[INDOLOGY] Sanskrit OCR

[Ajit Gargeshwari]

Namaskara Harry Spier,

Please see this message posted to this mailing list on 2 September 2018.

From: Martin Gluckman via INDOLOGY <indology at list.indology.info>
Date: Sun, 2 Sep 2018 at 4:55 AM
Subject: [INDOLOGY] Browser Based OCR Tool for Sanskrit
To: indology at list.indology.info <indology at list.indology.info>


Dear Friends,


I am happy to announce the completion of our browser based OCR tool that
has been developed for working primarily with Sanskrit text
(Devanagari/IAST or mixed) is now ready. This tool makes use of Google's
machine learning and supports many scripts including some undocumented and
experimental ones so you might be pleasantly surprised that a rare script
you are working on is supported or will be supported in future.


You may access it herewith: https://ocr.sanskritdictionary.com/


To make use of it simply paste an image into the browser and the
recognition will start automatically and output the text equivalent in
Unicode text. I personally use a free tool called Lightshot
<https://app.prntscr.com/en/index.html> to cut and paste selected parts of
the screen. You may also manually upload an image file if you prefer.


We have tested it with rather poorly printed texts and the results are very
promising and we hope this will be of use to the scholarly community. As
the system uses a machine learning engine it will constantly improve over
time.


I appreciate any feedback and suggestions for future improvement.


With kindest wishes,


Martin
_______________________________________________
INDOLOGY mailing list
INDOLOGY at list.indology.info
indology-owner at list.indology.info (messages to the list's managing
committee)
http://listinfo.indology.info (where you can change your list options or
unsubscribe)

On Mon, Nov 29, 2021 at 7:37 PM Harry Spier via INDOLOGY <
indology at list.indology.info> wrote:

> Dear list members,
> This link was given to me for online sanskrit OCR.
> https://ocr.sanskritdictionary.com/
>
> I don't recall if this has already been passed on to the list, but 've
> just tried it, pasting in some text from a Chaukhamba publication from the
> 1980's and it converted it to text perfectly.  It was even smart enough to
> join words separated by a dash at the end of lines.
>
> I didn't see any credits on the website. Does anyone know who is
> responsible for this website?
> Harry Spier
>
> _______________________________________________
> INDOLOGY mailing list
> INDOLOGY at list.indology.info
> https://list.indology.info/mailman/listinfo/indology


Regards
Ajit Gargeshwari
Web site Visit
https://archive.org/details/@sri_gargeshwari_digital_foundation
https://archive.org/details/karnatakasamskritauniversity
न जायते म्रियते वा कदाचिन्नायं भूत्वा भविता वा न भूयः।
अजो नित्यः शाश्वतोऽयं पुराणो न हन्यते हन्यमाने शरीरे।।2.20।।


On Mon, Nov 29, 2021 at 7:37 PM Harry Spier via INDOLOGY <
indology at list.indology.info> wrote:

> Dear list members,
> This link was given to me for online sanskrit OCR.
> https://ocr.sanskritdictionary.com/
>
> I don't recall if this has already been passed on to the list, but 've
> just tried it, pasting in some text from a Chaukhamba publication from the
> 1980's and it converted it to text perfectly.  It was even smart enough to
> join words separated by a dash at the end of lines.
>
> I didn't see any credits on the website. Does anyone know who is
> responsible for this website?
> Harry Spier
>
> _______________________________________________
> INDOLOGY mailing list
> INDOLOGY at list.indology.info
> https://list.indology.info/mailman/listinfo/indology
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://list.indology.info/pipermail/indology/attachments/20211129/24bb4d4c/attachment.htm>