Abstract

The purpose of this paper is to discuss how to evaluate the complicated human hand motion. The advantages of this evaluation method are it doesn't depend on the hand size and its form and makes the hand motion classified even if having a little difference which is incomprehensible by appearances. The data of the hand motion is measured by CyberGlove and its characteristic values are obtained based on the statistical method. The characteristic values of the hand motion are the one-dimensional data gathered with the Principal Component Analysis (PCA) from the angle data measured and the quantity of the movement. The hand motion is evaluated from the characteristic values by the terms of 'accuracy', 'repeatability' and 'efficiency'. The effectiveness of the proposed evaluation is shown through the experiments of using chopsticks

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call