The Evaluation of Textile Design's Visual Feature by Using a Genetic Algorithm

The designs that have been stored in early days are often used as a reference when textile designs are created. To effectively use these resources, a wellequipped design database must be constructed and a useful searching method must be studied. As for a design searching method, searching methods that deal with human subjective information are requested. A technique for these searching methods, one method that uses visual features of textile design is proposed. Therefore, we were interested in spatial frequencies as visual feature of textile design. We investigated a correspondence between the subjective evaluation obtained from the subjectivity as "pop out feeling" and the objective evaluation obtained from spatial frequencies of textile design image by using a genetic algorithm. In the result, it shows that the subjective evaluation based on the subjectivity as "pop out feeling" is related to lower components of spatial frequencies of textile design image. In this view point, we feel that lower components of spatial frequency domains are available for one of subjective searching items of the subjective design searches.