Indian Government Launches A Web Based Optical Character Recognition System

Sachin Pilot, Indian Minister of State for Communications and Information Technology, has launched a new web based Optical Character Recognition (OCR) system for Hindi and Punjabi.

Explaining that this initiative will be a significant move towards the digital inclusion of differently-abled people from various linguistic backgrounds, Sachin Pilot hoped that it will also pave the way for wider usage of Indian languages in governance applications.

For people who aren’t familiar with OCR technology, it is a process through which handwritten, typewritten, or printed text is converted to electronic form. This will allow editing of printed books and documents, searching for any specific word/phrase, and also implementing techniques like machine translation or text-to-speech on it.

Along with the OCR system, Sachin Pilot also launched a text-to-speech system across six languages – Hindi, Marathi, Bangla, Telugu, Tamil, and Malayalam.

This effectively means that developers can now finally integrate this system in their software and users can listen to regional books and documents on any device which supports text-to-speech technology i.e. mobile phones, e-book readers, tablets, computers, and so on. Also, if the device sports a screen reader, users will be able to easily navigate and perform basic operations on it.

Both the systems were developed by Technology Development for Indian Language (TDIL), a program driven by India’s Department of Information Technology.

While the text-to-speech system has already been integrated with OCR-A font and Non Visual Desktop Access (NVDA), a free and open source screen reader for Windows OS, the Optical Character Recognition, is on showcase at TDIL Data Centre.

[Image Credit]