Visual Attention Adversarial Networks for Chinese Font Translation
Currently, many Chinese font translation models adopt the method of dividing character components to improve the quality of generated font images. However, character components require a large amount of manual annotation to decompose characters and determine the composition of each character as inpu...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/6/1388 |
| _version_ | 1797612183612293120 |
|---|---|
| author | Te Li Fang Yang Yao Song |
| author_facet | Te Li Fang Yang Yao Song |
| author_sort | Te Li |
| collection | DOAJ |
| description | Currently, many Chinese font translation models adopt the method of dividing character components to improve the quality of generated font images. However, character components require a large amount of manual annotation to decompose characters and determine the composition of each character as input for training. In this paper, we establish a Chinese font translation model based on generative adversarial network without decomposition. First, we improve the method of image enhancement for Chinese character images. It helps the model learning structure information of Chinese character strokes to generate font images with complete and accurate strokes. Second, we propose a visual attention adversarial network. By using visual attention block, the network catches global and local features for constructing details of characters. Experiments demonstrate our method generates high-quality Chinese character images with great style diversity including calligraphy characters. |
| first_indexed | 2024-03-11T06:38:48Z |
| format | Article |
| id | doaj.art-52e34751d3014164b61c7feebbff9f17 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T06:38:48Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-52e34751d3014164b61c7feebbff9f172023-11-17T10:44:50ZengMDPI AGElectronics2079-92922023-03-01126138810.3390/electronics12061388Visual Attention Adversarial Networks for Chinese Font TranslationTe Li0Fang Yang1Yao Song2Computer Science and Technology, School of Cyberspace Security and Computer, Hebei University, Baoding 071000, ChinaComputer Science and Technology, School of Cyberspace Security and Computer, Hebei University, Baoding 071000, ChinaComputer Science and Technology, School of Cyberspace Security and Computer, Hebei University, Baoding 071000, ChinaCurrently, many Chinese font translation models adopt the method of dividing character components to improve the quality of generated font images. However, character components require a large amount of manual annotation to decompose characters and determine the composition of each character as input for training. In this paper, we establish a Chinese font translation model based on generative adversarial network without decomposition. First, we improve the method of image enhancement for Chinese character images. It helps the model learning structure information of Chinese character strokes to generate font images with complete and accurate strokes. Second, we propose a visual attention adversarial network. By using visual attention block, the network catches global and local features for constructing details of characters. Experiments demonstrate our method generates high-quality Chinese character images with great style diversity including calligraphy characters.https://www.mdpi.com/2079-9292/12/6/1388Chinese font generationgenerative adversarial networkstyle translationvisual attention |
| spellingShingle | Te Li Fang Yang Yao Song Visual Attention Adversarial Networks for Chinese Font Translation Electronics Chinese font generation generative adversarial network style translation visual attention |
| title | Visual Attention Adversarial Networks for Chinese Font Translation |
| title_full | Visual Attention Adversarial Networks for Chinese Font Translation |
| title_fullStr | Visual Attention Adversarial Networks for Chinese Font Translation |
| title_full_unstemmed | Visual Attention Adversarial Networks for Chinese Font Translation |
| title_short | Visual Attention Adversarial Networks for Chinese Font Translation |
| title_sort | visual attention adversarial networks for chinese font translation |
| topic | Chinese font generation generative adversarial network style translation visual attention |
| url | https://www.mdpi.com/2079-9292/12/6/1388 |
| work_keys_str_mv | AT teli visualattentionadversarialnetworksforchinesefonttranslation AT fangyang visualattentionadversarialnetworksforchinesefonttranslation AT yaosong visualattentionadversarialnetworksforchinesefonttranslation |