請求書処理に最適なOCR（更新リスト）

// This code demonstrates how to use IronOCR to extract text from a receipt image.
var ocr = new IronTesseract();
ocr.Language = OcrLanguage.EnglishBest; // Set the OCR language to English
ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5; // Use Tesseract version 5

using (OcrInput ocrInput = new OcrInput("Demo.gif")) // Initialize OCR input with the image "Demo.gif"
{
    OcrResult ocrResult = ocr.Read(ocrInput); // Perform OCR reading
    // Extract the total price from the OCR result if present
    var totalPrice = ocrResult.Text.Contains("Total Current Charges") 
        ? ocrResult.Text.Split("Total Current Charges")[1].Split("\n")[0] 
        : "";
    Console.WriteLine("Total Current Charges : " + totalPrice); // Output the extracted total price
}

Imports Microsoft.VisualBasic

' This code demonstrates how to use IronOCR to extract text from a receipt image.
Dim ocr = New IronTesseract()
ocr.Language = OcrLanguage.EnglishBest ' Set the OCR language to English
ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5 ' Use Tesseract version 5

Using ocrInput As New OcrInput("Demo.gif") ' Initialize OCR input with the image "Demo.gif"
	Dim ocrResult As OcrResult = ocr.Read(ocrInput) ' Perform OCR reading
	' Extract the total price from the OCR result if present
	Dim totalPrice = If(ocrResult.Text.Contains("Total Current Charges"), ocrResult.Text.Split("Total Current Charges")(1).Split(vbLf)(0), "")
	Console.WriteLine("Total Current Charges : " & totalPrice) ' Output the extracted total price
End Using

// Enhanced invoice processing with image preprocessing
var ocr = new IronTesseract();
ocr.Language = OcrLanguage.EnglishBest;
ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5;

using (OcrInput ocrInput = new OcrInput("invoice.pdf"))
{
    // Apply preprocessing filters for better accuracy
    ocrInput.Sharpen();
    ocrInput.EnhanceResolution(225); // Optimize DPI for text recognition
    ocrInput.Deskew(); // Fix skewed scans

    // Read specific region for targeted extraction
    var invoiceRegion = new System.Drawing.Rectangle(100, 200, 400, 300);
    ocrInput.AddPdfPage(0, invoiceRegion);

    OcrResult ocrResult = ocr.Read(ocrInput);

    // Extract structured data
    foreach (var line in ocrResult.Lines)
    {
        if (line.Text.Contains("Invoice #"))
        {
            Console.WriteLine($"Found: {line.Text} - Confidence: {line.Confidence}%");
        }
    }
}

Imports IronOcr
Imports System.Drawing

' Enhanced invoice processing with image preprocessing
Dim ocr As New IronTesseract()
ocr.Language = OcrLanguage.EnglishBest
ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5

Using ocrInput As New OcrInput("invoice.pdf")
    ' Apply preprocessing filters for better accuracy
    ocrInput.Sharpen()
    ocrInput.EnhanceResolution(225) ' Optimize DPI for text recognition
    ocrInput.Deskew() ' Fix skewed scans

    ' Read specific region for targeted extraction
    Dim invoiceRegion As New Rectangle(100, 200, 400, 300)
    ocrInput.AddPdfPage(0, invoiceRegion)

    Dim ocrResult As OcrResult = ocr.Read(ocrInput)

    ' Extract structured data
    For Each line In ocrResult.Lines
        If line.Text.Contains("Invoice #") Then
            Console.WriteLine($"Found: {line.Text} - Confidence: {line.Confidence}%")
        End If
    Next
End Using

// Process multi-page invoice with table extraction
var ocr = new IronTesseract();
ocr.Language = OcrLanguage.EnglishBest;

using (OcrInput ocrInput = new OcrInput())
{
    // Add multiple invoice pages
    ocrInput.AddPdf("multi-page-invoice.pdf");

    // Enable table detection
    ocr.Configuration.ReadDataTables = true;

    OcrResult ocrResult = ocr.Read(ocrInput);

    // Export as searchable PDF
    ocrResult.SaveAsSearchablePdf("searchable-invoice.pdf");

    // Extract table data
    var tables = ocrResult.Tables;
    foreach (var table in tables)
    {
        Console.WriteLine($"Found table with {table.RowCount} rows");
    }
}

Imports IronTesseract

' Process multi-page invoice with table extraction
Dim ocr As New IronTesseract()
ocr.Language = OcrLanguage.EnglishBest

Using ocrInput As New OcrInput()
    ' Add multiple invoice pages
    ocrInput.AddPdf("multi-page-invoice.pdf")

    ' Enable table detection
    ocr.Configuration.ReadDataTables = True

    Dim ocrResult As OcrResult = ocr.Read(ocrInput)

    ' Export as searchable PDF
    ocrResult.SaveAsSearchablePdf("searchable-invoice.pdf")

    ' Extract table data
    Dim tables = ocrResult.Tables
    For Each table In tables
        Console.WriteLine($"Found table with {table.RowCount} rows")
    Next
End Using