Handwritten character recognition of Odia script

This paper presents a character recognition system of handwritten Odia script. Although, a lot of research has been carried out in handwritten character recognition, not considerable research has been carried out to recognize handwritten Odia characters. In this work we have attempted to classify 36 basic Odia consonants. Total 48 geometric features were extracted which includes shadow features, centroid features and distance based features. Weighted Euclidean Distance method has been used to classify the characters. The overall accuracy of our method is 87.6%. Further, Unicode mapping of the Odia characters has been proposed for uniform encoding of the Odia characters and thus paves the way for recognition and transmission of the characters easily.