Generating Handwritten Chinese Characters using CycleGAN

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.

Accepted at WACV 2018

References in corpus (5)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• WaveNet: A Generative Model for Raw Audio
• Fast Patch-based Style Transfer of Arbitrary Style
• Neural Style Transfer: A Review
• Learning to Write Stylized Chinese Characters by Reading a Handful of Examples

Cited by in corpus (12)

• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Content and Style Aware Generation of Text-line Images for Handwriting Recognition
• CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator
• Two Decades of Bengali Handwritten Digit Recognition: A Survey
• DG-Font: Deformable Generative Networks for Unsupervised Font Generation
• GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images
• Coconditional Autoencoding Adversarial Networks for Chinese Font Feature Learning
• FontGAN: A Unified Generative Framework for Chinese Character Stylization and De-stylization
• StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding
• Multiform Fonts-to-Fonts Translation via Style and Content Disentangled Representations of Chinese Character
• Few-shot Compositional Font Generation with Dual Memory
• Automatic Generation of Chinese Handwriting via Fonts Style Representation Learning