Group publication title:
Subject and Keywords:
The study of human handwriting movements is of great interest to researchers and biologists. It can lead to an understanding of the properties of the biological system that generates the human handwriting movements. With the identification of a dynamical system that exhibits characteristics similar to the biological one, it is possible to study handwriting movements, to identify their driving motor signals and to try to reproduce by machine the handwriting motion. ; In this paper, we give an analysis of modeling techniques for the handwriting process proposed in the literature. We show that either mathematical models based on the trajectories of handwritten objects or physical models obtained from the dynamic motion of the human hand can be used for modeling the handwriting process. ; We study the handwriting movements using these approaches and we give an analysis and synthesis of the driving motor signals. We apply the results to the generation of handwritten Arabic letters. We then propose a new synthesis technique where a more promising and realistic model can be obtained. We present the basic idea and expect that some improvement over the previous techniques can be obtained. The technique is based on Feedback Error Learning neural networks.