You do have to retrieve information/text from that to
be able to use it. Is that something to be tackled later?
Yes
Regards,
Pavanaja
-----Original Message-----
From: wikimediaindia-l-bounces(a)lists.wikimedia.org
[mailto:wikimediaindia-l-bounces@lists.wikimedia.org] On Behalf Of sankarshan
Sent: 18 September 2013 13:41
To: Wikimedia India Community list
Subject: Re: [Wikimediaindia-l] Announcement: CIS-A2K's Train The Trainer Program
On Wed, Sep 18, 2013 at 1:25 PM, Pavanaja U B <pavanaja(a)vishvakannada.com> wrote:
ScanTailor is not a OCR. It has got nothing to do with
Indian Languages.
Indeed. I realized that it clearly mentions that "Scanning, optical character
recognition, and assembling multi-page documents are out of scope of this project."
And, in that context, what is the use case in which ScanTailor would be handy? The website
states further states that "It performs operations such as page splitting, deskewing,
adding/removing borders, and others." From which I understand that is a necessary
step in the flow of actual_document -> photograph/scan -> re-alignment. But that
generates a digitized text. You do have to retrieve information/text from that to be able
to use it. Is that something to be tackled later?
--
sankarshan mukhopadhyay
<https://twitter.com/#!/sankarshan>
_______________________________________________
Wikimediaindia-l mailing list
Wikimediaindia-l(a)lists.wikimedia.org
To unsubscribe from the list / change mailing preferences visit
https://lists.wikimedia.org/mailman/listinfo/wikimediaindia-l