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.%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.
展开▼