Estimating Writing Neatness from Online Handwritten Data

Handwriting is the most fundamental expressive activity in learning. In order to utilize the nature, digital pen technology has been emerged to capture notes and transfer them. We have developed AirTransNote, a student note-sharing system that facilitates collaborative and interactive learning in conventional classrooms. With AirTransNote system, a teacher can immediately share student notes to the class by a projected screen to enhance a group learning. However, in order to improve the effectiveness of sharing notes, the teacher need to pick up an effective note for sharing. But selecting the suitable note during a lecture is difficult because it consumes much time. Also the students should change their mind to improve the presentation of their handwritten notes, because carefully written notes are more accessible for other students and they reduce irrelevant, careless mistakes. To facilitate improvements of the learning based on note sharing, we need a method to estimate the neatness of the note automatically. If the method is established, the teacher can easily select effective notes. It can also be applied to feedback the student to write better. We examined 14 basic features from handwritten notes by considering correlation coefficients, and found that the variance of pen speed, average of angular point, and average of pen speed were the significant features for evaluating neatness of the handwritten notes.