NET Maui에서 OCR을 수행하는 방법

// LEADTOOLS: Four namespaces, four packages, six steps before recognition
using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;
using Leadtools.Forms.DocumentWriters;

RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath)); // Step 1: two files on disk
var codecs = new RasterCodecs();                              // Step 2: codec layer
var engine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD); // Step 3: engine factory
engine.Startup(codecs, null, null, runtimePath);              // Step 4: blocking startup
// ... still need to create document, add page, call Recognize(), extract text

Imports Leadtools
Imports Leadtools.Ocr
Imports Leadtools.Codecs
Imports Leadtools.Forms.DocumentWriters

' LEADTOOLS: Four namespaces, four packages, six steps before recognition
RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath)) ' Step 1: two files on disk
Dim codecs As New RasterCodecs()                             ' Step 2: codec layer
Dim engine As IOcrEngine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD) ' Step 3: engine factory
engine.Startup(codecs, Nothing, Nothing, runtimePath)        ' Step 4: blocking startup
' ... still need to create document, add page, call Recognize(), extract text

// IronOCR: One namespace, one package, one line
using IronOcr;

IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";
var text = new IronTesseract().Read("document.jpg").Text;

Imports IronOcr

IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"
Dim text As String = New IronTesseract().Read("document.jpg").Text

dotnet remove package Leadtools
dotnet remove package Leadtools.Ocr
dotnet remove package Leadtools.Codecs
dotnet remove package Leadtools.Forms.DocumentWriters
dotnet remove package Leadtools.Pdf

// Before (LEADTOOLS)
using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;
using Leadtools.Forms.DocumentWriters;

// After (IronOCR)
using IronOcr;

Imports IronOcr

// Single line replaces the entire file-based license setup
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// Production pattern: pull from environment variable or secrets manager
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE");

Imports System

' Single line replaces the entire file-based license setup
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

' Production pattern: pull from environment variable or secrets manager
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE")

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

// Service class required purely to manage engine lifecycle
public class LeadtoolsOcrService : IDisposable
{
    private IOcrEngine _engine;
    private RasterCodecs _codecs;
    private readonly string _runtimePath;

    public LeadtoolsOcrService(string licPath, string keyPath, string runtimePath)
    {
        _runtimePath = runtimePath;

        // License setup — two files, both must be present
        RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath));

        // Codec layer — required before engine creation
        _codecs = new RasterCodecs();

        // Engine factory — engine type determines capability and cost
        _engine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD);

        // Blocking startup — loads runtime into memory (500–2000ms)
        _engine.Startup(_codecs, null, null, _runtimePath);
    }

    public bool IsReady => _engine?.IsStarted ?? false;

    public string Process(string imagePath)
    {
        if (!IsReady)
            throw new InvalidOperationException("Engine not started");

        using var image = _codecs.Load(imagePath);
        using var doc = _engine.DocumentManager.CreateDocument();
        var page = doc.Pages.AddPage(image, null);
        page.Recognize(null);
        return page.GetText(-1);
    }

    public void Dispose()
    {
        // Order is mandatory: Shutdown before Dispose
        if (_engine?.IsStarted == true)
            _engine.Shutdown();

        _engine?.Dispose();
        _codecs?.Dispose();
    }
}

Imports Leadtools
Imports Leadtools.Ocr
Imports Leadtools.Codecs
Imports System
Imports System.IO

' Service class required purely to manage engine lifecycle
Public Class LeadtoolsOcrService
    Implements IDisposable

    Private _engine As IOcrEngine
    Private _codecs As RasterCodecs
    Private ReadOnly _runtimePath As String

    Public Sub New(licPath As String, keyPath As String, runtimePath As String)
        _runtimePath = runtimePath

        ' License setup — two files, both must be present
        RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath))

        ' Codec layer — required before engine creation
        _codecs = New RasterCodecs()

        ' Engine factory — engine type determines capability and cost
        _engine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD)

        ' Blocking startup — loads runtime into memory (500–2000ms)
        _engine.Startup(_codecs, Nothing, Nothing, _runtimePath)
    End Sub

    Public ReadOnly Property IsReady As Boolean
        Get
            Return If(_engine?.IsStarted, False)
        End Get
    End Property

    Public Function Process(imagePath As String) As String
        If Not IsReady Then
            Throw New InvalidOperationException("Engine not started")
        End If

        Using image = _codecs.Load(imagePath)
            Using doc = _engine.DocumentManager.CreateDocument()
                Dim page = doc.Pages.AddPage(image, Nothing)
                page.Recognize(Nothing)
                Return page.GetText(-1)
            End Using
        End Using
    End Function

    Public Sub Dispose() Implements IDisposable.Dispose
        ' Order is mandatory: Shutdown before Dispose
        If _engine?.IsStarted = True Then
            _engine.Shutdown()
        End If

        _engine?.Dispose()
        _codecs?.Dispose()
    End Sub
End Class

using IronOcr;

// No lifecycle management needed — the service class becomes trivial
public class OcrService
{
    private readonly IronTesseract _ocr = new IronTesseract();

    // Always ready — no IsStarted check needed
    public string Process(string imagePath) => _ocr.Read(imagePath).Text;

    // No Dispose() needed for the engine
    // No Startup(), no Shutdown(), no codec layer
}

Imports IronOcr

' No lifecycle management needed — the service class becomes trivial
Public Class OcrService
    Private ReadOnly _ocr As New IronTesseract()

    ' Always ready — no IsStarted check needed
    Public Function Process(imagePath As String) As String
        Return _ocr.Read(imagePath).Text
    End Function

    ' No Dispose() needed for the engine
    ' No Startup(), no Shutdown(), no codec layer
End Class

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

public class LeadtoolsTiffBatchService
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    public List<string> ProcessMultiFrameTiff(string tiffPath)
    {
        var pageTexts = new List<string>();

        // Must query page count before iterating
        var info = _codecs.GetInformation(tiffPath, true);
        int frameCount = info.TotalPages;

        using var document = _engine.DocumentManager.CreateDocument();

        for (int frameNum = 1; frameNum <= frameCount; frameNum++)
        {
            // Load one frame at a time — must specify firstPage/lastPage
            using var frameImage = _codecs.Load(
                tiffPath,
                0,                            // bitsPerPixel
                CodecsLoadByteOrder.BgrOrGray,
                frameNum,                     // firstPage
                frameNum);                    // lastPage

            var page = document.Pages.AddPage(frameImage, null);
            page.Recognize(null);
            pageTexts.Add(page.GetText(-1));

            // GC pressure accumulates if disposal is missed on any frame
        }

        return pageTexts;
    }

    public Dictionary<string, List<string>> ProcessTiffDirectory(string directoryPath)
    {
        var results = new Dictionary<string, List<string>>();

        foreach (var tiffFile in Directory.GetFiles(directoryPath, "*.tiff"))
        {
            results[tiffFile] = ProcessMultiFrameTiff(tiffFile);

            // Manual GC between files to prevent memory growth
            GC.Collect();
            GC.WaitForPendingFinalizers();
        }

        return results;
    }
}

Imports Leadtools
Imports Leadtools.Ocr
Imports Leadtools.Codecs
Imports System.IO

Public Class LeadtoolsTiffBatchService
    Private ReadOnly _engine As IOcrEngine
    Private ReadOnly _codecs As RasterCodecs

    Public Function ProcessMultiFrameTiff(tiffPath As String) As List(Of String)
        Dim pageTexts As New List(Of String)()

        ' Must query page count before iterating
        Dim info = _codecs.GetInformation(tiffPath, True)
        Dim frameCount As Integer = info.TotalPages

        Using document = _engine.DocumentManager.CreateDocument()
            For frameNum As Integer = 1 To frameCount
                ' Load one frame at a time — must specify firstPage/lastPage
                Using frameImage = _codecs.Load(tiffPath, 0, CodecsLoadByteOrder.BgrOrGray, frameNum, frameNum)
                    Dim page = document.Pages.AddPage(frameImage, Nothing)
                    page.Recognize(Nothing)
                    pageTexts.Add(page.GetText(-1))

                    ' GC pressure accumulates if disposal is missed on any frame
                End Using
            Next
        End Using

        Return pageTexts
    End Function

    Public Function ProcessTiffDirectory(directoryPath As String) As Dictionary(Of String, List(Of String))
        Dim results As New Dictionary(Of String, List(Of String))()

        For Each tiffFile In Directory.GetFiles(directoryPath, "*.tiff")
            results(tiffFile) = ProcessMultiFrameTiff(tiffFile)

            ' Manual GC between files to prevent memory growth
            GC.Collect()
            GC.WaitForPendingFinalizers()
        Next

        Return results
    End Function
End Class

using IronOcr;

public class TiffBatchService
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public List<string> ProcessMultiFrameTiff(string tiffPath)
    {
        using var input = new OcrInput();
        input.LoadImageFrames(tiffPath);  // All frames loaded automatically

        var result = _ocr.Read(input);

        // Per-frame text available through result.Pages
        return result.Pages.Select(p => p.Text).ToList();
    }

    public Dictionary<string, List<string>> ProcessTiffDirectory(string directoryPath)
    {
        var results = new Dictionary<string, List<string>>();

        foreach (var tiffFile in Directory.GetFiles(directoryPath, "*.tiff"))
        {
            results[tiffFile] = ProcessMultiFrameTiff(tiffFile);
        }

        return results;
    }

    // Parallel processing across files — thread-safe out of the box
    public Dictionary<string, List<string>> ProcessTiffDirectoryParallel(string directoryPath)
    {
        var concurrentResults = new System.Collections.Concurrent.ConcurrentDictionary<string, List<string>>();
        var tiffFiles = Directory.GetFiles(directoryPath, "*.tiff");

        Parallel.ForEach(tiffFiles, tiffFile =>
        {
            using var input = new OcrInput();
            input.LoadImageFrames(tiffFile);
            var result = new IronTesseract().Read(input);
            concurrentResults[tiffFile] = result.Pages.Select(p => p.Text).ToList();
        });

        return new Dictionary<string, List<string>>(concurrentResults);
    }
}

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

Public Class TiffBatchService
    Private ReadOnly _ocr As New IronTesseract()

    Public Function ProcessMultiFrameTiff(tiffPath As String) As List(Of String)
        Using input As New OcrInput()
            input.LoadImageFrames(tiffPath) ' All frames loaded automatically

            Dim result = _ocr.Read(input)

            ' Per-frame text available through result.Pages
            Return result.Pages.Select(Function(p) p.Text).ToList()
        End Using
    End Function

    Public Function ProcessTiffDirectory(directoryPath As String) As Dictionary(Of String, List(Of String))
        Dim results As New Dictionary(Of String, List(Of String))()

        For Each tiffFile In Directory.GetFiles(directoryPath, "*.tiff")
            results(tiffFile) = ProcessMultiFrameTiff(tiffFile)
        Next

        Return results
    End Function

    ' Parallel processing across files — thread-safe out of the box
    Public Function ProcessTiffDirectoryParallel(directoryPath As String) As Dictionary(Of String, List(Of String))
        Dim concurrentResults As New ConcurrentDictionary(Of String, List(Of String))()
        Dim tiffFiles = Directory.GetFiles(directoryPath, "*.tiff")

        Parallel.ForEach(tiffFiles, Sub(tiffFile)
                                        Using input As New OcrInput()
                                            input.LoadImageFrames(tiffFile)
                                            Dim result = New IronTesseract().Read(input)
                                            concurrentResults(tiffFile) = result.Pages.Select(Function(p) p.Text).ToList()
                                        End Using
                                    End Sub)

        Return New Dictionary(Of String, List(Of String))(concurrentResults)
    End Function
End Class

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;
using Leadtools.Forms.DocumentWriters;

public class LeadtoolsDocumentWriterService
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    public void CreateSearchablePdfFromImages(string[] imagePaths, string outputPath)
    {
        using var document = _engine.DocumentManager.CreateDocument();

        foreach (var imagePath in imagePaths)
        {
            using var image = _codecs.Load(imagePath);
            var page = document.Pages.AddPage(image, null);
            page.Recognize(null);
        }

        // DocumentWriter configuration — four properties to set before save
        var pdfOptions = new PdfDocumentOptions
        {
            DocumentType = PdfDocumentType.Pdf,
            ImageOverText = true,     // Image layer visible, text layer searchable
            Linearized = false,
            Title = "Searchable Output"
        };

        // Apply options to the engine's writer instance
        _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions);

        // Save with format enum — the format must match the options set above
        document.Save(outputPath, DocumentFormat.Pdf, null);
    }

    public void CreateSearchablePdfFromPdf(string inputPdfPath, string outputPath)
    {
        var pdfInfo = _codecs.GetInformation(inputPdfPath, true);
        using var document = _engine.DocumentManager.CreateDocument();

        for (int i = 1; i <= pdfInfo.TotalPages; i++)
        {
            using var pageImage = _codecs.Load(inputPdfPath, 0,
                CodecsLoadByteOrder.BgrOrGray, i, i);

            var page = document.Pages.AddPage(pageImage, null);
            page.Recognize(null);
        }

        var pdfOptions = new PdfDocumentOptions
        {
            DocumentType = PdfDocumentType.Pdf,
            ImageOverText = true,
            Title = Path.GetFileNameWithoutExtension(inputPdfPath)
        };

        _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions);
        document.Save(outputPath, DocumentFormat.Pdf, null);
    }
}

Imports Leadtools
Imports Leadtools.Ocr
Imports Leadtools.Codecs
Imports Leadtools.Forms.DocumentWriters

Public Class LeadtoolsDocumentWriterService
    Private ReadOnly _engine As IOcrEngine
    Private ReadOnly _codecs As RasterCodecs

    Public Sub CreateSearchablePdfFromImages(imagePaths As String(), outputPath As String)
        Using document = _engine.DocumentManager.CreateDocument()

            For Each imagePath In imagePaths
                Using image = _codecs.Load(imagePath)
                    Dim page = document.Pages.AddPage(image, Nothing)
                    page.Recognize(Nothing)
                End Using
            Next

            ' DocumentWriter configuration — four properties to set before save
            Dim pdfOptions As New PdfDocumentOptions With {
                .DocumentType = PdfDocumentType.Pdf,
                .ImageOverText = True,     ' Image layer visible, text layer searchable
                .Linearized = False,
                .Title = "Searchable Output"
            }

            ' Apply options to the engine's writer instance
            _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions)

            ' Save with format enum — the format must match the options set above
            document.Save(outputPath, DocumentFormat.Pdf, Nothing)
        End Using
    End Sub

    Public Sub CreateSearchablePdfFromPdf(inputPdfPath As String, outputPath As String)
        Dim pdfInfo = _codecs.GetInformation(inputPdfPath, True)
        Using document = _engine.DocumentManager.CreateDocument()

            For i As Integer = 1 To pdfInfo.TotalPages
                Using pageImage = _codecs.Load(inputPdfPath, 0, CodecsLoadByteOrder.BgrOrGray, i, i)
                    Dim page = document.Pages.AddPage(pageImage, Nothing)
                    page.Recognize(Nothing)
                End Using
            Next

            Dim pdfOptions As New PdfDocumentOptions With {
                .DocumentType = PdfDocumentType.Pdf,
                .ImageOverText = True,
                .Title = Path.GetFileNameWithoutExtension(inputPdfPath)
            }

            _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions)
            document.Save(outputPath, DocumentFormat.Pdf, Nothing)
        End Using
    End Sub
End Class

using IronOcr;

public class SearchablePdfService
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public void CreateSearchablePdfFromImages(string[] imagePaths, string outputPath)
    {
        using var input = new OcrInput();
        foreach (var imagePath in imagePaths)
            input.LoadImage(imagePath);

        var result = _ocr.Read(input);
        result.SaveAsSearchablePdf(outputPath);  // DocumentWriter pipeline: gone
    }

    public void CreateSearchablePdfFromPdf(string inputPdfPath, string outputPath)
    {
        using var input = new OcrInput();
        input.LoadPdf(inputPdfPath);

        var result = _ocr.Read(input);
        result.SaveAsSearchablePdf(outputPath);
    }

    // Get bytes directly — useful for streaming responses in ASP.NET
    public byte[] CreateSearchablePdfBytes(string inputPdfPath)
    {
        using var input = new OcrInput();
        input.LoadPdf(inputPdfPath);
        return _ocr.Read(input).SaveAsSearchablePdfBytes();
    }
}

Imports IronOcr

Public Class SearchablePdfService
    Private ReadOnly _ocr As New IronTesseract()

    Public Sub CreateSearchablePdfFromImages(imagePaths As String(), outputPath As String)
        Using input As New OcrInput()
            For Each imagePath In imagePaths
                input.LoadImage(imagePath)
            Next

            Dim result = _ocr.Read(input)
            result.SaveAsSearchablePdf(outputPath) ' DocumentWriter pipeline: gone
        End Using
    End Sub

    Public Sub CreateSearchablePdfFromPdf(inputPdfPath As String, outputPath As String)
        Using input As New OcrInput()
            input.LoadPdf(inputPdfPath)

            Dim result = _ocr.Read(input)
            result.SaveAsSearchablePdf(outputPath)
        End Using
    End Sub

    ' Get bytes directly — useful for streaming responses in ASP.NET
    Public Function CreateSearchablePdfBytes(inputPdfPath As String) As Byte()
        Using input As New OcrInput()
            input.LoadPdf(inputPdfPath)
            Return _ocr.Read(input).SaveAsSearchablePdfBytes()
        End Using
    End Function
End Class

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

public class LeadtoolsFormFieldExtractor
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    // Invoice field extraction using named zones
    public InvoiceFields ExtractInvoiceFields(string invoicePath)
    {
        using var image = _codecs.Load(invoicePath);
        using var document = _engine.DocumentManager.CreateDocument();
        var page = document.Pages.AddPage(image, null);

        // Must clear auto-detected zones before adding custom ones
        page.Zones.Clear();

        // Zone definitions — index order matters for extraction
        var zoneDefinitions = new[]
        {
            new { Name = "InvoiceNumber", X = 450, Y = 80,  W = 200, H = 30 },
            new { Name = "InvoiceDate",   X = 450, Y = 115, W = 200, H = 30 },
            new { Name = "VendorName",    X = 50,  Y = 150, W = 300, H = 40 },
            new { Name = "TotalAmount",   X = 450, Y = 600, W = 200, H = 30 }
        };

        foreach (var def in zoneDefinitions)
        {
            var zone = new OcrZone
            {
                Bounds = new LeadRect(def.X, def.Y, def.W, def.H),
                ZoneType = OcrZoneType.Text,
                CharacterFilters = OcrZoneCharacterFilters.None,
                RecognitionModule = OcrZoneRecognitionModule.Auto
            };
            page.Zones.Add(zone);
        }

        page.Recognize(null);

        // Extract by index — must match insertion order exactly
        return new InvoiceFields
        {
            InvoiceNumber = page.Zones[0].Text?.Trim(),
            InvoiceDate   = page.Zones[1].Text?.Trim(),
            VendorName    = page.Zones[2].Text?.Trim(),
            TotalAmount   = page.Zones[3].Text?.Trim()
        };
    }
}

public class InvoiceFields
{
    public string InvoiceNumber { get; set; }
    public string InvoiceDate   { get; set; }
    public string VendorName    { get; set; }
    public string TotalAmount   { get; set; }
}

Imports Leadtools
Imports Leadtools.Ocr
Imports Leadtools.Codecs

Public Class LeadtoolsFormFieldExtractor
    Private ReadOnly _engine As IOcrEngine
    Private ReadOnly _codecs As RasterCodecs

    ' Invoice field extraction using named zones
    Public Function ExtractInvoiceFields(invoicePath As String) As InvoiceFields
        Using image = _codecs.Load(invoicePath)
            Using document = _engine.DocumentManager.CreateDocument()
                Dim page = document.Pages.AddPage(image, Nothing)

                ' Must clear auto-detected zones before adding custom ones
                page.Zones.Clear()

                ' Zone definitions — index order matters for extraction
                Dim zoneDefinitions = New() {
                    New With {.Name = "InvoiceNumber", .X = 450, .Y = 80, .W = 200, .H = 30},
                    New With {.Name = "InvoiceDate", .X = 450, .Y = 115, .W = 200, .H = 30},
                    New With {.Name = "VendorName", .X = 50, .Y = 150, .W = 300, .H = 40},
                    New With {.Name = "TotalAmount", .X = 450, .Y = 600, .W = 200, .H = 30}
                }

                For Each def In zoneDefinitions
                    Dim zone = New OcrZone With {
                        .Bounds = New LeadRect(def.X, def.Y, def.W, def.H),
                        .ZoneType = OcrZoneType.Text,
                        .CharacterFilters = OcrZoneCharacterFilters.None,
                        .RecognitionModule = OcrZoneRecognitionModule.Auto
                    }
                    page.Zones.Add(zone)
                Next

                page.Recognize(Nothing)

                ' Extract by index — must match insertion order exactly
                Return New InvoiceFields With {
                    .InvoiceNumber = page.Zones(0).Text?.Trim(),
                    .InvoiceDate = page.Zones(1).Text?.Trim(),
                    .VendorName = page.Zones(2).Text?.Trim(),
                    .TotalAmount = page.Zones(3).Text?.Trim()
                }
            End Using
        End Using
    End Function
End Class

Public Class InvoiceFields
    Public Property InvoiceNumber As String
    Public Property InvoiceDate As String
    Public Property VendorName As String
    Public Property TotalAmount As String
End Class

using IronOcr;

public class FormFieldExtractor
{
    private readonly IronTesseract _ocr = new IronTesseract();

    // Each field gets its own CropRectangle-scoped Read() call
    // No zone index management, no zone ordering dependency
    public InvoiceFields ExtractInvoiceFields(string invoicePath)
    {
        return new InvoiceFields
        {
            InvoiceNumber = ReadRegion(invoicePath, 450, 80,  200, 30),
            InvoiceDate   = ReadRegion(invoicePath, 450, 115, 200, 30),
            VendorName    = ReadRegion(invoicePath, 50,  150, 300, 40),
            TotalAmount   = ReadRegion(invoicePath, 450, 600, 200, 30)
        };
    }

    private string ReadRegion(string imagePath, int x, int y, int width, int height)
    {
        using var input = new OcrInput();
        input.LoadImage(imagePath, new CropRectangle(x, y, width, height));
        return _ocr.Read(input).Text.Trim();
    }

    // Batch: extract the same field from many invoices in parallel
    public Dictionary<string, string> ExtractInvoiceNumbersBatch(string[] invoicePaths)
    {
        var results = new System.Collections.Concurrent.ConcurrentDictionary<string, string>();

        Parallel.ForEach(invoicePaths, invoicePath =>
        {
            using var input = new OcrInput();
            input.LoadImage(invoicePath, new CropRectangle(450, 80, 200, 30));
            results[invoicePath] = new IronTesseract().Read(input).Text.Trim();
        });

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

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

Public Class FormFieldExtractor
    Private ReadOnly _ocr As New IronTesseract()

    ' Each field gets its own CropRectangle-scoped Read() call
    ' No zone index management, no zone ordering dependency
    Public Function ExtractInvoiceFields(invoicePath As String) As InvoiceFields
        Return New InvoiceFields With {
            .InvoiceNumber = ReadRegion(invoicePath, 450, 80, 200, 30),
            .InvoiceDate = ReadRegion(invoicePath, 450, 115, 200, 30),
            .VendorName = ReadRegion(invoicePath, 50, 150, 300, 40),
            .TotalAmount = ReadRegion(invoicePath, 450, 600, 200, 30)
        }
    End Function

    Private Function ReadRegion(imagePath As String, x As Integer, y As Integer, width As Integer, height As Integer) As String
        Using input As New OcrInput()
            input.LoadImage(imagePath, New CropRectangle(x, y, width, height))
            Return _ocr.Read(input).Text.Trim()
        End Using
    End Function

    ' Batch: extract the same field from many invoices in parallel
    Public Function ExtractInvoiceNumbersBatch(invoicePaths As String()) As Dictionary(Of String, String)
        Dim results As New ConcurrentDictionary(Of String, String)()

        Parallel.ForEach(invoicePaths, Sub(invoicePath)
                                           Using input As New OcrInput()
                                               input.LoadImage(invoicePath, New CropRectangle(450, 80, 200, 30))
                                               results(invoicePath) = New IronTesseract().Read(input).Text.Trim()
                                           End Using
                                       End Sub)

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

using Leadtools;
using Leadtools.Ocr;
using Leadtools.Codecs;

public class LeadtoolsStructuredExtractor
{
    private readonly IOcrEngine _engine;
    private readonly RasterCodecs _codecs;

    public List<WordLocation> ExtractWordsWithLocations(string imagePath)
    {
        var wordLocations = new List<WordLocation>();

        using var image = _codecs.Load(imagePath);
        using var document = _engine.DocumentManager.CreateDocument();
        var page = document.Pages.AddPage(image, null);
        page.Recognize(null);

        // Access words through the zone collection
        foreach (OcrZone zone in page.Zones)
        {
            foreach (OcrWord word in zone.Words)
            {
                wordLocations.Add(new WordLocation
                {
                    Text       = word.Value,
                    X          = word.Bounds.X,
                    Y          = word.Bounds.Y,
                    Width      = word.Bounds.Width,
                    Height     = word.Bounds.Height,
                    Confidence = word.Confidence
                });
            }
        }

        return wordLocations;
    }
}

public class WordLocation
{
    public string Text       { get; set; }
    public int    X          { get; set; }
    public int    Y          { get; set; }
    public int    Width      { get; set; }
    public int    Height     { get; set; }
    public int    Confidence { get; set; }
}

Imports Leadtools
Imports Leadtools.Ocr
Imports Leadtools.Codecs

Public Class LeadtoolsStructuredExtractor
    Private ReadOnly _engine As IOcrEngine
    Private ReadOnly _codecs As RasterCodecs

    Public Function ExtractWordsWithLocations(imagePath As String) As List(Of WordLocation)
        Dim wordLocations As New List(Of WordLocation)()

        Using image = _codecs.Load(imagePath)
            Using document = _engine.DocumentManager.CreateDocument()
                Dim page = document.Pages.AddPage(image, Nothing)
                page.Recognize(Nothing)

                ' Access words through the zone collection
                For Each zone As OcrZone In page.Zones
                    For Each word As OcrWord In zone.Words
                        wordLocations.Add(New WordLocation With {
                            .Text = word.Value,
                            .X = word.Bounds.X,
                            .Y = word.Bounds.Y,
                            .Width = word.Bounds.Width,
                            .Height = word.Bounds.Height,
                            .Confidence = word.Confidence
                        })
                    Next
                Next
            End Using
        End Using

        Return wordLocations
    End Function
End Class

Public Class WordLocation
    Public Property Text As String
    Public Property X As Integer
    Public Property Y As Integer
    Public Property Width As Integer
    Public Property Height As Integer
    Public Property Confidence As Integer
End Class

using IronOcr;

public class StructuredExtractor
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public List<WordLocation> ExtractWordsWithLocations(string imagePath)
    {
        var result = _ocr.Read(imagePath);

        // Five-level hierarchy: Pages > Paragraphs > Lines > Words > Characters
        return result.Pages
            .SelectMany(page => page.Paragraphs)
            .SelectMany(para => para.Lines)
            .SelectMany(line => line.Words)
            .Select(word => new WordLocation
            {
                Text       = word.Text,
                X          = word.X,
                Y          = word.Y,
                Width      = word.Width,
                Height     = word.Height,
                Confidence = (int)word.Confidence
            })
            .ToList();
    }

    // Paragraph-level extraction with position data
    public void PrintDocumentStructure(string imagePath)
    {
        var result = _ocr.Read(imagePath);
        Console.WriteLine($"Document confidence: {result.Confidence}%");

        foreach (var page in result.Pages)
        {
            Console.WriteLine($"Page {page.PageNumber}:");
            foreach (var paragraph in page.Paragraphs)
            {
                Console.WriteLine($"  Paragraph at ({paragraph.X}, {paragraph.Y}):");
                Console.WriteLine($"  {paragraph.Text}");
            }
        }
    }
}

Imports IronOcr

Public Class StructuredExtractor
    Private ReadOnly _ocr As New IronTesseract()

    Public Function ExtractWordsWithLocations(imagePath As String) As List(Of WordLocation)
        Dim result = _ocr.Read(imagePath)

        ' Five-level hierarchy: Pages > Paragraphs > Lines > Words > Characters
        Return result.Pages _
            .SelectMany(Function(page) page.Paragraphs) _
            .SelectMany(Function(para) para.Lines) _
            .SelectMany(Function(line) line.Words) _
            .Select(Function(word) New WordLocation With {
                .Text = word.Text,
                .X = word.X,
                .Y = word.Y,
                .Width = word.Width,
                .Height = word.Height,
                .Confidence = CInt(word.Confidence)
            }) _
            .ToList()
    End Function

    ' Paragraph-level extraction with position data
    Public Sub PrintDocumentStructure(imagePath As String)
        Dim result = _ocr.Read(imagePath)
        Console.WriteLine($"Document confidence: {result.Confidence}%")

        For Each page In result.Pages
            Console.WriteLine($"Page {page.PageNumber}:")
            For Each paragraph In page.Paragraphs
                Console.WriteLine($"  Paragraph at ({paragraph.X}, {paragraph.Y}):")
                Console.WriteLine($"  {paragraph.Text}")
            Next
        Next
    End Sub
End Class

// Remove this:
// RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath));

// Replace with this:
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE")
    ?? throw new InvalidOperationException("IRONOCR_LICENSE environment variable not set");

' Remove this:
' RasterSupport.SetLicense(licPath, File.ReadAllText(keyPath))

' Replace with this:
IronOcr.License.LicenseKey = If(Environment.GetEnvironmentVariable("IRONOCR_LICENSE"), Throw New InvalidOperationException("IRONOCR_LICENSE environment variable not set"))

// Remove the guard:
// if (!_engine.IsStarted)
//     throw new InvalidOperationException("Engine not started");

// IronTesseract is always ready — just call Read()
var result = _ocr.Read(imagePath);

// Remove this pattern:
// GC.Collect();
// GC.WaitForPendingFinalizers();

// Replace with standard using scope:
foreach (var filePath in filePaths)
{
    using var input = new OcrInput();
    input.LoadImage(filePath);
    var text = _ocr.Read(input).Text;
    // input disposed here — no accumulation
}

' Remove this pattern:
' GC.Collect()
' GC.WaitForPendingFinalizers()

' Replace with standard using scope:
For Each filePath In filePaths
    Using input As New OcrInput()
        input.LoadImage(filePath)
        Dim text = _ocr.Read(input).Text
        ' input disposed here — no accumulation
    End Using
Next

// Remove the options setup:
// var pdfOptions = new PdfDocumentOptions { ... };
// _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions);
// document.Save(outputPath, DocumentFormat.Pdf, null);

// Replace with:
result.SaveAsSearchablePdf(outputPath);

' Remove the options setup:
' Dim pdfOptions As New PdfDocumentOptions With { ... }
' _engine.DocumentWriterInstance.SetOptions(DocumentFormat.Pdf, pdfOptions)
' document.Save(outputPath, DocumentFormat.Pdf, Nothing)

' Replace with:
result.SaveAsSearchablePdf(outputPath)

// Each field is independent — reorder freely without breaking extraction
var invoiceNumber = ReadRegion(imagePath, 450, 80,  200, 30);
var invoiceDate   = ReadRegion(imagePath, 450, 115, 200, 30);
var vendorName    = ReadRegion(imagePath, 50,  150, 300, 40);
var totalAmount   = ReadRegion(imagePath, 450, 600, 200, 30);

' Each field is independent — reorder freely without breaking extraction
Dim invoiceNumber = ReadRegion(imagePath, 450, 80, 200, 30)
Dim invoiceDate = ReadRegion(imagePath, 450, 115, 200, 30)
Dim vendorName = ReadRegion(imagePath, 50, 150, 300, 40)
Dim totalAmount = ReadRegion(imagePath, 450, 600, 200, 30)

# Find all LEADTOOLS namespace imports
grep -rn "using Leadtools" --include="*.cs" .

# Find engine lifecycle calls
grep -rn "OcrEngineManager\|\.Startup(\|\.Shutdown()" --include="*.cs" .

# Find license file references
grep -rn "SetLicense\|LEADTOOLS\.LIC\|\.LIC\.KEY" --include="*.cs" .

# Find RasterCodecs usage
grep -rn "RasterCodecs\|_codecs\.Load\|GetInformation" --include="*.cs" .

# Find DocumentWriter usage
grep -rn "DocumentWriterInstance\|PdfDocumentOptions\|DocumentFormat\." --include="*.cs" .

# Find zone-based OCR
grep -rn "OcrZone\|page\.Zones\|LeadRect\|ZoneType" --include="*.cs" .

# Find GC workarounds to remove
grep -rn "GC\.Collect\|WaitForPendingFinalizers" --include="*.cs" .