Analyses of Local Mascot Characters and Proposal of Automatic Character Creation System Using Affective Words

抄録

In this paper, first, analyses of local community mascot characters are carried out to obtain knowledge to be the popular ones. Next a mascot characters automatic creation system is proposed using these findings. As for the analyses, we used 200 mascot characters. Many interesting findings could be obtained such that dark-round eyes tend to contribute to be popular as a mascot character. The proposed system utilizing these findings can create a mascot character reflecting a user's image inputted by affective words. Many parts having degrees of affective images are prepared in the proposed system and are combined to form a character using Rough Sets Theory and an Interactive Genetic Algorithm framework. We performed evaluation experiments. Many mascot characters satisfying user's image were created and remarkable results were obtained through subjective evaluations. For example, by using the extracted rules from the analyses and Interactive Genetic Algorithm, the proposed system can create much favorable mascot characters. Moreover, we found some interesting tendencies of the color used to paint characters. One of them is that gentle characters are often painted in colors with low saturation.