Creating New Chinese Fonts based on Manifold Learning and Adversarial Networks
| dc.contributor.author | Guo, Yuan | en_US |
| dc.contributor.author | Lian, Zhouhui | en_US |
| dc.contributor.author | Tang, Yingmin | en_US |
| dc.contributor.author | Xiao, Jianguo | en_US |
| dc.contributor.editor | Diamanti, Olga and Vaxman, Amir | en_US |
| dc.date.accessioned | 2018-04-14T18:32:49Z | |
| dc.date.available | 2018-04-14T18:32:49Z | |
| dc.date.issued | 2018 | |
| dc.description.abstract | The design of fonts, especially Chinese fonts, is known as a tough task that requires considerable time and professional skills. In this paper, we propose a method to easily generate Chinese font libraries in new styles based on manifold learning and adversarial networks. Starting from a number of existing fonts that cover various styles, we firstly use convolutional neural networks to obtain the representation features of these fonts, and then build a font manifold via non-linear mapping. Using the font manifold, we can interpolate and move between those existing fonts to get new font features, which are then fed into a generative network learned via adversarial training to generate the whole new font libraries. Experimental results demonstrate that high-quality Chinese fonts in various new styles against existing ones can be efficiently generated using our method. | en_US |
| dc.description.sectionheaders | Methods and Applications, User Studies | |
| dc.description.seriesinformation | EG 2018 - Short Papers | |
| dc.identifier.doi | 10.2312/egs.20181045 | |
| dc.identifier.issn | 1017-4656 | |
| dc.identifier.pages | 61-64 | |
| dc.identifier.uri | https://doi.org/10.2312/egs.20181045 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/egs20181045 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.subject | I.3.3 [Computer Graphics] | |
| dc.subject | Picture/Image Generation | |
| dc.subject | Line and curve generation | |
| dc.subject | I.2.4 [Artificial Intelligence] | |
| dc.subject | Learning | |
| dc.subject | Connectionism and neural nets | |
| dc.title | Creating New Chinese Fonts based on Manifold Learning and Adversarial Networks | en_US |
Files
Original bundle
1 - 1 of 1