🏆 UIST '15 (Poster) - Best Poster Award (People's Choice 2nd Place)

Color sommelier: interactive color recommendation system based on community-generated color palettes

KyoungHee Son

Seo Young Oh

Yongkwan Kim

Hayan Choi

Seok-Hyung Bae

Ganguk Hwang

[PDF]

We present Color Sommelier, an interactive color recommendation system based on community-generated color palettes that helps users to choose harmonious colors on the fly. We used an item-based collaborative filtering technique with Adobe Color CC palettes in order to take advantage of their ratings that reflect the general public’s color harmony preferences. Every time a user chooses a color(s), Color Sommelier calculates how harmonious each of the remaining colors is with the chosen color(s). This interactive recommendation enables users to choose colors iteratively until they are satisfied. To illustrate the usefulness of the algorithm, we implemented a coloring application with a specially designed color chooser. With the chooser, users can intuitively recognize the harmony score of each color based on its bubble size and use the recommendations at their discretion. The Color Sommelier algorithm is flexible enough to be applicable to any color chooser in any software package and is easy to implement.

Keywords: Interactive color recommendation; collaborative filtering

3 min. summary

Poster

People

Yongkwan Kim

Ph.D.

Hayan Choi

M.S.

Seok-Hyung Bae

Associate Professor

Awards

🏆 UIST '15 Best Poster Award (People's Choice 2nd Place)

Color Sommelier

KyoungHee Son, Seo Young Oh, Yongkwan Kim, Hayan Choi, Seok-Hyung Bae, and Ganguk Hwang

Department of Industrial Design, KAIST
© SketchLab All Rights Reserved.
Twitter
YouTube