Parametric identification of handwriting system based on RLS algorithm

This paper deals with parametric identification based on Recursive Least Squares algorithm (RLS) to describe the human handwriting process. The electromyographic EMG signals records of muscle activities in the forearm during handwriting movements contain the adequate information to present this biological process. So, the handwriting process can be described from the relationship between EMG signals and the pen-tip movement. An experimental approach has been carried out to measure the forearm EMG signals and the pen-tip displacements on writing some of fundamental drawing and Arabic letters. These measurements are used to identify the handwriting process. In this research, a new fourth order, linear model is proposed to identify handwriting process. Good qualitative and quantitative agreement was found between traces and trajectories calculated with identified system.