Chinese Handwriting Generation by Neural Network Based Style Transformation

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Chinese Handwriting Generation by Neural Network Based Style Transformation
	Bi-Ren Tan1 ; Fei Yin1 ; Yi-Chao Wu1 ; Cheng-Lin Liu2
	2017-12
会议名称	International Conference on Image and Graphics
会议录名称	Springer
会议日期	2017年9月
会议地点	中国上海
摘要	This paper proposes a novel learning-based approach to generate personal style handwritten characters. Given some training characters written by an individual, we first calculate the deformation of corresponding points between the handwritten characters and standard templates, and then learn the transformation of stroke trajectory using a neural network. The transformation can be used to generate handwritten characters of personal style from standard templates of all categories. In training, we use shape context features as predictors, and regularize the distortion of adjacent points for shape smoothness. Experimental results on online Chinese handwritten characters show that the proposed method can generate personal-style samples which appear to be naturally written.
关键词	Handwriting Generation Style Transformation Neural Network Learning
学科领域	模式识别
收录类别	EI
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/15621
专题	多模态人工智能系统全国重点实验室_模式分析与学习
通讯作者	Cheng-Lin Liu
作者单位	1.中国科学院自动化研究所 2.中国科学院大学
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Bi-Ren Tan,Fei Yin,Yi-Chao Wu,et al. Chinese Handwriting Generation by Neural Network Based Style Transformation[C],2017.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Chinese Handwriting （409KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载