Affective Image Adjustment with a Single Word

Xiaohui Wang, Jia Jia, Lianhong Cai


We present a complete system that automatically adjusts image color to meet a desired emotion. It will be more convenient for users, especially for non-professional users, to adjust an image with a semantic user input, for example, to make it lovelier. The whole algorithm is fully automatic, without any user interactions, and the inputs are simply the original image and an affective word (e.g. lovely). To achieve this goal, we solve several non-trivial problems. First, in order to find the proper color themes (template of colors) to reflect the expression of the affective word, we exploit the theoretical and empirical concepts in famous art theories and build a color theme - affective word relation model allowing efficient selection of candidate themes. Furthermore, we propose a novel strategy to select the most suitable color theme among the candidates. Second, to adjust image colors, we propose the Radial Basis Functions (RBF) based interpolation method, which is more effective in many scenarios as evidenced in experiments. We also evaluate the system with comprehensive user studies and its capability is confirmed by the results.


Affective Image Adjustment with a Single Word [pdf] [supplemental] [bibtex]
Xiaohui Wang, Jia Jia, Lianhong Cai
The Visual Computer, DOI: 10.1007/s00371-012-0755-3.

System Pipeline



Notice: Please cite our paper if you use any part of our resource in your research.

Color theme database

The databse contains more than 40,000 5-color themes, each of which has a coordinate in the image-scale space with two dimensions warm-cool and hard-soft. These 5-color themes are collected from "Art of Color Combinations" (490 themes) and Adobe Kuler (44,986 themes, database is part of the database in the paper.