用 IronOCR 在 C# 中将 OCR识别文本高亮为图像验证图片转文字

using IronOcr;

IronTesseract ocrTesseract = new IronTesseract();

using var ocrInput = new OcrInput();
ocrInput.LoadPdf("document.pdf");
ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_page_", ResultHighlightType.Paragraph);

Imports IronOcr

Private ocrTesseract As New IronTesseract()

Private ocrInput = New OcrInput()
ocrInput.LoadPdf("document.pdf")
ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_page_", ResultHighlightType.Paragraph)

using IronOcr;
using System;

// Initialize the OCR engine with custom configuration
IronTesseract ocrTesseract = new IronTesseract();

// Configure for better accuracy if needed
ocrTesseract.Configuration.ReadBarCodes = false; // Disable if not needed for performance
ocrTesseract.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd;

// Load the PDF document
using var ocrInput = new OcrInput();
ocrInput.LoadPdf("document.pdf");

// Generate highlights for each type
Console.WriteLine("Generating character-level highlights...");
ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_character_", ResultHighlightType.Character);

Console.WriteLine("Generating word-level highlights...");
ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_word_", ResultHighlightType.Word);

Console.WriteLine("Generating line-level highlights...");
ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_line_", ResultHighlightType.Line);

Console.WriteLine("Generating paragraph-level highlights...");
ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_paragraph_", ResultHighlightType.Paragraph);

Console.WriteLine("All highlight images have been generated successfully!");

Imports IronOcr
Imports System

' Initialize the OCR engine with custom configuration
Dim ocrTesseract As New IronTesseract()

' Configure for better accuracy if needed
ocrTesseract.Configuration.ReadBarCodes = False ' Disable if not needed for performance
ocrTesseract.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd

' Load the PDF document
Using ocrInput As New OcrInput()
    ocrInput.LoadPdf("document.pdf")

    ' Generate highlights for each type
    Console.WriteLine("Generating character-level highlights...")
    ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_character_", ResultHighlightType.Character)

    Console.WriteLine("Generating word-level highlights...")
    ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_word_", ResultHighlightType.Word)

    Console.WriteLine("Generating line-level highlights...")
    ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_line_", ResultHighlightType.Line)

    Console.WriteLine("Generating paragraph-level highlights...")
    ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_paragraph_", ResultHighlightType.Paragraph)
End Using

Console.WriteLine("All highlight images have been generated successfully!")

using IronOcr;
using System.IO;

IronTesseract ocrTesseract = new IronTesseract();

// Load a multi-page document
using var ocrInput = new OcrInput();
ocrInput.LoadPdf("multi-page-document.pdf");

// Create output directory if it doesn't exist
string outputDir = "highlighted_pages";
Directory.CreateDirectory(outputDir);

// Generate highlights for each page
// Files will be named: highlighted_pages/page_0.png, page_1.png, etc.
ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, 
    Path.Combine(outputDir, "page_"), 
    ResultHighlightType.Word);

// Count generated files for verification
int pageCount = Directory.GetFiles(outputDir, "page_*.png").Length;
Console.WriteLine($"Generated {pageCount} highlighted page images");

Imports IronOcr
Imports System.IO

Dim ocrTesseract As New IronTesseract()

' Load a multi-page document
Using ocrInput As New OcrInput()
    ocrInput.LoadPdf("multi-page-document.pdf")

    ' Create output directory if it doesn't exist
    Dim outputDir As String = "highlighted_pages"
    Directory.CreateDirectory(outputDir)

    ' Generate highlights for each page
    ' Files will be named: highlighted_pages/page_0.png, page_1.png, etc.
    ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, 
                                          Path.Combine(outputDir, "page_"), 
                                          ResultHighlightType.Word)

    ' Count generated files for verification
    Dim pageCount As Integer = Directory.GetFiles(outputDir, "page_*.png").Length
    Console.WriteLine($"Generated {pageCount} highlighted page images")
End Using

try
{
    using var ocrInput = new OcrInput();
    ocrInput.LoadPdf("document.pdf");

    // Apply image filters if needed for better recognition
    ocrInput.Deskew(); // Correct slight rotations
    ocrInput.DeNoise(); // Remove background noise

    ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_", ResultHighlightType.Word);
}
catch (Exception ex)
{
    Console.WriteLine($"Error during highlighting: {ex.Message}");
    // Log error details for debugging
}

Imports System

Try
    Using ocrInput As New OcrInput()
        ocrInput.LoadPdf("document.pdf")

        ' Apply image filters if needed for better recognition
        ocrInput.Deskew() ' Correct slight rotations
        ocrInput.DeNoise() ' Remove background noise

        ocrInput.HighlightTextAndSaveAsImages(ocrTesseract, "highlight_", ResultHighlightType.Word)
    End Using
Catch ex As Exception
    Console.WriteLine($"Error during highlighting: {ex.Message}")
    ' Log error details for debugging
End Try

public class OcrDebugger
{
    private readonly IronTesseract _tesseract;
    private readonly bool _debugMode;

    public OcrDebugger(bool enableDebugMode = false)
    {
        _tesseract = new IronTesseract();
        _debugMode = enableDebugMode;
    }

    public OcrResult ProcessDocument(string filePath)
    {
        using var input = new OcrInput();
        input.LoadPdf(filePath);

        // Apply preprocessing
        input.Deskew();
        input.DeNoise();

        // Generate debug highlights if in debug mode
        if (_debugMode)
        {
            string debugPath = $"debug_{Path.GetFileNameWithoutExtension(filePath)}_";
            input.HighlightTextAndSaveAsImages(_tesseract, debugPath, ResultHighlightType.Word);
        }

        // Perform actual OCR
        return _tesseract.Read(input);
    }
}

Imports System.IO

Public Class OcrDebugger
    Private ReadOnly _tesseract As IronTesseract
    Private ReadOnly _debugMode As Boolean

    Public Sub New(Optional enableDebugMode As Boolean = False)
        _tesseract = New IronTesseract()
        _debugMode = enableDebugMode
    End Sub

    Public Function ProcessDocument(filePath As String) As OcrResult
        Using input As New OcrInput()
            input.LoadPdf(filePath)

            ' Apply preprocessing
            input.Deskew()
            input.DeNoise()

            ' Generate debug highlights if in debug mode
            If _debugMode Then
                Dim debugPath As String = $"debug_{Path.GetFileNameWithoutExtension(filePath)}_"
                input.HighlightTextAndSaveAsImages(_tesseract, debugPath, ResultHighlightType.Word)
            End If

            ' Perform actual OCR
            Return _tesseract.Read(input)
        End Using
    End Function
End Class