Reaserchers from IIT Madras have developed easy multi-lingual optical character recognition (OCR) schemes for reading documents in Bharati script. They also have developed universal finger-spelling language (method) for the nine Indian languages It was developed in collaboration of TCS, Mumbai and can be used to generate sign language for hearing-impaired persons
About Bharati script
OCR schemes for Bharati script
It involve first separating (or segmenting) document into text and non-text. The text is then segmented into paragraphs, sentences words and letters. Each letter is then recognised as character in some recognisable format such as Unicode or ASCII. The letter has various components such as basic consonant, consonant modifiers, vowels etc.