NY Univ. Develops New Tool for Translating Sanskrit

NEW YORK, May 23, 2003: Sanskrit is among the world´s oldest recorded language, but putting works created over the last 3,000 years onto the Web has not been easy. Documents written in Devanagiri, a script used for Sanskrit, can be scanned as images. However, optical character recognition, O.C.R., software for turning Devanagiri texts into digital information that can be searched and reformatted has not been commercially available.

Devanagari script is used by over 500 million people all over the world, and is the base script of many Indian and South Asian languages such as Sanskrit, Hindi and Marathi.

A team of scientists and research students at the Center of Excellence in Document Analysis and Recognition (CEDAR), at the State University of New York at Buffalo, have been working on a new technology in an effort to accelerate the development of O.C.R. software for Devanagiri. The project is funded by the National Science Foundation (NSF), as part of its´ Digital Libraries initiative.

The project, named "Indian Language Technologies", is headed by Dr. Venugopal Govindaraju, Associate Director of CEDAR, and a professor of Computer Science & Engineering at the SUNY Buffalo. The other members of the group are Srirangaraj Setlur, Vemulapati Ramanaprasad, SuryaPrakash Kompalli and Swapnil Khedekar. The group is also working in collaboration with Indian Statistical Institute, (ISI) Kolkata.

The team has successfully developed a prototype, and are now distributing a script-recognition tool that they hope will become the international standard for software that can recognize Devanagiri.

Their script-recognition software can separate lines and individual characters written in the flowing script. It then offers an on-screen transliteration in Roman characters for proofreading.

This software can be downloaded free at: www.cedar.buffalo.edu/ILT