Recognition of objects by grasping force using Linear Discriminant Analysis(LDA)

A low cost dataglove system is developed by designing a glove equipped with Force Sensing Resistor (FSR) on to the thumb, index and middle finger, named as GloveMAP. The system involves the finger movements with some of grasping activities to investigate the force exerted on the fingertips during grasping five different shapes of objects with same weight. The output forces obtained from the experiment are then analyzed by finding the features of force objects grasping. Linear Discriminat Analysis (LDA) is used as classifier to process the features information of grasping force. The final result of the recognition rate for cylinder, rectangular, spherical, planar and disc objects are 87.5%, 90%, 85%, 92% and 95% respectively.