Handwritten Chinese Font Generation with Collaborative Stroke Refinement

TL;DR

This paper introduces a neural network model for generating handwritten Chinese fonts that effectively refines strokes, uses data augmentation, and requires minimal training samples, outperforming existing methods.

Contribution

The paper presents a novel neural network approach with collaborative stroke refinement, online zoom-augmentation, and adaptive pre-deformation, needing only 750 samples without extra datasets.

Findings

Outperforms state-of-the-art methods in handwritten Chinese font synthesis

Requires only 750 paired training samples, no pre-trained models or extra data

Effectively refines strokes and standardizes characters for better generation

Abstract

Automatic character generation is an appealing solution for new typeface design, especially for Chinese typefaces including over 3700 most commonly-used characters. This task has two main pain points: (i) handwritten characters are usually associated with thin strokes of few information and complex structure which are error prone during deformation; (ii) thousands of characters with various shapes are needed to synthesize based on a few manually designed characters. To solve those issues, we propose a novel convolutional-neural-network-based model with three main techniques: collaborative stroke refinement, using collaborative training strategy to recover the missing or broken strokes; online zoom-augmentation, taking the advantage of the content-reuse phenomenon to reduce the size of training set; and adaptive pre-deformation, standardizing and aligning the characters. The proposed model needs only 750 paired training samples; no pre-trained network, extra dataset resource or labels is needed. Experimental results show that the proposed method significantly outperforms the state-of-the-art methods under the practical restriction on handwritten font synthesis.