[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Savannah-register-public] [task #14795] Submission of c++ OCRLib
From: |
Alexander Stroganov |
Subject: |
[Savannah-register-public] [task #14795] Submission of c++ OCRLib |
Date: |
Mon, 1 Jan 2018 02:15:56 -0500 (EST) |
User-agent: |
Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12) AppleWebKit/602.1.50 (KHTML, like Gecko) Version/10.0 Safari/602.1.50 |
URL:
<http://savannah.nongnu.org/task/?14795>
Summary: Submission of c++ OCRLib
Project: Savannah Administration
Submitted by: www_buddism_ru
Submitted on: Mon 01 Jan 2018 07:15:55 AM UTC
Should Start On: Mon 01 Jan 2018 12:00:00 AM UTC
Should be Finished on: Thu 11 Jan 2018 12:00:00 AM UTC
Category: Project Approval
Priority: 5 - Normal
Status: None
Privacy: Public
Percent Complete: 0%
Assigned to: None
Open/Closed: Open
Discussion Lock: Any
Effort: 0.00
_______________________________________________________
Details:
A new project has been registered at Savannah
This project account will remain inactive until a site admin approves
or discards the registration.
= Registration Administration =
While this item will be useful to track the registration process,
*approving or discarding the registration must be done using the specific
Group Administration
<https://savannah.nongnu.org/siteadmin/groupedit.php?group_id=11802> page*,
accessible only to site administrators,
effectively *logged as site administrators* (superuser):
* Group Administration
<https://savannah.nongnu.org/siteadmin/groupedit.php?group_id=11802>
= Registration Details =
* Name: *c++ OCRLib*
* System Name: *ocrlib*
* Type: non-GNU software and documentation
* License: GNU General Public License v2 or later
----
==== Description: ====
GPL c++ library for OCR.
Main purpose of the library it is free OCR service for all Asian buddhist
languages - tibetan, sanskrit, sinhala and another languages.
At present on base of the library we run free service for tibetan and sanskrit
printed books and manuskript OCR.
OCR core include image preprocessing algorithms, fast convolution neural
network algorithm based on neocognitron, vector and focal line recognition
algorithms, grammar analysis and fussy search algorithms.
On base of OCRLib during the 2011-2017 year was processed about 1.2 millions
of tibetan printed texts pages OCR and about 30 000 pages of tibetan
manuscripts.
As part of this work we have developed two open source tibetan fonts.
==== Other Software Required: ====
pugixml + MIT license + https://github.com/zeux/pugixml
re2 + BSD 3-clause "New" or "Revised" License + https://github.com/google/re2
==== Other Comments: ====
main OCR core no need Dependencies.
For Linux we will need some GPL library to open Tiff and JPEG images.
==== Tarball URL: ====
https://github.com/RimeOCRLIB/OCRLib
_______________________________________________________
Reply to this item at:
<http://savannah.nongnu.org/task/?14795>
_______________________________________________
Message sent via/by Savannah
http://savannah.nongnu.org/
- [Savannah-register-public] [task #14795] Submission of c++ OCRLib,
Alexander Stroganov <=