摘要: 为自动生成新颖多样的3D动漫造型,提出一种改进的元胞遗传算法(CGA)。使用ACIS规则表达式对已有的3D动漫造型在3个方向上实施非均匀缩放变形,采用树结构编码生成长度和内容变化较大的规则表达式,通过人机交互的方式,利用专家知识确定个体适应度值。基于3D动漫造型创新系统ECTDS的实验结果表明,该算法可以生成一系列生动的创新造型。
关键词:
元胞遗传算法,
树结构编码,
人机交互,
3D动漫造型
Abstract: In order to generate a variety of innovative 3D animation modelings automatically, an improved Cellular Genetic Algorithm(CGA) is proposed. ACIS rule expressions are used to unevenly scale the existing 3D animation modeling in three directions, and tree-structure coding is adopted for the generation of rule expressions with diverse length and content. Through human-computer interaction, expert knowledge is used to determine the fitness value of individuals. Experimental results on ECTDS of 3D animation modeling innovation system show that the algorithm can generate a series of vivid and creative modelings.
Key words:
Cellular Genetic Algorithm(CGA),
tree-structure coding,
human-computer interaction,
3D animation modeling
中图分类号:
杨晓鹏, 刘弘, 于汉超. 改进CGA在3D动漫造型设计中的应用[J]. 计算机工程, 2012, 38(01): 248-250.
YANG Xiao-Feng, LIU Hong, XU Han-Chao. Application of Improved Cellular Genetic Algorithm in 3D Animation Modeling Design[J]. Computer Engineering, 2012, 38(01): 248-250.