Chinese Typography Transfer

TL;DR

This paper introduces a novel end-to-end deep learning architecture for Chinese typography transfer that generates realistic styled characters without complex segmentation or pre-training.

Contribution

The proposed model uniquely treats Chinese characters as inseparable images and combines convolutional and adversarial networks for style transfer without pre-processing.

Findings

Successfully transfers typography styles in printed and handwritten Chinese characters.

Produces realistic and high-quality styled characters.

Avoids complex segmentation and pre-training steps.

Abstract

In this paper, we propose a new network architecture for Chinese typography transformation based on deep learning. The architecture consists of two sub-networks: (1)a fully convolutional network(FCN) aiming at transferring specified typography style to another in condition of preserving structure information; (2)an adversarial network aiming at generating more realistic strokes in some details. Unlike models proposed before 2012 relying on the complex segmentation of Chinese components or strokes, our model treats every Chinese character as an inseparable image, so pre-processing or post-preprocessing are abandoned. Besides, our model adopts end-to-end training without pre-trained used in other deep models. The experiments demonstrates that our model can synthesize realistic-looking target typography from any source typography both on printed style and handwriting style.