Hand Pattern Recognition from Semg Signals Using Signal Processing

Abstract

Recognition of hand patterns using sEMG signals can play a significant role in improving and empowering people's life experiences for their daily activities based on artificial limbs or prothetics. EMG signals have been used to develop a novel algorithm using time domain descriptor characteristics derived from the techniques of sEMG signals. The obtained signal consists of two-channel voltage levels. These signals were processed and characteristics like zero order moment, second order moment and fourth order moment were evaluated. A fusion of root mean square logarithm, second and fourth order time difference logarithm, and wavelength ratio was the final characteristic matrix. These features are evaluated at each instant for each candidate, thus establishing a feature bank.