Abstract
In this paper, we propose a system that automatically creates fonts which reflect a user's kansei and outputs them by inputting some impression words about fonts. The proposed system consists of two major parts, creating fonts part and evaluating fonts part, and it operates based on genetic algorithm (GA). In the evaluating fonts part, the system calculates the fitness value of the font created in the creating fonts part. In the creating fonts part, some font parameters are added to the basic data of characters such as control points. These font parameters are expressed as a gene and it is possible to create various fonts by means of GA operations. The evaluating fonts part estimates the impression of the created font using fuzzy rules. And the system calculates Euclidean distance between the user's inputs and the values that the system infers as the fitness value. By repeating these processes, the system creates the font which the user desires. In addition, the system can adjust to the user's kansei by introducing the learning based on his/her absolute evaluation. The validity of the proposed system is confirmed by experiments in respect of the following points: Euclidean distance between the user's evaluation and the estimation of the system, the adaptability of the system to individual kansei and the variety of fonts that the system creates.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
