IIT Madras team develops easy OCR system for reading documents in Bharati script containing with how many Indian languges?

The research team from IIT Madras has used a multi-lingual Optical Character Recognition (OCR) scheme to develop a method for reading documents in Bharati script. The researchers have also developed a finger-spelling method that can be used by hearing-impaired persons to generate sign language, in collaboration with TCS Mumbai. The Bharati script is a conglomeration of 9 Indian languages, namely, Devnagari, Bengali, Gurmukhi, Gujarati, Oriya, Telugu, Kannada, Malayalam and Tamil. In the last 10 years, Professor V. Srinivasa Chakravarthy's research team at IIT Madras has worked on developing this script. he OCR scheme first segments the document into 2 parts, text and non-text. After this, the text is separated into paragraphs, sentences words and letters, where every letter is recognised as a character in ASCII (American Standard Code for Information Interchange) or Unicode. The letter again has several components, namely, the basic consonant, consonant modifiers, vowels.