欢迎访问《图学学报》 分享到:

图学学报

• 计算机图形学 • 上一篇    下一篇

基于哈希的二维工程 CAD 图纸检索技术

  

  1. 南京理工大学自动化学院,江苏 南京 210094
  • 出版日期:2018-10-31 发布日期:2018-11-16

Retrieval of 2D Engineering CAD Drawings Based on Hashing

  1. School of Automation, Nanjing University of Science and Technology, Nanjing Jiangsu 210094, China
  • Online:2018-10-31 Published:2018-11-16

摘要: 针对企业在设计创新过程中大量采用已有计算机辅助设计(CAD)图纸进行设计重 用的情况,提出了一种基于哈希的二维工程 CAD 图纸检索方法。首先基于环形分割算法提取 工程 CAD 图纸中每个组件对象几何特征;基于传统 LBP 算子提出了一种局部拓扑矢量量化模 式(T-LVQP),实现对各个组件拓扑特征的提取;然后基于协方差描述符融合几何特征和拓扑特 征,通过 LBG 算法将所有组件按照几何特征分组后得到工程 CAD 图纸的特征向量表达;最后 通过迭代量化哈希算法生成图纸的哈希序列。实验结果表明,该算法检索速度快、准确度高, 对于二维工程 CAD 图纸具有较好的检索效果。

关键词: 工程 CAD 图, 检索, 环形分割, 局部拓扑矢量量化模式, 特征融合, 迭代量化哈希

Abstract: In the process of design innovation, a large number of companies use existing computer aided design (CAD) drawings as the basis for design reuse. In this paper, hash algorithm is applied to the retrieval of 2D engineering CAD drawings. The algorithm extracts geometry features of each component in the engineering CAD drawing based on ring partition, and the topology of local vector quantization pattern (T-LVQP) is proposed to extract the topological features of each component based on LBP operator. Then, all components in the drawings are classified into groups according to geometric features by the LBG algorithm, and the feature vector of each drawing is obtained via fused features based on the co-variance descriptor. Finally, the Hash sequence is generated by iterative quantization Hashing. The experimental results show that the algorithm has good performance in speed and accuracy for the retrieval of 2D engineering CAD drawings.

Key words: engineering CAD drawings, retrieval, ring partition, topology-local vector quantization pattern, feature fusion, iterative quantization Hashing