Title :
New Method of Primitive Feature Recognition Based on Graphics Comparability
Author :
Liu, Jianping ; Ye, Bangyan ; Peng, Jianxi ; Wu, Bo
Author_Institution :
Foshan Polytech. Coll., Foshan, China
Abstract :
For improving validity and efficiency of 3D reconstruction from 2D engineering drawings, this paper presents a new method of primitive feature recognition based on graphics comparability determining of view loop. Main steps of this method are as follows: Firstly separate three views of single or combined primitive bodies by loop search, and then code view loops of primitive body and calculate graphics similarity measure of two view loops, further determine type of primitive body by projection rules and extract different information of modeling feature for different primitive bodies. Based on the mentioned above, different reconstruction algorithms are applied for different primitive bodies. Application module of 3D intelligent reconstruction system is developed together with the tools of Object ARX 2008 and Visual C# 2.0 in AutoCAD 2008 environment and this algorithm is actualized. The validity of feature recognition is verified by examples.
Keywords :
CAD; computer graphics; image reconstruction; mechanical engineering computing; 2D engineering drawings; 3D intelligent reconstruction system; 3D reconstruction; AutoCAD 2008; Object ARX 2008; Visual C# 2.0; graphics comparability; primitive feature recognition; reconstruction algorithms; view loop determination; Computer graphics; Data mining; Educational institutions; Engineering drawings; Intelligent systems; Intelligent vehicles; Pattern matching; Reconstruction algorithms; Shape measurement; Solids;
Conference_Titel :
Intelligent Systems, 2009. GCIS '09. WRI Global Congress on
Conference_Location :
Xiamen
Print_ISBN :
978-0-7695-3571-5
DOI :
10.1109/GCIS.2009.465