摘要
根据中文字体风格转换研究发展的不同阶段进行方法分类,简要回顾传统方法,梳理分析深度学习方法.介绍常用的公开数据集和评价标准.分别从提高生成质量、增强个性化差异、减少训练样本数量和学习书法字体风格共4个方面展望未来研究.
The research works of Chinese font style transfer were classified according to different stages of research development.The traditional methods were briefly reviewed and the deep learning-based methods were combed and analyzed.The commonly used open data sets and evaluation criteria were introduced.The future research trends were expected from four aspects,which were to improve the generation quality,enhance personalized differences,reduce the number of training samples,and learn calligraphy font style.
作者
程若然
赵晓丽
周浩军
叶翰辰
CHENG Ruo-ran;ZHAO Xiao-li;ZHOU Hao-jun;YE Han-chen(School of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China)
出处
《浙江大学学报(工学版)》
EI
CAS
CSCD
北大核心
2022年第3期510-519,530,共11页
Journal of Zhejiang University:Engineering Science
基金
国家自然科学基金资助项目(61772328).
关键词
字体风格转换
深度学习
图像翻译
神经网络
字体生成
font style transfer
deep learning
image translation
neural network
font generation