Aspose.OCR を使用して .NET でスキャンされた PDF からテキストを抽出する方法

dotnet add package Aspose.OCR

using Aspose.OCR;

Metered license = new Metered();
license.SetMeteredKey("<your public key>", "<your private key>");
Console.WriteLine("License configured successfully.");

OcrInput input = new OcrInput(Aspose.OCR.InputType.PDF);
input.Add("scanned_sample.pdf", 0, 3); // Process first 3 pages of the PDF
Console.WriteLine("Scanned PDF loaded successfully.");

Aspose.OCR.AsposeOcr recognitionEngine = new Aspose.OCR.AsposeOcr();
RecognitionSettings settings = new RecognitionSettings();
settings.Language = Aspose.OCR.Language.Latin;  // Set OCR language (e.g., Latin for English)

List<Aspose.OCR.RecognitionResult> results = recognitionEngine.Recognize(input, settings);
Console.WriteLine("Text extracted from PDF.");

string recognizedText = results[0].RecognitionText;
Console.WriteLine($"Recognized Text: {recognizedText}");

// Save the result to a text file
results[0].Save("output.txt", Aspose.OCR.SaveFormat.Text);
Console.WriteLine("Recognized text saved to output.txt.");