利用多级弦长弯曲度复函数构建复杂面实体综合形状相似度量模型

Establishment of the Comprehensive Shape Similarity Model for Complex Polygon Entity by Using Bending Mutilevel Chord Complex Function

介绍了一种复杂带洞面实体空间对象的几何相似度度量方法。该方法提取面实体的中心距离、轮廓线的多级弦长、弯曲度及凸凹性等特征,构造多级弯曲度半径复函数对其局部和整体特征进行描述,并通过傅里叶变换得到傅里叶形状描述子对面实体间的形状相似性进行度量。同时根据场景完整度和相似性度量模型计算复杂带洞多边形中每个场景的匹配度,利用多级特征完成复杂面实体间的几何相似性度量。对不同空间复杂度的面实体的几何相似性的度量试验表明,该方法简单可行且不失精度,结果符合人类认知。

A method about shape similarity measurement of complex holed objects is proposed in this paper.The method extracts features including centroid distance,multilevel chord length,bending degree and concavityconvexity of a geometric object,to construct complex functions based on multilevel bending degree and radius.The complex functions are capable of describing geometry shape from entirety to part.The similarity between geometric objects can be measured by the shape descriptor which is based on the fast Fourier transform of the complex functions.Meanwhile,the matching degree of each scene of complex holed polygons can be got by scene completeness and shape similarity model.And using the feature of multi-level can accomplish the shape similarity measurement among complex geometric objects.Experimenting on geometric objects of different space complexity,the results match human’s perceive and show that this method is simple with precision.