A Chinese Handwriting Education System with Automatic Error Detection

Abstract

We build a distance education application of a Chinese handwriting education system that allows students to do practice at anytime and anywhere. As an intelligent tutor, the system can automatically check the handwriting errors, such as the stroke production errors, stroke sequence error and stroke relationship error. Then our system should provide useful feedback to the student. In this paper, attributed relational graph matching is used to locate the handwriting errors. The pruning strategy is applied to reduce the computational time. The experiment results show that our proposal can handle more handwriting error cases than existing methods with a higher accuracy.