EasyFont: A Style Learning based System to Easily Build Your Large-scale Handwriting Fonts

Zhouhui Lian Bo Zhao Xudong Chen Jianguo Xiao

 Institute of Computer Science and Technology, Peking University, Beijing, P.R.China

 lianzhouhui@pku.edu.cn




Abstract

Generating personal handwriting fonts with large amounts of characters is a boring and time-consuming task. For example, the official standard GB18030-2000 for commercial font products consists of 27533 Chinese characters. Consistently and correctly writing out such huge amounts of characters is usually an impossible mission for ordinary people. To solve this problem, we propose a handy system to automatically synthesize personal handwritings for all characters (e.g., Chinese) in the font library by learning style from a small number (as few as 1%) of carefully-selected samples written by an ordinary person. Major technical contributions of our system are twofold. First, we design an effective stroke extraction algorithm that constructs best-suited reference data from a trained font skeleton manifold and then establishes correspondence between target and reference characters via a non-rigid point set registration approach. Second, we develop a set of novel techniques to learn and recover users' overall handwriting styles and detailed handwriting behaviors. Experiments including Turing tests with 97 participants demonstrate that the proposed system generates high-quality synthesis results which are indistinguishable from original handwritings. Using our system, for the first time the practical handwriting font library in a user's personal style with arbitrarily large numbers of Chinese characters can be generated automatically. It can also be observed from our experiments that recently-popularized deep learning based synthesizing methods are not able to properly handle this task, which implies the necessary of expert knowledge and handcrafted rules for many applications.

 

Downloads

Snapshot for paper EasyFont: A Style Learning based System to Easily Build Your Large-scale Handwriting Fonts, vol. 38, no. 1, Article No. 6, Dec. 2018

Zhouhui Lian, Bo Zhao, Xudong Chen, Jianguo Xiao

paper [ Pre-print 10.73MB]

data [ Supplementary materials 1.5MB]

data [ Rendering results of 27533 characters in GB18030-2000 for User3 10.3MB]

data [ Rendering results of 27533 characters in GB18030-2000 for User4 9.8MB]

data [ Rendering results of 27533 characters in GB18030-2000 for User5 10.7MB]

data [ GB18030-Kaiti-Reference-data 285MB]

data [ Font Skeleton Manifold 1.1GB]

data [ Input data for User1 3.1MB]

data [ Input data for User2 3.2MB]

data [ Input data for User3 1.5MB]

data [ Input data for User4 2.5MB]

data [ Input data for User5 4.2MB]

data [ Please send an email to lianzhouhui@pku.edu.cn for more handwriting samples.]


 

 

Links

Snapshot for paper Our Font Generation Website

http://www.flexifont.com/

Turing Tests

http://ask.flexifont.com/testcase/LinFont775SL2017

http://ask.flexifont.com/testcase/YMM775SL2017

http://ask.flexifont.com/testcase/XJG775SL2017

Real Applications

Our method has been adopted by a company called Founder handwritting. Here is the APP using our style learning module to automatically genereate your handwritting fonts. Have fun!


visits since June. 2017