一种基于人工免疫聚类的三维模型检索算法  

3D Model Retrieval Algorithm Based on Artificial Immune Clustering

作　　者：吕洋[1] 刘平[1] 唐奇峰[1] 

机构地区：[1]广西师范大学计算机科学与信息工程学院,桂林541004

出　　处：《现代计算机》2011年第4期57-59,共3页Modern Computer

摘　　要：为提高对三维模型检索的性能,通过借鉴生物免疫系统中的克隆选择原理和记忆机制,将一种具有更快收敛速度和更高收敛精度的人工免疫K-Means混合聚类算法应用于三维模型对称特性提取上,经过采样、计算得出三维模型的实际对称平面,以此作为特征信息进行三维模型的检索。对比实验表明,该方法可以获得较优的检索性能。In order to improve the performance of 3D model retrieval,inspires the clone selection principle and memory mechanism of the vertebrate immune system,applies a hybrid algorithm combining K-Means algorithm and artificial immune algorithm which can converge to the global optimum faster and has higher accuracy to extracting symmetry feature of 3D model,samples and calculates then can have the real symmetry planes of 3D model,regards these symmetry planes of 3D model as the feature of 3D model and achieves the aim of 3D model retrieval.Experimental result indicates that the proposed method can have a better retrieval result.

关 键 词：三维模型检索 人工免疫 K-MEANS 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]