Color Name Models

Jeffrey Heer & Maureen Stone

Our ability to reliably name colors provides a link between visual perception and symbolic cognition. In this project, we investigate how a statistical model of color naming can enable user interfaces to meaningfully mimic this link and support enhanced interactions.

We construct a probabilistic model of color naming from a large, unconstrained set of human color name judgments. This model can be used to map between colors and names and to define metrics for color saliency (how reliably a color is named) and color name distance (the similarity between colors based on naming patterns).

This model can enable enhanced user interfaces. Demo applications linked below include a color dictionary & thesaurus, evaluation aids for color palette design and name-based pixel selection methods for image editing.

applications

Color Dictionary & Thesaurus
Color Palette Analyzer
Named-Based Image Editing Pixel Selector (Requires HTML Canvas Support)
Saliency Map of LAB Color Space (Requires SVG Support)

publications

Color Naming Models for Color Selection, Image Editing and Palette Design.
Jeffrey Heer & Maureen Stone. ACM Human Factors in Computing Systems (CHI), 2012.

software

All data and source code is available on GitHub.