New Method of Feature Recognition from Engineering Drawings Based on Multi-granularity Information Acquisition

For improving the validity and efficiency of 3D reconstruction of engineering drawings, this paper presents a new method of feature recognition based on multi-granularity information acquisition. In this method, by analyzing the line-frames of combined primitive views and hidden semantics in engineering drawing, combined relationship of graphics primitives can be identified, then imitating line-frames partition method of figuration analysis, view loop separation of individual primitive is realized by inertial loop search with some priority. This algorithm is actualized in AutoCAD 2008 environment with development tools of Object ARX2008 and Visual C#2.0. With this algorithm, an application module of 3D intelligent reconstruction system is developed and finally the validity of this research is verified by examples.