基于子块的三维模型检索算法

针对三维模型检索性能较低的问题,提出一种基于子块的三维模型检索算法。首先,对经过预处理的模型进行骨架提取,并记录每个骨架点相应的几何和拓扑结构信息;然后,将骨架划分成多个子块,为每个子块定义一个权值因子;最后,通过比较子块的相似度来计算模型整体的相似度。实验表明,该算法可以得到较好的检索性能。

Retrieval of 3D Models Based on Block

To improve the efficiency of 3D model retrieval, an efficient retrieval of 3D models based on block was proposed. The axis skeleton, the information of geometry and topology of skeleton point were got after preprocessing of model. The skeleton was segmented into a set of blocks. The weight was defined for each block of the skeleton. Finally, by calculating the similarity between blocks, the similarity of 3D models was achieved. The experimental results show that this algorithm can achieve better retrieving efficiency than other algorithms.