Image of Varanasi - Home to the Sampurnanand Sanskrit University

OCR in Indian Languages

Angreezi mein kehtae hai…….

This song from the Amitabh Bachhan starrer was a hit and did give us cues to express our love to our beloved in various Indian languages. The song writer and the movie crew understood the diversity in India, and capitalised on this opportunity with a song that still appeals to people from all parts of India.

At EisenVault, the document management system that we created is for SME’s and organisation spread all across India. One key feature on EisenVault, that is also being provided as a cloud based document management system to Indian and global organisations, was the ability to search every word on a document including scanned pdf, JPEG etc. This would be possible with our integrated OCR engine. We understand that in India people use their local language in their work environment so we are adding capabilities for OCR in Indian languages like Bengali, Tamil, Telugu, Kannada, Hindi, Gujarati etc. This will help customers store and smartly retrieve documents from the digital vault as and when required.

We have ambitions of going global and would be adding ocr capabilities in Russian, Arabic, Romanian, Hungarian and many other global languages. Hopefully like we took cue from the movie on Indian languages, we will soon have someone take a cue from EisenVault and write a global version of the same saying “Japanese mein kehtae hai”.