Extraction of Design Principal Pattern Related to Kansei Value

Abstract

The purpose of this study was to extract visual design elements related to Kansei value by applying principal component analysis (PCA) to color images. A questionnaire survey on impression evaluations for images of various sports shoes was conducted for Japanese and Americans. The shoe images used in the survey were converted to the CIE Lab color system, and by applying PCA to value based on each axis (i.e., the luminance axis, the red-green axis, and the yellow-blue axis), the components of the shoe design could be visualized by the patterns of brightness and color. As a result of factor analysis applied to the rating data, factors with similar interpretation were extracted, while principal patterns of shoe design related to the impression factor were different between regions. This method using PCA is considered to lead to the realization of design direction that matches the user’s characteristics.