Roorda, Auke (2024) Geometric Analysis of Typefaces. Master's Thesis / Essay, Computing Science.
|
Text
mCS2024RoordaAC.pdf Download (7MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
Toestemming.pdf Restricted to Registered users only Download (200kB) |
Abstract
In the creative digital world, there is a need for typefaces that meet expectations that are difficult to define, such as having a certain feeling to them, which are expressed by the typographic features of a font. We hypothesize that machine learning models trained to map fonts to their semantic attributes are limited in their effectiveness due to the use of suboptimal features. We aim to improve this process by providing explicit features of fonts designed to capture typographic variations. These features are extracted by traversing the outlines and medial axes of glyphs, using directives capable of handling the many variations in glyph shapes. We construct directives to compute 11 different groups of typographic features, such as weight, contrast, and slant on each font, and visually evaluate the measured features. A web page is created to allow browsing of fonts by these features. Additionally, we compute and compare different definitions of the same typographic feature found in various typography-related research. We find that this approach works well for computing typographic features and yields intuitive feature values that are usable for font search and classification.
| Item Type: | Thesis (Master's Thesis / Essay) |
|---|---|
| Supervisor name: | Kosinka, J. and Tursun, O.T. |
| Degree programme: | Computing Science |
| Thesis type: | Master's Thesis / Essay |
| Language: | English |
| Date Deposited: | 30 Aug 2024 11:51 |
| Last Modified: | 26 Nov 2024 08:34 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/34131 |
Actions (login required)
 |
View Item |