Thank you very much for your reply.

I just need the "raw" confidence value of separated characters. In my
work, I need to evaluate if each segmented connected component is a
character or not.

Thai

On Jun 29, 1:29 am, tmbdev <[email protected]> wrote:
> OCRopus outputs full confidence values in the .fst files that it
> produces.  Those confidence values are negative log likelihoods.
>
> It does not output confidence values after alignment with the language
> model because that's not really a good thing to do; you need the
> segmentation alternatives in order to interpret the confidence values
> correctly.
>
> Tom
>
> On Jun 28, 11:56 pm, hvthaibk <[email protected]> wrote:
>
> > Hi,
>
> > I am wondering if there is any way to obtain the confidence value of
> > each recognized character by OCRopus.
>
> > Thanks for your reply
>
> > Thai
--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"ocropus" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to 
[email protected]
For more options, visit this group at 
http://groups.google.com/group/ocropus?hl=en
-~----------~----~----~----~------~----~------~--~---

Reply via email to