IronOCRで検索可能なPDFの力を解き放つ：ウェビナーの概要

using IronOcr;
using IronPdf;

// Initialize IronOCR
var ocr = new IronTesseract();

// Configure OCR for accessibility compliance
ocr.Configuration.ReadBarCodes = true;
ocr.Configuration.RenderSearchablePdf = true;

// Read the scanned PDF
using var input = new OcrInput();
input.AddPdf("scanned-document.pdf");

// Perform OCR and create searchable PDF/UA compliant document
var result = ocr.Read(input);
result.SaveAsSearchablePdf("compliant-output.pdf");

Imports IronOcr
Imports IronPdf

' Initialize IronOCR
Dim ocr As New IronTesseract()

' Configure OCR for accessibility compliance
ocr.Configuration.ReadBarCodes = True
ocr.Configuration.RenderSearchablePdf = True

' Read the scanned PDF
Using input As New OcrInput()
    input.AddPdf("scanned-document.pdf")

    ' Perform OCR and create searchable PDF/UA compliant document
    Dim result = ocr.Read(input)
    result.SaveAsSearchablePdf("compliant-output.pdf")
End Using

using IronOcr;

// Create a new OCR engine instance
var ocr = new IronTesseract();

// Configure language and accuracy settings
ocr.Language = OcrLanguage.English;
ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd;

// Load the scanned PDF
using var input = new OcrInput();
input.AddPdf("invoice-scan.pdf");

// Apply image improve for better accuracy
input.DeNoise();
input.Deskew();
input.EnhanceResolution(225);

// Perform OCR and save as searchable PDF
var result = ocr.Read(input);
result.SaveAsSearchablePdf("searchable-invoice.pdf");

// Extract text for indexing
string extractedText = result.Text;
Console.WriteLine($"Extracted {extractedText.Length} characters");

Imports IronOcr

' Create a new OCR engine instance
Dim ocr As New IronTesseract()

' Configure language and accuracy settings
ocr.Language = OcrLanguage.English
ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd

' Load the scanned PDF
Using input As New OcrInput()
    input.AddPdf("invoice-scan.pdf")

    ' Apply image improve for better accuracy
    input.DeNoise()
    input.Deskew()
    input.EnhanceResolution(225)

    ' Perform OCR and save as searchable PDF
    Dim result = ocr.Read(input)
    result.SaveAsSearchablePdf("searchable-invoice.pdf")

    ' Extract text for indexing
    Dim extractedText As String = result.Text
    Console.WriteLine($"Extracted {extractedText.Length} characters")
End Using

using IronOcr;
using System.Drawing;

var ocr = new IronTesseract();

// Load PDF and define extraction regions
using var input = new OcrInput();
input.AddPdf("purchase-order.pdf", 1); // Process first page only

// Define bounding box for PO number field (x, y, width, height)
var poNumberArea = new Rectangle(450, 100, 150, 50);
input.AddPdfPage("purchase-order.pdf", 1, poNumberArea);

// Extract just the PO number
var result = ocr.Read(input);
string poNumber = result.Text.Trim();

// Define multiple regions for batch extraction
var regions = new Dictionary<string, Rectangle>
{
    { "PONumber", new Rectangle(450, 100, 150, 50) },
    { "TotalAmount", new Rectangle(450, 600, 150, 50) },
    { "VendorName", new Rectangle(50, 200, 300, 50) }
};

// Extract data from each region
var extractedData = new Dictionary<string, string>();
foreach (var region in regions)
{
    input.Clear();
    input.AddPdfPage("purchase-order.pdf", 1, region.Value);
    var regionResult = ocr.Read(input);
    extractedData[region.Key] = regionResult.Text.Trim();
}

Imports IronOcr
Imports System.Drawing

Dim ocr As New IronTesseract()

' Load PDF and define extraction regions
Using input As New OcrInput()
    input.AddPdf("purchase-order.pdf", 1) ' Process first page only

    ' Define bounding box for PO number field (x, y, width, height)
    Dim poNumberArea As New Rectangle(450, 100, 150, 50)
    input.AddPdfPage("purchase-order.pdf", 1, poNumberArea)

    ' Extract just the PO number
    Dim result = ocr.Read(input)
    Dim poNumber As String = result.Text.Trim()

    ' Define multiple regions for batch extraction
    Dim regions As New Dictionary(Of String, Rectangle) From {
        {"PONumber", New Rectangle(450, 100, 150, 50)},
        {"TotalAmount", New Rectangle(450, 600, 150, 50)},
        {"VendorName", New Rectangle(50, 200, 300, 50)}
    }

    ' Extract data from each region
    Dim extractedData As New Dictionary(Of String, String)()
    For Each region In regions
        input.Clear()
        input.AddPdfPage("purchase-order.pdf", 1, region.Value)
        Dim regionResult = ocr.Read(input)
        extractedData(region.Key) = regionResult.Text.Trim()
    Next
End Using

using IronOcr;
using System.IO;
using System.Threading.Tasks;

public async Task ProcessDocumentBatch(string folderPath)
{
    var ocr = new IronTesseract();
    ocr.Configuration.RenderSearchablePdf = true;

    // Get all PDF files in directory
    var pdfFiles = Directory.GetFiles(folderPath, "*.pdf");

    // Process files in parallel for maximum efficiency
    await Parallel.ForEachAsync(pdfFiles, async (file, ct) =>
    {
        using var input = new OcrInput();
        input.AddPdf(file);

        var result = await Task.Run(() => ocr.Read(input));

        // Save searchable version
        var outputPath = Path.Combine(folderPath, "searchable", Path.GetFileName(file));
        result.SaveAsSearchablePdf(outputPath);

        // Log processing results
        Console.WriteLine($"Processed: {file} - {result.Pages.Length} pages");
    });
}

Imports IronOcr
Imports System.IO
Imports System.Threading.Tasks

Public Async Function ProcessDocumentBatch(folderPath As String) As Task
    Dim ocr As New IronTesseract()
    ocr.Configuration.RenderSearchablePdf = True

    ' Get all PDF files in directory
    Dim pdfFiles = Directory.GetFiles(folderPath, "*.pdf")

    ' Process files in parallel for maximum efficiency
    Await Task.WhenAll(pdfFiles.Select(Function(file) Task.Run(Async Function()
                                                                  Using input As New OcrInput()
                                                                      input.AddPdf(file)

                                                                      Dim result = Await Task.Run(Function() ocr.Read(input))

                                                                      ' Save searchable version
                                                                      Dim outputPath = Path.Combine(folderPath, "searchable", Path.GetFileName(file))
                                                                      result.SaveAsSearchablePdf(outputPath)

                                                                      ' Log processing results
                                                                      Console.WriteLine($"Processed: {file} - {result.Pages.Length} pages")
                                                                  End Using
                                                              End Function)))
End Function