Innovative On-line Handwriting Identification Algorithm Based on Stroke Features

Thehandwritinganalysisisafieldofgreatinterestsincesup- ports the study of different personal characteristics of the human beings, including identity, character, and neurological disabilities. In particular, the handwriting identification area, which also includes the handwrit- ten signature verification, is a topic continuously investigated since the freehand writing of a manuscript, as well as the appending of a personal signature on a paper document, are still the most widespread ways to certify documents in legal, financial and administrative fields. The rapid diffusion of devices that enable user interaction by means of freehand or capacity pen based writing, and the growing successes obtained in processing the digital handwriting, are allowing us to extend more and more the boundaries of this fascinating area. The automatic handwrit- ing identification is an engaging matter that supports several application contexts including the personal identification. In this paper we present a novel on-line handwriting identification algorithm based on the com- putation of the static and dynamic features of the strokes composing an handwritten text. Extensive experiments have demonstrated the useful- ness and the accuracy of the proposed method.