Handwritten Odia Character Recognition

Abstract

Odia is one of the oldest and popular languages of India, spoken by more than 44 million people, especially in Odisha, India. Some characters in Odia are made up of more than one connected symbols.Compound characters are written by associating modifiers with consonants, resulting in a huge number of possible combinations, running into hundreds of thousands. Therefore, systems developed for recognition of other scripts, like Roman, cannot be used directly for the Odia language. In the present work, we have proposed robust structural solution for Odia character recognition where, a given text is segmented into lines and then each line is segmented into individual words and then each word is segmented into individual characters or basic symbols. Basic symbols are identified as the fundamental units of segmentation used for recognition. Using unique structure of some characters we have found better result as comparison to other methods.