Smooth Morphing of Handwritten Text

There are several approaches for pen-based systems to improve legibility of handwritten text, e.g. smoothing the strokes composing the characters and words. A very challenging solution is the smooth morphing approach: handwritten strokes are transformed gradually into perfectly legible characters provided by a previously executed handwriting recognition process. In this paper we present our approach to a smooth real-time metamorphosis of handwritten characters into clean typography. Our main contributions are a new hybrid algorithm for character mapping, heuristics for splitting and joining strokes, and finding a stroke mapping with the use of radial distances. We implemented our methods in a whiteboard application that provides intuitive to use editing operations due to floating menus and stroke gestures. The implementation is based on the Microsoft Tablet PC SDK and the handwriting recognizer provided with the Tablet PC operating system.