Can ABBYY OCR return the recognized language of the extracted text

  • Last Post 25 April 2014
rsteng2 posted this 25 April 2014

I live in a multilingual country. There is high chances the customer will process a document of different language. I know that ABBYY OCR can recognize the targeted languages. However, can it return the language being recognized along with the extracted text? as a second variable other than the extracted text or a totally different function. Thanks.

Order By: Standard | Newest | Votes
Anastasia Galimova posted this 25 April 2014

Could you please specify the product you use?

rsteng2 posted this 25 April 2014

Oh, sorry. I use ABBYY OCR SDK for windows phone.this is the function to set the language: ProcessingSettings settings = new ProcessingSettings(); settings.SetLanguage("English,ChineseTaiwan, Japanese"); settings.OutputFormat = OutputFormat.txt; But can I get the language while downloading the result?

Anastasia Galimova posted this 28 April 2014

You can perform export to XML and find there the information about language for each text fragment. For example:

-<formatting lang="EnglishUnitedStates">
-<formatting lang="FrenchStandard">