A model for variability effects in handprinting with implications for the design of handwriting character recognition systems

An implementation of a model for recognition of handwriting with variability that is combinational and syntactic is presented. The work is a synthesis of theoretical aspects and observations of handprinting styles in a large collection gathered during the development of a commercial online character recognition system. Several physical factors affecting variability in handprint are reviewed. A combinatorial predictive model for these factors and its use in a particular design of a device for online character recognition is presented, in which the variability effects are treated separately from the recognition process. Beyond the use in this system, the model implies several substantial testing and performance problems for reliable handwritten character recognition.<
>