算子优化遗传算法的插画艺术设计模型  

Illustration Art Design Model Based on Operator Optimization Genetic Algorithm

作　　者：曾俊蓉[1] 申丽珍[2] 窦继涛[1] Zeng Junrong;Shen Lizhen;Dou Jitao(Information Engineering Institute,Jiujiang Vocational and Technical College,Jiujiang Jiangxi 332007,China;Library of Wenzhou University,Wenzhou Zhejiang 325000,China)

机构地区：[1]九江职业技术学院信息工程学院,江西九江332007 [2]温州大学图书馆,浙江温州325000

出　　处：《科技通报》2017年第8期166-169,共4页Bulletin of Science and Technology

基　　金：2016年江西省高校人文社科立项课题(课题编号:YS161006)

摘　　要：针对标准遗传算法在插画艺术设计的应用中还存在搜索效率低下、复杂度过高等问题。本文提出了一种基于算子及聚类优化遗传算法的插画艺术设计模型。首先在遗传算法运行中依据种群的特点来动态调整交叉概率和变异概率的数值,以提高算法的搜索效率,然后引入K-medoids算法对遗传算法进行聚类优化,并采用一个成本函数来进行评估聚类质量的好坏,以优化原算法的复杂度,最后采用改进遗传算法对随机插画艺术设计。通过实例仿真表明,本文提出的改进算法对插画艺术设计的实现,艺术性和创新性更高。In order to overcome the problems such as low efficiency and high complexity of the standard genetic algorithm in the design of illustration art design,this paper proposes an illustration art design model based on operator and clustering optimization genetic algorithm.Firstly,the genetic algorithm is used to dynamically adjust the value of crossover probability and mutation probability according to the characteristics of the population.Then,the search efficiency of the algorithm can be improved.Secondly,K-Medoids algorithm is introduced to carry out the clustering optimization of the GA algorithm,and a cost function is used to evaluate the quality of the clustering,which can optimize the complexity of the original algorithm.Thirdly,the improved GA algorithm is used to design the random illustration art design.Simulations show that the improved algorithm proposed in this paper is more artistic and innovation in illustration art design.

关 键 词：K-GA算法 插画艺术 艺术设计 算子优化 聚类优化 

分 类 号：TP391.72[自动化与计算机技术—计算机应用技术]