Old Southeast Asian Script Recognition Using Evolutionary Algorithm

Abstract

This paper proposes an approach to off-line handwritten Isan Dhamma character recognition by using the concept of evolutionary algorithm. The objective of this paper is to recognize Isan Dhamma characters straight from the character images without any feature extraction process. The performance of the proposed approach is compared to the results of the test done by 23 educated Buddhist monks. The experimental results demonstrate a very promising performance of the proposed approach.