View labeling for automated interpretation of engineering drawings

摘要

A method is presented for segmenting engineering drawings into views and identifying the corresponding view points. A set of 2.5D view-based coordinate systems is introduced as an intermediate between the 2D drawing-based system and the 3D object-based coordinates, and a formal technique is developed for constructing transformation matrices between coordinates. The method accommodates auxiliary views in addition to the standard orthogonal set, and the number of views and their positions need not be known a priori. Drawings with moderate errors in line placement and view alignment can also be handled. A rule based approach, using evidential reasoning, is applied for labeling the views.