如何在 C# 中對 PDF 進行 OCR 識別：使用 .NET 從掃描文件中提取文字

using IronOcr;

// Initialize the OCR engine
var ocr = new IronTesseract();

// Load the PDF and perform OCR
using var input = new OcrInput();
input.LoadPdf("scanned-report.pdf");

// Run recognition
OcrResult result = ocr.Read(input);

// Access the extracted text
string text = result.Text;
Console.WriteLine(text);

Imports IronOcr

' Initialize the OCR engine
Dim ocr As New IronTesseract()

' Load the PDF and perform OCR
Using input As New OcrInput()
    input.LoadPdf("scanned-report.pdf")

    ' Run recognition
    Dim result As OcrResult = ocr.Read(input)

    ' Access the extracted text
    Dim text As String = result.Text
    Console.WriteLine(text)
End Using

using IronOcr;
using System.Collections.Generic;

var ocr = new IronTesseract();

// Specify pages to process (zero-based: 0 = first page)
var targetPages = new List<int> { 0, 2, 4 };

using var input = new OcrInput();
input.LoadPdf("lengthy-document.pdf", pageIndices: targetPages);

OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr
Imports System.Collections.Generic

Dim ocr As New IronTesseract()

' Specify pages to process (zero-based: 0 = first page)
Dim targetPages As New List(Of Integer) From {0, 2, 4}

Using input As New OcrInput()
    input.LoadPdf("lengthy-document.pdf", pageIndices:=targetPages)

    Dim result As OcrResult = ocr.Read(input)
    Console.WriteLine(result.Text)
End Using

using IronOcr;
using IronSoftware.Drawing;

var ocr = new IronTesseract();

// Define the scan region: X, Y, Width, Height (all in pixels from top-left)
var invoiceFields = new Rectangle[]
{
    new Rectangle(130, 290, 250, 50)   // Invoice number field
};

using var input = new OcrInput();
input.LoadPdf("invoice.pdf", contentAreas: invoiceFields);

OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr
Imports IronSoftware.Drawing

Dim ocr As New IronTesseract()

' Define the scan region: X, Y, Width, Height (all in pixels from top-left)
Dim invoiceFields As Rectangle() = {
    New Rectangle(130, 290, 250, 50)   ' Invoice number field
}

Using input As New OcrInput()
    input.LoadPdf("invoice.pdf", contentAreas:=invoiceFields)

    Dim result As OcrResult = ocr.Read(input)
    Console.WriteLine(result.Text)
End Using

using IronOcr;

var ocr = new IronTesseract();

using var input = new OcrInput();
// Load PDF at higher DPI for improved text recognition on small fonts
input.LoadPdf("poor-quality-scan.pdf", dpi: 300);

// Apply image correction filters
input.Deskew();    // Automatically straighten rotated pages
input.DeNoise();   // Remove scanning artifacts and speckles

OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr

Dim ocr = New IronTesseract()

Using input = New OcrInput()
    ' Load PDF at higher DPI for improved text recognition on small fonts
    input.LoadPdf("poor-quality-scan.pdf", dpi:=300)

    ' Apply image correction filters
    input.Deskew()    ' Automatically straighten rotated pages
    input.DeNoise()   ' Remove scanning artifacts and speckles

    Dim result As OcrResult = ocr.Read(input)
    Console.WriteLine(result.Text)
End Using

using IronOcr;

var ocr = new IronTesseract();

using var input = new OcrInput();
input.LoadPdf("protected.pdf", password: "secret123");

OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr

Dim ocr As New IronTesseract()

Using input As New OcrInput()
    input.LoadPdf("protected.pdf", password:="secret123")

    Dim result As OcrResult = ocr.Read(input)
    Console.WriteLine(result.Text)
End Using

var ocr = new IronTesseract();
ocr.Language = OcrLanguage.German;

Dim ocr As New IronTesseract()
ocr.Language = OcrLanguage.German

using IronOcr;

var ocr = new IronTesseract();

using var input = new OcrInput();
input.LoadPdf("scanned-archive.pdf");

OcrResult result = ocr.Read(input);

// Save as a searchable PDF
result.SaveAsSearchablePdf("output-searchable.pdf");

Imports IronOcr

Dim ocr As New IronTesseract()

Using input As New OcrInput()
    input.LoadPdf("scanned-archive.pdf")

    Dim result As OcrResult = ocr.Read(input)

    ' Save as a searchable PDF
    result.SaveAsSearchablePdf("output-searchable.pdf")
End Using

using IronOcr;

var ocr = new IronTesseract();
ocr.Configuration.ReadBarCodes = true;

using var input = new OcrInput();
input.LoadPdf("shipment-labels.pdf");

OcrResult result = ocr.Read(input);

// Access recognized text
Console.WriteLine(result.Text);

// Access barcode data
foreach (var barcode in result.Barcodes)
{
    Console.WriteLine($"Type: {barcode.Format}, Value: {barcode.Value}");
}

Imports IronOcr

Dim ocr As New IronTesseract()
ocr.Configuration.ReadBarCodes = True

Using input As New OcrInput()
    input.LoadPdf("shipment-labels.pdf")

    Dim result As OcrResult = ocr.Read(input)

    ' Access recognized text
    Console.WriteLine(result.Text)

    ' Access barcode data
    For Each barcode In result.Barcodes
        Console.WriteLine($"Type: {barcode.Format}, Value: {barcode.Value}")
    Next
End Using