Jak wyodrębnić tekst arabski z obrazów za pomocą narzędzi OCR

// GdPicture: every frame = new integer ID = manual release required
using var pdf = new GdPicturePDF();
pdf.LoadFromFile("multi-page.tiff", false);

var frameIds = new List<int>();
try
{
    for (int i = 1; i <= pdf.GetPageCount(); i++)
    {
        pdf.SelectPage(i);
        int frameId = pdf.RenderPageToGdPictureImage(200, false); // new allocation
        if (frameId != 0) frameIds.Add(frameId);
        // ... OCR call here ...
    }
}
finally
{
    foreach (var id in frameIds) _imaging.ReleaseGdPictureImage(id); // manual per-frame release
}

Imports System.Collections.Generic

' GdPicture: every frame = new integer ID = manual release required
Using pdf As New GdPicturePDF()
    pdf.LoadFromFile("multi-page.tiff", False)

    Dim frameIds As New List(Of Integer)()
    Try
        For i As Integer = 1 To pdf.GetPageCount()
            pdf.SelectPage(i)
            Dim frameId As Integer = pdf.RenderPageToGdPictureImage(200, False) ' new allocation
            If frameId <> 0 Then frameIds.Add(frameId)
            ' ... OCR call here ...
        Next
    Finally
        For Each id In frameIds
            _imaging.ReleaseGdPictureImage(id) ' manual per-frame release
        Next
    End Try
End Using

// IronOCR: the using statement handles everything
using var input = new OcrInput();
input.LoadImageFrames("multi-page.tiff");
var result = new IronTesseract().Read(input);

Imports IronOcr

Dim input As New OcrInput()
Using input
    input.LoadImageFrames("multi-page.tiff")
    Dim result = New IronTesseract().Read(input)
End Using

dotnet remove package GdPicture.NET
dotnet remove package GdPicture.NET.OCR
dotnet remove package GdPicture.NET.PDF

// Before (GdPicture)
using GdPicture14;

// After (IronOCR)
using IronOcr;

Imports IronOcr

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

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

// Remove this
LicenseManager lm = new LicenseManager();
lm.RegisterKEY("GDPICTURE-LICENSE-KEY");

using GdPicture14;

public class GdPictureTiffProcessor
{
    private readonly GdPictureImaging _imaging;
    private readonly GdPictureOCR _ocr;

    public string ExtractTextFromTiff(string tiffPath)
    {
        var text = new StringBuilder();

        // Load TIFF through the imaging component
        int tiffId = _imaging.CreateGdPictureImageFromFile(tiffPath);

        if (tiffId == 0)
            throw new Exception($"TIFF load failed: {_imaging.GetStat()}");

        // Outer try: release the original TIFF handle
        try
        {
            int frameCount = _imaging.GetPageCount(tiffId);

            for (int i = 1; i <= frameCount; i++)
            {
                // Switch to frame — modifies the existing ID in place
                _imaging.SelectPage(tiffId, i);

                // Clone frame to a new image ID for OCR
                int frameId = _imaging.CloneImage(tiffId);

                if (frameId == 0) continue;

                // Inner try: release each cloned frame ID
                try
                {
                    _ocr.SetImage(frameId);
                    _ocr.Language = "eng";

                    string resultId = _ocr.RunOCR();

                    if (!string.IsNullOrEmpty(resultId))
                    {
                        text.AppendLine($"[Frame {i}] {_ocr.GetOCRResultText(resultId)}");
                    }
                }
                finally
                {
                    // Release cloned frame — critical for each iteration
                    _imaging.ReleaseGdPictureImage(frameId);
                }
            }
        }
        finally
        {
            // Release original TIFF handle
            _imaging.ReleaseGdPictureImage(tiffId);
        }

        return text.ToString();
    }
}

Imports GdPicture14
Imports System.Text

Public Class GdPictureTiffProcessor
    Private ReadOnly _imaging As GdPictureImaging
    Private ReadOnly _ocr As GdPictureOCR

    Public Function ExtractTextFromTiff(tiffPath As String) As String
        Dim text As New StringBuilder()

        ' Load TIFF through the imaging component
        Dim tiffId As Integer = _imaging.CreateGdPictureImageFromFile(tiffPath)

        If tiffId = 0 Then
            Throw New Exception($"TIFF load failed: {_imaging.GetStat()}")
        End If

        ' Outer try: release the original TIFF handle
        Try
            Dim frameCount As Integer = _imaging.GetPageCount(tiffId)

            For i As Integer = 1 To frameCount
                ' Switch to frame — modifies the existing ID in place
                _imaging.SelectPage(tiffId, i)

                ' Clone frame to a new image ID for OCR
                Dim frameId As Integer = _imaging.CloneImage(tiffId)

                If frameId = 0 Then Continue For

                ' Inner try: release each cloned frame ID
                Try
                    _ocr.SetImage(frameId)
                    _ocr.Language = "eng"

                    Dim resultId As String = _ocr.RunOCR()

                    If Not String.IsNullOrEmpty(resultId) Then
                        text.AppendLine($"[Frame {i}] {_ocr.GetOCRResultText(resultId)}")
                    End If
                Finally
                    ' Release cloned frame — critical for each iteration
                    _imaging.ReleaseGdPictureImage(frameId)
                End Try
            Next
        Finally
            ' Release original TIFF handle
            _imaging.ReleaseGdPictureImage(tiffId)
        End Try

        Return text.ToString()
    End Function
End Class

using IronOcr;

public class IronOcrTiffProcessor
{
    public string ExtractTextFromTiff(string tiffPath)
    {
        using var input = new OcrInput();
        input.LoadImageFrames(tiffPath);  // all frames loaded, all cleanup automatic

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

        // Per-frame text is available on result.Pages
        foreach (var page in result.Pages)
            Console.WriteLine($"[Frame {page.PageNumber}] {page.Text}");

        return result.Text;
    }
}

Imports IronOcr

Public Class IronOcrTiffProcessor
    Public Function ExtractTextFromTiff(tiffPath As String) As String
        Using input As New OcrInput()
            input.LoadImageFrames(tiffPath) ' all frames loaded, all cleanup automatic

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

            ' Per-frame text is available on result.Pages
            For Each page In result.Pages
                Console.WriteLine($"[Frame {page.PageNumber}] {page.Text}")
            Next

            Return result.Text
        End Using
    End Function
End Class

using GdPicture14;

public class GdPictureStreamOcr : IDisposable
{
    private readonly GdPictureImaging _imaging;
    private readonly GdPictureOCR _ocr;

    public GdPictureStreamOcr()
    {
        // Plugin initialization required before stream loading is possible
        var lm = new LicenseManager();
        lm.RegisterKEY("GDPICTURE-LICENSE-KEY");

        _imaging = new GdPictureImaging();
        _ocr = new GdPictureOCR();
        _ocr.ResourceFolder = @"C:\GdPicture\Resources\OCR"; // path must exist at runtime
    }

    public string ExtractTextFromStream(Stream documentStream)
    {
        // Load stream into imaging component to get an image ID
        int imageId = _imaging.CreateGdPictureImageFromStream(documentStream);

        if (imageId == 0)
            throw new Exception($"Stream load failed: {_imaging.GetStat()}");

        try
        {
            _ocr.SetImage(imageId);
            _ocr.Language = "eng";

            string resultId = _ocr.RunOCR();

            if (string.IsNullOrEmpty(resultId))
                throw new Exception($"OCR failed: {_ocr.GetStat()}");

            return _ocr.GetOCRResultText(resultId);
        }
        finally
        {
            _imaging.ReleaseGdPictureImage(imageId);
        }
    }

    public void Dispose()
    {
        _ocr?.Dispose();
        _imaging?.Dispose();
    }
}

IRON VB CONVERTER ERROR developers@ironsoftware.com

using IronOcr;

public class IronOcrStreamOcr
{
    public string ExtractTextFromStream(Stream documentStream)
    {
        using var input = new OcrInput();
        input.LoadImage(documentStream);  // stream accepted directly — no imaging component

        return new IronTesseract().Read(input).Text;
    }
}

Imports IronOcr

Public Class IronOcrStreamOcr
    Public Function ExtractTextFromStream(documentStream As Stream) As String
        Using input As New OcrInput()
            input.LoadImage(documentStream) ' stream accepted directly — no imaging component

            Return New IronTesseract().Read(input).Text
        End Using
    End Function
End Class

using GdPicture14;
using System.Threading.Tasks;

public class GdPictureAsyncWrapper
{
    private readonly GdPictureImaging _imaging;
    private readonly GdPictureOCR _ocr;
    private readonly SemaphoreSlim _lock = new SemaphoreSlim(1, 1);

    public async Task<string> ExtractTextAsync(string imagePath)
    {
        // Must acquire lock: GdPictureOCR is not thread-safe
        await _lock.WaitAsync();

        try
        {
            return await Task.Run(() =>
            {
                int imageId = _imaging.CreateGdPictureImageFromFile(imagePath);

                if (imageId == 0)
                    throw new Exception($"Load failed: {_imaging.GetStat()}");

                try
                {
                    _ocr.SetImage(imageId);
                    _ocr.Language = "eng";

                    string resultId = _ocr.RunOCR();

                    if (string.IsNullOrEmpty(resultId))
                        throw new Exception($"OCR failed: {_ocr.GetStat()}");

                    return _ocr.GetOCRResultText(resultId);
                }
                finally
                {
                    _imaging.ReleaseGdPictureImage(imageId);
                }
            });
        }
        finally
        {
            _lock.Release();
        }
    }
}

Imports GdPicture14
Imports System.Threading.Tasks

Public Class GdPictureAsyncWrapper
    Private ReadOnly _imaging As GdPictureImaging
    Private ReadOnly _ocr As GdPictureOCR
    Private ReadOnly _lock As New SemaphoreSlim(1, 1)

    Public Async Function ExtractTextAsync(imagePath As String) As Task(Of String)
        ' Must acquire lock: GdPictureOCR is not thread-safe
        Await _lock.WaitAsync()

        Try
            Return Await Task.Run(Function()
                                      Dim imageId As Integer = _imaging.CreateGdPictureImageFromFile(imagePath)

                                      If imageId = 0 Then
                                          Throw New Exception($"Load failed: {_imaging.GetStat()}")
                                      End If

                                      Try
                                          _ocr.SetImage(imageId)
                                          _ocr.Language = "eng"

                                          Dim resultId As String = _ocr.RunOCR()

                                          If String.IsNullOrEmpty(resultId) Then
                                              Throw New Exception($"OCR failed: {_ocr.GetStat()}")
                                          End If

                                          Return _ocr.GetOCRResultText(resultId)
                                      Finally
                                          _imaging.ReleaseGdPictureImage(imageId)
                                      End Try
                                  End Function)
        Finally
            _lock.Release()
        End Try
    End Function
End Class

using IronOcr;

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

    public async Task<string> ExtractTextAsync(string imagePath)
    {
        // ReadAsync is natively async — no Task.Run wrapper, no lock required
        var result = await _ocr.ReadAsync(imagePath);
        return result.Text;
    }

    public async Task<string> ExtractFromStreamAsync(Stream stream)
    {
        using var input = new OcrInput();
        input.LoadImage(stream);

        var result = await _ocr.ReadAsync(input);
        return result.Text;
    }
}

Imports IronOcr
Imports System.IO
Imports System.Threading.Tasks

Public Class IronOcrAsyncService
    Private ReadOnly _ocr As New IronTesseract()

    Public Async Function ExtractTextAsync(imagePath As String) As Task(Of String)
        ' ReadAsync is natively async — no Task.Run wrapper, no lock required
        Dim result = Await _ocr.ReadAsync(imagePath)
        Return result.Text
    End Function

    Public Async Function ExtractFromStreamAsync(stream As Stream) As Task(Of String)
        Using input As New OcrInput()
            input.LoadImage(stream)

            Dim result = Await _ocr.ReadAsync(input)
            Return result.Text
        End Using
    End Function
End Class

using GdPicture14;
using System.Collections.Concurrent;
using System.Threading.Tasks;

public class GdPictureParallelBatch
{
    private readonly string _resourceFolder = @"C:\GdPicture\Resources\OCR";

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

        // Each thread must have its own component instances
        Parallel.ForEach(imagePaths, imagePath =>
        {
            // Create per-thread instances — shared instances cause failures
            using var threadImaging = new GdPictureImaging();
            using var threadOcr = new GdPictureOCR();
            threadOcr.ResourceFolder = _resourceFolder;

            // Re-register license per thread (may be required depending on SDK version)
            var lm = new LicenseManager();
            lm.RegisterKEY("GDPICTURE-LICENSE-KEY");

            int imageId = threadImaging.CreateGdPictureImageFromFile(imagePath);

            if (imageId == 0)
            {
                results[imagePath] = $"ERROR: {threadImaging.GetStat()}";
                return;
            }

            try
            {
                threadOcr.SetImage(imageId);
                threadOcr.Language = "eng";

                string resultId = threadOcr.RunOCR();
                results[imagePath] = string.IsNullOrEmpty(resultId)
                    ? $"ERROR: {threadOcr.GetStat()}"
                    : threadOcr.GetOCRResultText(resultId);
            }
            finally
            {
                threadImaging.ReleaseGdPictureImage(imageId);
            }
        });

        return results;
    }
}

Imports GdPicture14
Imports System.Collections.Concurrent
Imports System.Threading.Tasks

Public Class GdPictureParallelBatch
    Private ReadOnly _resourceFolder As String = "C:\GdPicture\Resources\OCR"

    Public Function ProcessBatch(imagePaths As String()) As ConcurrentDictionary(Of String, String)
        Dim results As New ConcurrentDictionary(Of String, String)()

        ' Each thread must have its own component instances
        Parallel.ForEach(imagePaths, Sub(imagePath)
            ' Create per-thread instances — shared instances cause failures
            Using threadImaging As New GdPictureImaging()
                Using threadOcr As New GdPictureOCR()
                    threadOcr.ResourceFolder = _resourceFolder

                    ' Re-register license per thread (may be required depending on SDK version)
                    Dim lm As New LicenseManager()
                    lm.RegisterKEY("GDPICTURE-LICENSE-KEY")

                    Dim imageId As Integer = threadImaging.CreateGdPictureImageFromFile(imagePath)

                    If imageId = 0 Then
                        results(imagePath) = $"ERROR: {threadImaging.GetStat()}"
                        Return
                    End If

                    Try
                        threadOcr.SetImage(imageId)
                        threadOcr.Language = "eng"

                        Dim resultId As String = threadOcr.RunOCR()
                        results(imagePath) = If(String.IsNullOrEmpty(resultId), $"ERROR: {threadOcr.GetStat()}", threadOcr.GetOCRResultText(resultId))
                    Finally
                        threadImaging.ReleaseGdPictureImage(imageId)
                    End Try
                End Using
            End Using
        End Sub)

        Return results
    End Function
End Class

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

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

        // IronTesseract is thread-safe — one instance handles all threads
        var ocr = new IronTesseract();

        Parallel.ForEach(imagePaths, imagePath =>
        {
            try
            {
                results[imagePath] = ocr.Read(imagePath).Text;
            }
            catch (Exception ex)
            {
                results[imagePath] = $"ERROR: {ex.Message}";
            }
        });

        return results;
    }
}

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

Public Class IronOcrParallelBatch
    Public Function ProcessBatch(imagePaths As String()) As ConcurrentDictionary(Of String, String)
        Dim results As New ConcurrentDictionary(Of String, String)()

        ' IronTesseract is thread-safe — one instance handles all threads
        Dim ocr As New IronTesseract()

        Parallel.ForEach(imagePaths, Sub(imagePath)
            Try
                results(imagePath) = ocr.Read(imagePath).Text
            Catch ex As Exception
                results(imagePath) = $"ERROR: {ex.Message}"
            End Try
        End Sub)

        Return results
    End Function
End Class

using GdPicture14;

public class GdPictureByteArrayOcr
{
    private readonly GdPictureImaging _imaging;
    private readonly GdPictureOCR _ocr;

    public List<string> ExtractParagraphsFromBytes(byte[] imageBytes)
    {
        var paragraphs = new List<string>();

        // Byte array must go through MemoryStream to reach CreateGdPictureImageFromStream
        using var ms = new MemoryStream(imageBytes);
        int imageId = _imaging.CreateGdPictureImageFromStream(ms);

        if (imageId == 0)
            throw new Exception($"Byte array load failed: {_imaging.GetStat()}");

        try
        {
            _ocr.SetImage(imageId);
            _ocr.Language = "eng";

            string resultId = _ocr.RunOCR();

            if (string.IsNullOrEmpty(resultId))
                throw new Exception($"OCR failed: {_ocr.GetStat()}");

            // Paragraph-level data requires iterating block structure
            int blockCount = _ocr.GetOCRResultBlockCount(resultId);

            for (int b = 0; b < blockCount; b++)
            {
                var blockText = new StringBuilder();
                int lineCount = _ocr.GetOCRResultBlockLineCount(resultId, b);

                for (int l = 0; l < lineCount; l++)
                {
                    int wordCount = _ocr.GetOCRResultBlockLineWordCount(resultId, b, l);

                    for (int w = 0; w < wordCount; w++)
                    {
                        blockText.Append(_ocr.GetOCRResultBlockLineWordText(resultId, b, l, w));
                        blockText.Append(" ");
                    }
                }

                string text = blockText.ToString().Trim();
                if (!string.IsNullOrEmpty(text))
                    paragraphs.Add(text);
            }
        }
        finally
        {
            _imaging.ReleaseGdPictureImage(imageId);
        }

        return paragraphs;
    }
}

Imports GdPicture14
Imports System.IO
Imports System.Text

Public Class GdPictureByteArrayOcr
    Private ReadOnly _imaging As GdPictureImaging
    Private ReadOnly _ocr As GdPictureOCR

    Public Function ExtractParagraphsFromBytes(imageBytes As Byte()) As List(Of String)
        Dim paragraphs As New List(Of String)()

        ' Byte array must go through MemoryStream to reach CreateGdPictureImageFromStream
        Using ms As New MemoryStream(imageBytes)
            Dim imageId As Integer = _imaging.CreateGdPictureImageFromStream(ms)

            If imageId = 0 Then
                Throw New Exception($"Byte array load failed: {_imaging.GetStat()}")
            End If

            Try
                _ocr.SetImage(imageId)
                _ocr.Language = "eng"

                Dim resultId As String = _ocr.RunOCR()

                If String.IsNullOrEmpty(resultId) Then
                    Throw New Exception($"OCR failed: {_ocr.GetStat()}")
                End If

                ' Paragraph-level data requires iterating block structure
                Dim blockCount As Integer = _ocr.GetOCRResultBlockCount(resultId)

                For b As Integer = 0 To blockCount - 1
                    Dim blockText As New StringBuilder()
                    Dim lineCount As Integer = _ocr.GetOCRResultBlockLineCount(resultId, b)

                    For l As Integer = 0 To lineCount - 1
                        Dim wordCount As Integer = _ocr.GetOCRResultBlockLineWordCount(resultId, b, l)

                        For w As Integer = 0 To wordCount - 1
                            blockText.Append(_ocr.GetOCRResultBlockLineWordText(resultId, b, l, w))
                            blockText.Append(" "c)
                        Next
                    Next

                    Dim text As String = blockText.ToString().Trim()
                    If Not String.IsNullOrEmpty(text) Then
                        paragraphs.Add(text)
                    End If
                Next
            Finally
                _imaging.ReleaseGdPictureImage(imageId)
            End Try
        End Using

        Return paragraphs
    End Function
End Class

using IronOcr;

public class IronOcrByteArrayOcr
{
    public List<string> ExtractParagraphsFromBytes(byte[] imageBytes)
    {
        using var input = new OcrInput();
        input.LoadImage(imageBytes);  // byte array accepted directly

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

        // Paragraphs are a first-class typed collection
        return result.Paragraphs
            .Select(p => p.Text)
            .Where(t => !string.IsNullOrWhiteSpace(t))
            .ToList();
    }
}

Imports IronOcr

Public Class IronOcrByteArrayOcr
    Public Function ExtractParagraphsFromBytes(imageBytes As Byte()) As List(Of String)
        Using input As New OcrInput()
            input.LoadImage(imageBytes) ' byte array accepted directly

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

            ' Paragraphs are a first-class typed collection
            Return result.Paragraphs _
                .Select(Function(p) p.Text) _
                .Where(Function(t) Not String.IsNullOrWhiteSpace(t)) _
                .ToList()
        End Using
    End Function
End Class

grep -rn "ReleaseGdPictureImage\|imageId\|resultId" --include="*.cs" .

// Remove all of this
int imageId = _imaging.CreateGdPictureImageFromFile(path);
try
{
    _ocr.SetImage(imageId);
    string resultId = _ocr.RunOCR();
    return _ocr.GetOCRResultText(resultId);
}
finally
{
    _imaging.ReleaseGdPictureImage(imageId);
}

// Replace with
using var input = new OcrInput();
input.LoadImage(path);
return new IronTesseract().Read(input).Text;

' Remove all of this
Dim imageId As Integer = _imaging.CreateGdPictureImageFromFile(path)
Try
    _ocr.SetImage(imageId)
    Dim resultId As String = _ocr.RunOCR()
    Return _ocr.GetOCRResultText(resultId)
Finally
    _imaging.ReleaseGdPictureImage(imageId)
End Try

' Replace with
Using input As New OcrInput()
    input.LoadImage(path)
    Return New IronTesseract().Read(input).Text
End Using

# Remove the filesystem folder from deployment artifacts
# Add language NuGet packages to the project instead
:InstallCmd dotnet add package IronOcr.Languages.French, IronOcr.Languages.German

try
{
    var result = new IronTesseract().Read(imagePath);
    return result.Text;
}
catch (FileNotFoundException ex)
{
    _logger.LogError("Input file missing: {Path}", ex.FileName);
    throw;
}
catch (IronOcr.Exceptions.OcrException ex)
{
    _logger.LogError("OCR processing failed: {Message}", ex.Message);
    throw;
}

Imports IronOcr
Imports System.IO

Try
    Dim result = New IronTesseract().Read(imagePath)
    Return result.Text
Catch ex As FileNotFoundException
    _logger.LogError("Input file missing: {Path}", ex.FileName)
    Throw
Catch ex As IronOcr.Exceptions.OcrException
    _logger.LogError("OCR processing failed: {Message}", ex.Message)
    Throw
End Try

# Find all files with GdPicture namespace
grep -rln "using GdPicture" --include="*.cs" .

# After replacing, verify nothing remains
grep -rn "GdPicture14\|GdPictureOCR\|GdPictureImaging\|GdPicturePDF" --include="*.cs" .

using var input = new OcrInput();
input.LoadImage("scanned-document.tiff");
input.Deskew();        // no separate plugin license
input.DeNoise();
input.Contrast();

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

Imports IronOcr

Using input As New OcrInput()
    input.LoadImage("scanned-document.tiff")
    input.Deskew() ' no separate plugin license
    input.DeNoise()
    input.Contrast()

    Dim result = New IronTesseract().Read(input)
End Using

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

# Find all image ID creation points
grep -rn "CreateGdPictureImageFromFile\|CreateGdPictureImageFromStream\|RenderPageToGdPictureImage\|CloneImage" --include="*.cs" .

# Find all release calls — these map to using block boundaries
grep -rn "ReleaseGdPictureImage" --include="*.cs" .

# Find all resource folder assignments
grep -rn "ResourceFolder" --include="*.cs" .

# Find all OCR result ID accesses
grep -rn "RunOCR\|GetOCRResult\|resultId" --include="*.cs" .

# Find all GdPictureStatus checks
grep -rn "GdPictureStatus\|GetStat()" --include="*.cs" .

# Count GdPicture-dependent files
grep -rln "GdPicture14" --include="*.cs" . | wc -l