taskSwathanthra Malayalam Computing - Tasks: task #6353, functional...

 
 

You are not allowed to post comments on this tracker with your current authentification level.

task #6353: functional optical-character-recognition application

Submitted by:  Praveen Arimbrathodiyil <praveen_a>
Submitted on:  Thu 04 Jan 2007 01:15:14 PM UTC  
 
Category: ocrShould Start On: Wed 03 Jan 2007 06:30:00 PM UTC
Should be Finished on: Sun 14 Jun 2009 06:30:00 PM UTCPriority: 7 - High
Status: In ProgressPrivacy: Public
Percent Complete: 20%Assigned to: jinesh <jiesh_kj007>
Open/Closed: OpenEffort: 0.00

(Jump to the original submission Jump to the original submission)

Sat 14 Mar 2009 06:21:19 PM UTC, comment #7:

An initial test version is available. Experiments are on. WIll report more on the details coming weeks.

http://wiki.smc.org.in/OCR

has the details of work and plans. An analysis of the system will be done soon with more improvements.

jinesh <jiesh_kj007>
Project MemberIn charge of this item.
Mon 02 Mar 2009 10:09:43 AM UTC, comment #6:

I conducted an initial study of Tesseract OCR. Details I have put up in

http://logbookofanobserver.wordpress.com/2009/03/01/tesseract-and-malayalam-some-intial-experiments/

Intial Observations and Future and Immediate plans i tried to explain there. I believe it is possible to get a pretty decent classifier system from tesseract. What i am not quite sure is, about the segmentation inputs and post processing done.

I am doing a proper study of the classifier system right now. Will be updating the current base system, which i updated with experimental Malayalam Support to a better system pretty soon!

jinesh <jiesh_kj007>
Project MemberIn charge of this item.
Mon 24 Dec 2007 10:02:28 AM UTC, comment #5:

The GSOC project failed to complete the project and we need somebody to take up. Note that it is not a good idea to start from the scratch.
This is is a high priority project.
http://code.google.com/p/tesseract-ocr will be a good starting point.

Santhosh Thottingal <santhosh>
Project Administrator
Wed 07 Feb 2007 11:06:03 AM UTC, comment #4:

Akshara source code is available in svn
http://akshara.svn.sourceforge.net/viewvc/akshara/

Praveen Arimbrathodiyil <praveen_a>
Sun 14 Jan 2007 02:58:58 PM UTC, comment #3:

Antony and his friends from MES Engineering College ahve been doing a good work on akshara OCR http://sourceforge.net/projects/akshara

We'll get the code in svn once he finishes his exams. Also we need to have a website for akshara, any volunteers?

Praveen Arimbrathodiyil <praveen_a>
Mon 08 Jan 2007 07:49:29 AM UTC, comment #2:

Antony has been working on akshara project and it is 60-70% complete now.

Project site is at http://sourceforge.net/projects/akshara

Praveen Arimbrathodiyil <praveen_a>
Mon 08 Jan 2007 07:37:03 AM UTC, comment #1:

Others working on an OCR.

http://varamozhi.wikia.com/wiki/Help:Contents/OCR
Says

There has been following attempts in Malayalam OCR:

1. By E C Vijil in 2001-2002. He was a student of Thrissur Engg
College and IIT Bombay. He didn't go much beyond initial concept of
idea. His email ids are vijilec അറ്റ് yahoo.com, vijilec അറ്റ്
hotmail.com. His Mizhi OCR site can still be accessed.
2. The OCR used by Mr.Unni K Varma in Panchathanthra.org. This OCR
is in the beta stage of the development. It generates latex directly;
further details are not known. Contact address: contact അറ്റ്
panchathantra.org
3. Chithira V (chitira അറ്റ് gmail.com), a student of Computer
Science & Engg. from Govt. Engg. College, Thrissur was doing a
Malayalam OCR development as a part of her final year project. Further
details are unknown.
4. -unavailable- from MES has done a miniproject in OCR.

Lets try to follow up with them.

Praveen Arimbrathodiyil <praveen_a>
Thu 04 Jan 2007 01:15:14 PM UTC, original submission:

We need to have an ocr application for malayalam. We might want to have a serious look at http://sourceforge.net/projects/tesseract-ocr

Praveen Arimbrathodiyil <praveen_a>

 

No files currently attached

 

Depends on the following items: None found

Items that depend on this one: None found

 

Carbon-Copy List
  • -unavailable- added by jiesh_kj007 (Posted a comment)
  • -unavailable- added by jiesh_kj007 (group mailing list)
  • -unavailable- added by santhosh (Posted a comment)
  • -unavailable- added by praveen_a (Submitted the item)
  •  

    Do you think this task is very important?
    If so, you can click here to add your encouragement to it.
    This task has 0 encouragements so far.

    Only logged-in users can vote.

     

    Please enter the title of George Orwell's famous dystopian book (it's a date):

     

     

    Follow 14 latest changes.

    Date Changed By Updated Field Previous Value => Replaced By
    Sat 14 Mar 2009 06:21:19 PM UTCjiesh_kj007Percent Complete10%=>20%
    Mon 02 Mar 2009 10:09:43 AM UTCjiesh_kj007Should be Finished onWed 03 Dec 2008 12:00:00 AM UTC=>Sun 14 Jun 2009 06:30:00 PM UTC
      StatusNone=>In Progress
      Percent Complete0%=>10%
      Assigned toNone=>jiesh_kj007
      Carbon-Copy-=>Added -unavailable-
    Mon 24 Dec 2007 10:02:28 AM UTCsanthoshShould be Finished onThu 03 Jan 2008 06:30:00 PM UTC=>Wed 03 Dec 2008 12:00:00 AM UTC
      StatusIn Progress=>None
      Percent Complete60%=>0%
      Assigned toantonyfm=>None
    Sun 14 Jan 2007 02:58:58 PM UTCpraveen_aAssigned toNone=>antonyfm
    Mon 08 Jan 2007 07:49:29 AM UTCpraveen_aStatusNone=>In Progress
      Percent Complete0%=>60%
    Thu 04 Jan 2007 01:15:14 PM UTCpraveen_aCarbon-Copy-=>Added -unavailable-

    Back to the top


    Powered by Savane 3.1-cleanup