Use of Gradient Information for Recognition of Indian Scripts

Recently there is growing trend among worldwide researchers to recognize handwritten characters of many languages and scripts. Much of research work is done in English and Japanese like languages. However on Indian scripts the research work is comparatively lagging. Among Indian Scripts most of the research work available is on mainly Devanagari and Bangla scripts. The work on other Indian scripts is in beginning stage. In this work offline recognition of isolated handwritten characters and numerals of both Gurmukhi and Devanagari scripts is presented. All experiments have been conducted on different databases of characters and numerals of Gurmukhi and Devanagari Scripts.35 basic characters of Gurmukhi script and 36 basic consonants of Devanagari Script have been considered and all are assumed to be isolated and bearing header lines on top to recognize. In numerals handwritten samples of 10 digits of both Gurmukhi and Devanagari from different writers are considered.