Learning High-Level Feature by Deep Belief Networks for 3-D Model Retrieval and Recognition
Learning High-Level Feature by Deep Belief Networks for 3-D Model Retrieval and Recognition
复制标题
通过深度置信网络学习高级特征以进行 3D 模型检索和识别
DOI：
10.1109/tmm.2014.2351788
复制
发表时间：
2014-12-01
影响因子：
7.3
通讯作者：
Ji, Rongrong
中科院分区：
文献类型：
--
作者：
Bu, Shuhui;Liu, Zhenbao;Ji, Rongrong
近年来，三维形状分析吸引了广泛的研究努力，其中的主要挑战在于设计一个有效的高层次的三维形状特征。在本文中，我们提出了一个多层次的三维形状特征提取框架，通过使用深度学习。首先将低层三维形状描述符编码成几何词袋，从中发现中层模式以探索词之间的几何关系。在此之后，通过深度信念网络学习高级形状特征，这对于形状分类和检索任务更具鉴别力。三维形状识别和检索实验表明，该方法的性能优于国家的最先进的方法相比，上级。
3-D shape analysis has attracted extensive research efforts in recent years, where the major challenge lies in designing an effective high-level 3-D shape feature. In this paper, we propose a multi-level 3-D shape feature extraction framework by using deep learning. The low-level 3-D shape descriptors are first encoded into geometric bag-of-words, from which middle-level patterns are discovered to explore geometric relationships among words. After that, high-level shape features are learned via deep belief networks, which are more discriminative for the tasks of shape classification and retrieval. Experiments on 3-D shape recognition and retrieval demonstrate the superior performance of the proposed method in comparison to the state-of-the-art methods.