Subscribe to answers

Difference between Cloud OCR and FRE SDK (ver. 12)

163 Views
Last Post 26 November 2018

Alexander Ivakhnenko posted this 26 November 2018 - Last edited 26 November 2018

Hello Fine Reader Team,

I have developed application what works with Cloud OCR API.

I use TextRecognition feature.

The Cloud API returns me good result what can be reviewed in attached "Cloud API Results.png" file.

Now I try to use FineReader Engine SDK (version 12).

I use TextExtraction_Accuracy predefined profile.

But in this case I see bad recognition results ("FRE SDK Results.png" file).

I think I need to set up additional Parameters settings.

But I have tried some settings and combinations... And I have no expected results.

What difference between Parameters settings for Cloud API and TextExtraction_Accuracy predefined profile?

#Permalink
0
0
0

Attached Files

1 Comments

Alexander Ivakhnenko posted this 26 November 2018

My code snippets:

1) FRE SDK:

public DocumentModel RecognizeDocument(byte[] imageContent)
{
   DocumentModel result;

   var engineLoader = new InprocLoader();
   try
   {
       var engine = engineLoader.InitializeEngine(_customerProjectId);
       engine.LoadPredefinedProfile("TextExtraction_Accuracy");

       var document = engine.CreateFRDocument();
       using (var abbyyStream = new AbbyReadStream(imageContent))
       {
           // TODO: (alex) what about PrepareMode?
           document.AddImageFileFromStream(abbyyStream, PrepareMode: null);
       }

       // TODO: (alex) what about DocumentProcessingParams?
       document.Process(null);

       var exportParams = engine.CreateXMLExportParams();
       exportParams.WriteCharAttributes = XMLCharAttributesEnum.XCA_Extended;
       exportParams.WriteCharacterRecognitionVariants = true;

       using (var abbyyStream = new AbbyyFileWriter())
       {
           document.ExportToMemory(abbyyStream, FileExportFormatEnum.FEF_XML, exportParams);
           var data = abbyyStream.Stream.ConvertToArray();
           result = data.DesirializeXml<DocumentModel>();
       }
   }
   finally
   {
       engineLoader.ExplicitlyUnload();
   }

   return result;
}

2) OCR API:

public TaskModel CreateRecognitionTask(byte[] imageContent, LanguageEnum language)
{
   var client = new RestClient(Domain);

   var request = new RestRequest($"/processImage?profile=textExtraction&exportFormat=xml&xml:writeRecognitionVariants=true&readBarcodes=false&language={language}")
   {
       Method = Method.POST
   };

   AddAuthorizationHeader(request);

   request.XmlSerializer = new DotNetXmlSerializer();
   request.AddParameter("application/octet-stream", imageContent, ParameterType.RequestBody);

   var response = client.Execute<TaskResponseModel>(request);
   ThrowExceptionIfNeeded(response);

   return response.Data.Task;
}