Feature Extraction and recognition of Modifiers in Handwritten Marathi (Devanagari) Tex

Abstract This research work deals with the feature extraction and recognition of Modifiers in Marathi Text (Devanagari). Many researchers are working on the handwritten Marathi character recognition. As compare to English and other languages Marathi is little bit complex language. Marathi language contains 12 common vowels and 36 consonants. In addition to this there are compound characters. In this research work, the handwritten text is split in three regions namely region above Shirorekha upper region i.e. upper modifier, main character and lower region i.e. lower modifier below the character. Shape features are extracted for upper and lower modifiers. Support vector machine is used as classifier and the average recognition rate is compatible.