A Hybrid Approach to Rendering Handwritten Characters

Sara L. Su
Massachusetts Institute of Technology
Computer Science and Artificial Intelligence Laboratory
Cambridge, Massachusetts 02139
USA

sarasu@mit.edu
http://www.mit.edu/~sarasu

Abstract

With the growing popularity of pen-based computers comes the need to display clear handwritten characters at small sizes on low-resolution displays. This paper describes a method for automatically constructing hinted TrueType fonts from on-line handwriting data. Hints add extra information to glyph outlines in the form of imperative constraints overriding side effects of the rasterization process. We use an aggressive matching strategy to find correspondences between an input glyph and a previously-hinted template, considering both global and local features to allow hinting even when they differ in shape and topology. Recognizing that stroke width statistics are among features that characterize a person's handwriting, we recalculate global values in the control value table (CVT) before transfer to preserve the characteristics of the original handwriting.

Keywords

Handwriting, automatic hinting, digital typography, shape matching, pen-based interaction.

Co-authors

Chenyu Wu
Carnegie Mellon University
Robotics Institute
Pittsburgh, PA 15213
USA
Ying-Qing Xu
Microsoft Research Asia
Visual Computing Group
Beijing, 100080
China
Heung-Yeung Shum
Microsoft Research Asia
Visual Computing Group
Beijing, 100080
China