SDK de OCR para .NET : Uma biblioteca de reconhecimento de texto para C#

using IronOcr;

// Reusable OCR service encapsulating the IronTesseract engine
public class OcrService
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public string ExtractText(string filePath)
    {
        using var input = new OcrInput();

        // LoadPdf for PDF files; LoadImage for raster formats
        if (filePath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase))
            input.LoadPdf(filePath);
        else
            input.LoadImage(filePath);

        return _ocr.Read(input).Text;
    }

    public async Task<string> ExtractTextAsync(string filePath)
    {
        using var input = new OcrInput();

        if (filePath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase))
            input.LoadPdf(filePath);
        else
            input.LoadImage(filePath);

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

Imports IronOcr

' Reusable OCR service encapsulating the IronTesseract engine
Public Class OcrService
    Private ReadOnly _ocr As New IronTesseract()

    Public Function ExtractText(filePath As String) As String
        Using input As New OcrInput()
            ' LoadPdf for PDF files; LoadImage for raster formats
            If filePath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase) Then
                input.LoadPdf(filePath)
            Else
                input.LoadImage(filePath)
            End If

            Return _ocr.Read(input).Text
        End Using
    End Function

    Public Async Function ExtractTextAsync(filePath As String) As Task(Of String)
        Using input As New OcrInput()
            If filePath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase) Then
                input.LoadPdf(filePath)
            Else
                input.LoadImage(filePath)
            End If

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

using IronOcr;

var service = new OcrService();
string text = await service.ExtractTextAsync("invoice.pdf");
Console.WriteLine(text);

Imports IronOcr

Dim service = New OcrService()
Dim text As String = Await service.ExtractTextAsync("invoice.pdf")
Console.WriteLine(text)

using IronOcr;

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

    public string ProcessLowQualityDocument(string filePath)
    {
        using var input = new OcrInput();

        if (filePath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase))
            input.LoadPdf(filePath);
        else
            input.LoadImage(filePath);

        // Chain preprocessing filters in order of operation
        input.DeNoise();              // Remove scan artifacts and speckling
        input.Deskew();               // Correct page tilt up to 35 degrees
        input.Scale(150);             // Enlarge small text for better recognition
        input.Binarize();             // Convert to black/white for cleaner edges
        input.EnhanceResolution(300); // Sharpen blurry or low-DPI input

        var result = _ocr.Read(input);

        // Confidence below 70 often signals a preprocessing mismatch
        if (result.Confidence < 70)
            Console.WriteLine($"Warning: low confidence ({result.Confidence:F1}%)");

        return result.Text;
    }
}

Imports IronOcr

Public Class AccuracyOptimizedOcr
    Private ReadOnly _ocr As New IronTesseract()

    Public Function ProcessLowQualityDocument(filePath As String) As String
        Using input As New OcrInput()

            If filePath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase) Then
                input.LoadPdf(filePath)
            Else
                input.LoadImage(filePath)
            End If

            ' Chain preprocessing filters in order of operation
            input.DeNoise()              ' Remove scan artifacts and speckling
            input.Deskew()               ' Correct page tilt up to 35 degrees
            input.Scale(150)             ' Enlarge small text for better recognition
            input.Binarize()             ' Convert to black/white for cleaner edges
            input.EnhanceResolution(300) ' Sharpen blurry or low-DPI input

            Dim result = _ocr.Read(input)

            ' Confidence below 70 often signals a preprocessing mismatch
            If result.Confidence < 70 Then
                Console.WriteLine($"Warning: low confidence ({result.Confidence:F1}%)")
            End If

            Return result.Text
        End Using
    End Function
End Class

using IronOcr;
using Microsoft.Extensions.Logging;

public class ProductionOcrService
{
    private readonly IronTesseract _ocr;
    private readonly ILogger<ProductionOcrService> _logger;

    public ProductionOcrService(ILogger<ProductionOcrService> logger)
    {
        _logger = logger;
        _ocr = new IronTesseract
        {
            Configuration =
            {
                RenderSearchablePdfsAndHocr = true,
                ReadBarCodes = true
            }
        };
    }

    public async Task<IReadOnlyList<string>> ProcessBatchAsync(
        IEnumerable<string> filePaths,
        int maxDegreeOfParallelism = 4)
    {
        var results = new System.Collections.Concurrent.ConcurrentBag<string>();

        var options = new ParallelOptions
        {
            MaxDegreeOfParallelism = maxDegreeOfParallelism
        };

        await Parallel.ForEachAsync(filePaths, options, async (filePath, ct) =>
        {
            try
            {
                using var input = new OcrInput();

                if (filePath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase))
                    input.LoadPdf(filePath);
                else
                    input.LoadImage(filePath);

                var result = await _ocr.ReadAsync(input);
                results.Add(result.Text);
                _logger.LogInformation("Processed {FilePath} at {Confidence:F1}% confidence",
                    filePath, result.Confidence);
            }
            catch (Exception ex)
            {
                _logger.LogError(ex, "OCR failed for {FilePath}", filePath);
                results.Add(string.Empty);
            }
        });

        return results.ToList();
    }

    public void CreateSearchablePdf(string inputPath, string outputPath)
    {
        using var input = new OcrInput();

        if (inputPath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase))
            input.LoadPdf(inputPath);
        else
            input.LoadImage(inputPath);

        _ocr.Read(input).SaveAsSearchablePdf(outputPath);
        _logger.LogInformation("Searchable PDF written to {OutputPath}", outputPath);
    }
}

Imports IronOcr
Imports Microsoft.Extensions.Logging
Imports System.Collections.Concurrent
Imports System.Threading.Tasks

Public Class ProductionOcrService
    Private ReadOnly _ocr As IronTesseract
    Private ReadOnly _logger As ILogger(Of ProductionOcrService)

    Public Sub New(logger As ILogger(Of ProductionOcrService))
        _logger = logger
        _ocr = New IronTesseract With {
            .Configuration = New TesseractConfiguration With {
                .RenderSearchablePdfsAndHocr = True,
                .ReadBarCodes = True
            }
        }
    End Sub

    Public Async Function ProcessBatchAsync(filePaths As IEnumerable(Of String), Optional maxDegreeOfParallelism As Integer = 4) As Task(Of IReadOnlyList(Of String))
        Dim results = New ConcurrentBag(Of String)()

        Dim options = New ParallelOptions With {
            .MaxDegreeOfParallelism = maxDegreeOfParallelism
        }

        Await Parallel.ForEachAsync(filePaths, options, Async Function(filePath, ct)
            Try
                Using input As New OcrInput()
                    If filePath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase) Then
                        input.LoadPdf(filePath)
                    Else
                        input.LoadImage(filePath)
                    End If

                    Dim result = Await _ocr.ReadAsync(input)
                    results.Add(result.Text)
                    _logger.LogInformation("Processed {FilePath} at {Confidence:F1}% confidence", filePath, result.Confidence)
                End Using
            Catch ex As Exception
                _logger.LogError(ex, "OCR failed for {FilePath}", filePath)
                results.Add(String.Empty)
            End Try
        End Function)

        Return results.ToList()
    End Function

    Public Sub CreateSearchablePdf(inputPath As String, outputPath As String)
        Using input As New OcrInput()
            If inputPath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase) Then
                input.LoadPdf(inputPath)
            Else
                input.LoadImage(inputPath)
            End If

            _ocr.Read(input).SaveAsSearchablePdf(outputPath)
            _logger.LogInformation("Searchable PDF written to {OutputPath}", outputPath)
        End Using
    End Sub
End Class

using IronOcr;
using System.Text.RegularExpressions;

public record Invoice(
    string? InvoiceNumber,
    DateOnly? Date,
    decimal? TotalAmount,
    string RawText
);

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

    public Invoice ExtractInvoiceData(string invoicePath)
    {
        using var input = new OcrInput();

        if (invoicePath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase))
            input.LoadPdf(invoicePath);
        else
            input.LoadImage(invoicePath);

        input.DeNoise();
        input.Deskew();

        var result = _ocr.Read(input);
        string text = result.Text;

        return new Invoice(
            InvoiceNumber: ExtractInvoiceNumber(text),
            Date: ExtractDate(text),
            TotalAmount: ExtractAmount(text),
            RawText: text
        );
    }

    private static string? ExtractInvoiceNumber(string text)
    {
        var match = Regex.Match(text, @"Invoice\s*#?:?\s*(\S+)", RegexOptions.IgnoreCase);
        return match.Success ? match.Groups[1].Value : null;
    }

    private static DateOnly? ExtractDate(string text)
    {
        // Numeric format: MM/DD/YYYY
        var numeric = Regex.Match(text, @"\b(\d{1,2}/\d{1,2}/\d{2,4})\b");
        if (numeric.Success && DateTime.TryParse(numeric.Groups[1].Value, out var d1))
            return DateOnly.FromDateTime(d1);

        // Written format: January 15, 2025
        var written = Regex.Match(text,
            @"\b(January|February|March|April|May|June|July|August|September|October|November|December)\s+(\d{1,2}),?\s+(\d{4})\b",
            RegexOptions.IgnoreCase);
        if (written.Success && DateTime.TryParse(written.Value, out var d2))
            return DateOnly.FromDateTime(d2);

        return null;
    }

    private static decimal? ExtractAmount(string text)
    {
        var match = Regex.Match(text, @"\$\s*(\d+(?:\.\d{2})?)");
        return match.Success && decimal.TryParse(match.Groups[1].Value, out var amt)
            ? amt
            : null;
    }
}

Imports IronOcr
Imports System.Text.RegularExpressions

Public Class Invoice
    Public Property InvoiceNumber As String
    Public Property Date As DateOnly?
    Public Property TotalAmount As Decimal?
    Public Property RawText As String

    Public Sub New(invoiceNumber As String, [date] As DateOnly?, totalAmount As Decimal?, rawText As String)
        Me.InvoiceNumber = invoiceNumber
        Me.Date = [date]
        Me.TotalAmount = totalAmount
        Me.RawText = rawText
    End Sub
End Class

Public Class InvoiceOcrService
    Private ReadOnly _ocr As New IronTesseract()

    Public Function ExtractInvoiceData(invoicePath As String) As Invoice
        Using input As New OcrInput()

            If invoicePath.EndsWith(".pdf", StringComparison.OrdinalIgnoreCase) Then
                input.LoadPdf(invoicePath)
            Else
                input.LoadImage(invoicePath)
            End If

            input.DeNoise()
            input.Deskew()

            Dim result = _ocr.Read(input)
            Dim text As String = result.Text

            Return New Invoice(
                InvoiceNumber:=ExtractInvoiceNumber(text),
                [Date]:=ExtractDate(text),
                TotalAmount:=ExtractAmount(text),
                RawText:=text
            )
        End Using
    End Function

    Private Shared Function ExtractInvoiceNumber(text As String) As String
        Dim match = Regex.Match(text, "Invoice\s*#?:?\s*(\S+)", RegexOptions.IgnoreCase)
        Return If(match.Success, match.Groups(1).Value, Nothing)
    End Function

    Private Shared Function ExtractDate(text As String) As DateOnly?
        ' Numeric format: MM/DD/YYYY
        Dim numeric = Regex.Match(text, "\b(\d{1,2}/\d{1,2}/\d{2,4})\b")
        If numeric.Success AndAlso DateTime.TryParse(numeric.Groups(1).Value, Nothing) Then
            Return DateOnly.FromDateTime(DateTime.Parse(numeric.Groups(1).Value))
        End If

        ' Written format: January 15, 2025
        Dim written = Regex.Match(text,
            "\b(January|February|March|April|May|June|July|August|September|October|November|December)\s+(\d{1,2}),?\s+(\d{4})\b",
            RegexOptions.IgnoreCase)
        If written.Success AndAlso DateTime.TryParse(written.Value, Nothing) Then
            Return DateOnly.FromDateTime(DateTime.Parse(written.Value))
        End If

        Return Nothing
    End Function

    Private Shared Function ExtractAmount(text As String) As Decimal?
        Dim match = Regex.Match(text, "\$\s*(\d+(?:\.\d{2})?)")
        Dim amt As Decimal
        Return If(match.Success AndAlso Decimal.TryParse(match.Groups(1).Value, amt), amt, Nothing)
    End Function
End Class

using IronOcr;

// Configure multi-language recognition
var ocr = new IronTesseract();
ocr.Language = OcrLanguage.EnglishBest;  // Swap for any of 125+ supported languages

// For mixed-language documents, combine language packs
ocr.AddSecondaryLanguage(OcrLanguage.German);

using var input = new OcrInput();
input.LoadPdf("multilingual-contract.pdf");
var result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr

' Configure multi-language recognition
Dim ocr As New IronTesseract()
ocr.Language = OcrLanguage.EnglishBest  ' Swap for any of 125+ supported languages

' For mixed-language documents, combine language packs
ocr.AddSecondaryLanguage(OcrLanguage.German)

Using input As New OcrInput()
    input.LoadPdf("multilingual-contract.pdf")
    Dim result = ocr.Read(input)
    Console.WriteLine(result.Text)
End Using