Date of Award

6-1-2017

Document Type

Thesis (Master's)

Department or Program

Department of Computer Science

First Advisor

Qiang Liu

Second Advisor

Lorie Loeb

Abstract

Font design is an important area in digital art. However, designers have to design character one by one manually. At the same time, Chinese contains more than 20,000 characters. Chinese offical dataset GB 18030-2000 has 27,533 characters. ZhongHuaZiHai, an official Chinese dictionary, contains 85,568 characters. And JinXiWenZiJing, an dataset published by AINet company, includes about 160,000 chinese characters. Thus Chinese font design is a hard task. In the paper, we introduce a method to help designers finish the process faster. With the method, designers only need to design a small set of Chinese characters. Other characters will be generated automatically. Deep neural network develops fast these years and is very powerful. We tried many kinds of deep neural network with different structure and finally use the one we introduce here. The generated characters have similar style as the ones designed by designer as shown in experiment part.

Comments

Originally posted in the Dartmouth College Computer Science Technical Report Series, number TR2017-830.

Share

COinS