PDFTron OCR 的替代方案 - IronOCR

//Azure Vision OCR— text extraction from a document image (requires Azure SDK)
using Azure;
using Azure.AI.Vision.ImageAnalysis;
var endpoint = new Uri("https://<your-resource>.cognitiveservices.azure.com/");
var credential = new AzureKeyCredential("<your-api-key>");
var client = new ImageAnalysisClient(endpoint, credential);
// Read operation analyzes the whole image for printed and handwritten text
var result = client.Analyze(
    BinaryData.FromStream(File.OpenRead("invoice.png")),
    VisualFeatures.Read);
foreach (var block in result.Value.Read.Blocks)
    foreach (var line in block.Lines)
        Console.WriteLine(line.Text);

Imports Azure
Imports Azure.AI.Vision.ImageAnalysis

Dim endpoint As New Uri("https://<your-resource>.cognitiveservices.azure.com/")
Dim credential As New AzureKeyCredential("<your-api-key>")
Dim client As New ImageAnalysisClient(endpoint, credential)

' Read operation analyzes the whole image for printed and handwritten text
Dim result = client.Analyze(BinaryData.FromStream(File.OpenRead("invoice.png")), VisualFeatures.Read)

For Each block In result.Value.Read.Blocks
    For Each line In block.Lines
        Console.WriteLine(line.Text)
    Next
Next

//IronOCR— local text extraction from a scanned document with preprocessing
using IronOcr;
var ocr = new IronTesseract();
ocr.Language = OcrLanguage.English;
using var input = new OcrInput();
input.LoadPdf("invoice.pdf");
// Preprocessing filters improve accuracy on low-quality scans
input.Deskew();
input.DeNoise();
OcrResult result = ocr.Read(input);
// Structured output: pages, paragraphs, lines, words with confidence data
foreach (var page in result.Pages)
    foreach (var line in page.Lines)
        Console.WriteLine($"{line.Text} (Confidence: {line.Confidence:P})");
// Export to searchable PDF for archival
result.SaveAsSearchablePdf("invoice_searchable.pdf");

Imports IronOcr

' IronOCR— local text extraction from a scanned document with preprocessing
Dim ocr As New IronTesseract()
ocr.Language = OcrLanguage.English
Using input As New OcrInput()
    input.LoadPdf("invoice.pdf")
    ' Preprocessing filters improve accuracy on low-quality scans
    input.Deskew()
    input.DeNoise()
    Dim result As OcrResult = ocr.Read(input)
    ' Structured output: pages, paragraphs, lines, words with confidence data
    For Each page In result.Pages
        For Each line In page.Lines
            Console.WriteLine($"{line.Text} (Confidence: {line.Confidence:P})")
        Next
    Next
    ' Export to searchable PDF for archival
    result.SaveAsSearchablePdf("invoice_searchable.pdf")
End Using