Data-driven coloring suggestions for graphic design
Abstract/Contents
- Abstract
- Whether it is designing room interiors, illustrations, or websites -- color choice is an integral component of many creative projects, affecting both function and aesthetic impact. However, choosing appropriate colors can be challenging. For example, colors can have semantic associations with particular concepts (e.g. ``profit" to green), which should be taken into account when creating a communicative design. In addition, because color aesthetic is complex, influenced by both spatial arrangement as well as evolving preferences, the coloring process often involves a lot of trial and tweaking. Instead of starting from a blank canvas, many designers will form ideas by looking at multiple examples, such as images or pre-made color themes. They may also create quick color thumbnail sketches to test color arrangements. This dissertation looks at facilitating the color choice process by automatically generating coloring suggestions, using existing and crowd-sourced data for grounding. We algorithmically observe how people make different color decisions by gathering hand-created examples from people and identifying potential predictive metrics. For example, when coloring a pattern, people may consider both the global set of colors as well as the suitability of adjacent colors, and we analyze examples of hand-created colorings to mine statistics on these properties. We then build models to predict the examples by using machine learning techniques to choose and balance between our pool of metrics. We present data-driven algorithms for both concrete and open-ended tasks -- assigning semantically-resonant colors for data visualizations, extracting color themes from images, and generating spatially-aware color assignments which can be guided by user constraints. Such suggestions can give people good default starting points, from which they can focus on more high-level or creative decisions.
Description
| Type of resource | text |
|---|---|
| Form | electronic; electronic resource; remote |
| Extent | 1 online resource. |
| Publication date | 2014 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Associated with | Lin, Sharon |
|---|---|
| Associated with | Stanford University, Department of Computer Science. |
| Primary advisor | Hanrahan, P. M. (Patrick Matthew) |
| Thesis advisor | Hanrahan, P. M. (Patrick Matthew) |
| Thesis advisor | Bernstein, Michael |
| Thesis advisor | Heer, Jeffrey Michael |
| Advisor | Bernstein, Michael |
| Advisor | Heer, Jeffrey Michael |
Subjects
| Genre | Theses |
|---|
Bibliographic information
| Statement of responsibility | Sharon Lin. |
|---|---|
| Note | Submitted to the Department of Computer Science. |
| Thesis | Thesis (Ph.D.)--Stanford University, 2014. |
| Location | electronic resource |
Access conditions
- Copyright
- © 2014 by Sharon Derie Lin
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...