IronOCRとSyncfusion OCRの比較

// Aspose.OCR: developer decides which corrections to apply
var api = new AsposeOcr();
var filters = new Aspose.OCR.Models.PreprocessingFilters.PreprocessingFilter();

// Every filter must be declared explicitly
filters.Add(PreprocessingFilter.AutoSkew());
filters.Add(PreprocessingFilter.AutoDenoising());
filters.Add(PreprocessingFilter.ContrastCorrectionFilter());
filters.Add(PreprocessingFilter.Threshold(128)); // must tune the threshold value

var settings = new RecognitionSettings
{
    PreprocessingFilters = filters,
    Language = Language.Eng
};

var result = api.RecognizeImage("poor-quality-scan.jpg", settings);
return result.RecognitionText;

Imports Aspose.OCR
Imports Aspose.OCR.Models.PreprocessingFilters

' Aspose.OCR: developer decides which corrections to apply
Dim api As New AsposeOcr()
Dim filters As New PreprocessingFilter()

' Every filter must be declared explicitly
filters.Add(PreprocessingFilter.AutoSkew())
filters.Add(PreprocessingFilter.AutoDenoising())
filters.Add(PreprocessingFilter.ContrastCorrectionFilter())
filters.Add(PreprocessingFilter.Threshold(128)) ' must tune the threshold value

Dim settings As New RecognitionSettings With {
    .PreprocessingFilters = filters,
    .Language = Language.Eng
}

Dim result = api.RecognizeImage("poor-quality-scan.jpg", settings)
Return result.RecognitionText

// Aspose.OCR: full pipeline for a typical scanned document
var api = new AsposeOcr();
var filters = new Aspose.OCR.Models.PreprocessingFilters.PreprocessingFilter();

// Step 1: fix rotation (must know to do this first)
filters.Add(PreprocessingFilter.AutoSkew());

// Step 2: remove noise
filters.Add(PreprocessingFilter.AutoDenoising());

// Step 3: contrast
filters.Add(PreprocessingFilter.ContrastCorrectionFilter());

// Step 4: binarize with a threshold you must choose
filters.Add(PreprocessingFilter.Binarize());

var settings = new RecognitionSettings
{
    PreprocessingFilters = filters,
    Language = Language.Eng
};

var result = api.RecognizeImage("scanned-invoice.jpg", settings);
Console.WriteLine(result.RecognitionText);

Imports Aspose.OCR
Imports Aspose.OCR.Models

' Aspose.OCR: full pipeline for a typical scanned document
Dim api As New AsposeOcr()
Dim filters As New PreprocessingFilters.PreprocessingFilter()

' Step 1: fix rotation (must know to do this first)
filters.Add(PreprocessingFilter.AutoSkew())

' Step 2: remove noise
filters.Add(PreprocessingFilter.AutoDenoising())

' Step 3: contrast
filters.Add(PreprocessingFilter.ContrastCorrectionFilter())

' Step 4: binarize with a threshold you must choose
filters.Add(PreprocessingFilter.Binarize())

Dim settings As New RecognitionSettings With {
    .PreprocessingFilters = filters,
    .Language = Language.Eng
}

Dim result = api.RecognizeImage("scanned-invoice.jpg", settings)
Console.WriteLine(result.RecognitionText)

// IronOCR: automatic preprocessing, zero filter configuration
var text = new IronTesseract().Read("scanned-invoice.jpg").Text;

// IronOCR: explicit preprocessing for a heavily degraded low-quality scan
using var input = new OcrInput();
input.LoadImage("poor-quality-photo.jpg");
input.Deskew();
input.DeNoise();
input.Contrast();
input.Binarize();
input.EnhanceResolution(300);
var result = new IronTesseract().Read(input);

Imports IronOcr

' IronOCR: automatic preprocessing, zero filter configuration
Dim text As String = New IronTesseract().Read("scanned-invoice.jpg").Text

' IronOCR: explicit preprocessing for a heavily degraded low-quality scan
Using input As New OcrInput()
    input.LoadImage("poor-quality-photo.jpg")
    input.Deskew()
    input.DeNoise()
    input.Contrast()
    input.Binarize()
    input.EnhanceResolution(300)
    Dim result = New IronTesseract().Read(input)
End Using

// Aspose.OCR: standard PDF, all pages
var api = new AsposeOcr();
var settings = new DocumentRecognitionSettings { Language = Language.Eng };
var results = api.RecognizePdf("document.pdf", settings);

var sb = new StringBuilder();
foreach (var page in results)
{
    sb.AppendLine(page.RecognitionText);
}
return sb.ToString();

Imports Aspose.OCR
Imports System.Text

Dim api As New AsposeOcr()
Dim settings As New DocumentRecognitionSettings With {.Language = Language.Eng}
Dim results = api.RecognizePdf("document.pdf", settings)

Dim sb As New StringBuilder()
For Each page In results
    sb.AppendLine(page.RecognitionText)
Next
Return sb.ToString()

// Aspose.OCR: encrypted PDFs require Aspose.PDF (separate license)
public string ExtractFromProtectedPdf(string pdfPath, string password)
{
    // Aspose.OCR alone CANNOT decrypt PDFs
    // You need Aspose.PDF (additional license cost)

    // Step 1: Decrypt with Aspose.PDF
    // Step 2: Convert pages to images (complex multi-step process)
    // Step 3: OCR the images
    // Step 4: Cleanup temp files

    throw new NotSupportedException(
        "Aspose.OCR requires Aspose.PDF (additional license) to handle " +
        "password-protected PDFs. This adds significant cost and complexity.");
}

' Aspose.OCR: encrypted PDFs require Aspose.PDF (separate license)
Public Function ExtractFromProtectedPdf(pdfPath As String, password As String) As String
    ' Aspose.OCR alone CANNOT decrypt PDFs
    ' You need Aspose.PDF (additional license cost)

    ' Step 1: Decrypt with Aspose.PDF
    ' Step 2: Convert pages to images (complex multi-step process)
    ' Step 3: OCR the images
    ' Step 4: Cleanup temp files

    Throw New NotSupportedException(
        "Aspose.OCR requires Aspose.PDF (additional license) to handle " &
        "password-protected PDFs. This adds significant cost and complexity.")
End Function

// IronOCR: standard PDF — direct, no settings object needed
var text = new IronTesseract().Read("document.pdf").Text;

// IronOCR: password-protected PDF — built-in, no extra license
using var input = new OcrInput();
input.LoadPdf("encrypted.pdf", Password: "secret123");
var result = new IronTesseract().Read(input);

// IronOCR: non-contiguous pages — single call
using var input = new OcrInput();
input.LoadPdfPages("large-report.pdf", new[] { 1, 3, 5, 12 });
var result = new IronTesseract().Read(input);

Imports IronOcr

' IronOCR: standard PDF — direct, no settings object needed
Dim text As String = New IronTesseract().Read("document.pdf").Text

' IronOCR: password-protected PDF — built-in, no extra license
Using input As New OcrInput()
    input.LoadPdf("encrypted.pdf", Password:="secret123")
    Dim result = New IronTesseract().Read(input)
End Using

' IronOCR: non-contiguous pages — single call
Using input As New OcrInput()
    input.LoadPdfPages("large-report.pdf", {1, 3, 5, 12})
    Dim result = New IronTesseract().Read(input)
End Using

// IronOCR: searchable PDF — one line
var result = new IronTesseract().Read("scanned-document.pdf");
result.SaveAsSearchablePdf("searchable-output.pdf");

Imports IronOcr

' IronOCR: searchable PDF — one line
Dim result = New IronTesseract().Read("scanned-document.pdf")
result.SaveAsSearchablePdf("searchable-output.pdf")

// Aspose.OCR: basic text extraction with confidence
var api = new AsposeOcr();
var settings = new RecognitionSettings
{
    Language = Language.Eng,
    AutoSkew = true
};

var result = api.RecognizeImage("document.jpg", settings);
string text = result.RecognitionText;
float confidence = result.RecognitionAreasConfidence.Average();

Imports Aspose.OCR

' Aspose.OCR: basic text extraction with confidence
Dim api As New AsposeOcr()
Dim settings As New RecognitionSettings With {
    .Language = Language.Eng,
    .AutoSkew = True
}

Dim result = api.RecognizeImage("document.jpg", settings)
Dim text As String = result.RecognitionText
Dim confidence As Single = result.RecognitionAreasConfidence.Average()

// Aspose.OCR: parallel batch — instance per thread due to thread-safety considerations
Parallel.ForEach(imagePaths,
    new ParallelOptions { MaxDegreeOfParallelism = 4 },
    path =>
    {
        var api = new AsposeOcr(); // new instance per thread
        var result = api.RecognizeImage(path, new RecognitionSettings());
        // handle result
    });

Imports System.Threading.Tasks
Imports Aspose.OCR

' Aspose.OCR: parallel batch — instance per thread due to thread-safety considerations
Parallel.ForEach(imagePaths, New ParallelOptions With {.MaxDegreeOfParallelism = 4}, Sub(path)
    Dim api As New AsposeOcr() ' new instance per thread
    Dim result = api.RecognizeImage(path, New RecognitionSettings())
    ' handle result
End Sub)

// IronOCR: basic text extraction with confidence
var result = new IronTesseract().Read("document.jpg");
string text = result.Text;
double confidence = result.Confidence; // single value, no average needed

Imports IronOcr

' IronOCR: basic text extraction with confidence
Dim result = New IronTesseract().Read("document.jpg")
Dim text As String = result.Text
Dim confidence As Double = result.Confidence ' single value, no average needed

// IronOCR: parallel batch — single shared instance, thread-safe
var ocr = new IronTesseract();

Parallel.ForEach(imagePaths, path =>
{
    var result = ocr.Read(path);
    // handle result
});

Imports IronOcr
Imports System.Threading.Tasks

' IronOCR: parallel batch — single shared instance, thread-safe
Dim ocr As New IronTesseract()

Parallel.ForEach(imagePaths, Sub(path)
    Dim result = ocr.Read(path)
    ' handle result
End Sub)

// Remove Aspose license initialization
// var license = new Aspose.OCR.License();
// license.SetLicense("Aspose.OCR.lic");

// Add IronOCR license at application startup
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";
// Or from environment variable (recommended for production)
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE");

' Remove Aspose license initialization
' Dim license As New Aspose.OCR.License()
' license.SetLicense("Aspose.OCR.lic")

' Add IronOCR license at application startup
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"
' Or from environment variable (recommended for production)
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE")

// Aspose.OCR: 0-based — first page is StartPage = 0, PagesNumber = 1
var settings = new DocumentRecognitionSettings { StartPage = 0, PagesNumber = 5 };

// IronOCR: 1-based — first page is page 1
using var input = new OcrInput();
input.LoadPdfPages("document.pdf", 1, 5); // pages 1 through 5

// IronOCR: non-contiguous pages
input.LoadPdfPages("document.pdf", new[] { 1, 3, 7 }); // specific page numbers

Imports Aspose.OCR
Imports IronOcr

' Aspose.OCR: 0-based — first page is StartPage = 0, PagesNumber = 1
Dim settings As New DocumentRecognitionSettings With {.StartPage = 0, .PagesNumber = 5}

' IronOCR: 1-based — first page is page 1
Using input As New OcrInput()
    input.LoadPdfPages("document.pdf", 1, 5) ' pages 1 through 5

    ' IronOCR: non-contiguous pages
    input.LoadPdfPages("document.pdf", {1, 3, 7}) ' specific page numbers
End Using

// Aspose.OCR: per-region confidence array averaged to a float
float asposeConfidence = result.RecognitionAreasConfidence.Average();

// IronOCR: single overall confidence value
double confidence = result.Confidence; // 0–100

// IronOCR: per-word confidence when granularity is needed
foreach (var word in result.Words)
{
    Console.WriteLine($"'{word.Text}': {word.Confidence:F1}%");
}

Imports System
Imports System.Linq

' Aspose.OCR: per-region confidence array averaged to a float
Dim asposeConfidence As Single = result.RecognitionAreasConfidence.Average()

' IronOCR: single overall confidence value
Dim confidence As Double = result.Confidence ' 0–100

' IronOCR: per-word confidence when granularity is needed
For Each word In result.Words
    Console.WriteLine($"'{word.Text}': {word.Confidence:F1}%")
Next

// Aspose.OCR preprocessing pipeline
var filters = new PreprocessingFilter();
filters.Add(PreprocessingFilter.AutoSkew());
filters.Add(PreprocessingFilter.ContrastCorrectionFilter());
filters.Add(PreprocessingFilter.AutoDenoising());
filters.Add(PreprocessingFilter.Binarize());

// IronOCR equivalent
using var input = new OcrInput();
input.LoadImage("document.jpg");
input.Deskew();
input.Contrast();
input.DeNoise();
input.Binarize();
var result = new IronTesseract().Read(input);

Imports Aspose.OCR
Imports IronOcr

' Aspose.OCR preprocessing pipeline
Dim filters As New PreprocessingFilter()
filters.Add(PreprocessingFilter.AutoSkew())
filters.Add(PreprocessingFilter.ContrastCorrectionFilter())
filters.Add(PreprocessingFilter.AutoDenoising())
filters.Add(PreprocessingFilter.Binarize())

' IronOCR equivalent
Using input As New OcrInput()
    input.LoadImage("document.jpg")
    input.Deskew()
    input.Contrast()
    input.DeNoise()
    input.Binarize()
    Dim result = New IronTesseract().Read(input)
End Using