package restore
dotnet restore
dotnet list package | grep IronOcr

# No version coordination logic needed — only one package to check

var result = ocr.Read(input);

// Direct access to structured data — no string manipulation
foreach (var page in result.Pages)
{
    foreach (var line in page.Lines)
    {
        // Line text, bounding box, and per-word data all available
        Console.WriteLine($"Line [{line.X},{line.Y}]: {line.Text}");

        foreach (var word in line.Words)
            Console.WriteLine($"  Word '{word.Text}' confidence: {word.Confidence}%");
    }
}

Dim result = ocr.Read(input)

' Direct access to structured data — no string manipulation
For Each page In result.Pages
    For Each line In page.Lines
        ' Line text, bounding box, and per-word data all available
        Console.WriteLine($"Line [{line.X},{line.Y}]: {line.Text}")

        For Each word In line.Words
            Console.WriteLine($"  Word '{word.Text}' confidence: {word.Confidence}%")
        Next
    Next
Next

# Find all XImage.OCR namespace imports
grep -r "RasterEdge.XImage.OCR\|Yiigo.Image.Ocr\|XImage.OCR" --include="*.cs" .

# Find all OCRHandler usages
grep -r "OCRHandler\|ocrHandler" --include="*.cs" .

# Find all string-based language assignments
grep -r "\.Language\s*=\s*\"" --include="*.cs" .
grep -r "\.Languages\s*=\s*new\[\]" --include="*.cs" .

# Find all XImage.OCR package references in project files
grep -r "RasterEdge.XImage.OCR\|XImage.OCR.Language" --include="*.csproj" .

# Count distinct language packs installed
grep "XImage.OCR.Language" --include="*.csproj" -r . | wc -l