Generating Handwritten Chinese Characters using CycleGAN

TL;DR

This paper introduces DenseNet CycleGAN, a novel approach for generating personalized handwritten Chinese characters from printed fonts, capable of handling both standard and calligraphic styles using unpaired training data.

Contribution

It presents a new DenseNet CycleGAN model for Chinese handwritten character generation and introduces content accuracy and style discrepancy metrics for evaluation.

Findings

Effective generation of handwritten Chinese characters demonstrated on CASIA and Lanting datasets.

Able to produce both standard and calligraphy styles with aesthetic quality.

Evaluation metrics provide a new way to assess generated Chinese handwriting.

Abstract

Handwriting of Chinese has long been an important skill in East Asia. However, automatic generation of handwritten Chinese characters poses a great challenge due to the large number of characters. Various machine learning techniques have been used to recognize Chinese characters, but few works have studied the handwritten Chinese character generation problem, especially with unpaired training data. In this work, we formulate the Chinese handwritten character generation as a problem that learns a mapping from an existing printed font to a personalized handwritten style. We further propose DenseNet CycleGAN to generate Chinese handwritten characters. Our method is applied not only to commonly used Chinese characters but also to calligraphy work with aesthetic values. Furthermore, we propose content accuracy and style discrepancy as the evaluation metrics to assess the quality of the handwritten characters generated. We then use our proposed metrics to evaluate the generated characters from CASIA dataset as well as our newly introduced Lanting calligraphy dataset.