KTM Language recognition

KTM Language recognition

Postby » Fri Jan 18, 2013 1:30 am

Hi, Using KTM for document extraction, I was wondering if it is possible to extract a "language code". In other words, can KTM recognize the document is in English, French, Dutch, German, Spanish, .... I guess it is more the OCR engine that "could" do this but maybe there is some hidden field in KTM with this extracted language code? Or is there a KTM locator that could do the job. Does anyone of you has experience with extracting the language code via KTM/OCR Engine? I know this extraction like any other extraction is comes with a likelyhood but that is OK. Regards Kris Bogaert, Belgium
Participant
 
Posts: 1
Joined: Wed Dec 19, 2012 4:08 am

Re: KTM Language recognition

Postby » Fri Jan 18, 2013 5:53 am

Hi!

There is a sample project for language based classification. It is located in Program files\Kofax\Transformation\Samples\CLSLoc_Language.zip

It can be used as You like

Hando
Participant
 
Posts: 362
Joined: Thu Jul 17, 2008 9:42 pm

Re: KTM Language recognition

Postby » Wed Jun 01, 2016 6:29 am

Hando,

I see the post is allready some years ago but maybe you can help me. I checked the sample project you mention but i do not see where the classification of the different langauges takes place.
Can you tell me how this sample should work?

Johan
Participant
 
Posts: 244
Joined: Wed Sep 13, 2006 10:21 pm

Re: KTM Language recognition

Postby » Wed Jun 08, 2016 1:57 am

Hi!

Believe me , it works :)
how to use it - create a classification locator in your project and set it to language classification project. Enjoy :)
If You see that there is some languages missing, You can add your own languages and as it works on content classifier, you need to add some text files in this language for training.

Hando
Participant
 
Posts: 362
Joined: Thu Jul 17, 2008 9:42 pm


Return to Kofax Transformation Modules General Discussion

Who is online

Users browsing this forum: No registered users and 2 guests