Abstract: 3D model retrieval is the hot topic nowadays. A 3D-model retrieval algorithm based on range images is proposed in this paper. This algorithm computes 3D models projection range images on six directions, and then computes edge direction histogram and Zernike moment of these range images. At last the system combines the two features for 3D model retrieval, and relevance feedback is used to realize the adjustment of the parameter until the satisfied 3D model obtained. The experiments show that the algorithm avoids the traditional visual shortcomings of the loss of spatial information, and improves the accuracy of the retrieval and robustness effectively.

Key words: 3D model, range image, edge direction, Zernike moment

摘要： 三维模型检索是现在的研究热点，提出一种基于深度图像的三维模型检索算法。对三维模型进行规范化处理，采用基于正交投影的方法计算三维模型在其包围立方体的六个面上的深度图像；提取深度图像的边界方向直方图和Zernike矩特征；利用特征距离度量进行三维模型检索，并采用相关反馈技术实现权值的调整，得到用户最满意的目标检索模型。对比实验表明，该算法避免了传统视觉图像丢失三维模型空间信息的缺点，有效地提高了检索的精确性和鲁棒性。

关键词: 三维模型, 深度图像, 边界方向, Zernike矩