Development and evaluation of a 3D graphics design system based on simulated human immune system

We propose an intuitive computer graphics authoring method based on interactive evolutionary computation (IEC). Our previous systems employed genetic algorithm (GA) and mainly focused on exploration of a single optimum 3D graphics model. The proposed method adopts a different computation strategy called immune algorithm (IA) to ease the creation of varied 3D models even if a user doesn't have any specific idea of final 3D products. Because artistic work like graphics design needs a process to diversify the user's imagery, a tool that allows the user to select his/her preferred one from a broad range of possible solutions is particularly desired. IA enables to effectively explore a wealth of solutions in a huge 3D parametric space by using its essential mechanisms such as antibody formation and self-regulating function. We conducted an experiment to verify the effectiveness of the proposed method. The result shows that the proposed method helps the user to easily generating wide variety of 3D graphics models.