C#でIronOCRを使ってスキャンされたドキュメントから文字起こし・テキスト抽出を行う

using IronOcr;
using System;

// Instantiate OCR engine
var ocr = new IronTesseract();

// Configure OCR engine
using var input = new OcrInput();
input.LoadImage("potter.tiff");

// Perform OCR
OcrResult result = ocr.ReadDocument(input);

Console.WriteLine(result.Text);

Imports IronOcr
Imports System

' Instantiate OCR engine
Private ocr = New IronTesseract()

' Configure OCR engine
Private input = New OcrInput()
input.LoadImage("potter.tiff")

' Perform OCR
Dim result As OcrResult = ocr.ReadDocument(input)

Console.WriteLine(result.Text)

using IronOcr;

var ocr = new IronTesseract();
using var input = new OcrInput();

// Load a multi-page PDF
input.LoadPdf("multi-page-document.pdf");

// Process all pages
OcrResult result = ocr.ReadDocument(input);

// Access individual page results
foreach (var page in result.Pages)
{
    Console.WriteLine($"Page {page.PageNumber}: {page.Text}");
}

Imports IronOcr

Dim ocr As New IronTesseract()
Using input As New OcrInput()

    ' Load a multi-page PDF
    input.LoadPdf("multi-page-document.pdf")

    ' Process all pages
    Dim result As OcrResult = ocr.ReadDocument(input)

    ' Access individual page results
    For Each page In result.Pages
        Console.WriteLine($"Page {page.PageNumber}: {page.Text}")
    Next

End Using

using IronOcr;

var ocr = new IronTesseract();
using var input = new OcrInput();

// Load and enhance image quality
input.LoadImage("low-quality-scan.jpg");
input.Deskew();  // Correct image skew
input.DeNoise(); // Remove background noise
input.Binarize(); // Convert to black and white

OcrResult result = ocr.ReadDocument(input);

Imports IronOcr

Dim ocr As New IronTesseract()
Using input As New OcrInput()
    ' Load and enhance image quality
    input.LoadImage("low-quality-scan.jpg")
    input.Deskew()  ' Correct image skew
    input.DeNoise() ' Remove background noise
    input.Binarize() ' Convert to black and white

    Dim result As OcrResult = ocr.ReadDocument(input)
End Using

using IronOcr;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadPdf("scanned-document.pdf");

// Process and save as searchable PDF
OcrResult result = ocr.ReadDocument(input);
result.SaveAsSearchablePdf("searchable-output.pdf");

Imports IronOcr

Dim ocr As New IronTesseract()
Using input As New OcrInput()
    input.LoadPdf("scanned-document.pdf")

    ' Process and save as searchable PDF
    Dim result As OcrResult = ocr.ReadDocument(input)
    result.SaveAsSearchablePdf("searchable-output.pdf")
End Using