How to use extract text from multiple image using Tesseract OCR in C#?

image2text.cs

  /// <summary>
  /// Method to extract text from an image.
  /// </summary>
  /// <param name="imagePaths">A path to entire images.</param>
  /// <returns>Returns a list of strings.</returns>
  private static List<List<string>> ExtractTextFromImage(List<string> imagePaths)
  {
      List<List<string>> allTexts = new();

      // Initialize the Tesseract engine
      string TessData = @"C:..\LANGUAGE_DATA_FOLDER_LOCATION";
      using var engine = new Tesseract.TesseractEngine(TessData, "eng", Tesseract.EngineMode.Default);

      foreach (var imagePath in imagePaths)
      {
          // Load and process the image
          using var img = Tesseract.Pix.LoadFromFile(imagePath);
          using var page = engine.Process(img);

          // Fetch and split the extracted text
          string extractedTexts = page.GetText();
          string[] words = extractedTexts.Split(new[] { ' ', '\t', '\r', '\n' }, StringSplitOptions.RemoveEmptyEntries);

          allTexts.Add(new List<string>(words));
      }

      // Return the extracted text as a list
      return allTexts;
  }