Skip to main content

Which Parts Determine the Impression of the Font?

Part of the Lecture Notes in Computer Science book series (LNIP,volume 12823)


Various fonts give different impressions, such as legible, rough, and comic-text. This paper aims to analyze the correlation between the local shapes, or parts, and the impression of fonts. By focusing on local shapes instead of the whole letter shape, we can realize more general analysis independent from letter shapes. The analysis is performed by newly combining SIFT and DeepSets, to extract an arbitrary number of essential parts from a particular font and aggregate them to infer the font impressions by nonlinear regression. Our qualitative and quantitative analyses prove that (1) fonts with similar parts have similar impressions, (2) many impressions, such as legible and rough, largely depend on specific parts, and (3) several impressions are very irrelevant to parts.


  • Font shape
  • Impression analysis
  • Part-based analysis

This is a preview of subscription content, access via your institution.

Buying options

USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-86334-0_47
  • Chapter length: 16 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
USD   89.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-86334-0
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   119.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.


  1. 1.

    As noted in [23], it is also possible to use another operation than the summation, such as element-wise max operation.

  2. 2.

    Fonts whose stroke is filled with textures such as “cross-hatching” give a huge number of SIFT descriptors because they have many corners. They inflate the average number of L; in fact, the median of L is 1, 223. In the later histogram-based analysis, we try to reduce the effect of such an extreme case by using the median-based aggregation instead of the average.

  3. 3.

    Recall that the original SIFT vector is a unit vector, i.e., \(\Vert \mathbf {x}^i_l\Vert =1\).


  1. Azadi, S., Fisher, M., Kim, V.G., Wang, Z., Shechtman, E., Darrell, T.: Multi-content GAN for few-shot font style transfer. In: CVPR, pp. 7564–7573 (2018)

    Google Scholar 

  2. Bay, H., Tuytelaars, T., Van Gool, L.: SURF: Speeded up robust features. In: Leonardis, Aleš, Bischof, Horst, Pinz, Axel (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006).

  3. Brumberger, E.R.: The rhetoric of typography: the awareness and impact of typeface appropriateness. Tech. Commun. 50(2), 224–231 (2003)

    Google Scholar 

  4. Cha, J., Chun, S., Lee, G., Lee, B., Kim, S., Lee, H.: Few-shot compositional font generation with dual memory. In: Vedaldi, Andrea, Bischof, Horst, Brox, Thomas, Frahm, Jan-Michael. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 735–751. Springer, Cham (2020).

  5. Chen, T., Wang, Z., Xu, N., Jin, H., Luo, J.: Large-scale tag-based font retrieval with generative feature learning. In: ICCV (2019)

    Google Scholar 

  6. Choi, S., Aizawa, K., Sebe, N.: FontMatcher: font image paring for harmonious digital graphic design. In: ACM IUI (2018)

    Google Scholar 

  7. Davis, R.C., Smith, H.J.: Determinants of feeling tone in type faces. J. Appl. Psychol. 17(6), 742–764 (1933)

    CrossRef  Google Scholar 

  8. Doyle, J.R., Bottomley, P.A.: Dressed for the occasion: font-product congruity in the perception of logotype. J. Consum. Psychol. 16(2), 112–123 (2006)

    CrossRef  Google Scholar 

  9. Grohmann, B., Giese, J.L., Parkman, I.D.: Using type font characteristics to communicate brand personality of new brands. J. Brand Manage. 20(5), 389–403 (2013)

    CrossRef  Google Scholar 

  10. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)

    Google Scholar 

  11. Henderson, P.W., Giese, J.L., Cote, J.A.: Impression management using typeface design. J. Market. 68(4), 60–72 (2004)

    CrossRef  Google Scholar 

  12. Kluger, Y., Basri, R., Chang, J.T., Gerstein, M.: Spectral biclustering of microarray data: coclustering genes and conditions. Genome Res. 13(4), 703–716 (2003)

    CrossRef  Google Scholar 

  13. Liu, Y., Wang, Z., Jin, H., Wassell, I.: Multi-task adversarial network for disentangled feature learning. In: CVPR (2018)

    Google Scholar 

  14. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comp. Vis. 60(2), 91–110 (2004)

    CrossRef  Google Scholar 

  15. Mackiewicz, J.: Audience perceptions of fonts in projected powerpoint text slides. Tech. Commun. 54(3), 295–307 (2007)

    Google Scholar 

  16. O’Donovan, P., Lībeks, J., Agarwala, A., Hertzmann, A.: Exploratory font selection using crowdsourced attributes. ACM Trans. Graphics 33(4), 92 (2014)

    Google Scholar 

  17. Poffenberger, A.T., Franken, R.: A study of the appropriateness of type faces. J. Appl. Psychol. 7(4), 312–329 (1923)

    CrossRef  Google Scholar 

  18. Shaikh, D., Chaparro, B.: Perception of fonts: perceived personality traits and appropriate uses. In: Digital Fonts and Reading, chap. 13. World Scientific (2016)

    Google Scholar 

  19. Shinahara, Y., Karamatsu, T., Harada, D., Yamaguchi, K., Uchida, S.: Serif or Sans: visual font analytics on book covers and online advertisements. In: ICDAR (2019)

    Google Scholar 

  20. Srivatsan, A., Barron, J., Klein, D., Berg-Kirkpatrick, T.: A deep factorization of style and structure in fonts. In: EMNLP-IJCNLP (2019)

    Google Scholar 

  21. Velasco, C., Woods, A.T., Hyndman, S., Spence, C.: The taste of typeface. i-Perception 6(4), 1–10 (2015)

    Google Scholar 

  22. Wang, Y., Gao, Y., Lian, Z.: Attribute2Font. ACM Trans. Graphics 39(4) (2020)

    Google Scholar 

  23. Zaheer, M., Kottur, S., Ravanbhakhsh, S., Póczos, B., Salakhutdinov, R., Smola, A.J.: Deep sets. NIPS (2017)

    Google Scholar 

  24. Zheng, L., Yang, Y., Tian, Q.: SIFT meets CNN: A decade survey of instance retrieval. IEEE Trans. Patt. Anal. Mach. Intell. 40(5), 1224–1244 (2018)

    CrossRef  Google Scholar 

Download references


This work was supported by JSPS KAKENHI Grant Number JP17H06100.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Masaya Ueda .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Ueda, M., Kimura, A., Uchida, S. (2021). Which Parts Determine the Impression of the Font?. In: Lladós, J., Lopresti, D., Uchida, S. (eds) Document Analysis and Recognition – ICDAR 2021. ICDAR 2021. Lecture Notes in Computer Science(), vol 12823. Springer, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-86333-3

  • Online ISBN: 978-3-030-86334-0

  • eBook Packages: Computer ScienceComputer Science (R0)