Multimedia Development of English Vocabulary Learning in Primary School
Author : Syaiful Rohim, Aim
Abstrak :
In this paper, we describe a prototype of web-based intelligent handwriting education_x000D_
system for autonomous learning of Bengali characters. Bengali language is used by more than_x000D_
211 million people of India and Bangladesh. Due to the socio-economical limitation, all of the_x000D_
population does not have the chance to go to school. This research project was aimed to develop_x000D_
an intelligent Bengali handwriting education system. As an intelligent tutor, the system can_x000D_
automatically check the handwriting errors, such as stroke production errors, stroke sequence_x000D_
errors, stroke relationship errors and immediately provide a feedback to the students to correct_x000D_
themselves. Our proposed system can be accessed from smartphone or iPhone that allows_x000D_
students to do practice their Bengali handwriting at anytime and anywhere. Bengali is a_x000D_
multi-stroke input characters with extremely long cursive shaped where it has stroke order_x000D_
variability and stroke direction variability. Due to this structural limitation, recognition speed is_x000D_
a crucial issue to apply traditional online handwriting recognition algorithm for Bengali_x000D_
language learning. In this work, we have adopted hierarchical recognition approach to improve_x000D_
the recognition speed that makes our system adaptable for web-based language learning. We_x000D_
applied writing speed free recognition methodology together with hierarchical recognition_x000D_
algorithm. It ensured the learning of all aged population, especially for children and older_x000D_
national. The experimental results showed that our proposed hierarchical recognition algorithm_x000D_
can provide higher accuracy than traditional multi-stroke recognition algorithm with more_x000D_
writing variability.