OCR: Как запустить распознавание текста в интересующей области изображения?
В этом разделе
Вот C#/VB.NET код, который демонстрирует, как запустить распознавание текста в интересующей области изображения:
class OcrEngineRecognitionRegionExample
{
/// <summary>
/// Recognizes text in the specified image region 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 OcrImageUsingTesseractEngine(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
foreach (Vintasoft.Imaging.VintasoftImage image in images)
{
// set the recognition region
tesseractOcr.RecognitionRegion =
new Vintasoft.Imaging.RegionOfInterest(0, 0, image.Width, image.Height / 2);
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();
}
}
}
Class OcrEngineRecognitionRegionExample
''' <summary>
''' Recognizes text in the specified image region 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 OcrImageUsingTesseractEngine(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
For Each image As Vintasoft.Imaging.VintasoftImage In images
' set the recognition region
tesseractOcr.RecognitionRegion = New Vintasoft.Imaging.RegionOfInterest(0, 0, image.Width, image.Height \ 2)
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
End Class