Cómo depurar el reconocimiento de texto OCR en C# con IronOCR

using IronOcr;
using IronOcr.Exceptions;

var ocr = new IronTesseract();

try
{
    using var input = new OcrInput();
    input.LoadPdf("invoice_scan.pdf");

    OcrResult result = ocr.Read(input);
    Console.WriteLine($"Text: {result.Text}");
    Console.WriteLine($"Confidence: {result.Confidence:P1}");
}
catch (IronOcrInputException ex)
{
    // File could not be loaded — corrupt, locked, or unsupported format
    Console.Error.WriteLine($"Input error: {ex.Message}");
}
catch (IronOcrDictionaryException ex)
{
    // Language pack missing — common in containerized deployments
    Console.Error.WriteLine($"Language pack error: {ex.Message}");
}
catch (IronOcrNativeException ex) when (ex.Message.Contains("AVX"))
{
    // CPU does not support AVX instructions
    Console.Error.WriteLine($"Hardware incompatibility: {ex.Message}");
}
catch (IronOcrLicensingException)
{
    Console.Error.WriteLine("License key is missing or invalid.");
}
catch (IronOcrProductException ex)
{
    // Catch-all for other IronOCR engine errors
    Console.Error.WriteLine($"OCR engine error: {ex.Message}");
    Console.Error.WriteLine($"Stack trace: {ex.StackTrace}");
}

Imports IronOcr
Imports IronOcr.Exceptions

Dim ocr As New IronTesseract()

Try
    Using input As New OcrInput()
        input.LoadPdf("invoice_scan.pdf")

        Dim result As OcrResult = ocr.Read(input)
        Console.WriteLine($"Text: {result.Text}")
        Console.WriteLine($"Confidence: {result.Confidence:P1}")
    End Using
Catch ex As IronOcrInputException
    ' File could not be loaded — corrupt, locked, or unsupported format
    Console.Error.WriteLine($"Input error: {ex.Message}")
Catch ex As IronOcrDictionaryException
    ' Language pack missing — common in containerized deployments
    Console.Error.WriteLine($"Language pack error: {ex.Message}")
Catch ex As IronOcrNativeException When ex.Message.Contains("AVX")
    ' CPU does not support AVX instructions
    Console.Error.WriteLine($"Hardware incompatibility: {ex.Message}")
Catch ex As IronOcrLicensingException
    Console.Error.WriteLine("License key is missing or invalid.")
Catch ex As IronOcrProductException
    ' Catch-all for other IronOCR engine errors
    Console.Error.WriteLine($"OCR engine error: {ex.Message}")
    Console.Error.WriteLine($"Stack trace: {ex.StackTrace}")
End Try

using IronOcr;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadImage("receipt.png");

OcrResult result = ocr.Read(input);
double confidence = result.Confidence;

Console.WriteLine($"Overall confidence: {confidence:P1}");

// Threshold-gated decision
if (confidence >= 0.90)
{
    Console.WriteLine("ACCEPT — high confidence, processing result.");
    ProcessResult(result.Text);
}
else if (confidence >= 0.70)
{
    Console.WriteLine("FLAG — moderate confidence, queuing for review.");
    QueueForReview(result.Text, confidence);
}
else
{
    Console.WriteLine("REJECT — low confidence, logging for investigation.");
    LogRejection("receipt.png", confidence);
}

// Drill into per-page and per-word confidence for diagnostics
foreach (var page in result.Pages)
{
    Console.WriteLine($"  Page {page.PageNumber}: {page.Confidence:P1}");

    var lowConfidenceWords = page.Words
        .Where(w => w.Confidence < 0.70)
        .ToList();

    foreach (var word in lowConfidenceWords)
    {
        Console.WriteLine($"    Low-confidence word: \"{word.Text}\" ({word.Confidence:P1})");
    }
}

Imports IronOcr

Dim ocr As New IronTesseract()
Using input As New OcrInput()
    input.LoadImage("receipt.png")

    Dim result As OcrResult = ocr.Read(input)
    Dim confidence As Double = result.Confidence

    Console.WriteLine($"Overall confidence: {confidence:P1}")

    ' Threshold-gated decision
    If confidence >= 0.9 Then
        Console.WriteLine("ACCEPT — high confidence, processing result.")
        ProcessResult(result.Text)
    ElseIf confidence >= 0.7 Then
        Console.WriteLine("FLAG — moderate confidence, queuing for review.")
        QueueForReview(result.Text, confidence)
    Else
        Console.WriteLine("REJECT — low confidence, logging for investigation.")
        LogRejection("receipt.png", confidence)
    End If

    ' Drill into per-page and per-word confidence for diagnostics
    For Each page In result.Pages
        Console.WriteLine($"  Page {page.PageNumber}: {page.Confidence:P1}")

        Dim lowConfidenceWords = page.Words _
            .Where(Function(w) w.Confidence < 0.7) _
            .ToList()

        For Each word In lowConfidenceWords
            Console.WriteLine($"    Low-confidence word: ""{word.Text}"" ({word.Confidence:P1})")
        Next
    Next
End Using

using IronOcr;

var ocr = new IronTesseract();

ocr.OcrProgress += (sender, e) =>
{
    Console.WriteLine(
        $"[OCR] {e.ProgressPercent}% complete | " +
        $"Page {e.PagesComplete}/{e.TotalPages} | " +
        $"Elapsed: {e.Duration.TotalSeconds:F1}s"
    );
};

using var input = new OcrInput();
input.LoadPdf("quarterly_report.pdf");

OcrResult result = ocr.Read(input);
Console.WriteLine($"Finished in {result.Pages.Count()} pages, confidence: {result.Confidence:P1}");

Imports IronOcr

Dim ocr = New IronTesseract()

AddHandler ocr.OcrProgress, Sub(sender, e)
    Console.WriteLine(
        $"[OCR] {e.ProgressPercent}% complete | " &
        $"Page {e.PagesComplete}/{e.TotalPages} | " &
        $"Elapsed: {e.Duration.TotalSeconds:F1}s"
    )
End Sub

Using input As New OcrInput()
    input.LoadPdf("quarterly_report.pdf")

    Dim result As OcrResult = ocr.Read(input)
    Console.WriteLine($"Finished in {result.Pages.Count()} pages, confidence: {result.Confidence:P1}")
End Using

using IronOcr;
using IronOcr.Exceptions;

var ocr = new IronTesseract();
Installation.LogFilePath = "batch_debug.log";
Installation.LoggingMode = Installation.LoggingModes.File;

string[] files = Directory.GetFiles("scans/", "*.pdf");
int succeeded = 0, failed = 0;
double totalConfidence = 0;
var failures = new List<(string File, string Error)>();

foreach (string file in files)
{
    try
    {
        using var input = new OcrInput();
        input.LoadPdf(file);

        OcrResult result = ocr.Read(input);
        totalConfidence += result.Confidence;
        succeeded++;

        Console.WriteLine($"OK: {Path.GetFileName(file)} — {result.Confidence:P1}");
    }
    catch (IronOcrInputException ex)
    {
        failed++;
        failures.Add((file, $"Input error: {ex.Message}"));
        Console.Error.WriteLine($"FAIL: {Path.GetFileName(file)} — {ex.Message}");
    }
    catch (IronOcrProductException ex)
    {
        failed++;
        failures.Add((file, $"Engine error: {ex.Message}"));
        Console.Error.WriteLine($"FAIL: {Path.GetFileName(file)} — {ex.Message}");
    }
    catch (Exception ex)
    {
        failed++;
        failures.Add((file, $"Unexpected: {ex.Message}"));
        Console.Error.WriteLine($"FAIL: {Path.GetFileName(file)} — {ex.GetType().Name}: {ex.Message}");
    }
}

// Summary report
Console.WriteLine($"\n--- Batch Summary ---");
Console.WriteLine($"Total: {files.Length} | Passed: {succeeded} | Failed: {failed}");
if (succeeded > 0)
    Console.WriteLine($"Average confidence: {totalConfidence / succeeded:P1}");

foreach (var (f, err) in failures)
    Console.WriteLine($"  {Path.GetFileName(f)}: {err}");

Imports IronOcr
Imports IronOcr.Exceptions
Imports System.IO

Dim ocr As New IronTesseract()
Installation.LogFilePath = "batch_debug.log"
Installation.LoggingMode = Installation.LoggingModes.File

Dim files As String() = Directory.GetFiles("scans/", "*.pdf")
Dim succeeded As Integer = 0
Dim failed As Integer = 0
Dim totalConfidence As Double = 0
Dim failures As New List(Of (File As String, Error As String))()

For Each file As String In files
    Try
        Using input As New OcrInput()
            input.LoadPdf(file)

            Dim result As OcrResult = ocr.Read(input)
            totalConfidence += result.Confidence
            succeeded += 1

            Console.WriteLine($"OK: {Path.GetFileName(file)} — {result.Confidence:P1}")
        End Using
    Catch ex As IronOcrInputException
        failed += 1
        failures.Add((file, $"Input error: {ex.Message}"))
        Console.Error.WriteLine($"FAIL: {Path.GetFileName(file)} — {ex.Message}")
    Catch ex As IronOcrProductException
        failed += 1
        failures.Add((file, $"Engine error: {ex.Message}"))
        Console.Error.WriteLine($"FAIL: {Path.GetFileName(file)} — {ex.Message}")
    Catch ex As Exception
        failed += 1
        failures.Add((file, $"Unexpected: {ex.Message}"))
        Console.Error.WriteLine($"FAIL: {Path.GetFileName(file)} — {ex.GetType().Name}: {ex.Message}")
    End Try
Next

' Summary report
Console.WriteLine(vbCrLf & "--- Batch Summary ---")
Console.WriteLine($"Total: {files.Length} | Passed: {succeeded} | Failed: {failed}")
If succeeded > 0 Then
    Console.WriteLine($"Average confidence: {totalConfidence / succeeded:P1}")
End If

For Each failure In failures
    Console.WriteLine($"  {Path.GetFileName(failure.File)}: {failure.Error}")
Next