Learning and Generation of Personal Handwriting Style Chinese Font

Lei, Yutian; Zhou, Liguang; Pan, Tianjiao; Qian, Huihuan; Sun, Zhenglong

doi:10.1109/robio.2018.8665297

Cited by 6 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been studied since the beginning of the digital age. The problem can be formulated either as a personal handwritten characters generation problem [20], or an automatic printed font generation problem [23]. In the early study of glyph synthesis, researchers focused on the geometric modeling, which relied on the hierarchical representation of simple strokes [34,35,22,36,7].…”

Section: Character Fonts Generationmentioning

confidence: 99%

End-to-End Rubbing Restoration Using Generative Adversarial Networks

Sun¹,

Zheng²,

Zhang³

2022

Preprint

View full text Add to dashboard Cite

Rubbing restorations are significant for preserving world cultural history. In this paper, we propose the Rub-bingGAN model for restoring incomplete rubbing characters. Specifically, we collect characters from the Zhang Menglong Bei and build up the first rubbing restoration dataset. We design the first generative adversarial network for rubbing restoration. 1 Based on the dataset we collect, we apply the RubbingGAN to learn the Zhang Menglong Bei font style and restore the characters. The results of experiments show that RubbingGAN can repair both slightly and severely incomplete rubbing characters fast and effectively.

show abstract

Section: Character Fonts Generationmentioning

confidence: 99%

End-to-End Rubbing Restoration Using Generative Adversarial Networks

Sun¹,

Zheng²,

Zhang³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…It is able to generate accuracy and clear font images. But the manual design methods are timeconsuming and laborious; the general design cycle of a new font takes 1-2 years [4]. Compared with manual design, automatic design using artificial intelligence methods has high efficiency and short design cycle.…”

Section: Introductionmentioning

confidence: 99%

Disentangled representation learning GANs for generalized and stable font fusion network

Qin

Zhang

Zhou

2021

IET Image Processing

View full text Add to dashboard Cite

Automatic generation of calligraphy fonts has attracted broad attention of researchers. However, previous font generation research mainly focused on the known font style imitation based on image to image translation. For poor interpretability, it is hard for deep learning to create new fonts with various font styles and features according to human understanding. To address this issue, the font fusion network based on generative adversarial networks (GANs) and disentangled representation learning is proposed in this paper to generate brand new fonts. It separates font into two understandable disentangled features: stroke style and skeleton shape. According to personal preferences, various new fonts with multiple styles can be generated by fusing the stroke style and skeleton shape of different fonts. First, this task improves the interpretability of deep learning, and is more challenging than simply imitating font styles. Second, considering the robustness of the network, a fuzzy supervised learning skill is proposed to enhance the stability of the fusion of two fonts with considerable discrepancy. Finally, instead of retraining, the authors' trained model can be quickly transferred to other font fusion samples. It improves the efficiency of the model. Qualitative and quantitative results demonstrate that the proposed method is capable of efficiently and stably generating the new font images with multiple styles. The source code and the implementation details of our model are available at https://github.com/Qinmengxi/Fontfusion.

show abstract