An efficient method for on-line Vietnamese handwritten character recognition

Abstract

This paper deals with the problem of recognizing Vietnamese handwritten characters. Vietnamese is an accented writing language. Accented characters increase the number of classes to be recognized, which causes declining in the performance of powerful classifier such as SVM. To overcome this challenge, an accented character is segmented into two parts: the root character or letter and the accent. They are recognized separately, and then combined to build the accented character. This approach avoids increasing the number of classes to be considered. Therefore, the correct recognition rate can be improved and the response time can be reduced. The data investigated in this work is on-line produced by a tablet. The combination of on-line and off-line features is used. The experimental investigations show that the handwritten character recognition built on 45 selected features can compete with the recognition rate and response time of other well known tested on standard databases such as UNIPEN and IRONOFF.