C# 中的 OCR CodeProject Tutorial：使用 IronOCR 從影像中萃取文字

// Install via Package Manager Console
Install-Package IronOCR

using System;
using IronOcr;
class Program
{
    static void Main(string[] args)
    {
        // Initialize the new Tesseract engine
        var ocr = new IronTesseract();
        // Load the image file and perform OCR
        using (var input = new OcrInput())
        {
            input.LoadImage(@"sample-document.png");
            // Process the image and extract text
            OcrResult result = ocr.Read(input);
            // Output the recognized text
            var text = result.Text;
            Console.WriteLine(text);
        }
    }
}

Imports System
Imports IronOcr

Class Program
    Shared Sub Main(args As String())
        ' Initialize the new Tesseract engine
        Dim ocr As New IronTesseract()
        ' Load the image file and perform OCR
        Using input As New OcrInput()
            input.LoadImage("sample-document.png")
            ' Process the image and extract text
            Dim result As OcrResult = ocr.Read(input)
            ' Output the recognized text
            Dim text As String = result.Text
            Console.WriteLine(text)
        End Using
    End Sub
End Class

using System;
using IronOcr;
class Program
{
    static void Main(string[] args)
    {
        var ocr = new IronTesseract();
        using (var input = new OcrInput())
        {
            // Load specific pages from a multi-page TIFF file
            int[] pageIndices = new int[] { 0, 1, 2 };
            input.LoadImageFrames(@"scanned-documents.tiff", pageIndices);
            // Apply image enhancement for better results
            input.Deskew();
            OcrResult result = ocr.Read(input);
            // Access page-by-page results
            foreach (var page in result.Pages)
            {
                Console.WriteLine($"Page {page.PageNumber}:");
                Console.WriteLine(page.Text);
            }
        }
    }
}

Imports System
Imports IronOcr

Class Program
    Shared Sub Main(ByVal args As String())
        Dim ocr As New IronTesseract()
        Using input As New OcrInput()
            ' Load specific pages from a multi-page TIFF file
            Dim pageIndices As Integer() = {0, 1, 2}
            input.LoadImageFrames("scanned-documents.tiff", pageIndices)
            ' Apply image enhancement for better results
            input.Deskew()
            Dim result As OcrResult = ocr.Read(input)
            ' Access page-by-page results
            For Each page In result.Pages
                Console.WriteLine($"Page {page.PageNumber}:")
                Console.WriteLine(page.Text)
            Next
        End Using
    End Sub
End Class

using System;
using IronOcr;
class Program
{
    static void Main(string[] args)
    {
        var ocr = new IronTesseract();
        // Configure the OCR engine for your language
        ocr.Language = OcrLanguage.English;
        try
        {
            using (var input = new OcrInput())
            {
                input.LoadImage(@"document.png");
                // Enhance low-quality images
                input.DeNoise();
                input.Deskew();
                OcrResult result = ocr.Read(input);
                if (result.Text.Length > 0)
                {
                    Console.WriteLine("Recognized text:");
                    Console.WriteLine(result.Text);
                }
            }
        }
        catch (Exception ex)
        {
            Console.WriteLine($"OCR Error: {ex.Message}");
        }
    }
}

Imports System
Imports IronOcr

Class Program
    Shared Sub Main(ByVal args As String())
        Dim ocr As New IronTesseract()
        ' Configure the OCR engine for your language
        ocr.Language = OcrLanguage.English
        Try
            Using input As New OcrInput()
                input.LoadImage("document.png")
                ' Enhance low-quality images
                input.DeNoise()
                input.Deskew()
                Dim result As OcrResult = ocr.Read(input)
                If result.Text.Length > 0 Then
                    Console.WriteLine("Recognized text:")
                    Console.WriteLine(result.Text)
                End If
            End Using
        Catch ex As Exception
            Console.WriteLine($"OCR Error: {ex.Message}")
        End Try
    End Sub
End Class

using System;
using IronOcr;
class Program
{
    static void Main(string[] args)
    {
        var ocr = new IronTesseract();
        using (var input = new OcrInput())
        {
            // Set document metadata
            input.Title = "Converted Document";
            // Load source images or existing PDF
            input.LoadImage(@"page1.png");
            input.LoadImage(@"page2.png");
            OcrResult result = ocr.Read(input);
            // Save as searchable PDF with embedded text layer
            result.SaveAsSearchablePdf(@"searchable-output.pdf");
            Console.WriteLine("Searchable PDF created successfully.");
            Console.WriteLine($"Total pages processed: {result.Pages.Count}");
        }
    }
}

Imports System
Imports IronOcr

Class Program
    Shared Sub Main(ByVal args As String())
        Dim ocr = New IronTesseract()
        Using input = New OcrInput()
            ' Set document metadata
            input.Title = "Converted Document"
            ' Load source images or existing PDF
            input.LoadImage("page1.png")
            input.LoadImage("page2.png")
            Dim result As OcrResult = ocr.Read(input)
            ' Save as searchable PDF with embedded text layer
            result.SaveAsSearchablePdf("searchable-output.pdf")
            Console.WriteLine("Searchable PDF created successfully.")
            Console.WriteLine($"Total pages processed: {result.Pages.Count}")
        End Using
    End Sub
End Class