结合XML技术的三维模型检索方法  

Research on 3D model retrieval based on XML technology

作　　者：胡敏[1] 马韵洁[1] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2010年第8期1189-1193,1207,共6页Journal of Hefei University of Technology：Natural Science

基　　金：安徽省自然科学基金资助项目(070412046)

摘　　要：文章提出了一种利用XML描述三维模型的基于内容的检索,详细说明了用XML描述的三维模型和各向异性预处理;在基于形状的特征提取上提出了一种改善检索精度的算法,该算法根据模型上任意3点组成的三角形与模型是否有交点,将采样的三角形分成2类,分别构建形状分布直方图,并将提取的特征值写入XML文档,省去了每次检索都要对模型库进行特征提取,整个算法提高了检索的速度与精度。This paper introduces a content-based retrieval which uses XML to describe 3D models.It expounds the 3D models described by XML and anisotropic preprocessing,and proposes an algorithm to improve the accuracy of retrieval based on shape feature extraction.According to whether there is an intersection point between stochastic triangles and the model,the sampling triangles are classified into two types,and then the shape distribution histograms are constructed respectively.The eigenvalues are written in XML documents,thus eliminating the feature extraction from the model-base for each search.The algorithm improves the retrieval speed and accuracy.

关 键 词：可扩展标记语言 三维模型检索 各向异性 特征提取 分类算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]