Skip to main content

2019 | OriginalPaper | Buchkapitel

Font Style Transfer Using Neural Style Transfer and Unsupervised Cross-domain Transfer

verfasst von : Atsushi Narusawa, Wataru Shimoda, Keiji Yanai

Erschienen in: Computer Vision – ACCV 2018 Workshops

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

In this paper, we study about font generation and conversion. The previous methods dealt with characters as ones made of strokes. On the contrary, we extract features, which are equivalent to the strokes, from font images and texture or pattern images using deep learning, and transform the design pattern of font images. We expect that generation of original font such as hand written characters will be generated automatically by the proposed approach. In the experiments, we have created unique datasets such as a ketchup character image dataset and improve image generation quality and readability of character by combining neural style transfer with unsupervised cross-domain learning.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Ulyanov, D., Lebedev, V., Lempitsky, A.V.: Texture networks: feed-forward synthesis of textures and stylized images. In: arXiv:1603.03417v1 (2016) Ulyanov, D., Lebedev, V., Lempitsky, A.V.: Texture networks: feed-forward synthesis of textures and stylized images. In: arXiv:​1603.​03417v1 (2016)
2.
Zurück zum Zitat Gantugs, A., Iwana, B.K., Narusawa, A., Yanai, K., Uchida, S.: Neural font style transfer. In: International Conference on Document Analysis and Recognition (2017) Gantugs, A., Iwana, B.K., Narusawa, A., Yanai, K., Uchida, S.: Neural font style transfer. In: International Conference on Document Analysis and Recognition (2017)
3.
Zurück zum Zitat Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2016) Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2016)
4.
Zurück zum Zitat Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Proceedings of European Conference on Computer Vision (2016) Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Proceedings of European Conference on Computer Vision (2016)
5.
Zurück zum Zitat Jun-Yan, Z., Taesung, P., Phillip, I., Alexei, E.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of IEEE International Conference on Computer Vision (2017) Jun-Yan, Z., Taesung, P., Phillip, I., Alexei, E.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of IEEE International Conference on Computer Vision (2017)
6.
7.
Zurück zum Zitat Li, C., Wand, M.: Combining Markov random fields and convolutional neural networks for image synthesis. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2016) Li, C., Wand, M.: Combining Markov random fields and convolutional neural networks for image synthesis. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2016)
8.
Zurück zum Zitat Lin, J., Hong, C., Chang, R., Wang, Y., Lin, S., Ho, J.: Complete font generation of Chinese characters in personal handwriting style. In: 2015 IEEE 34th International Performance Computing and Communications Conference (IPCCC), pp. 1–5. IEEE (2015) Lin, J., Hong, C., Chang, R., Wang, Y., Lin, S., Ho, J.: Complete font generation of Chinese characters in personal handwriting style. In: 2015 IEEE 34th International Performance Computing and Communications Conference (IPCCC), pp. 1–5. IEEE (2015)
9.
Zurück zum Zitat Miyazaki, T., et al.: Automatic generation of typographic font from a small font subset. In: arXiv preprint arXiv:1701.05703 (2017) Miyazaki, T., et al.: Automatic generation of typographic font from a small font subset. In: arXiv preprint arXiv:​1701.​05703 (2017)
10.
Zurück zum Zitat Phillip, I., Jun-Yan, Z., Tinghui, Z., Alexei, E.: Image-to-image translation with conditional adversarial networks. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2017) Phillip, I., Jun-Yan, Z., Tinghui, Z., Alexei, E.: Image-to-image translation with conditional adversarial networks. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2017)
11.
Zurück zum Zitat Shuai, Y., Jiaying, L., Zhouhui, L., Zongming, G.: Awesome typography: statistics-based text effects transfer. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2016) Shuai, Y., Jiaying, L., Zhouhui, L., Zongming, G.: Awesome typography: statistics-based text effects transfer. In: Proceedings of IEEE Computer Vision and Pattern Recognition (2016)
12.
Zurück zum Zitat Songhua, X., Lau, F.C.M., Kwok-Wai, C., Yunhe, P.: Automatic generation of artistic Chinese calligraphy. In: IEEE Intelligent Systems (2005) Songhua, X., Lau, F.C.M., Kwok-Wai, C., Yunhe, P.: Automatic generation of artistic Chinese calligraphy. In: IEEE Intelligent Systems (2005)
13.
Zurück zum Zitat Taigman, Y., Polyak, A., Wolf, L.: Unsupervised cross-domain image generation. In: International Conference on Learning Representation (2017) Taigman, Y., Polyak, A., Wolf, L.: Unsupervised cross-domain image generation. In: International Conference on Learning Representation (2017)
14.
Zurück zum Zitat Yi, Z., Zhang, H., Tan, P., Gong, M.: DualGAN: unsupervised dual learning for image-to-image translation. In: Proceedings of IEEE International Conference on Computer Vision, pp. 2849–2857 (2017) Yi, Z., Zhang, H., Tan, P., Gong, M.: DualGAN: unsupervised dual learning for image-to-image translation. In: Proceedings of IEEE International Conference on Computer Vision, pp. 2849–2857 (2017)
15.
Zurück zum Zitat Zong, A., Zhu, Y.: StrokeBank: automating personalized Chinese handwriting generation. In: Advancement of Artificial Intelligence, pp. 3024–3030 (2014) Zong, A., Zhu, Y.: StrokeBank: automating personalized Chinese handwriting generation. In: Advancement of Artificial Intelligence, pp. 3024–3030 (2014)
Metadaten
Titel
Font Style Transfer Using Neural Style Transfer and Unsupervised Cross-domain Transfer
verfasst von
Atsushi Narusawa
Wataru Shimoda
Keiji Yanai
Copyright-Jahr
2019
DOI
https://doi.org/10.1007/978-3-030-21074-8_9

Premium Partner