В этом разделе
Представляет абстрактный базовый класс для механизма оптического распознавания символов.
Объектная модель
Синтаксис
'Declaration
Public MustInherit Class OcrEngine
public abstract class OcrEngine
public __gc abstract class OcrEngine
public ref class OcrEngine abstract
Пример
Вот C#/VB.NET код, который демонстрирует, как распознавать текст на изображении с помощью механизма OCR Tesseract.
''' <summary>
''' Recognizes text in image using Tesseract OCR engine.
''' </summary>
''' <param name="filename">The name of file, which stores images with text.</param>
''' <param name="ocrLanguage">The language of recognizing text.</param>
Public Shared Sub RecognizeTextInImageUsingTesseractOcrEngine(filename As String, ocrLanguage As Vintasoft.Imaging.Ocr.OcrLanguage)
' create an image collection
Using images As New Vintasoft.Imaging.ImageCollection()
' add images from file to the image collection
images.Add(filename)
System.Console.WriteLine("Create Tesseract OCR engine...")
' create the Tesseract OCR engine
Using tesseractOcr As New Vintasoft.Imaging.Ocr.Tesseract.TesseractOcr()
System.Console.WriteLine("Initialize OCR engine...")
' init the Tesseract OCR engine
tesseractOcr.Init(New Vintasoft.Imaging.Ocr.OcrEngineSettings(ocrLanguage))
' for each image in image collection
For Each image As Vintasoft.Imaging.VintasoftImage In images
System.Console.WriteLine("Recognize the image...")
' recognize text in image
Dim ocrResult As Vintasoft.Imaging.Ocr.Results.OcrPage = tesseractOcr.Recognize(image)
' output the recognized text
System.Console.WriteLine("Page Text:")
System.Console.WriteLine(ocrResult.GetText())
System.Console.WriteLine()
Next
' shutdown the Tesseract OCR engine
tesseractOcr.Shutdown()
End Using
' free images
images.ClearAndDisposeItems()
End Using
End Sub
/// <summary>
/// Recognizes text in image using Tesseract OCR engine.
/// </summary>
/// <param name="filename">The name of file, which stores images with text.</param>
/// <param name="ocrLanguage">The language of recognizing text.</param>
public static void RecognizeTextInImageUsingTesseractOcrEngine(
string filename,
Vintasoft.Imaging.Ocr.OcrLanguage ocrLanguage)
{
// create an image collection
using (Vintasoft.Imaging.ImageCollection images =
new Vintasoft.Imaging.ImageCollection())
{
// add images from file to the image collection
images.Add(filename);
System.Console.WriteLine("Create Tesseract OCR engine...");
// create the Tesseract OCR engine
using (Vintasoft.Imaging.Ocr.Tesseract.TesseractOcr tesseractOcr =
new Vintasoft.Imaging.Ocr.Tesseract.TesseractOcr())
{
System.Console.WriteLine("Initialize OCR engine...");
// init the Tesseract OCR engine
tesseractOcr.Init(new Vintasoft.Imaging.Ocr.OcrEngineSettings(ocrLanguage));
// for each image in image collection
foreach (Vintasoft.Imaging.VintasoftImage image in images)
{
System.Console.WriteLine("Recognize the image...");
// recognize text in image
Vintasoft.Imaging.Ocr.Results.OcrPage ocrResult = tesseractOcr.Recognize(image);
// output the recognized text
System.Console.WriteLine("Page Text:");
System.Console.WriteLine(ocrResult.GetText());
System.Console.WriteLine();
}
// shutdown the Tesseract OCR engine
tesseractOcr.Shutdown();
}
// free images
images.ClearAndDisposeItems();
}
}
Иерархия наследования
Требования
Целевые платформы: .NET 8; .NET 7; .NET 6; .NET Framework 4.8, 4.7, 4.6, 4.5, 4.0, 3.5
Смотрите также