“…B Patil and Subbareddy [4] have proposed a neural network based system for script identification of Kannada, Hindi and English languages. Dhandra et al, [5] have exploited the use of discriminating features (aspect ratio, strokes, eccentricity, etc,) as a tool for determining the script at word level in a bi-lingual document containing Kannada, Tamil and Devnagari containing English numerals. A method to automatically separate text lines of Roman, Devanagari and Telugu scripts has been proposed by Pal et al, [6].…”