The effectiveness of random selection for IGA-based texture search

Abstract

This paper provides a novel texture search method for texture images. Creating a computer graphics (CG) is a popular task in many media creations. However, CG creators require their abundant time and effort. In addition, it is difficult for non-professional creators to make a 3D CG scene. This is because that they have to choose appropriate colors, textures, and lighting patterns in addition to 3D CG modeling. To reduce creators' work time and effort, some prior studies have tried to support for 3D CG creations by procedural modeling, texture synthesis, or automatic parameter setting technique. However, there are no supporting systems for choosing textures. Thus, this study addresses the problem. The proposed method enables to choose an appropriate texture image easily and quickly. The method uses an interactive genetic algorithm (IGA) with random selection (RS) system. This paper describes a framework of the proposed method using IGA with RS.