New method of feature reconstruction from engineering drawings based on similarity measure of primitive views

Authors:
Jianping Liu;Bangyan Ye;Jianxi Peng;Bo Wu
Affiliations:
Foshan Polytechnic College, Foshan, Guangdong, China and School of Mechanical & Automotive Engineering, South China Univ. of Tech., Guangzhou, Guangdong, China;School of Mechanical & Automotive Engineering, South China Univ. of Tech., Guangzhou, Guangdong, China;Foshan Polytechnic College, Foshan, Guangdong, China;School of Mechanical & Automotive Engineering, South China Univ. of Tech., Guangzhou, Guangdong, China
Venue:
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 7
Year:
2009

Citing 2
Cited 0

Top-Down Construction of 3-D Mechanical Object Shapes from Engineering Drawings

Computer
Knowledge-Directed Interpretation of Mechanical Engineering Drawings

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.01

Visualization

Abstract

A new method of feature recognition based on similarity measure of primitive views is put forward to enhance efficiency of reconstruction of 3D solid mode of mechanical part from engineering drawing and expand its application in this paper, The details of this method include separating three views of single and combined primitive bodies by view loop searching; coding primitive view loops and calculating graphics similarity measure of two view loops; determining type of primitive body by projection rules and extract information of modeling feature of different primitive bodies. As a result, algorithms for feature recognition and 3D reconstruction are improved. Finally, an application module of 3D intelligent reconstruction system is established in AutoCAD 2008 environment with software tool of Object ARX 2008 and Visual C# 2.0, and the validity of feature recognition algorithms is verified by some examples.