←Select platform

DetectLanguages Method

Summary

Detects the language of the page from a list of languages that is provided by the user.

Syntax

Objective-C

WinRT C#

C++

public string[] DetectLanguages( 
   string[] languages 
)

Function DetectLanguages( _ 
   ByVal languages() As String _ 
) As String()

string[] DetectLanguages(  
   string[] languages 
)

- (NSArray<NSNumber *> *)detectLanguages:(NSArray<NSNumber *> *)languages error:(NSError **)error

function Leadtools.Forms.Ocr.IOcrPage.DetectLanguages(  
   languages  
)

array<String^>^ DetectLanguages(  
   array<String^>^ languages 
)

Parameters

languages
An array of String objects that contains the names of the languages to check for. The language values used throughout the LEADTOOLS OCR toolkit are string values based on RFC 4646 (Windows Vista and later). The name could be an ISO 639 two-letter lowercase culture code associated with a language or a combination of ISO 630 and ISO 3166 two-letter uppercase subculture codes associated with a country or region.

It's suggested to use few (fewer than 5) languages only. The recognition engine will use all those language dictionaries to recognize the words in the document.

Return Value

An array of String objects that contains the names of the detected page language(s).

Remarks

DetectLanguages is only supported in the LEADTOOLS Professional and Advantage OCR engines.

The page may contain a single language only, but it can be any Latin-alphabet or Asian language.

Note: Automatic detection of Greek and Cyrillic is not proposed.

If the language can not be determined, the language of the previous page will be used.

To improve the detection accuracy, set an array with possible languages to be used, then pass it through the languages parameter.

Automatic language detection is performed as a relatively fast initial processing step before character recognition. Therefore, the accuracy will dependent on the image quality and many other conditions.

Use the GetSupportedLanguages to obtain a list of the languages supported by the IOcrEngine.

Use the IsLanguageSupported to check if a given language is supported by the IOcrEngine.

Example

This example will detect images with English, French, and German languages.

using Leadtools; 
using Leadtools.Codecs; 
using Leadtools.Forms.Ocr; 
using Leadtools.Forms; 
using Leadtools.Forms.DocumentWriters; 
using Leadtools.WinForms; 
using Leadtools.Drawing; 
using Leadtools.ImageProcessing; 
using Leadtools.ImageProcessing.Color; 
 
public void DetectLanguagesExample() 
{ 
   string tifFileName = Path.Combine(LEAD_VARS.ImagesDir, "OCR1.tif"); 
 
   // Create an instance of the engine 
   using (IOcrEngine ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.Professional, false)) 
   { 
      // Start the engine using default parameters 
      ocrEngine.Startup(null, null, null, null); 
 
      // Create an OCR document 
      using (IOcrDocument ocrDocument = ocrEngine.DocumentManager.CreateDocument()) 
      { 
         // Add this image to the document 
         IOcrPage ocrPage = ocrDocument.Pages.AddPage(tifFileName, null); 
 
         // Auto detect page language. 
         string[] languages = { "en", "fr", "de" }; 
         string[] pageLanguages = ocrPage.DetectLanguages(languages); 
 
         if (pageLanguages != null && pageLanguages.Length > 0) 
         { 
            Console.WriteLine("Page language(s):{0}", Environment.NewLine); 
            foreach (string lang in pageLanguages) 
            { 
               // Get the friendly name of this language using the .NET CultureInfo class 
               CultureInfo ci = new CultureInfo(lang); 
               Console.WriteLine("{0}{1}", ci.EnglishName, Environment.NewLine); 
            } 
         } 
      } 
 
      // Shutdown the engine 
      // Note: calling Dispose will also automatically shutdown the engine if it has been started 
      ocrEngine.Shutdown(); 
   } 
} 
 
static class LEAD_VARS 
{ 
   public const string ImagesDir = @"C:\Users\Public\Documents\LEADTOOLS Images"; 
}

Imports Leadtools 
Imports Leadtools.Codecs 
Imports Leadtools.Forms.Ocr 
Imports Leadtools.Forms.DocumentWriters 
 
Public Sub DetectLanguagesExample() 
   Dim tifFileName As String = Path.Combine(LEAD_VARS.ImagesDir, "OCR1.tif") 
 
   ' Create an instance of the engine 
   Using ocrEngine As IOcrEngine = OcrEngineManager.CreateEngine(OcrEngineType.Professional, False) 
      ' Start the engine using default parameters 
      ocrEngine.Startup(Nothing, Nothing, Nothing, Nothing) 
 
      ' Create an OCR document 
      Using ocrDocument As IOcrDocument = ocrEngine.DocumentManager.CreateDocument() 
         ' Add this image to the document 
         Dim ocrPage As IOcrPage = ocrDocument.Pages.AddPage(tifFileName, Nothing) 
 
         ' Auto detect page language. 
         Dim languages As String() = {"en", "fr", "de"} 
         Dim pageLanguages As String() = ocrPage.DetectLanguages(languages) 
 
         If pageLanguages IsNot Nothing AndAlso pageLanguages.Length > 0 Then 
            Console.WriteLine("Page language(s):{0}", Environment.NewLine) 
            For Each lang As String In pageLanguages 
               ' Get the friendly name of this language using the .NET CultureInfo class 
               Dim ci As New CultureInfo(lang) 
               Console.WriteLine("{0}{1}", ci.EnglishName, Environment.NewLine) 
            Next 
         End If 
      End Using 
 
      ' Shutdown the engine 
      ' Note: calling Dispose will also automatically shutdown the engine if it has been started 
      ocrEngine.Shutdown() 
   End Using 
End Sub 
 
Public NotInheritable Class LEAD_VARS 
   Public Const ImagesDir As String = "C:\Users\Public\Documents\LEADTOOLS Images" 
End Class