Loading...

Read code changes on dictionary basis

Support for GdPicture Tessaract Plugin.

Read code changes on dictionary basis

Postby lordnedox » Sun Oct 10, 2010 5:23 am

Hi,
i'm trying to read the following codes:

Image
obtaining the following result:
dictionary it: ((21457
dictionary en, fr: (C1457)

and
Image
obtaining the following result:
dictionary it, en: 8E00728l»89
dictionary fr: 8E00728489

Could someone explain me how is the dictionary used on simple codes like these?

I tried also setting the allowed characters string, only to numbers and capital letters, and then i get the first "8" recognised as a "S". How is this algorithm working too?

Thanks
Regards
Marco
lordnedox
 
Posts: 16
Joined: Sun Oct 10, 2010 5:13 am

Re: Read code changes on dictionary basis

Postby Loïc » Wed Oct 13, 2010 12:08 pm

Hi,

The dictionary files are use to make a choice between several possibilities. This choice depends on the dict file content...
I can not resume the algorithm behavior in a few words since it is a very complex process. But in a future release we will try to add feature to increase/decrease the trust in the dictionaries content to provide better result on ref numbers.

Kind regards,

Loïc
Loïc Carrère, support team.
www.orpalis.com
User avatar
Loïc
Site Admin
 
Posts: 4437
Joined: Tue Oct 17, 2006 10:48 pm
Location: France


Return to GdPicture Tesseract OCR Engine Plugin

Who is online

Users browsing this forum: No registered users and 0 guests