Nothing Special   »   [go: up one dir, main page]

Skip to main content

Front Cover Image Database of Japanese Manga and Typeface Estimation of Their Title

  • Conference paper
  • First Online:
Frontiers of Computer Vision (IW-FCV 2023)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1857))

Included in the following conference series:

  • 119 Accesses

Abstract

Front cover design of books like Manga is one of the most important factors for appealing contents to users. Fonts used for the title in the front cover are carefully selected among a lot of ones for fitting selected fonts to the content and the design. However, this task to select fonts, that increases attractions of the front cover and are appropriate for human characters pictured in the front cover, is not easy. Few experienced designers or editors can do well. In this paper we try to estimate and recommend appropriate typefaces of fonts that seem to be appropriate for title fonts from an image of front cover of Manga and Light novels. To evaluate our framework, we gathered front cover images of Manga and Light novels, and created database that containing five kinds of images; front cover images with/without title fonts, whole-body images with/without title fonts, and face images. Each image has two types of label encoded from the count number of 5 typefaces used for title fonts. Experimental results using our database show that about 70% of typefaces are correctly estimated and suggest a strong relationship between fonts used for title and front covers.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Suzuki, D., Uru, D.: OniAni (in Japanese), vol.1, Media Factory (2010)

    Google Scholar 

  2. Haruba, N.: The Quintessential Quintuplets (in Japanese), vol.7, Kodansha (2019)

    Google Scholar 

  3. Shinhara, Y., Karamatsu, T., Harada, D., Yamaguchi, K., Uchida, S.: Serif or sans: visual font analytic on book covers and online advertisements. In: Proceedings of International Conference on Document Analysis and Recognition (2019)

    Google Scholar 

  4. Imakawa, S., Kodoi, T.: What kind of restaurant does the characters on the signboards conjure up? Graduate School  Educ. Bull. Hiroshima Univ. 65, 249–256 (2016)

    Google Scholar 

  5. Akime, J., Morisawa, H.: Otome-Ge no Koryakutaishou ni Narimashita (in Japanese), vol. 2, Ascii Media Works (2012)  

    Google Scholar 

  6. BNN Editorial Department: The design of Light Novels. BNN Shin-sha (2018)

    Google Scholar 

  7. Sannoumaru, S., Yuzuki R.: Logotype!. Ritto-sha  (in Japanese), A5 edn. (2015)

    Google Scholar 

  8. MdN Editorial Department: The Graphics Design of Manga & Anime (in Japanese)  MdN EXTRA, vol.1, MdN Corporation (2014) 

    Google Scholar 

  9. MdN Editorial Department.: The Graphics Design of Manga & Anime (in Japanese),  MdN EXTRA, vol. 2, MdN Corporation (2015) 

    Google Scholar 

  10. Nichibou Editorial Department.: The New Comics Design (in Japanese). Japan Publicaitons Inc. (2020)

    Google Scholar 

  11. Nichibou Editorial Department.: The New Comics Design 2 (in Japanese). Japan Publicaitons Inc (2021)

    Google Scholar 

  12. Morisawa + DESIGNNING Editorial Department.: Type and Font Book (in Japanese). Mainichi Communications (2010)

    Google Scholar 

  13. Date C.: Moji-no-Kihon (in Japanese). Graphics-sha (2020)

    Google Scholar 

  14. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of International Conference of Learning Representation (2015)

    Google Scholar 

  15. Natsumi, K., Shizuki, M.: Hazakura ga Kita Natsu (in Japanese). Ascii Media Works (2008)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Minoru Mori .

Editor information

Editors and Affiliations

Appendix

Appendix

Other examples of 2 kinds of front cover images, 2 kinds of whole-body images, and face images in our database are shown below (Fig. 7, 8 and 11).

Fig. 7.
figure 7

Examples of front cover images with title fonts

Fig. 8.
figure 8

Examples of front cover images with no title fonts

Fig. 9.
figure 9

Examples of whole-body images with fonts

Fig. 10.
figure 10

Examples of whole-body images with no fonts

Fig. 11.
figure 11

Examples of face images (enlarged)

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ishiyama, S., Sakai, K., Mori, M. (2023). Front Cover Image Database of Japanese Manga and Typeface Estimation of Their Title. In: Na, I., Irie, G. (eds) Frontiers of Computer Vision. IW-FCV 2023. Communications in Computer and Information Science, vol 1857. Springer, Singapore. https://doi.org/10.1007/978-981-99-4914-4_12

Download citation

  • DOI: https://doi.org/10.1007/978-981-99-4914-4_12

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-99-4913-7

  • Online ISBN: 978-981-99-4914-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics