PRINCIPAL COMPONENT ANALYSIS FOR THE CLASSIFICATION OF FINGERS MOVEMENT DATA USING DATAGLOVE "GLOVEMAP"
Nazrul H. Adnan, Wan Khairunizam, Shariman Ab, Juliana Aida Abu Bakar, Jalan Raja Laut · 2013
Nowadays, many classifier methods have been used to classify or categorizehuman body motions of human posture including the classification of fingers movement. Principal Component Analysis (PCA) is one of classical method that capable to be used to reduce the dimensional dataset of hand motion as well as to measure the capacity of the fingers movement of the hand grasping.The objective of this paper is to analyze thehuman grasping feature between thumbs, index and middle fingers while grasping an object using PCAbasedtechniques. The finger movement dataare measured using a low cost DataGlove“GloveMAP” which is based on fingers adapted postural movement (or EigenFingers) of the principal component. The fingers movement is estimated from the bending representative of proximal and intermediate phalanges of thumb, index and middle fingers. The effectiveness of the proposed assessment analysis is shown through the experimental study of three fingers motions. The experimental results showed that the use of the first and the second principal components allows for distinguishing between three fingers grasping and represent the features for an appropriate manipulation of the object grasping.