提出了一种基于2维多边形集相似性度量的3维模型检索方法，它的主要思想是用一组沿着特定方向的2维切片表示3维模型，其中这些2维切片由多个多边形组成，从而将3维形状之间的匹配问题转换为多边形集之间的相似性度量问题。这种方法涉及以下3个问题：切片方向的选择、切割方法和多边形集之间的相似性度量。针对这些问题，分别给出了相应的方法和规则，并通过实验验证了这种方法的有效性。

In this paper, we present an approach based on similarity measuring between 2D polygon sets for 3D model retrieval. The basic idea is to represent the 3D model by a series of slices composed of 2D polygon sets along certain directions. In this way, the shape-matching problem between 3D models is transformed into the similarity measuring between 2D polygon sets, in which three problems are involved: the selection of cutting directions, cutting methods and similarity measuring. To solve these problems, some strategies and rules are proposed, and their are proved by some experiments.