Abstract
We propose a favored feature based shape generation system which helps the user to externalize his or her latent image of styling design into shape. The system estimates the favored features to which the user unconsciously pays more attention, and automatically generates design samples based on the favored feature. The system makes the user notice his/her own unconscious preferences by showing the favored features. Thus, the user becomes consciously aware of his/her own latent perspectives of design. Through repetition of the operation of the system, the user gradually expands his/her perspectives and generates design samples based on them. The proposed method is compared with the manual design system, in which the user manually adjusts the design parameters and its effectiveness demonstrated by a design experiment using a 3D cylinder model consisting of superquadratic ellipse cross sections.
