提出一种基于相对角度分布和聚类的3维模型检索算法RAC（relative-rangle clustering）。定义模型表面点的相对角度分布函数，作为模型新的特征量，并对模型进行相对角度特征提取。经过实验证明相对角度特征对模型的几何形状分类效果较好。针对提取模型表面点的相对角度使得模型的特征量维数较大，检索时间较长，又使用聚类的方法对特征量进行近一步降维处理。实验结果表明与其他几种算法相比，RAC检索效果更好。

In this paper, we propose a novel 3D model retrieval algorithm based on Relative angle-distribution and clustering (RAC). A geometric feature vector based on relative-angle distribution (RAD) of surface points is defined. The experimental results demonstrate that RAD is a good global feature for shape classification. To reduce the feature dimensions and improve the computational efficiency, clustering is employed. The model classification results show that compared with other methods, our algorithm RAC (relative angle clustering) achieves better retrieval accuracy and efficiency.