PDFTron OCR 替代品 - IronOCR

// Define the base path for PDFTron SDK files
string PDFNET_BASE = @"C:\PDFTron\PDFNetDotNet4\";
// Configure paths for libraries and resources
string libPath = Path.Combine(PDFNET_BASE, "Lib");
string ocrModulePath = Path.Combine(PDFNET_BASE, "OCRModule");

' Define the base path for PDFTron SDK files
Dim PDFNET_BASE As String = "C:\PDFTron\PDFNetDotNet4\"
' Configure paths for libraries and resources
Dim libPath As String = Path.Combine(PDFNET_BASE, "Lib")
Dim ocrModulePath As String = Path.Combine(PDFNET_BASE, "OCRModule")

// PDFTron image conversion and OCR workflow
PDFDoc doc = new PDFDoc("input.pdf");

// Convert to various formats before OCR
Convert.ToSvg(doc, "output.svg");
Convert.ToXps("input.pdf", "output.xps");

// Configure TIFF conversion with OCR preparation
Convert.TiffOutputOptions tiff_options = new Convert.TiffOutputOptions();
tiff_options.SetDPI(300); // Optimal DPI for OCR
tiff_options.SetDither(true);
tiff_options.SetMono(true);
Convert.ToTiff("input.pdf", "output.tiff", tiff_options);

// Additional format conversions
Convert.ToXod("input.pdf", "output.xod");
Convert.ToHtml("input.pdf", "output.html");

// OCR module must be separately configured for text extraction

' PDFTron image conversion and OCR workflow
Dim doc As New PDFDoc("input.pdf")

' Convert to various formats before OCR
Convert.ToSvg(doc, "output.svg")
Convert.ToXps("input.pdf", "output.xps")

' Configure TIFF conversion with OCR preparation
Dim tiff_options As New Convert.TiffOutputOptions()
tiff_options.SetDPI(300) ' Optimal DPI for OCR
tiff_options.SetDither(True)
tiff_options.SetMono(True)
Convert.ToTiff("input.pdf", "output.tiff", tiff_options)

' Additional format conversions
Convert.ToXod("input.pdf", "output.xod")
Convert.ToHtml("input.pdf", "output.html")

' OCR module must be separately configured for text extraction

// InitializeIronOCRwith improved settings
var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.EnglishBest;
Ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5;

using (var Input = new OcrInput())
{
    // Add single or multiple images
    Input.AddImage(@"invoice.png");
    Input.AddImage(@"receipt.jpg");

    // Configure image preprocessing
    Input.DeNoise();
    Input.Deskew();
    Input.EnhanceResolution(300);

    // Perform OCR with structured output
    var Result = Ocr.Read(Input);

    // Access results with confidence scores
    Console.WriteLine($"Text: {Result.Text}");
    Console.WriteLine($"Confidence: {Result.Confidence}%");

    // Extract structured data
    foreach (var page in Result.Pages)
    {
        foreach (var paragraph in page.Paragraphs)
        {
            Console.WriteLine(paragraph.Text);
        }
    }
}

Imports IronOcr

' Initialize IronOCR with improved settings
Dim Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.EnglishBest
Ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5

Using Input = New OcrInput()
    ' Add single or multiple images
    Input.AddImage("invoice.png")
    Input.AddImage("receipt.jpg")

    ' Configure image preprocessing
    Input.DeNoise()
    Input.Deskew()
    Input.EnhanceResolution(300)

    ' Perform OCR with structured output
    Dim Result = Ocr.Read(Input)

    ' Access results with confidence scores
    Console.WriteLine($"Text: {Result.Text}")
    Console.WriteLine($"Confidence: {Result.Confidence}%")

    ' Extract structured data
    For Each page In Result.Pages
        For Each paragraph In page.Paragraphs
            Console.WriteLine(paragraph.Text)
        Next
    Next
End Using

using (var Input = new OcrInput())
{
    Input.AddImage("low-quality-scan.jpg");

    // Apply image corrections
    Input.DeNoise(); // Remove image noise
    Input.Deskew(); // Correct rotation
    Input.Scale(200); // Upscale low-res images
    Input.Binarize(); // Convert to black/white
    Input.EnhanceContrast(); // Improve text visibility
    Input.Sharpen(); // Improve edges

    // Process with optimizations
    var Result = Ocr.Read(Input);
}

Imports System

Using Input As New OcrInput()
    Input.AddImage("low-quality-scan.jpg")

    ' Apply image corrections
    Input.DeNoise() ' Remove image noise
    Input.Deskew() ' Correct rotation
    Input.Scale(200) ' Upscale low-res images
    Input.Binarize() ' Convert to black/white
    Input.EnhanceContrast() ' Improve text visibility
    Input.Sharpen() ' Improve edges

    ' Process with optimizations
    Dim Result = Ocr.Read(Input)
End Using

// Process multi-page TIFF files
Input.AddMultiFrameTiff("multipage-document.tiff");
// Each frame processes as a separate page

' Process multi-page TIFF files
Input.AddMultiFrameTiff("multipage-document.tiff")
' Each frame processes as a separate page

// PDFTron PDF processing example (abbreviated)
class PDFProcessor
{
    static bool ConvertSpecificFormats()
    {
        bool err = false;
        try
        {
            using (PDFDoc pdfdoc = new PDFDoc())
            {
                // Convert XPS to PDF first
                Console.WriteLine("Converting from XPS");
                pdftron.PDF.Convert.FromXps(pdfdoc, inputPath + "document.xps");
                pdfdoc.Save(outputPath + "converted.pdf", SDFDoc.SaveOptions.e_remove_unused);

                // OCR module processes separately
                // Requires additional configuration not shown
            }
        }
        catch (PDFNetException e)
        {
            Console.WriteLine(e.Message);
            err = true;
        }
        return err;
    }
}

Imports pdftron
Imports pdftron.PDF
Imports System

Class PDFProcessor
    Private Shared Function ConvertSpecificFormats() As Boolean
        Dim err As Boolean = False
        Try
            Using pdfdoc As New PDFDoc()
                ' Convert XPS to PDF first
                Console.WriteLine("Converting from XPS")
                pdftron.PDF.Convert.FromXps(pdfdoc, inputPath & "document.xps")
                pdfdoc.Save(outputPath & "converted.pdf", SDFDoc.SaveOptions.e_remove_unused)

                ' OCR module processes separately
                ' Requires additional configuration not shown
            End Using
        Catch e As PDFNetException
            Console.WriteLine(e.Message)
            err = True
        End Try
        Return err
    End Function
End Class

// Process entire PDF with automatic page handling
var Ocr = new IronTesseract();
using (var Input = new OcrInput())
{
    // Add complete PDF - all pages processed automatically
    Input.AddPdf("annual-report.pdf");

    // Or process specific pages only
    Input.AddPdfPage("large-document.pdf", pageNumber: 5);

    // Process multiple specific pages
    IEnumerable<int> pages = new List<int> { 1, 3, 5, 7, 9 };
    Input.AddPdfPages("selected-pages.pdf", pages);

    // Handle password-protected PDFs
    Input.AddPdf("secure-document.pdf", password: "admin123");

    // Configure OCR settings
    Ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd;

    // Execute OCR
    var Result = Ocr.Read(Input);

    // Save results in multiple formats
    Result.SaveAsTextFile("extracted-text.txt");
    Result.SaveAsHocrFile("structured-output.html");
    Result.SaveAsSearchablePdf("searchable-version.pdf");
}

Imports IronTesseract

' Process entire PDF with automatic page handling
Dim Ocr As New IronTesseract()
Using Input As New OcrInput()
    ' Add complete PDF - all pages processed automatically
    Input.AddPdf("annual-report.pdf")

    ' Or process specific pages only
    Input.AddPdfPage("large-document.pdf", pageNumber:=5)

    ' Process multiple specific pages
    Dim pages As IEnumerable(Of Integer) = New List(Of Integer) From {1, 3, 5, 7, 9}
    Input.AddPdfPages("selected-pages.pdf", pages)

    ' Handle password-protected PDFs
    Input.AddPdf("secure-document.pdf", password:="admin123")

    ' Configure OCR settings
    Ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd

    ' Execute OCR
    Dim Result = Ocr.Read(Input)

    ' Save results in multiple formats
    Result.SaveAsTextFile("extracted-text.txt")
    Result.SaveAsHocrFile("structured-output.html")
    Result.SaveAsSearchablePdf("searchable-version.pdf")
End Using

// Advanced PDF processing with region targeting
var Ocr = new IronTesseract();
using (var Input = new OcrInput())
{
    // Define specific regions for targeted OCR
    var headerArea = new System.Drawing.Rectangle(0, 0, 800, 200);
    var contentArea = new System.Drawing.Rectangle(50, 250, 700, 800);

    // Add PDF with region specifications
    Input.AddPdf("invoice.pdf");

    // Process with confidence analysis
    var Result = Ocr.Read(Input);

    // Extract data with structure preservation
    foreach (var page in Result.Pages)
    {
        Console.WriteLine($"Page {page.PageNumber}:");

        // Extract tables
        var tables = page.Tables;
        foreach (var table in tables)
        {
            // Process tabular data
            Console.WriteLine($"Table found: {table.RowCount}x{table.ColumnCount}");
        }

        // Extract paragraphs with formatting
        foreach (var paragraph in page.Paragraphs)
        {
            Console.WriteLine($"Paragraph: {paragraph.Text}");
            Console.WriteLine($"Font Size: {paragraph.FontSize}");
        }
    }
}

Imports IronTesseract
Imports System.Drawing

' Advanced PDF processing with region targeting
Dim Ocr As New IronTesseract()
Using Input As New OcrInput()
    ' Define specific regions for targeted OCR
    Dim headerArea As New Rectangle(0, 0, 800, 200)
    Dim contentArea As New Rectangle(50, 250, 700, 800)

    ' Add PDF with region specifications
    Input.AddPdf("invoice.pdf")

    ' Process with confidence analysis
    Dim Result = Ocr.Read(Input)

    ' Extract data with structure preservation
    For Each page In Result.Pages
        Console.WriteLine($"Page {page.PageNumber}:")

        ' Extract tables
        Dim tables = page.Tables
        For Each table In tables
            ' Process tabular data
            Console.WriteLine($"Table found: {table.RowCount}x{table.ColumnCount}")
        Next

        ' Extract paragraphs with formatting
        For Each paragraph In page.Paragraphs
            Console.WriteLine($"Paragraph: {paragraph.Text}")
            Console.WriteLine($"Font Size: {paragraph.FontSize}")
        Next
    Next
End Using

//IronOCRexport capabilities
var Result = Ocr.Read(Input);

// Export as searchable PDF
Result.SaveAsSearchablePdf("searchable.pdf");

// Export as hOCR (HTML with OCR data)
Result.SaveAsHocrFile("output.hocr");

// Export with custom formatting
string html = Result.AsHocrString();
string text = Result.Text;
byte[] pdfBytes = Result.AsByteArray();

'IronOCR export capabilities
Dim Result = Ocr.Read(Input)

' Export as searchable PDF
Result.SaveAsSearchablePdf("searchable.pdf")

' Export as hOCR (HTML with OCR data)
Result.SaveAsHocrFile("output.hocr")

' Export with custom formatting
Dim html As String = Result.AsHocrString()
Dim text As String = Result.Text
Dim pdfBytes As Byte() = Result.AsByteArray()

// ConfigureIronOCRfor barcode detection
var Ocr = new IronTesseract();
Ocr.Configuration.ReadBarCodes = true;

using (var Input = new OcrInput())
{
    // Add images or PDFs containing barcodes
    Input.AddImage("shipping-label.png");
    Input.AddPdf("inventory-report.pdf");

    // Process with barcode detection
    var Result = Ocr.Read(Input);

    // Extract barcode data
    foreach (var barcode in Result.Barcodes)
    {
        Console.WriteLine($"Type: {barcode.Type}");
        Console.WriteLine($"Value: {barcode.Value}");
        Console.WriteLine($"Location: {barcode.X},{barcode.Y}");

        // Handle different barcode types
        switch (barcode.Type)
        {
            case BarcodeType.QRCode:
                ProcessQRCode(barcode.Value);
                break;
            case BarcodeType.Code128:
                ProcessShippingCode(barcode.Value);
                break;
            case BarcodeType.DataMatrix:
                ProcessInventoryCode(barcode.Value);
                break;
        }
    }

    // Combined text and barcode extraction
    Console.WriteLine($"Text found: {Result.Text}");
    Console.WriteLine($"Barcodes found: {Result.Barcodes.Count()}");
}

Imports IronOcr

' Configure IronOCR for barcode detection
Dim Ocr As New IronTesseract()
Ocr.Configuration.ReadBarCodes = True

Using Input As New OcrInput()
    ' Add images or PDFs containing barcodes
    Input.AddImage("shipping-label.png")
    Input.AddPdf("inventory-report.pdf")

    ' Process with barcode detection
    Dim Result = Ocr.Read(Input)

    ' Extract barcode data
    For Each barcode In Result.Barcodes
        Console.WriteLine($"Type: {barcode.Type}")
        Console.WriteLine($"Value: {barcode.Value}")
        Console.WriteLine($"Location: {barcode.X},{barcode.Y}")

        ' Handle different barcode types
        Select Case barcode.Type
            Case BarcodeType.QRCode
                ProcessQRCode(barcode.Value)
            Case BarcodeType.Code128
                ProcessShippingCode(barcode.Value)
            Case BarcodeType.DataMatrix
                ProcessInventoryCode(barcode.Value)
        End Select
    Next

    ' Combined text and barcode extraction
    Console.WriteLine($"Text found: {Result.Text}")
    Console.WriteLine($"Barcodes found: {Result.Barcodes.Count()}")
End Using

// Target specific areas in documents
var Ocr = new IronTesseract();
using (var Input = new OcrInput())
{
    // Define regions for form fields
    var nameFieldArea = new Rectangle(100, 200, 400, 50);
    var addressArea = new Rectangle(100, 300, 400, 150);
    var signatureArea = new Rectangle(100, 500, 300, 100);

    // Add document with region specifications
    Input.Add("application-form.pdf", nameFieldArea);

    // Process specific region
    var nameResult = Ocr.Read(Input);
    Console.WriteLine($"Name: {nameResult.Text}");

    // Process multiple regions
    Input.Clear();
    Input.Add("application-form.pdf", addressArea);
    var addressResult = Ocr.Read(Input);
    Console.WriteLine($"Address: {addressResult.Text}");
}

Imports IronTesseract

' Target specific areas in documents
Dim Ocr As New IronTesseract()
Using Input As New OcrInput()
    ' Define regions for form fields
    Dim nameFieldArea As New Rectangle(100, 200, 400, 50)
    Dim addressArea As New Rectangle(100, 300, 400, 150)
    Dim signatureArea As New Rectangle(100, 500, 300, 100)

    ' Add document with region specifications
    Input.Add("application-form.pdf", nameFieldArea)

    ' Process specific region
    Dim nameResult = Ocr.Read(Input)
    Console.WriteLine($"Name: {nameResult.Text}")

    ' Process multiple regions
    Input.Clear()
    Input.Add("application-form.pdf", addressArea)
    Dim addressResult = Ocr.Read(Input)
    Console.WriteLine($"Address: {addressResult.Text}")
End Using

// Configure parallel processing
var Ocr = new IronTesseract();
Ocr.Configuration.ReadMultithreaded = true;
Ocr.Configuration.MaxThreads = Environment.ProcessorCount;

// Process multiple documents concurrently
var tasks = new List<Task<OcrResult>>();
foreach (var file in documentFiles)
{
    tasks.Add(Task.Run(() => 
    {
        using (var input = new OcrInput())
        {
            input.AddPdf(file);
            return Ocr.Read(input);
        }
    }));
}

var results = await Task.WhenAll(tasks);

' Configure parallel processing
Dim Ocr As New IronTesseract()
Ocr.Configuration.ReadMultithreaded = True
Ocr.Configuration.MaxThreads = Environment.ProcessorCount

' Process multiple documents concurrently
Dim tasks As New List(Of Task(Of OcrResult))()
For Each file In documentFiles
    tasks.Add(Task.Run(Function() 
                           Using input As New OcrInput()
                               input.AddPdf(file)
                               Return Ocr.Read(input)
                           End Using
                       End Function))
Next

Dim results = Await Task.WhenAll(tasks)