TamilOCR
converts printed Tamil into digital text
documents in Unicode encoding.
Digitized texts can be stored in
different output formats including plain Unicode UTF-8 or RTF (Rich Text
Format), and can be opened with text editors such as OpenOffice or Microsoft
Word for further processing. TamilOCR yields accurate results for a wide range of modern Hindi fonts without training, saving the time otherwise needed to type Devanagari texts.