Generating Copybooks from Consistent Handwriting Styles

The automatic extraction of handwriting styles is an important process that can be used for various applications in the processing of handwriting. We propose a novel method that employs hierarchical clustering to explore prominent clusters of handwriting. So-called membership vectors are introduced to describe the handwriting of a writer. Each membership vector reveals the frequency of occurrence of prototypical characters in a writer's handwriting. By clustering these vectors, consistent handwriting styles can be extracted, similar to the exemplar handwritings documented in copybooks. The results presented here are challenging. The most prominent handwriting styles detected correspond to the broad style categories cursive, mixed, and print.