拓扑和形状特征相结合的三维模型检索

3D Model Retrieval based on both the Topology and Shape Features

针对整体相似性检索算法在局部细节特征上的表达能力不足,提出了一种将拓扑和形状特征相结合的三维模型相似性比较方法.首先提取三维模型的骨架,获得模型的整体拓扑特征;然后根据骨架节点将模型分解为多个子部分,并利用球面谐波算法提取每一个子部分的形状特征.模型的匹配分为3步进行:整体骨架的拓扑特征相似性比较,相对应的子部分的局部形状特征相似性比较,模型总的相似性是整体骨架相似性与对应子部分局部形状相似性的加权和.实验结果表明:该方法从整体到局部、由粗到精,综合考虑了拓扑和形状特征,较传统的考虑单一拓扑或形状特征的检索算法有较高的检索精度,同时又支持基于局部特征的相似性检索.

The 3D model retrieval methods accounting for only global shape features are unable to compare models elaborately at a local level of detail. In this paper we present a new framework for 3D model retrieval considering both the global topology feature and the local shape feature of the candidate models . Firstly, we employ the Potential Field Method to acquire the skeleton of the model, and decompose it into several sub-parts according to the skeleton nodes. Then, we extract the local shape feature of each sub-part using the Spherical Harmonical Method. During the process of model matching, a three-step strategy is adopted. In the first step, we evaluate the similarity of global topology feature between the two skeletons and establish the corresponding relationship of the sub-parts between the two models. In the second step, we evaluate the similarity of local shape feature between each pair of corresponding sub-parts. The overall similarity of the two models is finally estimated by the weighted sum of the similarities on the above two aspects. Experimental results show that the result of this method is more satisfactory than those by the traditional methods based solely on the shape feature or the topology feature. Besides, this method supports the matching based on the local feature.