Affective image adjustment with a single word

Abstract 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 ex-ample, to make it lovelier. The whole algorithm is fully auto-matic, without any user interactions, and the inputs are sim-ply 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. Fur-thermore, we propose a novel strategy to select the most suit-able 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