Isolated Sinhala handwritten character recognition using part based matching technique

Abstract

This paper presents a novel approach for Sinhala handwritten character recognition using a part based matching technique. The Sinhala character set consist of some common parts. Therefore, the characters can be split into its parts. Each part in turn, can be considered as an atomic element, which these characters are composed of. The proposed method splits the characters into their atomic parts and then conducts the recognition process. Template matching is used to compare the character parts and characters. To improve the recognition process, the global characteristics of the characters are used. Experimental results show that the proposed method gives an average accuracy of 46% where the maximum accuracy is 100% and the minimum accuracy is 11%.