形状群组的分类和检索算法  

A Novel Algorithm of Classification and Retrieval for Shape Group

作　　者：宋瑞霞[1] 陈曦[1] 孙红磊[1] 姚东星[1] 薛冠辰[1] 

机构地区：[1]北方工业大学理学院,北京100144

出　　处：《计算机辅助设计与图形学学报》2011年第12期1981-1986,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(10771002);北京市自然科学基金(1102017);北京市自然科学基金重点项目暨北京市教委科技发展计划重点项目(KZ201210009011);澳门科学技术发展基金(006/2011/A1)

摘　　要：由多个彼此分离的轮廓所构成的整体称为一个"形状群组".文中基于一类称作V-系统的正交系,提出一种形状群组的特征描述方法.首先将一个形状群组用V-系统的有限个基函数精确表达出来,然后在频域提取其特征向量,再给出2个形状群组间的相似度量,从而得到一类形状群组的分类检索方法.由于V-系统能够精确重构每个形状群组,因此对形状群组的特征描述是准确可靠的.最后进行了大量的形状群组的分类检索对比实验,结果表明,该方法相比经典的傅里叶描述子、Zernike矩、不变矩和几何中心矩均有明显的优势.A shape group is composed of several separate contours.Based on an orthogonal function system called V-system,a novel algorithm for extracting features for shape group is presented.First,a shape group is accurately expressed with finite basis functions of V-system,and then its feature vector is extracted in the frequency domain.Based on extracted feature vectors,similarity measure value between two shape groups is calculated and then a new shape group classification and retrieval method is proposed.As the V-system can accurately reconstruct the shape group,the features of shape group obtained by V-system is accurate and reliable.Experiment results show that the classification and retrieval performance of our method is superior over the classical Fourier descriptor,Zernike moments,invariant moments,and geometric center moments.

关 键 词：V-系统 V-描述子 形状群组 分类 检索 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]