IronOCR 和 AWS Textract OCR 之間的比較

using FREngine;

public class AbbyyOcrService : IDisposable
{
    private IEngine _engine;

    public AbbyyOcrService(string sdkPath, string licensePath)
    {
        // Step 1: Create engine loader
        var loader = new EngineLoader();

        // Step 2: Load engine — fails if license files are missing or expired
        _engine = loader.GetEngineObject(sdkPath, licensePath);

        // Step 3: Select recognition profile
        _engine.LoadPredefinedProfile("DocumentConversion_Accuracy");

        // Step 4: Configure language data (each language adds deployment complexity)
        var langParams = _engine.CreateLanguageParams();
        langParams.Languages.Add("English");
    }

    public string ExtractText(string imagePath)
    {
        var document = _engine.CreateFRDocument();

        try
        {
            document.AddImageFile(imagePath, null, null);
            document.Process(null);
            return document.PlainText.Text;
        }
        finally
        {
            // Must close — skipping this causes memory leaks
            document.Close();
        }
    }

    public void Dispose()
    {
        _engine = null;
    }
}

Imports FREngine

Public Class AbbyyOcrService
    Implements IDisposable

    Private _engine As IEngine

    Public Sub New(sdkPath As String, licensePath As String)
        ' Step 1: Create engine loader
        Dim loader = New EngineLoader()

        ' Step 2: Load engine — fails if license files are missing or expired
        _engine = loader.GetEngineObject(sdkPath, licensePath)

        ' Step 3: Select recognition profile
        _engine.LoadPredefinedProfile("DocumentConversion_Accuracy")

        ' Step 4: Configure language data (each language adds deployment complexity)
        Dim langParams = _engine.CreateLanguageParams()
        langParams.Languages.Add("English")
    End Sub

    Public Function ExtractText(imagePath As String) As String
        Dim document = _engine.CreateFRDocument()

        Try
            document.AddImageFile(imagePath, Nothing, Nothing)
            document.Process(Nothing)
            Return document.PlainText.Text
        Finally
            ' Must close — skipping this causes memory leaks
            document.Close()
        End Try
    End Function

    Public Sub Dispose() Implements IDisposable.Dispose
        _engine = Nothing
    End Sub
End Class

using FREngine;

// ABBYY: Load high-accuracy profile for difficult documents
var loader = new EngineLoader();
var engine = loader.GetEngineObject(
    @"C:\Program Files\ABBYY SDK\FineReader Engine\Bin",
    @"C:\Program Files\ABBYY SDK\License"
);
engine.LoadPredefinedProfile("DocumentConversion_Accuracy");

var document = engine.CreateFRDocument();
try
{
    document.AddImageFile("difficult-scan.jpg", null, null);
    document.Process(null);
    var text = document.PlainText.Text;
}
finally
{
    document.Close();
}

Imports FREngine

' ABBYY: Load high-accuracy profile for difficult documents
Dim loader As New EngineLoader()
Dim engine = loader.GetEngineObject(
    "C:\Program Files\ABBYY SDK\FineReader Engine\Bin",
    "C:\Program Files\ABBYY SDK\License"
)
engine.LoadPredefinedProfile("DocumentConversion_Accuracy")

Dim document = engine.CreateFRDocument()
Try
    document.AddImageFile("difficult-scan.jpg", Nothing, Nothing)
    document.Process(Nothing)
    Dim text = document.PlainText.Text
Finally
    document.Close()
End Try

using IronOcr;

// IronOCR:自動預處理handles most real-world document quality issues
var ocr = new IronTesseract();
var result = ocr.Read("invoice-scan.jpg");
Console.WriteLine(result.Text);
Console.WriteLine($"Confidence: {result.Confidence}%");

Imports IronOcr

' IronOCR:自動預處理handles most real-world document quality issues
Dim ocr As New IronTesseract()
Dim result = ocr.Read("invoice-scan.jpg")
Console.WriteLine(result.Text)
Console.WriteLine($"Confidence: {result.Confidence}%")

using var input = new OcrInput();
input.LoadImage("low-quality-scan.jpg");
input.Deskew();           // Correct rotation up to several degrees
input.DeNoise();          // Remove scanner noise and artifacts
input.Contrast();         // Enhance text/background separation
input.Binarize();         // Convert to optimal black/white
input.EnhanceResolution(300);  // Scale to 300 DPI for engine

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

Imports IronOcr

Using input As New OcrInput()
    input.LoadImage("low-quality-scan.jpg")
    input.Deskew()           ' Correct rotation up to several degrees
    input.DeNoise()          ' Remove scanner noise and artifacts
    input.Contrast()         ' Enhance text/background separation
    input.Binarize()         ' Convert to optimal black/white
    input.EnhanceResolution(300)  ' Scale to 300 DPI for engine

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

IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE");

Imports System

IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE")

using FREngine;

public string ProcessPdf(string pdfPath)
{
    var document = _engine.CreateFRDocument();

    try
    {
        // Open PDF through a separate file object
        var pdfFile = _engine.CreatePDFFile();
        pdfFile.Open(pdfPath, null, null);

        // Add each page individually
        for (int i = 0; i < pdfFile.PageCount; i++)
        {
            document.AddImageFile(
                pdfPath,
                null,
                _engine.CreatePDFExportParams()
            );
        }

        document.Process(null);
        return document.PlainText.Text;
    }
    finally
    {
        document.Close();
    }
}

public void CreateSearchablePdf(string inputPath, string outputPath)
{
    var document = _engine.CreateFRDocument();

    try
    {
        document.AddImageFile(inputPath, null, null);
        document.Process(null);

        // Configure export parameters before export
        var exportParams = _engine.CreatePDFExportParams();
        exportParams.Scenario = PDFExportScenarioEnum.PDES_Balanced;

        document.Export(outputPath, FileExportFormatEnum.FEF_PDF, exportParams);
    }
    finally
    {
        document.Close();
    }
}

Imports FREngine

Public Function ProcessPdf(ByVal pdfPath As String) As String
    Dim document = _engine.CreateFRDocument()

    Try
        ' Open PDF through a separate file object
        Dim pdfFile = _engine.CreatePDFFile()
        pdfFile.Open(pdfPath, Nothing, Nothing)

        ' Add each page individually
        For i As Integer = 0 To pdfFile.PageCount - 1
            document.AddImageFile(pdfPath, Nothing, _engine.CreatePDFExportParams())
        Next

        document.Process(Nothing)
        Return document.PlainText.Text
    Finally
        document.Close()
    End Try
End Function

Public Sub CreateSearchablePdf(ByVal inputPath As String, ByVal outputPath As String)
    Dim document = _engine.CreateFRDocument()

    Try
        document.AddImageFile(inputPath, Nothing, Nothing)
        document.Process(Nothing)

        ' Configure export parameters before export
        Dim exportParams = _engine.CreatePDFExportParams()
        exportParams.Scenario = PDFExportScenarioEnum.PDES_Balanced

        document.Export(outputPath, FileExportFormatEnum.FEF_PDF, exportParams)
    Finally
        document.Close()
    End Try
End Sub

using IronOcr;

// Read any PDF — multi-page handled automatically
using var input = new OcrInput();
input.LoadPdf("scanned-document.pdf");
var result = new IronTesseract().Read(input);
Console.WriteLine(result.Text);

//受密碼保護的 PDF— one parameter
using var secureInput = new OcrInput();
secureInput.LoadPdf("encrypted.pdf", Password: "secret");
var secureResult = new IronTesseract().Read(secureInput);

// Create searchable PDF — one method call
var ocrResult = new IronTesseract().Read("scanned.pdf");
ocrResult.SaveAsSearchablePdf("searchable-output.pdf");

Imports IronOcr

' Read any PDF — multi-page handled automatically
Using input As New OcrInput()
    input.LoadPdf("scanned-document.pdf")
    Dim result = New IronTesseract().Read(input)
    Console.WriteLine(result.Text)
End Using

' 受密碼保護的 PDF— one parameter
Using secureInput As New OcrInput()
    secureInput.LoadPdf("encrypted.pdf", Password:="secret")
    Dim secureResult = New IronTesseract().Read(secureInput)
End Using

' Create searchable PDF — one method call
Dim ocrResult = New IronTesseract().Read("scanned.pdf")
ocrResult.SaveAsSearchablePdf("searchable-output.pdf")

// Remove all of this:
// var loader = new EngineLoader();
// _engine = loader.GetEngineObject(sdkPath, licensePath);
// _engine.LoadPredefinedProfile("DocumentConversion_Accuracy");
// var document = _engine.CreateFRDocument();
// document.AddImageFile(imagePath, null, null);
// document.Process(null);
// string text = document.PlainText.Text;
// document.Close();

// Replace with:
var text = new IronTesseract().Read(imagePath).Text;

Imports IronOcr

Dim text As String = New IronTesseract().Read(imagePath).Text

// ABBYY zone-based extraction required zone creation,
// bounds setting, type assignment, and page.Zones.Add()

// IronOCR: CropRectangle passed directly to LoadImage
var region = new CropRectangle(x: 0, y: 0, width: 600, height: 100);
using var input = new OcrInput();
input.LoadImage("invoice.jpg", region);
var headerText = new IronTesseract().Read(input).Text;

Imports IronOcr

' ABBYY zone-based extraction required zone creation,
' bounds setting, type assignment, and page.Zones.Add()

' IronOCR: CropRectangle passed directly to LoadImage
Dim region As New CropRectangle(x:=0, y:=0, width:=600, height:=100)
Using input As New OcrInput()
    input.LoadImage("invoice.jpg", region)
    Dim headerText As String = New IronTesseract().Read(input).Text
End Using