Analysis of Stroking Motions in Drawing by Experts for Development of a Learning Support System

Illustrators who have some drawing experience can sometimes draw an ideal stroke repeatedly. However, they cannot always reproduce an ideal stroke that they have drawn, because they do not understand how they moved their own hands to draw it. In order to solve this problem, a new learning support system based on presenting the ideal stroking motion of the learner as a teacher´s motion is needed so that learners can enhance their own drawing skills. In order to clarify the differences in motion between good and bad drawing strokes as the first step in the development of such a system, this paper analyzes the stroking motions of experts in the process of drawing circles. Several features are exploited, namely, the pen speed, the pen pressure, the time required to draw each quarter circle, and the movement of the hand. With these features, the accuracy of classification using machine learning is 67% on average. This means that stroke speed, pen pressure, and stroke rhythm (which is the specific pattern of changes in speed) may be useful to distinguish between good and bad strokes.