A statistical parametric model for recognition and synthesis of handwriting

Abstract

A new parametric model for excellent quality synthesis of English script in on-line systems is presented, which uses a fixed length letter segmentation. The script vertical and horizontal velocities are modeled as the impulse response of a two-dimensional linear time-varying second-order system. An Analysis-by-Synthesis approach is proposed, in which the model's parameters are estimated by solving a non-linear optimization problem. In addition, a statistical model for the ABC letters is presented, which is based on the parametric representation. This composite statistical and parametric model may be utilized in aplications such as writer imitation, character recognition and writer identification.