Generating Handwriting via Decoupled Style Descriptors

TL;DR

This paper introduces the Decoupled Style Descriptor (DSD) model for handwriting generation, which separates character and writer styles, enabling more flexible and higher-quality handwriting synthesis with improved results over previous methods.

Contribution

The paper presents a novel DSD model that explicitly decouples character and writer styles, enhancing the diversity and adaptability of handwriting generation.

Findings

Generated handwriting preferred 88% over baseline

Achieved 89.38% writer identification accuracy from a single sample

Improved flexibility in generating new character and writer styles

Abstract

Representing a space of handwriting stroke styles includes the challenge of representing both the style of each character and the overall style of the human writer. Existing VRNN approaches to representing handwriting often do not distinguish between these different style components, which can reduce model capability. Instead, we introduce the Decoupled Style Descriptor (DSD) model for handwriting, which factors both character- and writer-level styles and allows our model to represent an overall greater space of styles. This approach also increases flexibility: given a few examples, we can generate handwriting in new writer styles, and also now generate handwriting of new characters across writer styles. In experiments, our generated results were preferred over a state of the art baseline method 88% of the time, and in a writer identification task on 20 held-out writers, our DSDs achieved 89.38% accuracy from a single sample word. Overall, DSDs allows us to improve both the quality and flexibility over existing handwriting stroke generation approaches.