IronOCRを使ったC#での文字認識・文字起こし進捗追跡の方法

using IronOcr;
using System;
using System.Diagnostics;

public class OcrProgressTracker
{
    private readonly IronTesseract _tesseract;
    private Stopwatch _stopwatch;
    private int _lastReportedPercent = 0;

    public OcrProgressTracker()
    {
        _tesseract = new IronTesseract();

        // Configure for optimal performance
        _tesseract.Language = OcrLanguage.EnglishBest;
        _tesseract.Configuration.ReadBarCodes = false;

        // Subscribe to progress event
        _tesseract.OcrProgress += OnOcrProgress;
    }

    private void OnOcrProgress(object sender, OcrProgressEventsArgs e)
    {
        // Only report significant progress changes (every 10%)
        if (e.ProgressPercent - _lastReportedPercent >= 10 || e.ProgressPercent == 100)
        {
            _lastReportedPercent = e.ProgressPercent;

            Console.WriteLine($"Progress: {e.ProgressPercent}%");
            Console.WriteLine($"Pages: {e.PagesComplete}/{e.TotalPages}");
            Console.WriteLine($"Elapsed: {e.Duration.TotalSeconds:F1}s");

            // Estimate remaining time
            if (e.ProgressPercent > 0 && e.ProgressPercent < 100)
            {
                var estimatedTotal = e.Duration.TotalSeconds / (e.ProgressPercent / 100.0);
                var remaining = estimatedTotal - e.Duration.TotalSeconds;
                Console.WriteLine($"Estimated remaining: {remaining:F1}s");
            }

            Console.WriteLine("---");
        }
    }

    public OcrResult ProcessDocument(string filePath)
    {
        _stopwatch = Stopwatch.StartNew();

        using var input = new OcrInput();
        input.LoadPdf(filePath);

        // Apply image filters for better accuracy
        input.Deskew();
        input.DeNoise();

        var result = _tesseract.Read(input);

        _stopwatch.Stop();
        Console.WriteLine($"Total processing time: {_stopwatch.Elapsed.TotalSeconds:F1}s");

        return result;
    }
}

Imports IronOcr
Imports System
Imports System.Diagnostics

Public Class OcrProgressTracker
    Private ReadOnly _tesseract As IronTesseract
    Private _stopwatch As Stopwatch
    Private _lastReportedPercent As Integer = 0

    Public Sub New()
        _tesseract = New IronTesseract()

        ' Configure for optimal performance
        _tesseract.Language = OcrLanguage.EnglishBest
        _tesseract.Configuration.ReadBarCodes = False

        ' Subscribe to progress event
        AddHandler _tesseract.OcrProgress, AddressOf OnOcrProgress
    End Sub

    Private Sub OnOcrProgress(sender As Object, e As OcrProgressEventsArgs)
        ' Only report significant progress changes (every 10%)
        If e.ProgressPercent - _lastReportedPercent >= 10 OrElse e.ProgressPercent = 100 Then
            _lastReportedPercent = e.ProgressPercent

            Console.WriteLine($"Progress: {e.ProgressPercent}%")
            Console.WriteLine($"Pages: {e.PagesComplete}/{e.TotalPages}")
            Console.WriteLine($"Elapsed: {e.Duration.TotalSeconds:F1}s")

            ' Estimate remaining time
            If e.ProgressPercent > 0 AndAlso e.ProgressPercent < 100 Then
                Dim estimatedTotal = e.Duration.TotalSeconds / (e.ProgressPercent / 100.0)
                Dim remaining = estimatedTotal - e.Duration.TotalSeconds
                Console.WriteLine($"Estimated remaining: {remaining:F1}s")
            End If

            Console.WriteLine("---")
        End If
    End Sub

    Public Function ProcessDocument(filePath As String) As OcrResult
        _stopwatch = Stopwatch.StartNew()

        Using input As New OcrInput()
            input.LoadPdf(filePath)

            ' Apply image filters for better accuracy
            input.Deskew()
            input.DeNoise()

            Dim result = _tesseract.Read(input)

            _stopwatch.Stop()
            Console.WriteLine($"Total processing time: {_stopwatch.Elapsed.TotalSeconds:F1}s")

            Return result
        End Using
    End Function
End Class

using System;
using System.Windows.Forms;
using IronOcr;

public partial class OcrForm : Form
{
    private IronTesseract _tesseract;
    private ProgressBar progressBar;
    private Label statusLabel;

    public OcrForm()
    {
        InitializeComponent();
        _tesseract = new IronTesseract();
        _tesseract.OcrProgress += UpdateProgress;
    }

    private void UpdateProgress(object sender, OcrProgressEventsArgs e)
    {
        // Ensure UI updates happen on the main thread
        if (InvokeRequired)
        {
            BeginInvoke(new Action(() => UpdateProgress(sender, e)));
            return;
        }

        progressBar.Value = e.ProgressPercent;
        statusLabel.Text = $"Processing page {e.PagesComplete} of {e.TotalPages}";

        // Show completion message
        if (e.ProgressPercent == 100)
        {
            MessageBox.Show($"OCR completed in {e.Duration.TotalSeconds:F1} seconds");
        }
    }
}

Imports System
Imports System.Windows.Forms
Imports IronOcr

Public Partial Class OcrForm
    Inherits Form

    Private _tesseract As IronTesseract
    Private progressBar As ProgressBar
    Private statusLabel As Label

    Public Sub New()
        InitializeComponent()
        _tesseract = New IronTesseract()
        AddHandler _tesseract.OcrProgress, AddressOf UpdateProgress
    End Sub

    Private Sub UpdateProgress(sender As Object, e As OcrProgressEventsArgs)
        ' Ensure UI updates happen on the main thread
        If InvokeRequired Then
            BeginInvoke(New Action(Sub() UpdateProgress(sender, e)))
            Return
        End If

        progressBar.Value = e.ProgressPercent
        statusLabel.Text = $"Processing page {e.PagesComplete} of {e.TotalPages}"

        ' Show completion message
        If e.ProgressPercent = 100 Then
            MessageBox.Show($"OCR completed in {e.Duration.TotalSeconds:F1} seconds")
        End If
    End Sub
End Class

using IronOcr;
using System;
using System.Threading;

public async Task ProcessLargeDocumentWithTimeout()
{
    var cts = new CancellationTokenSource();
    var tesseract = new IronTesseract();

    // Set a timeout of 5 minutes
    cts.CancelAfter(TimeSpan.FromMinutes(5));

    tesseract.OcrProgress += (s, e) =>
    {
        Console.WriteLine($"Progress: {e.ProgressPercent}% - Page {e.PagesComplete}/{e.TotalPages}");

        // Check if we should cancel based on progress
        if (e.Duration.TotalMinutes > 4 && e.ProgressPercent < 50)
        {
            Console.WriteLine("Processing too slow, cancelling...");
            cts.Cancel();
        }
    };

    try
    {
        using var input = new OcrInput();
        input.LoadPdf("large-document.pdf");

        var result = await Task.Run(() => 
            tesseract.Read(input, cts.Token), cts.Token);

        Console.WriteLine("OCR completed successfully");
    }
    catch (OperationCanceledException)
    {
        Console.WriteLine("OCR operation was cancelled");
    }
}

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

Public Async Function ProcessLargeDocumentWithTimeout() As Task
    Dim cts As New CancellationTokenSource()
    Dim tesseract As New IronTesseract()

    ' Set a timeout of 5 minutes
    cts.CancelAfter(TimeSpan.FromMinutes(5))

    AddHandler tesseract.OcrProgress, Sub(s, e)
                                          Console.WriteLine($"Progress: {e.ProgressPercent}% - Page {e.PagesComplete}/{e.TotalPages}")

                                          ' Check if we should cancel based on progress
                                          If e.Duration.TotalMinutes > 4 AndAlso e.ProgressPercent < 50 Then
                                              Console.WriteLine("Processing too slow, cancelling...")
                                              cts.Cancel()
                                          End If
                                      End Sub

    Try
        Using input As New OcrInput()
            input.LoadPdf("large-document.pdf")

            Dim result = Await Task.Run(Function() tesseract.Read(input, cts.Token), cts.Token)

            Console.WriteLine("OCR completed successfully")
        End Using
    Catch ex As OperationCanceledException
        Console.WriteLine("OCR operation was cancelled")
    End Try
End Function