Grasp analysis using multi-fingered manipulation of objects

The rapid development of technologies that are emerging during this era produces the evolution of human-computer interaction (HCI). Dataglove is one of sensor technologies resultant from HCI advancement. Dataglove provides vital information of finger grasping activities for HCI and Human-Machine Interface (HMI) by providing physical data of finger bending. Nevertheless, data acquisitions from Dataglove need to be processed and analyzed in order to effectively train the computer to recognize the finger grasping activities. The purpose of this research is to recognize the grasping objects by using feature extraction and clustering techniques. The conclusion will determine grasping features of subject to grasp the experimental object with the thumb, index and middle fingers of GloveMAP. Based on fingers movement adapted, this study gives the grasping features in order to justify the best grasping for each subject grasp behavior.