GSoC/GCI Archive
Google Summer of Code 2013

Ankur India

Web Page: https://github.com/ankur-india/ankur-india/wiki/Project-Ideas

Mailing List: http://lists.ankur.org.in/listinfo.cgi/project-ideas-ankur.org.in

Ankur.org.in is a group of volunteers who collaborate to promote localization and internationalization with the specific aim of improving usage of Bengali in Free and Open Source Software projects. The group is involved in internationalization and localization especially translations, content development, development of tools, utilities, widgets and APIs that help facilitate a wider community of like minded collaborators to participate in a community building process.

Please read this document for GSoC 2013 participation.

If you'd like to apply as a mentor for our organization, please contact one of the admins on #ankur.org.in (on irc.freenode.net) or, email them after registering here.

 

 

 

Projects

  • Improving accuracy of Bengali OCR tools OCR for languages with connected scripts is a widely popular subject, and a few open source projects can be found on the cloud, but none of them are complete as a whole. This project aims to extended an OCR tool for Bengali language, with an aim to improve accuracy up to 98%.
  • Improving information retrieval methods for OCR data sets consisting of Indic scripts This project aims at improving IR methods for OCRed data i.e. erroneous data. The mis-classification error introduced by OCR can significantly degrade the IR efficiency. We have to develop some IR methods which take these errors into account and give better results accordingly.
  • Speech based query and result retrieval system for Indian languages This projects intends to provide an easily extensible framework for utilizing speech input to query a data store of content and, provide result set. The goal of the project is to implement the system in Telugu along with a documented process of how to extend it to other Indian languages.
  • To implement a tool for improving the aesthetic quality of fonts of Indic scripts There are a lot of fonts for Roman scripts but when it comes to fonts for Indic scripts like Devanagri, Bengali, Telugu, there is a dearth of good quality Open Type fonts. This tool would facilitate in providing tests enabling Font developers to contribute more to Open Type Indic fonts.